diff --git a/homework/hw2/.ipynb_checkpoints/Aqui deben subir su hw2-checkpoint.txt b/homework/hw2/.ipynb_checkpoints/Aqui deben subir su hw2-checkpoint.txt new file mode 100644 index 000000000..e69de29bb diff --git a/homework/hw2/259359_hw2_2025_1/.ipynb_checkpoints/Tarea 2 VF-checkpoint.ipynb b/homework/hw2/259359_hw2_2025_1/.ipynb_checkpoints/Tarea 2 VF-checkpoint.ipynb new file mode 100644 index 000000000..14a9c762a --- /dev/null +++ b/homework/hw2/259359_hw2_2025_1/.ipynb_checkpoints/Tarea 2 VF-checkpoint.ipynb @@ -0,0 +1,1304 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 3, + "id": "466ae9b3-3bb6-4118-a26b-2660b02ec0b2", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Concursos seleccionados:\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idnamestartTime
482053Good Bye 2024: 2025 is NEAR2024-12-28 14:35:00
492043Educational Codeforces Round 173 (Rated for Di...2024-12-24 14:35:00
512051Codeforces Round 995 (Div. 3)2024-12-22 14:35:00
522049Codeforces Round 994 (Div. 2)2024-12-20 14:35:00
532048Codeforces Global Round 282024-12-19 14:35:00
542044Codeforces Round 993 (Div. 4)2024-12-15 14:35:00
562040Codeforces Round 992 (Div. 2)2024-12-08 14:35:00
572050Codeforces Round 991 (Div. 3)2024-12-05 14:35:00
582046Codeforces Round 990 (Div. 1)2024-12-03 06:25:00
592047Codeforces Round 990 (Div. 2)2024-12-03 06:25:00
602042Educational Codeforces Round 172 (Rated for Di...2024-12-02 14:35:00
622034Rayan Programming Contest 2024 - Selection (Co...2024-11-30 14:35:00
642039CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!)2024-11-23 14:35:00
662037Codeforces Round 988 (Div. 3)2024-11-17 14:35:00
672031Codeforces Round 987 (Div. 2)2024-11-15 12:35:00
682028Codeforces Round 986 (Div. 2)2024-11-10 15:35:00
692029Refact.ai Match 1 (Codeforces Round 985)2024-11-09 14:35:00
702036Codeforces Round 984 (Div. 3)2024-11-02 14:35:00
712032Codeforces Round 983 (Div. 2)2024-11-01 14:35:00
722026Educational Codeforces Round 171 (Rated for Di...2024-10-28 14:35:00
732035Codeforces Global Round 272024-10-27 14:35:00
742027Codeforces Round 982 (Div. 2)2024-10-26 14:35:00
752033Codeforces Round 981 (Div. 3)2024-10-24 14:35:00
762023Codeforces Round 980 (Div. 1)2024-10-20 09:05:00
772024Codeforces Round 980 (Div. 2)2024-10-20 09:05:00
782030Codeforces Round 979 (Div. 2)2024-10-19 14:05:00
792025Educational Codeforces Round 170 (Rated for Di...2024-10-14 14:35:00
802022Codeforces Round 978 (Div. 2)2024-10-13 19:35:00
812021Codeforces Round 977 (Div. 2, based on COMPFES...2024-10-06 06:05:00
832020Codeforces Round 976 (Div. 2) and Divide By Ze...2024-09-29 15:35:00
842018Codeforces Round 975 (Div. 1)2024-09-27 13:35:00
852019Codeforces Round 975 (Div. 2)2024-09-27 13:35:00
862014Codeforces Round 974 (Div. 3)2024-09-21 14:45:00
872013Codeforces Round 973 (Div. 2)2024-09-20 14:35:00
902005Codeforces Round 972 (Div. 2)2024-09-14 14:35:00
912009Codeforces Round 971 (Div. 4)2024-09-03 14:35:00
922008Codeforces Round 970 (Div. 3)2024-09-01 14:35:00
932006Codeforces Round 969 (Div. 1)2024-08-30 14:35:00
942007Codeforces Round 969 (Div. 2)2024-08-30 14:35:00
952010Testing Round 19 (Div. 3)2024-08-28 20:35:00
962003Codeforces Round 968 (Div. 2)2024-08-25 14:35:00
972001Codeforces Round 967 (Div. 2)2024-08-20 14:35:00
982004Educational Codeforces Round 169 (Rated for Di...2024-08-15 14:35:00
992000Codeforces Round 966 (Div. 3)2024-08-13 14:40:00
1002002EPIC Institute of Technology Round August 2024...2024-08-11 14:35:00
1011998Codeforces Round 965 (Div. 2)2024-08-10 14:35:00
1021999Codeforces Round 964 (Div. 4)2024-08-06 14:35:00
1031993Codeforces Round 963 (Div. 2)2024-08-04 14:35:00
1041997Educational Codeforces Round 168 (Rated for Di...2024-07-30 14:35:00
1051991Pinely Round 4 (Div. 1 + Div. 2)2024-07-28 14:35:00
1061996Codeforces Round 962 (Div. 3)2024-07-26 14:35:00
1071995Codeforces Round 961 (Div. 2)2024-07-23 14:35:00
1081990Codeforces Round 960 (Div. 2)2024-07-20 14:35:00
1091994Codeforces Round 959 sponsored by NEAR (Div. 1...2024-07-18 14:35:00
1101988Codeforces Round 958 (Div. 2)2024-07-15 14:35:00
1111992Codeforces Round 957 (Div. 3)2024-07-11 14:35:00
1121983Codeforces Round 956 (Div. 2) and ByteRace 20242024-07-07 14:35:00
\n", + "
" + ], + "text/plain": [ + " id name \\\n", + "48 2053 Good Bye 2024: 2025 is NEAR \n", + "49 2043 Educational Codeforces Round 173 (Rated for Di... \n", + "51 2051 Codeforces Round 995 (Div. 3) \n", + "52 2049 Codeforces Round 994 (Div. 2) \n", + "53 2048 Codeforces Global Round 28 \n", + "54 2044 Codeforces Round 993 (Div. 4) \n", + "56 2040 Codeforces Round 992 (Div. 2) \n", + "57 2050 Codeforces Round 991 (Div. 3) \n", + "58 2046 Codeforces Round 990 (Div. 1) \n", + "59 2047 Codeforces Round 990 (Div. 2) \n", + "60 2042 Educational Codeforces Round 172 (Rated for Di... \n", + "62 2034 Rayan Programming Contest 2024 - Selection (Co... \n", + "64 2039 CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!) \n", + "66 2037 Codeforces Round 988 (Div. 3) \n", + "67 2031 Codeforces Round 987 (Div. 2) \n", + "68 2028 Codeforces Round 986 (Div. 2) \n", + "69 2029 Refact.ai Match 1 (Codeforces Round 985) \n", + "70 2036 Codeforces Round 984 (Div. 3) \n", + "71 2032 Codeforces Round 983 (Div. 2) \n", + "72 2026 Educational Codeforces Round 171 (Rated for Di... \n", + "73 2035 Codeforces Global Round 27 \n", + "74 2027 Codeforces Round 982 (Div. 2) \n", + "75 2033 Codeforces Round 981 (Div. 3) \n", + "76 2023 Codeforces Round 980 (Div. 1) \n", + "77 2024 Codeforces Round 980 (Div. 2) \n", + "78 2030 Codeforces Round 979 (Div. 2) \n", + "79 2025 Educational Codeforces Round 170 (Rated for Di... \n", + "80 2022 Codeforces Round 978 (Div. 2) \n", + "81 2021 Codeforces Round 977 (Div. 2, based on COMPFES... \n", + "83 2020 Codeforces Round 976 (Div. 2) and Divide By Ze... \n", + "84 2018 Codeforces Round 975 (Div. 1) \n", + "85 2019 Codeforces Round 975 (Div. 2) \n", + "86 2014 Codeforces Round 974 (Div. 3) \n", + "87 2013 Codeforces Round 973 (Div. 2) \n", + "90 2005 Codeforces Round 972 (Div. 2) \n", + "91 2009 Codeforces Round 971 (Div. 4) \n", + "92 2008 Codeforces Round 970 (Div. 3) \n", + "93 2006 Codeforces Round 969 (Div. 1) \n", + "94 2007 Codeforces Round 969 (Div. 2) \n", + "95 2010 Testing Round 19 (Div. 3) \n", + "96 2003 Codeforces Round 968 (Div. 2) \n", + "97 2001 Codeforces Round 967 (Div. 2) \n", + "98 2004 Educational Codeforces Round 169 (Rated for Di... \n", + "99 2000 Codeforces Round 966 (Div. 3) \n", + "100 2002 EPIC Institute of Technology Round August 2024... \n", + "101 1998 Codeforces Round 965 (Div. 2) \n", + "102 1999 Codeforces Round 964 (Div. 4) \n", + "103 1993 Codeforces Round 963 (Div. 2) \n", + "104 1997 Educational Codeforces Round 168 (Rated for Di... \n", + "105 1991 Pinely Round 4 (Div. 1 + Div. 2) \n", + "106 1996 Codeforces Round 962 (Div. 3) \n", + "107 1995 Codeforces Round 961 (Div. 2) \n", + "108 1990 Codeforces Round 960 (Div. 2) \n", + "109 1994 Codeforces Round 959 sponsored by NEAR (Div. 1... \n", + "110 1988 Codeforces Round 958 (Div. 2) \n", + "111 1992 Codeforces Round 957 (Div. 3) \n", + "112 1983 Codeforces Round 956 (Div. 2) and ByteRace 2024 \n", + "\n", + " startTime \n", + "48 2024-12-28 14:35:00 \n", + "49 2024-12-24 14:35:00 \n", + "51 2024-12-22 14:35:00 \n", + "52 2024-12-20 14:35:00 \n", + "53 2024-12-19 14:35:00 \n", + "54 2024-12-15 14:35:00 \n", + "56 2024-12-08 14:35:00 \n", + "57 2024-12-05 14:35:00 \n", + "58 2024-12-03 06:25:00 \n", + "59 2024-12-03 06:25:00 \n", + "60 2024-12-02 14:35:00 \n", + "62 2024-11-30 14:35:00 \n", + "64 2024-11-23 14:35:00 \n", + "66 2024-11-17 14:35:00 \n", + "67 2024-11-15 12:35:00 \n", + "68 2024-11-10 15:35:00 \n", + "69 2024-11-09 14:35:00 \n", + "70 2024-11-02 14:35:00 \n", + "71 2024-11-01 14:35:00 \n", + "72 2024-10-28 14:35:00 \n", + "73 2024-10-27 14:35:00 \n", + "74 2024-10-26 14:35:00 \n", + "75 2024-10-24 14:35:00 \n", + "76 2024-10-20 09:05:00 \n", + "77 2024-10-20 09:05:00 \n", + "78 2024-10-19 14:05:00 \n", + "79 2024-10-14 14:35:00 \n", + "80 2024-10-13 19:35:00 \n", + "81 2024-10-06 06:05:00 \n", + "83 2024-09-29 15:35:00 \n", + "84 2024-09-27 13:35:00 \n", + "85 2024-09-27 13:35:00 \n", + "86 2024-09-21 14:45:00 \n", + "87 2024-09-20 14:35:00 \n", + "90 2024-09-14 14:35:00 \n", + "91 2024-09-03 14:35:00 \n", + "92 2024-09-01 14:35:00 \n", + "93 2024-08-30 14:35:00 \n", + "94 2024-08-30 14:35:00 \n", + "95 2024-08-28 20:35:00 \n", + "96 2024-08-25 14:35:00 \n", + "97 2024-08-20 14:35:00 \n", + "98 2024-08-15 14:35:00 \n", + "99 2024-08-13 14:40:00 \n", + "100 2024-08-11 14:35:00 \n", + "101 2024-08-10 14:35:00 \n", + "102 2024-08-06 14:35:00 \n", + "103 2024-08-04 14:35:00 \n", + "104 2024-07-30 14:35:00 \n", + "105 2024-07-28 14:35:00 \n", + "106 2024-07-26 14:35:00 \n", + "107 2024-07-23 14:35:00 \n", + "108 2024-07-20 14:35:00 \n", + "109 2024-07-18 14:35:00 \n", + "110 2024-07-15 14:35:00 \n", + "111 2024-07-11 14:35:00 \n", + "112 2024-07-07 14:35:00 " + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "#Parte 1: Extracción de Datos desde la API de Codeforces\n", + "#Carga las librerías necesarias.\n", + "\n", + "#Hace una solicitud al endpoint contest.list de Codeforces.\n", + "\n", + "#Convierte la respuesta en un DataFrame.\n", + "\n", + "#Filtra los concursos que se realizaron entre julio y diciembre de 2024, y cuyo nombre contiene “Hello”, “Round” o “Good Bye”.\n", + "\n", + "#Muestra los concursos seleccionados para trabajar con ellos en las siguientes etapas.\n", + "#-----------------------------------------------------------------------------------------------------------------------------# \n", + "# Importamos las librerías necesarias\n", + "import requests\n", + "import pandas as pd\n", + "from datetime import datetime\n", + "\n", + "# Esta función convierte un timestamp a una fecha legible\n", + "def timestamp_to_date(timestamp):\n", + " return datetime.utcfromtimestamp(timestamp)\n", + "\n", + "# 1. Obtenemos la lista de concursos desde el endpoint contest.list\n", + "url_contests = \"https://codeforces.com/api/contest.list\"\n", + "response = requests.get(url_contests)\n", + "contests_data = response.json()\n", + "\n", + "# Verificamos que la respuesta haya sido exitosa\n", + "assert contests_data['status'] == 'OK', \"No se pudo obtener la lista de concursos\"\n", + "\n", + "# Convertimos los datos a un DataFrame para filtrarlos fácilmente\n", + "df_contests = pd.DataFrame(contests_data['result'])\n", + "\n", + "# Convertimos los timestamps a fechas legibles\n", + "df_contests['startTime'] = df_contests['startTimeSeconds'].apply(timestamp_to_date)\n", + "\n", + "# Filtramos los concursos por:\n", + "# - Fechas entre julio y diciembre 2024\n", + "# - Nombre que contenga 'Hello', 'Round' o 'Good Bye'\n", + "df_contests_filtered = df_contests[\n", + " (df_contests['startTime'] >= datetime(2024, 7, 1)) &\n", + " (df_contests['startTime'] <= datetime(2024, 12, 31)) &\n", + " (df_contests['name'].str.contains('Hello|Round|Good Bye', case=False, na=False))\n", + "].copy()\n", + "\n", + "# Mostramos los concursos seleccionados\n", + "print(\"Concursos seleccionados:\")\n", + "display(df_contests_filtered[['id', 'name', 'startTime']])" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "e3755325-e639-4e03-8f87-95925eebab2e", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "📥 Extrayendo datos para el concurso: Good Bye 2024: 2025 is NEAR (ID: 2053)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 173 (Rated for Div. 2) (ID: 2043)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 995 (Div. 3) (ID: 2051)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 994 (Div. 2) (ID: 2049)\n", + "📥 Extrayendo datos para el concurso: Codeforces Global Round 28 (ID: 2048)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 993 (Div. 4) (ID: 2044)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 992 (Div. 2) (ID: 2040)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 991 (Div. 3) (ID: 2050)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 990 (Div. 1) (ID: 2046)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 990 (Div. 2) (ID: 2047)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 172 (Rated for Div. 2) (ID: 2042)\n", + "📥 Extrayendo datos para el concurso: Rayan Programming Contest 2024 - Selection (Codeforces Round 989, Div. 1 + Div. 2) (ID: 2034)\n", + "📥 Extrayendo datos para el concurso: CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!) (ID: 2039)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 988 (Div. 3) (ID: 2037)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 987 (Div. 2) (ID: 2031)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 986 (Div. 2) (ID: 2028)\n", + "📥 Extrayendo datos para el concurso: Refact.ai Match 1 (Codeforces Round 985) (ID: 2029)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 984 (Div. 3) (ID: 2036)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 983 (Div. 2) (ID: 2032)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 171 (Rated for Div. 2) (ID: 2026)\n", + "📥 Extrayendo datos para el concurso: Codeforces Global Round 27 (ID: 2035)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 982 (Div. 2) (ID: 2027)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 981 (Div. 3) (ID: 2033)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 980 (Div. 1) (ID: 2023)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 980 (Div. 2) (ID: 2024)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 979 (Div. 2) (ID: 2030)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 170 (Rated for Div. 2) (ID: 2025)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 978 (Div. 2) (ID: 2022)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 977 (Div. 2, based on COMPFEST 16 - Final Round) (ID: 2021)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 976 (Div. 2) and Divide By Zero 9.0 (ID: 2020)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 975 (Div. 1) (ID: 2018)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 975 (Div. 2) (ID: 2019)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 974 (Div. 3) (ID: 2014)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 973 (Div. 2) (ID: 2013)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 972 (Div. 2) (ID: 2005)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 971 (Div. 4) (ID: 2009)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 970 (Div. 3) (ID: 2008)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 969 (Div. 1) (ID: 2006)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 969 (Div. 2) (ID: 2007)\n", + "📥 Extrayendo datos para el concurso: Testing Round 19 (Div. 3) (ID: 2010)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 968 (Div. 2) (ID: 2003)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 967 (Div. 2) (ID: 2001)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 169 (Rated for Div. 2) (ID: 2004)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 966 (Div. 3) (ID: 2000)\n", + "📥 Extrayendo datos para el concurso: EPIC Institute of Technology Round August 2024 (Div. 1 + Div. 2) (ID: 2002)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 965 (Div. 2) (ID: 1998)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 964 (Div. 4) (ID: 1999)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 963 (Div. 2) (ID: 1993)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 168 (Rated for Div. 2) (ID: 1997)\n", + "📥 Extrayendo datos para el concurso: Pinely Round 4 (Div. 1 + Div. 2) (ID: 1991)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 962 (Div. 3) (ID: 1996)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 961 (Div. 2) (ID: 1995)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 960 (Div. 2) (ID: 1990)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 959 sponsored by NEAR (Div. 1 + Div. 2) (ID: 1994)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 958 (Div. 2) (ID: 1988)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 957 (Div. 3) (ID: 1992)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 956 (Div. 2) and ByteRace 2024 (ID: 1983)\n", + "✅ Extracción completa de todos los concursos.\n" + ] + } + ], + "source": [ + "#Parte 2: Extracción de Datos por Concurso\n", + "import time\n", + "\n", + "# Definimos funciones para cada endpoint\n", + "\n", + "# 1. Obtener standings y problemas\n", + "def get_standings(contest_id):\n", + " url = f\"https://codeforces.com/api/contest.standings?contestId={contest_id}&from=1&count=5000\"\n", + " res = requests.get(url)\n", + " data = res.json()\n", + " if data['status'] == 'OK':\n", + " return data['result']\n", + " return None\n", + "\n", + "# 2. Obtener submissions\n", + "def get_submissions(contest_id):\n", + " url = f\"https://codeforces.com/api/contest.status?contestId={contest_id}\"\n", + " res = requests.get(url)\n", + " data = res.json()\n", + " if data['status'] == 'OK':\n", + " return data['result']\n", + " return None\n", + "\n", + "# 3. Obtener cambios de rating\n", + "def get_rating_changes(contest_id):\n", + " url = f\"https://codeforces.com/api/contest.ratingChanges?contestId={contest_id}\"\n", + " res = requests.get(url)\n", + " data = res.json()\n", + " if data['status'] == 'OK':\n", + " return data['result']\n", + " return None\n", + "\n", + "# 4. Obtener usuarios calificados (solo una vez)\n", + "def get_rated_users():\n", + " url = \"https://codeforces.com/api/user.ratedList?activeOnly=false\"\n", + " res = requests.get(url)\n", + " data = res.json()\n", + " if data['status'] == 'OK':\n", + " return data['result']\n", + " return None\n", + "\n", + "# Creamos un diccionario para almacenar toda la información\n", + "contest_details = {}\n", + "\n", + "# Iteramos sobre los concursos filtrados anteriormente\n", + "for _, row in df_contests_filtered.iterrows():\n", + " contest_id = row['id']\n", + " print(f\"📥 Extrayendo datos para el concurso: {row['name']} (ID: {contest_id})\")\n", + "\n", + " contest_details[contest_id] = {\n", + " 'name': row['name'],\n", + " 'start_time': row['startTime'],\n", + " 'standings': get_standings(contest_id),\n", + " 'submissions': get_submissions(contest_id),\n", + " 'rating_changes': get_rating_changes(contest_id)\n", + " }\n", + " \n", + " # Esperamos 1 segundo entre llamadas para no sobrecargar la API\n", + " time.sleep(1)\n", + "\n", + "# Obtenemos la lista completa de usuarios calificados (solo una vez)\n", + "rated_users = get_rated_users()\n", + "\n", + "print(\"✅ Extracción completa de todos los concursos.\")" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "35384891-e07f-4036-8ca3-1534cafbdf9a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "✅ Archivos CSV guardados con éxito.\n" + ] + } + ], + "source": [ + "#Código para guardar los archivos .csv por concurso\n", + "import os\n", + "\n", + "# Creamos una carpeta para almacenar los CSVs\n", + "base_folder = \"codeforces_data\"\n", + "os.makedirs(base_folder, exist_ok=True)\n", + "\n", + "for contest_id, data in contest_details.items():\n", + " folder_name = os.path.join(base_folder, f\"contest_{contest_id}\")\n", + " os.makedirs(folder_name, exist_ok=True)\n", + "\n", + " # Guardamos standings (solo rows, no problems)\n", + " if data['standings'] and 'rows' in data['standings']:\n", + " df_standings = pd.json_normalize(data['standings']['rows'])\n", + " df_standings.to_csv(os.path.join(folder_name, \"standings.csv\"), index=False)\n", + "\n", + " # Guardamos submissions\n", + " if data['submissions']:\n", + " df_submissions = pd.json_normalize(data['submissions'])\n", + " df_submissions.to_csv(os.path.join(folder_name, \"submissions.csv\"), index=False)\n", + "\n", + " # Guardamos cambios de rating\n", + " if data['rating_changes']:\n", + " df_rating = pd.DataFrame(data['rating_changes'])\n", + " df_rating.to_csv(os.path.join(folder_name, \"rating_changes.csv\"), index=False)\n", + "\n", + "# También exportamos la lista de usuarios calificados\n", + "if rated_users:\n", + " df_users = pd.DataFrame(rated_users)\n", + " df_users.to_csv(os.path.join(base_folder, \"rated_users.csv\"), index=False)\n", + "\n", + "print(\"✅ Archivos CSV guardados con éxito.\")" + ] + }, + { + "cell_type": "markdown", + "id": "7176043e-b79e-41ab-9761-e7b466904b97", + "metadata": {}, + "source": [ + "## Parte 3: Descripción del Dataset\n", + "## 📄 Descripción del Dataset\n", + "\n", + "### 🔗 Endpoints de la API utilizados:\n", + "\n", + "- `contest.list`: Lista de todos los concursos públicos en Codeforces.\n", + "- `contest.standings`: Información sobre los problemas de un concurso y la clasificación de los usuarios.\n", + "- `contest.status`: Todas las submissions de un concurso.\n", + "- `contest.ratingChanges`: Cambios de rating de los usuarios después del concurso.\n", + "- `user.ratedList`: Lista de todos los usuarios con rating en Codeforces.\n", + "\n", + "### 🧱 Estructura del dataset\n", + "\n", + "Para cada concurso se extrajeron tres tablas:\n", + "\n", + "1. **Standings (`standings.csv`)**\n", + " - `party.members[0].handle`: Usuario.\n", + " - `problemResults`: Lista con información sobre cada problema (puntos, tiempo, etc.).\n", + " - `rank`, `points`, `successfulHackCount`, etc.\n", + "\n", + "2. **Submissions (`submissions.csv`)**\n", + " - `id`: ID de la submission.\n", + " - `creationTimeSeconds`: Fecha y hora de envío (en timestamp).\n", + " - `relativeTimeSeconds`: Tiempo desde el inicio del concurso.\n", + " - `verdict`: Resultado de la solución (OK, Wrong Answer, etc.).\n", + " - `programmingLanguage`: Lenguaje usado.\n", + " - `problem.index` y `problem.rating`: Información del problema resuelto.\n", + "\n", + "3. **Rating Changes (`rating_changes.csv`)**\n", + " - `handle`: Usuario.\n", + " - `oldRating`, `newRating`: Puntos antes y después del concurso.\n", + " - `rank`: Posición en el concurso.\n", + "\n", + "4. **Usuarios (`rated_users.csv`)**\n", + " - `handle`: Nombre del usuario.\n", + " - `country`, `city`, `rating`, `maxRating`, etc.\n", + "\n", + "### 📌 Variables clave para el análisis posterior\n", + "\n", + "- `finished_n`: Si el usuario resolvió el problema `n`.\n", + "- `n_language`: Lenguaje usado para resolver el problema `n`.\n", + "- `relative_time_n`: Tiempo desde el inicio del concurso hasta la solución del problema `n`.\n", + "- `time_to_answer_n`: Diferencia de tiempo entre problemas resueltos.\n", + "- `rating_n`: Dificultad del problema.\n", + "- `rating_achieved`: Suma de los ratings de los problemas resueltos por el usuario.\n", + "- `contest_name`, `contest_start_time`: Contexto del concurso.\n", + "- `country`, `city`, `rating`, `max_rating`: Información del perfil del usuario." + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "c4d47475-dd97-46e4-bc23-15efa52f7cf9", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 57/57 [02:19<00:00, 2.45s/it]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "✅ Dataset final con 264595 filas y 64 columnas.\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
author_handlecontest_idcontest_namecontest_start_timecountrycityratingmax_ratingrating_achievedrating_1...rating_10finished_10relative_time_1010_languagetime_to_answer_10rating_11finished_11relative_time_1111_languagetime_to_answer_11
0jiangly2053Good Bye 2024: 2025 is NEAR1735396500ChinaChongqing3710.04039.022900800...3500.0True2.147484e+09C++23 (GCC 14-64, msys2)2.147479e+09NaNNaNNaNNaNNaN
1ecnerwala2053Good Bye 2024: 2025 is NEAR1735396500United StatesCupertino3627.03668.015900800...3500.0FalseNaNNoneNaNNaNNaNNaNNaNNaN
2Benq2053Good Bye 2024: 2025 is NEAR1735396500United StatesPrinceton3539.03833.022900800...3500.0True2.147484e+09C++23 (GCC 14-64, msys2)2.147479e+09NaNNaNNaNNaNNaN
3Egor2053Good Bye 2024: 2025 is NEAR1735396500GermanyAugsburg2937.03235.016000800...3500.0FalseNaNNoneNaNNaNNaNNaNNaNNaN
4Radewoosh2053Good Bye 2024: 2025 is NEAR1735396500PolandWarsaw3463.03759.019400800...3500.0FalseNaNNoneNaNNaNNaNNaNNaNNaN
\n", + "

5 rows × 64 columns

\n", + "
" + ], + "text/plain": [ + " author_handle contest_id contest_name contest_start_time \\\n", + "0 jiangly 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "1 ecnerwala 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "2 Benq 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "3 Egor 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "4 Radewoosh 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "\n", + " country city rating max_rating rating_achieved rating_1 \\\n", + "0 China Chongqing 3710.0 4039.0 22900 800 \n", + "1 United States Cupertino 3627.0 3668.0 15900 800 \n", + "2 United States Princeton 3539.0 3833.0 22900 800 \n", + "3 Germany Augsburg 2937.0 3235.0 16000 800 \n", + "4 Poland Warsaw 3463.0 3759.0 19400 800 \n", + "\n", + " ... rating_10 finished_10 relative_time_10 10_language \\\n", + "0 ... 3500.0 True 2.147484e+09 C++23 (GCC 14-64, msys2) \n", + "1 ... 3500.0 False NaN None \n", + "2 ... 3500.0 True 2.147484e+09 C++23 (GCC 14-64, msys2) \n", + "3 ... 3500.0 False NaN None \n", + "4 ... 3500.0 False NaN None \n", + "\n", + " time_to_answer_10 rating_11 finished_11 relative_time_11 11_language \\\n", + "0 2.147479e+09 NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN \n", + "2 2.147479e+09 NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN \n", + "\n", + " time_to_answer_11 \n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN \n", + "\n", + "[5 rows x 64 columns]" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Parte 4: Código para limpieza y creación de variables\n", + "from collections import defaultdict\n", + "from tqdm import tqdm\n", + "import pandas as pd\n", + "\n", + "# Crear diccionario para acceder fácilmente a los datos de cada usuario\n", + "# Esto evita tener que buscar a cada usuario en la lista de rated_users una y otra vez\n", + "users_dict = {user['handle']: user for user in rated_users}\n", + "\n", + "# Estructura para almacenar todo el dataset limpio\n", + "final_data = []\n", + "\n", + "# Recorremos cada concurso\n", + "for contest_id, data in tqdm(contest_details.items()):\n", + " contest_name = data['name']\n", + " contest_start = data['standings']['contest']['startTimeSeconds']\n", + " problems = data['standings']['problems']\n", + " \n", + " # Crear diccionario de problemas (para acceder por problem.index)\n", + " problem_info = {p['index']: p for p in problems}\n", + " \n", + " # Creamos un mapeo de handle -> cambios de rating\n", + " ratings = {r['handle']: r for r in data.get('rating_changes', [])}\n", + " \n", + " # Agrupar submissions por usuario y problema\n", + " submissions_by_user = defaultdict(lambda: defaultdict(list))\n", + " for sub in data['submissions']:\n", + " if 'author' in sub and 'members' in sub['author']:\n", + " handle = sub['author']['members'][0]['handle']\n", + " problem_index = sub['problem']['index']\n", + " submissions_by_user[handle][problem_index].append(sub)\n", + "\n", + " # Procesamos cada fila del standings (un usuario)\n", + " for row in data['standings']['rows']:\n", + " handle = row['party']['members'][0]['handle']\n", + " user_data = {\n", + " 'author_handle': handle,\n", + " 'contest_id': contest_id,\n", + " 'contest_name': contest_name,\n", + " 'contest_start_time': contest_start,\n", + " }\n", + "\n", + " # Añadir país, ciudad, rating actual y máximo (si tenemos)\n", + " if handle in users_dict:\n", + " user = users_dict[handle]\n", + " user_data.update({\n", + " 'country': user.get('country'),\n", + " 'city': user.get('city'),\n", + " 'rating': user.get('rating'),\n", + " 'max_rating': user.get('maxRating'),\n", + " })\n", + "\n", + " # Añadir rating_achieved\n", + " rating_change = ratings.get(handle)\n", + " if rating_change:\n", + " user_data['rating_achieved'] = rating_change['newRating']\n", + " else:\n", + " user_data['rating_achieved'] = None\n", + "\n", + " # Variables por problema\n", + " total_rating = 0\n", + " prev_time = 0\n", + " for i, prob in enumerate(problems, 1):\n", + " p_index = prob['index']\n", + " p_rating = prob.get('rating')\n", + " user_data[f'rating_{i}'] = p_rating\n", + "\n", + " # Revisamos si el usuario envió un \"OK\" para este problema\n", + " subs = submissions_by_user[handle].get(p_index, [])\n", + " solved = False\n", + " min_time = None\n", + " lang = None\n", + " for sub in subs:\n", + " if sub.get('verdict') == 'OK':\n", + " solved = True\n", + " if min_time is None or sub['relativeTimeSeconds'] < min_time:\n", + " min_time = sub['relativeTimeSeconds']\n", + " lang = sub.get('programmingLanguage')\n", + " user_data[f'finished_{i}'] = solved\n", + " user_data[f'relative_time_{i}'] = min_time\n", + " user_data[f'{i}_language'] = lang\n", + "\n", + " # Sumar rating logrado\n", + " if solved and p_rating:\n", + " total_rating += p_rating\n", + "\n", + " # Calcular tiempo entre respuestas (si hay min_time)\n", + " if min_time is not None:\n", + " user_data[f'time_to_answer_{i}'] = min_time - prev_time\n", + " prev_time = min_time\n", + " else:\n", + " user_data[f'time_to_answer_{i}'] = None\n", + "\n", + " user_data['rating_achieved'] = total_rating\n", + " final_data.append(user_data)\n", + "\n", + "# Convertimos a DataFrame\n", + "df_final = pd.DataFrame(final_data)\n", + "\n", + "print(f\"✅ Dataset final con {df_final.shape[0]} filas y {df_final.shape[1]} columnas.\")\n", + "df_final.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "9668f163-bb6b-4d6c-8588-073e0f55debe", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Fabrizio\\AppData\\Local\\Temp\\ipykernel_30260\\767654638.py:20: FutureWarning: \n", + "\n", + "Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `y` variable to `hue` and set `legend=False` for the same effect.\n", + "\n", + " sns.barplot(x=top_countries.values, y=top_countries.index, palette='viridis')\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Fabrizio\\AppData\\Local\\Temp\\ipykernel_30260\\767654638.py:39: FutureWarning: \n", + "\n", + "Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `y` variable to `hue` and set `legend=False` for the same effect.\n", + "\n", + " sns.barplot(x=language_counts.values, y=language_counts.index, palette='coolwarm')\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1IAAAImCAYAAABZ4rtkAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjEsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvc2/+5QAAAAlwSFlzAAAPYQAAD2EBqD+naQAAVvpJREFUeJzt3Qd4VGX2x/GThC6g4oqwoIvKCtgoCoiCYkPsvS4IKmBHsLOy9oKiguhiW9G/CItrb7gi6uq6KoLYKYoKCwqI0iFASOb//F652cmkkITAnJn5fp4nhExuZt6577137rnvec/NisViMQMAAAAAlFt2+RcFAAAAAAiBFAAAAABUEIEUAAAAAFQQgRQAAAAAVBCBFAAAAABUEIEUAAAAAFQQgRQAAAAAVBCBFAAAAABUEIEUAAAAqlQsFkt2E4DNjkAK2MyuvfZaa9GiRZlfPXv2tOeffz78f968ecluMhIk9s39998ffsbm22cOOeQQ80ztUzsz9f1XtUmTJoV9St9Lo/1Py2h/9C4vL89OOukk++CDD8yrzbWdLV++3K6++mqbMmVKlT7v999/H9qr5we8qJbsBgDp7qKLLrIzzjij8OeRI0fatGnT7IEHHih8rG7dutagQQN7+umnrWHDhklqKcrr1FNPtS5duiS7GUjjY8bZZ5+d7GZgEzz00EPWqFEj23///S3TtrPp06fbSy+9ZCeffHKVPu8uu+xihx56qN1666121113VelzA5VFIAVsZjvttFP4iihgqlGjhrVp06bYsvod/NMJkr6AzSH+eIHU8/PPP9sjjzxif//7382zVNzO+vXrZ127drVevXrZHnvskezmAKT2AV6UlNqn1IgePXpY69atrUOHDnbNNdfY4sWLi/zNXnvtFZbT1T/9/4gjjrC33347pEHow0Z/e/jhh9trr71W7LU+//xzO/HEE23vvfe2Y4891v75z38WadOKFSvsjjvusMMOOyw89zHHHGPPPvtsuVJ03n//ffvTn/4Unrtbt242duzYIstpGY3KKf1Fy0QjdLNnz7b+/fvbAQccEIJNpT1+8sknxdJ71FZdUdUyuuqrkb6VK1fan//8Z9tnn33CY0OHDi2Sp7927dpwJfOggw6yPffcM7zn8ePHF2lXQUFBeC59WGvd6TWWLVtWZJmSUvv0PHovbdu2DW2//vrri/1dIqWpDBs2zG6//XZr3769dezYMaTELF26tMhyzzzzTHhuvVetq+OPP95ef/31Iv25++67h+X02tpWZs2aZfn5+eGETv2mv9Pfa3T0o48+2mi71CZtP/q76667Ljyudul9ad1qezjttNPsww8/LPK3//nPf8LjWg96TxdeeKF99913lV5Xf/nLX8Iyei/xbrvttrC+lEIl33zzjZ1//vnWrl278HXxxRfb3Llzi22X48aNs4MPPjgso7aWRNuA1pv2G20n2qdGjx5tFaFtROvxnXfese7du4dtSeslPnWttDYlplzp/9o/1Cd6z1pvV1xxha1atSq088ADDwzb/KWXXmpLliwp0g5tE0cffXR4H9qm1a74danXUj/fcMMN4fWPOuqoYuu6vMeMaN98/PHHC9/zc889F3735Zdf2nnnnRfar9e54IIL7Ntvvy32OtpuzzrrrLB9af1vbL3/9NNPdvnll4dtXq+n96IR/6o4XuhvtT927tw5nLR36tQp/Jy4jhPp/f/+978P6zzexIkTw3av96ZtWiMrq1evLvy9+kbv+V//+ldYt9G29+KLL5b5eupDrVtlNOhYrb7Rfv7DDz+E7U/PpXWjkXSNFsX/XeJ2NmLECLvzzjvD+tDz6Hl1TI7oeKyv0tIy9RWNcul7/LIb2+/XrFljN954Y9ie9d61DT322GNFXmv77be3/fbbzx5++OEy1wmwpRBIAU5NnjzZevfubbVq1bLhw4eHD/yPP/44fDjpAyeyfv36cFKlD84HH3zQateubVdeeWU4UdGJk1JMlC6oIGzBggVFXkMnnkqV0EnazjvvbAMGDLB33303/E6voROaV155xfr06RNOPHTCoZNqPefGDBw4MJzc//Wvfw0fyjfddFOxYErPow95fXjrhEEnUfqg1QnM4MGD7e6777asrKxwcqT3Hk+/32233cJ71gnOfffdZ6ecckpYX3o/Ct7+9re/FZ7o6QRJJ9c6aT3nnHPC3+kDXe2MP1HRyZTarOfS82yzzTZ2zz33lPletW50MqeTNL0Xvc4bb7wRTiLi+6okWidTp04NAav6Uetf/RKd0I0ZMyaccOgESScPWica0VQfx/enTn5HjRoVAoxBgwbZrrvuGpZV204//fSwLm655ZYQDF122WWWm5tbZrv0ujrh099rXSgIVT+89dZbYZ1p3WhUTttGFEwpcNHJqk6CtH7VFp3M6SqygpPKrCsFjb/88kuRAETPpUBSAUL16tXDa2j7//XXX8NJoF5XbTnzzDPDY/HUbu0LWqfq/5LoZE5tO+6448I2qhM6BTHaLipCFz30WtqPtH1q29SJafzJbHnbpL6dP39+CLwVnL766qvh4okuWKhftU7VN2p3RNuLAlHtH3ofurDx6KOPhsfi6UKMnlvvT9tgTk5Oqe+prGNGfEDQt2/fcNFCJ8wK3NUXovWoAEKvpz5LDLK1H2jb0Paj9Fkt+3//93+lrl89x9dffx3ek/ZTbRt6n4nPW9HjhfYPHWv1PAoydUKvn3VBSn1QFh0zdTxLfEzbutLTtJ4vueQSe/nll8P+Eh+8LVq0yG6++ebwWgqSmzZtGraNxPeT6NNPP7WnnnoqBEdah1pe+53+rz679957wzrXcaMsTz75ZLgIp7/Tuv/qq6/C65eXAk5tx6LvWnfl3e+1bbz33nvh9bS+tZ1pG4qC8Yj2R10s1IUEIOliKNFDDz0U69GjR4X/7oUXXogdeeSRsT333DN21FFHxcaPH79Z2ofUdc0118QOPvjgYo8/99xzsd122y02d+7c8PPpp58eO+aYY2Lr168vXOb777+PtWrVKvbUU08V+ZuxY8cWLvPaa6+Fx4YPH1742Jdffhkee/PNN4v83QMPPFC4TEFBQez444+PnXrqqeHnMWPGhGWmTp1apJ1//vOfY3vttVdsyZIlJb6/jz76KPzdoEGDijx+4YUXxg444IDwOqJlevXqVWSZyy67LNaxY8fYihUrCh/Ly8uLHXHEEbGTTz45/Kz1o78dMGBA4TKLFi0Kj5111llF3k+7du1it956a/j5/fffD8to/cS78sorQ7v0OsuWLYvtsccesaFDhxZZ5rzzzivSNyNGjAg/y9KlS8P+/pe//KXI30yePDksE/VVSbQddOjQIbZ8+fLCx9RH+rt33303/HzHHXcUa89XX30Vlnn11VeL9OeLL75YZLnLL7889sQTTxR57I033gjLfvrpp2W267DDDivy2NNPPx3+7rPPPiuyjv/0pz/FTjrppPCz2qNlFixYULjM559/Hrv33ntDn5Z3XcXvI3oN/T9+e/rggw+KtEXvc//99y+y3Wj73GeffWJDhgwpsl3+9a9/jZVF+1iLFi1iDz/8cJHHhw0bFrb7xYsXF64jtbM00Taiz4RIbm5u2Naibbe0NiUeI/T/Ll26hG000r1791jbtm2LbDvnn39+7Ljjjgv/1+N777137Prrry/y3P/4xz/Ca37zzTeFr6Wf58+fX+Z6Kc8xI9o3dYyId8opp4TPw/hjmfY1bfv9+/cvsi5uuummIn970UUXxTp16hTLz88vfH61RbRdqU/mzZtXuPzatWtjhx56aOzSSy/dpOPFtGnTYmeeeWbsv//9b5H2aB3reFSaWbNmFTnWRs994IEHhuNIvGg7fuedd4psM3o88uOPP4bHHnvssVJfM+pDvXZE/Z74XHoOPaZ1X9p2pq/4frr//vvD30Tbvc6LEs+Nor7T95J+Lu9+r/U6ePDgIstoe4vWT2T69Onh7/71r3+Vuk6ALYURqVKuxGoEoKI0uVJX63U1TFetlE6jKzC6UgRUhK6GKoVGKWi6WqlRJ33tuOOOYaQhMSUp/ir2dtttF74rlSOiURVJrHakFJ2IRn6UVvLFF1+EK4QaAWrSpEmxK+S6Sq/RCbWvLPHPLbriq6utGj2ItGrVqsgyek2lOKn4RqRatWph5EFXRuOvQMa363e/+134rlSU+Pez9dZbh/RE0aiJHtM6jdanvpTOonYpzeizzz4LqWJqQ7wjjzyy1Pepv1m3bl3Y3+Ptu+++Yf0ljqQl0uvXq1evyM96zxqRFF1h1lVk9Z1eS8cZHaNErxsvcX3qCr1GkXTlXqMOurKrq+Al/W2ixOfS+lNaja44R+tOo2BaV+obpehom6tZs2a40q9RoX//+9/WsmXLMIKlPq3MulKfaZtTWlTUZh1fmzVrVriNa8RDqV0aXYjaptfT8yZWTUt8X4n0XNrn1A+J24m2+/g0041RP8a/V7VPaUtR35a3TdG2reeL3+Y1IhS/7Wg/j7Z3fe5oPy7pfUj8MUR/V945f2UdM0p6P0pdU1qf9qH4ka769euHbSexz5VaGE/Pr1FFjZIk0jap19phhx0K3192dnZYx4n9XtHjhZ5Xo8XaLpXaplE3jZKoHWXtO1E6qUaSIvobjR4n9oVSX7WdJh7P4+fPRv0SnwJYErVdnw2J77E8nwPxNAod30/R629sBLss5d3vlfb5j3/8I4xmanRN61IjV8qsiKe/ESrcwgOKTcRZuHBhGIZWCok+pCtCH7xKFdBwvAIpUfqFTl50kCgtXQMoiT7olKKiNBx9JdLJarz4wCOiFL+NSawQqCBM27JeXyfGOnFOFH1Ab6wErU5uEp9b4nPi69SpU2QZ/S56/sTXVLs0p6Gs95z4fPGU0qbn0PyM0iaIR+9p2223LfK7ktZDfJujNpbU7ujErLzrSSeCev3oef/73/+GFBmdNCqNTalBCk5Kuk9L4vvXCaxSKvVd20Pz5s3D3I2S/jZR4nNp/SngLG2Ct36n59cJkFKSNJdOaUI6YVZqm1LAKruulN6nlCwFZkr3mjBhQggQ49um+ReJ891KKuBS1jYSPZcoeC/tc6K89J7ig59oP0icA7exNlV2exeld5W2vUe22morK6+yjhkltUt9qt+Xt88Tl4s/bigQTXyPc+bMKXWbjD/5r+j6i+Y6KSVSr6N2KWVV+1FZ+3T0u/jjb9QX2hf1VVZfJP6tjgfl2V9Len/l3bZKe+34149ScyujvPu9LkQrcNPFHqWr6kvnTkq1jY558W2M/zwAkoVAKo7yrHWiop1YOcw//vhjkd9r0qZyvzWPQyc/+qBVfrPmK+gqu5bXfI94iRMlgfLQiY2ukGqOVEkndOUJksojOkGIaC6KrkbqyqWucOokpaQT5pKCjUSakB1fFSqaqxKdGJVEr6k2lPWaiScd5aUr9zqp0Ml9Sf7whz+EK+tRWxWwRBJPfBPbLGp3/N9E7dYoYlkSJ65rlEePKQDQyYtOhHVcUmCiq+Q6MdcxSCNTZdFJhuYvaRK4RnDUNp0U6cq65iZUZv3pApPmXZUkugIfFQ7RFWiN3mgCvE5GdSJU2XWlkRc9r+ZF6T3opF2jVPFt0zw8zX1LlBjIbIwCP9G8nJICjCgQLY+Sthu997L2gaoSvQ/1V0kXBks6qd3UY0ZJ+6b6Rsey0vbraJQkklh0JPq7ktaZnlsjkSoAURJ9NleW5jQNGTLErrrqqjBvMwrINb9QFyZKEx0X4wPLqC/UTrU3UbRfpIrEYiTlGS0rz36v/tIFaH2piIjOuTS3SvP24osllXbBC0gGUvviaNhdgVJJH+aaAKkrqqq6pEm+GrnSh7oOshKlK+mAosnEmsyqCjmaEAlUlK4uqlCDUkKUahF9/fGPfwzbaFk3rawIpUtFdMVTV/pVUEIfaEo70cWBxNRUXWjQiX18WszGnls0iVspGWWV3NVr6sMz/kqjPrT1Iar3vyknRjqB0f6p9xm/TlXtTRdOlGqjq5+66p1YvVBtKo1SZ9QuHRfiaTRaJwOljYDFH1viU4VUMEBt0TFEAZWOLUqVU1ujoEB/s7GrxNp2dNKrUXKNFEVXlsvzt6WtP01W1wlt/PpTWpIm6etk+oknngjpWno/Wid6D7qqLFoXm7KuNCqlESltC1ou/jgdVSlUoBm1S6MHas+bb75ZofepdCPRuo9/n0qPVNZBWUF1IqW7qc3xP2v9a71sblrX2k81ghb/PrQNqfBAZdOiyjpmlEQXL9QX+ryMPwHXKISq0+lv4+mxeOrvxo0bhwsdidTv2j8UaMe/R11k0IWHsopmbIwuAigA0sWIKIhSarEeL2vfiQLt+EIwCh6032idx7dTF2SVfhtfZTAVPpsSixYlprsmrvfy7PfaN1SgQ0VVovWo7B5dSNQy8aLXr8hFDWBzYUSqnHRFVUFUdGNVnQxqiF7pJTo4Rid+qjajajya06CrvhqxUnrAlvjgRHrR/DqNRuhqnK6+R1XZNDdJ21VVUEUkzfvQiYjKJKvSU1QhS1dhNUdAOeoqR64RB10Y0DwbbePRVdbSaLtXCqLy/XWypWBkY9Xv9Lw60dTJfzQSE+XK62R9U2hulAI1rTt9aT6BRqBUQUrpYtHJkn6nOZIa9VOZXY3glBVI6Yq62qpgTO1VIKFjgk66FcAkzhVLpOBEV2D1nvV/neSqPZovIAo+NSdKKS9a5zoxj0bVypq3oD7VSY+OXTp51peOSVH5+orOedD2oL7QqI8qQurkVvNQlHqqEv1671pfGgHRNqPHdEKlKok6idJ62ZR1pbkzGiFQ+l5UCSzxpteqTqbqcNruNBKmk/74KnbloRE87W+qAqcLCQoCdLKuSm3aByqa9q0KiroIpxNpZSgomFd/b266Wq8gQOtWn0/anhRU6WeNEMWnSlXVMaM0OobpAqP6Xmmemoeo9E8F3NpW4qncuUYCdSFJQZS2d72m2pxII/YKmvT93HPPDe9Z24fm2Wi9bwpdKNJ9oLTNaTvVaJv6T6MqZY0gKWjSCb6CC83vEu0HmieoFF39X8+nURWNtqhPUul+SGq7PgdU1U8XnxUMJZZnj+btKSjWutK2trH9XhewtB40mq1ltB9qv3vhhReKVUDUutXxObroASQTgVQ56YqRTrri76ET5Szrg0Q7vujDIjoZ0NVR/R2BFCpD9y7RB7c+WBTIaBvTB422p5Ju5lsZyj1XiWQFKjpxUaAWfTjpg0onNQp+opMxnSSoiIBGSDZG5dr1Iajn199FJc7LohE3BW8KJnQipJMnndAocNjUD02NyOjkTe9FbVL6nq4IKzCIP5nTybiuouvkUF8apdIFEq2r0uj+PUp3UqChE3gFDCrRqxPojc1R0BVXBUjRsjp+6KQropMtrXMVnVBAohMPzRdSqWCdxCTe0yX+ZEZ/q5NQpSPp5FTHJLVRk7n1t/H3kNkYtU0BnbYHlYjXiIKCPJ0k6yRWdMKkwE0nTLoQoOBfgYi2qyilp7LrSoGu9gmNgGn5eHpdtU3BjtKndGxWqWu1QyWUK0onidpGFATq6reCIAVyamNFRzm03aivNKKlK+86OS9pdGVzUHs1v0/7lC5E6KRWn0Xqm/giFVV1zCiNXlPHLR0D9NrajvU3KlWvfT6eSm6rrbqYoVFHHQtKm6+m/Vd9pG1S7VKAp0C3vMeosmg/1Mm+Lhxp/em1dDFGgaCCbH3uxxd3iKfjnC4IaZ+NKENF+6Dem7Z7bevaHnThYWPpv56o5L7mberYrnWvi1Pq16i8vahPVVhC+6QCYY1ElWe/V9l39bu2KaX8ab9TP+r4FU/rVgUoEufMAcmQpdJ9SXll53QA1NXI6GaAOpnTyUJJV0z1QaX7gugAqwNH/IeKTmJ0VaakSdBAsujmmgpUlEYWX12qKkQ3ZFTwE42qoGQKZJSepKveSC9KwdVFkJkzZ1o62JzHjHSjUSbd900BgQINVB2dl2mkTxe1FcgDycYcqXLSFRYNM+tKYvSlK5UKlJQ3rZECXW1KLAmt+RdlzQkBAADpQ6NXSjcsqeIqNo2CU41kEUTBCwKpclIqjOYX6AqjAiqVItbVOaW3aERKQ8zKR1cqiYaxNfSt9BuloZRUSQoAAKQnpbJpZOr9999PdlPShtIpNT9Lc80AL0jtK2dqn6jqkHLDVR1K+b1Ky1FRifhJ98oDVw6wDqDKn9bBVEP8AAAAANIHgRQAAAAAVBCpfQAAAABQQQRSAAAAAFBBGX8fqU8//TTccyS6DxQAAACAzJSXlxfuY6n7SG5Mxo9IKYjyMk1M7dCd3r20J5PRFz7QD37QFz7QDz7QD37QFz7E0qgfKhIbZPyIVDQStddeeyW7KbZ69epwY9/mzZsX3ukbyUFf+EA/+EFf+EA/+EA/+EFf+LA6jfrhyy+/LPeyGT8iBQAAAAAVRSAFAAAAABVEIAUAAAAAFUQgBQAAAAAVRCAFAAAAABVEIAUAAAAAFUQgBQAAAAAVRCAFAAAAABVEIAUAAAAAFUQgBQAAAAAVRCAFAAAAABVEIAUAAAAAFUQgBQAAAAAVRCAFAAAAABVEIAUAAAAAFUQgBQAAAAAVRCAFAAAAABVEIAUAAAAAFUQgBQAAAAAVRCDlyBezfrVx7/1iS1esTXZTAAAAAJSBQMqRNyfPsxnz1tjUb35JdlMAAAAAlIFAypFY7Lfv+fkFyW4KAAAAgDIQSDmSvaE3CjYEVAAAAAB8IpByJDsrK3wviIamAAAAALhEIOUxkGJICgAAAHCNQMqR7OzfAikGpAAAAADfCKQc2TAgRWofAAAA4ByBlMMRKVL7AAAAAN8IpByOSDEgBQAAAPhGIOUIxSYAAACA1EAg5TG1jyEpAAAAwDUCKYcjUjECKQAAAMA1V4HUww8/bD179ixzmW+//db69etnHTt2tE6dOln//v3tp59+snSwYUDKyOwDAAAAfHMTSI0ZM8aGDx9e5jJLliyxc845x2rVqmWjR4+2Rx991BYvXmx9+vSxtWvXWqrLYo4UAAAAkBKqJbsBCxcutBtuuMEmTZpkzZo1K3PZiRMn2urVq+2uu+4KwZQMHTrUunbtalOnTg0jVKmMOVIAAABAakj6iNTXX39t1atXt5dfftlat25d5rIKlEaOHFkYREl29m9vYfny5ZbqKH8OAAAApIakj0gdcsgh4as8mjZtGr7iPfLIIyGwat++faXboOIOGulKtoL8/PB93bo8F+3JZLm5uUW+IznoBz/oCx/oBx/oBz/oCx9y06gfFBdE023cB1KbQvOknnrqKRs8eLA1aNCg0s+Tl5dn06dPt2RbvnxZ+L5s2XIX7YHZ7Nmzk90E0A+u0Bc+0A8+0A9+0Bc+zE6TfqhRo0b6BlKKFO+77z578MEH7cILL9xopb+NUWph8+bNLdmmzplhZiusbr161qpVq2Q3J6PpiooOBpq3V7t27WQ3J2PRD37QFz7QDz7QD37QFz7kplE/zJo1q9zLplwgpdGjQYMG2auvvhq+9+7de5OfU8N3derUsWSrUaN6+J6dk+OiPbBwMKAvko9+8IO+8IF+8IF+8IO+8KF2GvRDedP6UjKQuvrqq+3NN9+0e+65x44++mhLxxvyUv4cAAAA8M11IJWfnx/uE1WvXr1QUOL555+38ePHh2CqQ4cOtmjRosJlo2VSGeXPAQAAgNSQ9PLnZZk/f7517tw5BE+idD7RfaT0ePxXtEwq2xBHUf4cAAAAcM7ViNSQIUOK/KxS5zNnziz8edSoUZbOsqIRKVL7AAAAANdcj0hlmmiOFCNSAAAAgG8EUo5ERUIYkQIAAAB8I5ByhGITAAAAQGogkPJY/pxACgAAAHCNQMph1b6CgmS3BAAAAEBZCKQcpvbFGJECAAAAXCOQciSL1D4AAAAgJRBIOUL5cwAAACA1EEg5QvlzAAAAIDUQSDnCHCkAAAAgNRBIeazaRxwFAAAAuEYg5fE+UkRSAAAAgGsEUg5T+6jaBwAAAPhGIOUI5c8BAACA1EAg5XCOFHEUAAAA4BuBlCNZUWofc6QAAAAA1wikPBabYEgKAAAAcI1AyuENeWMFyW4JAAAAgLIQSDlC1T4AAAAgNRBIOUJqHwAAAJAaCKQcVu0rILUPAAAAcI1AymFqX4wRKQAAAMA1AilHuCEvAAAAkBoIpDzOkeI+UgAAAIBrBFKOZG/oDQakAAAAAN8IpBwhtQ8AAABIDQRSDlP7KDYBAAAA+EYg5QjlzwEAAIDUQCDlsPw5qX0AAACAbwRSjjBHCgAAAEgNBFIOq/aR2gcAAAD4RiDlCMUmAAAAgNRAIOUIqX0AAABAaiCQclhsgjgKAAAA8I1AymX5cyIpAAAAwDMCKYdzpEjtAwAAAHwjkHI4R0pxFAUnAAAAAL8IpByWPxey+wAAAAC/CKQcpvYJI1IAAACAXwRSDlP7hIITAAAAgF8EUg7LnwsFJwAAAAC/CKQciYujGJECAAAAHCOQcjpHijgKAAAA8ItAypG4OIpiEwAAAIBjBFJe50gxJAUAAAC4RSDltWofI1IAAACAWwRSzkSxFCNSAAAAgF8EUs5E2X0MSAEAAAB+EUg5w4gUAAAA4B+BlNN5UsyRAgAAAPwikHImKjdBIAUAAAD4RSDldI4UqX0AAACAXwRSzmRtiKQYkAIAAAD8IpDymtrHiBQAAADgFoGU19Q+hqQAAAAAtwiknKH8OQAAAOAfgZQzlD8HAAAA/COQcpraRxwFAAAA+EUg5QypfQAAAIB/rgKphx9+2Hr27FnmMkuWLLErrrjC2rdvbx06dLCbbrrJcnNzLV2Q2gcAAAD4V82cGDNmjA0fPtz23XffMpfr379/CJyeeOIJW758uV133XW2evVqu/POOy0dMCIFAAAA+Jf0QGrhwoV2ww032KRJk6xZs2ZlLvvpp5/axx9/bOPHj7ddd901PHbzzTdbnz597PLLL7cddtjBUh1zpAAAAAD/kp7a9/XXX1v16tXt5ZdfttatW5e57JQpU2z77bcvDKJE6X1Kh/vkk08sHXBDXgAAAMC/pI9IHXLIIeGrvKNXjRs3LvJYjRo1bJtttrH58+dXug2xWCykByabUhajOVKr16xx0aZMFc27S6f5d6mIfvCDvvCBfvCBfvCDvvAhN436QXFBdD7uPpCqCHWOAqdENWvWtLVr11b6efPy8mz69OnmKbVvzpz/Wo28n5PdnIw3e/bsZDcB9IMr9IUP9IMP9IMf9IUPs9OkH0qKN1I+kKpVq5atW7eu2OMKourUqVPp51VqYfPmzc3HiNTC8P+mTZtaqxbbJ7tJGUt9oYOB5u3Vrl072c3JWPSDH/SFD/SDD/SDH/SFD7lp1A+zZs0q97IpFUg1atTIJk6cWOQxBVZLly61hg0bVvp5NXy3KYFYVYqGEmvUqOmmTZlMBwP6IfnoBz/oCx/oBx/oBz/oCx9qp0E/lDetz0WxiYrQvaMWLFhgc+bMKXxMVfxkn332sXQQ9V0+xSYAAAAAt1wHUvn5+bZo0SJbs2ZN+FlV/dq1a2cDBw60L774wj766CO7/vrr7YQTTkiL0ufxc6S4IS8AAADgl+tASpX4OnfuHO4bFQ21PfDAA2H+UK9evWzAgAF24IEH2o033mjpIhqRUsUQAAAAAD65miM1ZMiQIj8rYJo5c2aRx7bbbjsbMWKEpasoL5P7SAEAAAB+uR6RykT/S+1LdksAAAAAlIZAypmoTggjUgAAAIBfBFJOU/uYIwUAAAD4RSDltNgEI1IAAACAXwRSzlD+HAAAAPCPQMrriBRxFAAAAOAWgZQzlD8HAAAA/COQciZK7aPYBAAAAOAXgZQzFJsAAAAA/COQ8praRxwFAAAAuEUg5Qw35AUAAAD8I5ByJntDj1D+HAAAAPCLQMrpHCmKTQAAAAB+EUg5k7UhuY/UPgAAAMAvAimn5c+JowAAAAC/CKScofw5AAAA4B+BlNPy58yRAgAAAPwikPI6IkUgBQAAALhFIOV1jhSpfQAAAIBbBFJuR6SS3RIAAAAApSGQcjpHihEpAAAAwC8CKaepfRSbAAAAAPwikHJmQxzFiBQAAADgGIGU0zlS+YxIAQAAAG4RSLm9j1SyWwIAAACgNARSzlD+HAAAAPCPQMppah/FJgAAAAC/CKScpvblMyIFAAAAuEUg5QzlzwEAAAD/CKScpvYVFCS7JQAAAABKQyDlNZBiRAoAAABwi0DKmawNt+QlkAIAAAD8IpByJntDj1D+HAAAAPCLQMoZyp8DAAAA/hFIeU3to9gEAAAA4BaBlNPy58yRAgAAAPwikHKGqn0AAACAfwRSbu8jRSAFAAAAeEUg5Uz2hkiKYhMAAACAXwRSbkekkt0SAAAAAKUhkHKGOVIAAACAfwRSzmRtiKSYIwUAAAD4RSDltPw5c6QAAAAAvwiknNkQR5HaBwAAADhGIOUM5c8BAAAA/wiknJY/J44CAAAA/CKQcoYRKQAAAMA/AimngRTFJgAAAAC/CKSc4T5SAAAAgH8EUl7nSJHaBwAAALhFIOV2RCrZLQEAAABQGgIpZyg2AQAAAPhHIOU0tY9iEwAAAIBfBFLOMCIFAAAA+Ecg5QxzpAAAAAD/CKSc2RBHUf4cAAAAcIxAyhnKnwMAAAD+EUg5Te2j2AQAAADgV9IDqYKCAhsxYoR16dLF2rRpY3379rW5c+eWuvyvv/5qV1xxhe23337WsWNHGzhwoC1cuNDSBcUmAAAAAP+SHkiNHDnSxo4da7fccouNGzcuBFZ9+vSxdevWlbj8gAED7KeffrLHH388fOn/F198saVdah9xFAAAAOBWUgMpBUujRo2y/v37W9euXa1ly5Y2bNgwW7BggU2YMKHY8suXL7ePP/44jFq1atXKdt99d+vXr599+eWXtnTpUkuvqn1EUgAAAIBXSQ2kZsyYYatWrbJOnToVPla/fv0QIE2ePLnY8rVq1bKtttrKXnzxRVu5cmX4eumll2znnXcOf5dWc6QYkgIAAADcqpbMF9fIkzRu3LjI4w0bNiz8XbwaNWrYkCFD7Prrr7d9993XsrKywrJPPfWUZWdXPiZUYYfVq1dbsuXm5hYGUvlO2pSp1Bfx35Ec9IMf9IUP9IMP9IMf9IUPuWnUD4oLFGO4D6Sila0AKV7NmjVt2bJlJb6x6dOnW9u2bcM8qvz8/JAKeNFFF9nf//53q1u3bqXakZeXF57XW/lzL23KZLNnz052E0A/uEJf+EA/+EA/+EFf+DA7TfohMTZxGUgpVS+aKxX9X9auXWu1a9cutvzrr78eRp/eeeedwqDpoYcesoMPPtieffZZ6927d6XaUb16dWvevLklmwLLr2Z8F/6vKVKaB4bk9YUOBs2aNStxW8SWQT/4QV/4QD/4QD/4QV/4kE79MGvWrHIvm9RAKkrp+/nnn22nnXYqfFw/t2jRotjyU6ZMCfOh4keett566/DYnDlzKt0ODd/VqVPHPIgfSKxVq7ZlZ5dvaBGbhw4GXraNTEY/+EFf+EA/+EA/+EFf+FA7DfqhvGl9SS82oSp9CoomTZpUpDLftGnTrH379sWWb9SoUQiYNGIV0TyiefPmhQg4HcQHTtyUFwAAAPApO9n5hz169LC7777b3nrrrVDFTzfYVcDUrVu3MAdq0aJFtmbNmrD8CSecUHgvKS2rr8svvzzMqTrppJMsHcTHwJRABwAAAHxK+g15dQ+pU045xQYPHmxnnnmm5eTk2GOPPRbmLc2fP986d+5s48ePD8uqQp9u3quRml69etk555wTltNj9erVs3QQP5pIBXQAAADAp6TOkRIFTldddVX4StS0aVObOXNmkcd23XXXUGAiXRUJpIikAAAAAJeSPiKFksufC4EUAAAA4BOBlOMRKYpNAAAAAD4RSDkOpPIZkQIAAABcIpBynNrHgBQAAADgE4GUQ1EsRflzAAAAwCcCKcc35aXYBAAAAOATgZTj9D5GpAAAAIA0vI/Ur7/+auvWrSusLldQUGC5ubk2ZcqUcHNdVM6GASlGpAAAAIB0CqRmzJhhV155pX333Xcl/j4rK4tAqgpS+xiQAgAAANIokLrrrrts2bJlds0119g777xjNWrUsIMPPtjee++98PXkk09WfUsziAJRIbUPAAAASKM5Up9//rlddtll1rt3bzvqqKNCOt9ZZ51lDz30kB122GE2evToqm9pJs6RIrUPAAAASJ9ASvOimjVrFv6v70r1i5x00kn22WefVV0LMxDlzwEAAIA0DKR+//vf29y5cwsDqZUrV9q8efPCz0rzU9ofKo/y5wAAAEAaBlLdunWze+65x9544w3bYYcdbJdddrHhw4fbzJkzbdSoUbbjjjtWfUszsGofA1IAAABAGgVSl1xyibVr186effbZ8POgQYPszTfftBNOOME++ugju/TSS6u6nRmFOVIAAABAGlbtq1mzpo0YMcLy8vLCz126dLFXXnnFvv76a9tjjz1sp512qup2ZmZqH0NSAAAAQPrdkLd69eqF/1fwRABVNSh/DgAAAKRJIHXooYfaX//6V2vZsqUdcsghhSf7JdHvJk6cWFVtzNw5UgXJbgkAAACATQqkOnToYFtttVXh/8sKpLBpGJECAAAA0iSQuuOOOwr/P2TIkGK/X79+vVWrtkmZgtiA8ucAAABAGlbtk0ceecT69etX+PMnn3xinTt3tqeeeqqq2paxCqv2MSIFAAAApE8gpXtF6b5RuhlvRIUmunfvHkarnnnmmapsY8aJsiYZkQIAAAB8qlQu3rhx42zAgAFFRqQaN25sgwcPtt/97nf2xBNP2KmnnlqV7czI1D4GpAAAAIA0GpFauHCh7bXXXiX+rnXr1jZv3rxNbVdGi6r2kdoHAAAApFEg1aRJE/vwww9L/N3kyZOtUaNGm9qujMYNeQEAAIA0TO077bTTbOjQoZaXl2eHHXaYbbfddrZ48WJ755137PHHH7crrrii6luaieXPmSMFAAAApE8g1bt375DeN3r06DAfKpKTk2O9evWyc845pyrbmLlV+wikAAAAAJcqfeOna665xi666CL79NNPbdmyZVa/fn3be++9bdttt63aFmag7A0Jl2T2AQAAAD5t0h1069WrZwceeGDVtQYBqX0AAABAGgZSa9assQcffDDMicrNzbWCgoJigcDEiROrqo0ZhxvyAgAAAGkYSN1222327LPPWocOHaxVq1aWHeWioUpQ/hwAAABIw0BqwoQJNnDgwCI35MVmKH9Oah8AAADgUqWGklT2XIUlsHnnSMUYkQIAAADSJ5Dq3Lmzvffee1XfGhRJ7csvOvUMAAAAQCqn9h111FF2ww03hJvwtm7d2mrXrl1smRNOOKEq2pfRqX2MSAEAAABpFEgNGDAgfH/xxRfDV0mpaQRSVVD+nEAKAAAASJ9A6q233qr6lqBY+fMYxSYAAACA9AmkmjRpUuTntWvXWo0aNQpHUrBpotWYz4gUAAAAkD6BlHz//fc2YsQI++CDD2zlypX2zDPPhHtL7bLLLtazZ8+qbWXGlj9PdksAAAAAVFnVvunTp9spp5xiX3/9tR177LGFRRFycnLs9ttvtxdeeKEyT4vE1D5GpAAAAID0GZG68847bc8997RRo0aFn8eMGRO+Dx48OKT5Pfnkk3biiSdWbUszSPaG8JYb8gIAAABpNCL12WefWe/eva1atWrF5kWpNPrs2bOrqn0ZPSJF1T4AAAAgjQKpmjVr2po1a0r83dKlS0PhCVQe5c8BAACANAykDjjggFBoYsGCBUVO/letWhXS/fbff/+qbGPGiVL7iKMAAACANJojddVVV9npp59u3bt3t5YtW4YgasiQIfbDDz+EAgn33ntv1bc0E0ekmCMFAAAApM+IVOPGje2ll16yXr16hcBpp512stWrV9sxxxxjzz//vO24445V39JMnCNFIAUAAACk132ktt12Wxs4cGDVtgZF7yNFbh8AAACQPoHU5MmTN7pM+/btK/PUCCNSv31nRAoAAABIo0CqZ8+eYR5P/A1jE8ug66a92NQb8ia7JQAAAACqLJDSDXcTaY7UlClTwtyp+++/vzJPiw0ofw4AAACkYSDVoUOHEh/v2rWr1alTxx588EF7+OGHN7VtlunlzwmkAAAAgDSq2leWfffd1z7++OOqftqMQvlzAAAAIMMCqbffftu22mqrqn7ajEL5cwAAACANU/vOPvvsYo8VFBTYggUL7Mcff7S+fftWRdss01P7yOwDAAAA0iiQiq/WF8nOzrbddtvNzj//fDv55JOrom0Zi2ITAAAAQBoGUqNHjy722Pr1661atUrf3xdxSO0DAAAA0nSO1COPPGL9+vUr/PmTTz6xzp0721NPPVVVbctYhTfkZUQKAAAASJ9AatSoUTZ8+HBr1qxZ4WM77bSTde/e3YYMGWLPPPNMVbYx42RviKQYkQIAAADSKJAaN26cDRgwwP785z8XPta4cWMbPHiwXXLJJfbEE0+U+7lUpGLEiBHWpUsXa9OmTShUMXfu3FKXz8vLs3vuuadw+R49etj06dMtHedIMSAFAAAApFEgtXDhQttrr71K/F3r1q1t3rx55X6ukSNH2tixY+2WW24JAZoCqz59+ti6detKXP7GG2+0559/3m6//XZ77rnnrEGDBiH4WrFihaULRqQAAACANAykmjRpYh9++GGJv5s8ebI1atSoXM+jYElpgv3797euXbtay5YtbdiwYaGM+oQJE4otr5EqBU+33XZbGJHadddd7dZbb7UaNWrYV199ZemCOVIAAACAb5Uqs3faaafZ0KFDQ5rdYYcdZtttt50tXrzY3nnnHXv88cftiiuuKNfzzJgxw1atWmWdOnUqfKx+/fq2++67h4DsmGOOKbL8f/7zH6tXr54deOCBRZbXTYDTCeXPAQAAgDQMpHr37h3S+1QGPX4+VE5OjvXq1cvOOeeccj2PRp6i+VXxGjZsWPi7eD/88IPtuOOOYbRKVQPVBgVd1157bRidSrfUPuIoAAAAwKdK3/jpmmuusYsuusg+++wzW7p0aRgZ2nvvvW3bbbct93Pk5uaG70rNi1ezZk1btmxZseVXrlxpc+bMCfOqrr766vCaDz74oJ111lk2fvz4MDJW2RsMr1692pItWh/r8/LC97y89S7alYmivoi+IznoBz/oCx/oBx/oBz/oCx9y06gfFBdE2WEbs0l30N1qq61s++23Dy/Yrl27cFPeiqhVq1bhXKno/7J27VqrXbt28cZWqxaCKc2jikag9P+DDjrIXnjhhVCkojKUouip8t/ixb+G78uWr3DVrkw0e/bsZDcB9IMr9IUP9IMP9IMf9IUPs9OkHxIHeao8kHrppZdCGfJFixaFqE33jrr//vutevXq4fHyNCBK6fv555/Dfagi+rlFixbFllcRCwVT8Wl8CsCU7leRSoGJ1ObmzZtbsimK1wa4/fa/M7MlIVBt1apVspuVkaK+0L3SSgrqsWXQD37QFz7QDz7QD37QFz7kplE/zJo1q9zLViqQUhqdUvuOO+44O/jgg23gwIHh8cMPP9xuuummkHqn+0xtjKr01a1b1yZNmlQYSC1fvtymTZsW7g+VqH379mHU68svvywsv75mzZpQze/oo4+2ylIgWKdOHfOiVs3fgtCsrGxX7cpEOhjQB8lHP/hBX/hAP/hAP/hBX/hQOw36obxpfZUOpB566CE744wzwj2d8vPzCx8/+eSTQ/W+f/zjH+UKpDRqpYDp7rvvDveDUll1VQPUyFO3bt3Cc+v5VKlPI0/77ruv7b///iGIu/nmm22bbbYJN/NVkYvjjz/e0kU2N+QFAAAA0u8+Uqqep9Gn0m7Iq2p65aV7SJ1yyik2ePBgO/PMM0NQ9Nhjj4V0u/nz51vnzp3DCFhE6YMdOnSwSy65JPyd5kw9+eSTIRBLF5Q/BwAAAHyr1IiUquN99913dsABBxT7nR6vSPU8BU5XXXVV+ErUtGlTmzlzZpHHlAqokTB9pauo/DmBFAAAAJBGI1JHHXVUSKn75z//GSruRaMoX331VZgf1b1796puZ0bZEEdZQQGBFAAAAJA2I1Ka//TNN9+E79nZv8ViPXv2DPc80jymyy67rKrbmVGiOVIEUgAAAIBPlQqkVCTib3/7m/3nP/+xjz76KNyQVwUhNHdJ93SqSLULFBetPjL7AAAAgDQKpM4777xw81vNkSppnhSqZo5UPpEUAAAAkD5zpKZOncqo0xYIpGIEUgAAAED6BFJdunSxl19+2fLy8qq+Rfhf+XPmSAEAAADpk9pXs2bNEEi9/vrrtuuuuxa7g7ECgf/7v/+rqjZmbNU+BqQAAACANAqkFixYYG3bti38OTEFjZS0qhmRymdECgAAAEjtQGrChAm23377Wf369W306NGbt1UZrvCGvARSAAAAQGrPkdK9oWbPnl3ksUcffdR+/fXXzdGujBbdR4qRPQAAACDFA6nEk/r8/Hy79957Q5ofNs8cqQICKQAAACB9qvZFGDHZzKl9rF4AAAAg/QIpbB7RLbqYIwUAAAD4RCDleI4UgRQAAACQpoFUVKobVSdap6ROAgAAAGlwH6mLL77YatSoUeSxCy64wKpXr14sEJg4cWLVtDCj50gRSAEAAAApHUideOKJm7clKF61ryDZLQEAAACwSYHUHXfcUd5FUVVzpBiRAgAAAFyi2ITj1D7mSAEAAAA+EUg5RPlzAAAAwDcCKc/FJgikAAAAAJcIpByXPyeOAgAAAHwikPJctY85UgAAAIBLBFIOUWwCAAAA8I1AynH5c8VRBFMAAACAPwRSjgMpYZ4UAAAA4A+BlENxcRSV+wAAAACHCKQcz5ESCk4AAAAA/hBIOS5/LjFGpAAAAAB3CKQcihuQYkQKAAAAcIhAyn1qX1KbAgAAAKAEBFLeq/YRSQEAAADuEEg5r9rHfaQAAAAAfwiknBabiIIpRqQAAAAAfwiknKf3UWwCAAAA8IdAynnBiYKCZLcEAAAAQCICKef3kmJECgAAAPCHQMqpnA09Q7EJAAAAwB8CKe8jUhSbAAAAANwhkHJebCKfQAoAAABwh0DK+YgUqX0AAACAPwRSTuVEVfuIowAAAAB3CKScyqbYBAAAAOAWgZTz1D7mSAEAAAD+EEg5vyEvI1IAAACAPwRSTlH+HAAAAPCLQMqpnMJAKtktAQAAAJCIQMqpDXGUFZDaBwAAALhDIOV8jhSBFAAAAOAPgZRTFJsAAAAA/CKQciqbYhMAAACAWwRS3gMp4igAAADAHQIpp7I29AwjUgAAAIA/BFLuR6QIpAAAAABvCKScB1IxRqQAAAAAdwiknKL8OQAAAOAXgZT7QCrZLQEAAACQiEDKqQ2ZfRSbAAAAABwikPI+R4rUPgAAAMCdpAdSBQUFNmLECOvSpYu1adPG+vbta3Pnzi3X37788svWokULmzdvnqUbbsgLAAAA+JX0QGrkyJE2duxYu+WWW2zcuHEhsOrTp4+tW7euzL/78ccf7eabb7Z0RbEJAAAAwK+kBlIKlkaNGmX9+/e3rl27WsuWLW3YsGG2YMECmzBhQql/p2Drqquusj322MPSPpAqSHZLAAAAALgKpGbMmGGrVq2yTp06FT5Wv35923333W3y5Mml/t1DDz1keXl5dv7551vaF5tgRAoAAABwp1oyX1wjT9K4ceMijzds2LDwd4m++OKLMIr17LPP2sKFC6ukHSrosHr1aku23Nzcwu+xDUNRa9euddG2TBPfF0ge+sEP+sIH+sEH+sEP+sKH3DTqB8UFWdGIhudAKlrZNWrUKPJ4zZo1bdmyZcWWV0Bx5ZVXhq9mzZpVWSCl0a3p06ebF7Nnz7aVK1eE///403ybPv23/yM5fYHkox/8oC98oB98oB/8oC98mJ0m/ZAYm7gMpGrVqlU4Vyr6fzQKU7t27WLL33rrrbbzzjvbGWecUaXtqF69ujVv3tySTYGlNkAFiVt/vs5s3hrbYYdG1qrVjsluWsaJ74uStkVsGfSDH/SFD/SDD/SDH/SFD7lp1A+zZs0q97JJDaSilL6ff/7Zdtppp8LH9bPKmid67rnnQoTYtm3b8HN+fn74fswxx9gFF1wQvipDw3d16tQxL7QBVq/2W9dUq1bdVdsyjfqC9Z989IMf9IUP9IMP9IMf9IUPtdOgH8qb1pf0QEpV+urWrWuTJk0qDKSWL19u06ZNsx49ehRbPrGS3+effx6q9z3yyCO22267WTqh/DkAAADgV1IDKY0uKWC6++67rUGDBtakSRMbOnSoNWrUyLp16xZGnBYvXmz16tULqX9/+MMfivx9VJDi97//vW2zzTaWjoGUJrwBAAAA8CXpN+TVPaROOeUUGzx4sJ155pmWk5Njjz32WJi3NH/+fOvcubONHz/eMk32hmHFggICKQAAAMCbpI5IiQInpefpK1HTpk1t5syZpf5tx44dy/x9WgRSxFEAAACAO0kfkcJGbshLJAUAAAC4QyDlFMUmAAAAAL8IpJyn9sUYkQIAAADcIZByPiKVz4gUAAAA4A6BlPvy58luCQAAAIBEBFJOUWwCAAAA8ItAyvscKYakAAAAAHcIpJwHUvmMSAEAAADuEEg5RflzAAAAwC8CKedzpIijAAAAAH8IpLyPSJHaBwAAALhDIOVUzoYhKVL7AAAAAH8IpJzKYkQKAAAAcItAyn3582S3BAAAAEAiAimnuCEvAAAA4BeBlFM5lD8HAAAA3CKQcor7SAEAAAB+EUg5lRVV7SO1DwAAAHCHQMopik0AAAAAfhFIObUhs48RKQAAAMAhAimnmCMFAAAA+EUg5RRzpAAAAAC/CKScYkQKAAAA8ItAyimKTQAAAAB+EUg5lb2hZ0jtAwAAAPwhkHI+IkVqHwAAAOAPgZRTFJsAAAAA/CKQcopiEwAAAIBfBFJOUWwCAAAA8ItAyimKTQAAAAB+EUg5RbEJAAAAwC8CKaeyojlSjEgBAAAA7hBIuZ8jRSAFAAAAeEMg5T21ryDZLQEAAACQiEDKe7EJRqQAAAAAdwikvN+Ql0AKAAAAcIdAyvsNeSk2AQAAALhDIOUUxSYAAAAAvwiknKLYBAAAAOAXgZRTFJsAAAAA/CKQcqZ69eqh0ATFJgAAAAC/qiW7AfgfBU977LGH5eTkWHb22s1SbEJzrqIgDQAAAEDlEEg5oyDqvU/n2pz5K8LPuWvX2+sf/FAlz7113Zq2/96/r5LnAgAAADIZgZRDy1assRWr88L/8wtitmTFb6NTAAAAAHxgjpRThdl3TJECAAAA3CGQch5IcR8pAAAAwB8CKaeyN9Q/V2ofAAAAAF8IpJyqlp1VGEgxKgUAAAD4QiDlVE7O/7qGUSkAAADAFwIpp6rl/O9eT+vzC5LaFgAAAABFEUg5pZvm5kTpffmMSAEAAACeEEg5lrNhVIoRKQAAAMAXAinHqm2YJ7WeESkAAADAFQIpx3KiEuiMSAEAAACuEEilQMGJ9VTtAwAAAFwhkEqB1D5GpAAAAABfCKQco9gEAAAA4BOBVEqMSJHaBwAAAHiS9ECqoKDARowYYV26dLE2bdpY3759be7cuaUu/+2331q/fv2sY8eO1qlTJ+vfv7/99NNPlo4YkQIAAAB8SnogNXLkSBs7dqzdcsstNm7cuBBY9enTx9atW1ds2SVLltg555xjtWrVstGjR9ujjz5qixcvDsuvXbvW0k21DVX7KDYBAAAA+JLUQErB0qhRo8KoUteuXa1ly5Y2bNgwW7BggU2YMKHY8hMnTrTVq1fbXXfdZbvttpvtueeeNnToUPvuu+9s6tSplm5yKDYBAAAAuJTUQGrGjBm2atWqkKIXqV+/vu2+++42efLkYstrOY1gaUQqkr1h1Gb58uWWtuXPCaQAAAAAV6ol88U18iSNGzcu8njDhg0LfxevadOm4SveI488EgKr9u3bW7qh2AQAAADgU1IDqdzc3PC9Ro0aRR6vWbOmLVu2bKN/r3lSTz31lA0ePNgaNGhQ6XbEYrGQMphsSnWsXbu2rV+/3vLy1qsUx2+Pr8+3vLy8TX7+9etzCte73jM2vm1G35Ec9IMf9IUP9IMP9IMf9IUPuWnUDzpHzsr6LSvMdSAVpegpgIhP11PhCAUUZb3B++67zx588EG78MILrWfPnpvUDgUp06dPt2TTe95mm21sxcoVtujXlZa7+reCG6tXr7FFixZt8vNnFdQN33/44Ye02NC3hNmzZye7CaAfXKEvfKAffKAf/KAvfJidJv2QOMjjMpCKUvp+/vln22mnnQof188tWrQoNegZNGiQvfrqq+F77969N7kd1atXt+bNm1uyRZUK69WtZ7Hs2rY6f4XZT4ssp1p123777Tf5+bet/1uwuvPOOzMitREKNHUwaNasWZlBPTYv+sEP+sIH+sEH+sEP+sKH3DTqh1mzZpV72aQGUqrSV7duXZs0aVJhIKWiEdOmTbMePXqU+DdXX321vfnmm3bPPffY0UcfXSXt0PBdnTp1quS5NrUdUq1aNatePctq1qgeflb1cwV7m0rPK6m+gW9JWlceto1MRz/4QV/4QD/4QD/4QV/4UDsN+qG8aX1JD6Q0bKaA6e677w5znJo0aRLKmTdq1Mi6detm+fn54T5R9erVC6l/zz//vI0fPz4EUx06dCiS7hYtk47FJqjaBwAAAPiS9Bvy6h5Sp5xySigYceaZZ1pOTo499thjYQRm/vz51rlz5xA8idL5RPeR0uPxX9Ey6SRnQ/lz7iMFAAAA+JLUESlR4HTVVVeFr0QqdT5z5szCn3Xz3kxC+XMAAADAp6SPSKF03JAXAAAA8IlAyrGc7A1zpFRtAgAAAIAbBFIpMCJVUBCzAsqVAwAAAG4QSDmWs2GOlDBPCgAAAPCDQMqxnOz/1bFnnhQAAADgB4GU8xuCRcEUJdABAAAAPwikUuamvKT2AQAAAF4QSKVIwYn8AkakAAAAAC8IpFKk4AQjUgAAAIAfBFIpk9rHiBQAAADgBYGUczlRah8jUgAAAIAbBFLOVctmRAoAAADwhkAqVYpNEEgBAAAAbhBIpUqxiQJS+wAAAAAvCKRSZESK1D4AAADADwKpFBmRotgEAAAA4AeBlHOUPwcAAAD8IZByLieb1D4AAADAGwKpFBmRyqfYBAAAAOAGgZRzlD8HAAAA/CGQSpXy5xSbAAAAANwgkHKO8ucAAACAPwRSzlH+HAAAAPCHQMq5alTtAwAAANwhkEqZqn0EUgAAAIAXBFLOUWwCAAAA8IdAyjmKTQAAAAD+EEilSGpfLGZWwE15AQAAABcIpJzL2TAiJYxKAQAAAD4QSDmXnZVlUSjFPCkAAADABwIp57Kysv53Lykq9wEAAAAuEEilAApOAAAAAL4QSKWAwhEpUvsAAAAAFwikUgAjUgAAAIAvBFIpoFo2I1IAAACAJwRSKVQCnREpAAAAwAcCqRS6Ke96bsgLAAAAuEAglVLFJhiRAgAAADwgkEoBFJsAAAAAfCGQSqHUPopNAAAAAD4QSKWAnGxGpAAAAABPCKRSqdgEI1IAAACACwRSKVT+PL+AESkAAADAAwKpFMCIFAAAAOALgVQKoPw5AAAA4AuBVAqg/DkAAADgC4FUCqiWTflzAAAAwBMCqRQqNsGIFAAAAOADgVQqFZsoYEQKAAAA8IBAKpXKnzMiBQAAALhAIJVS5c8JpAAAAAAPCKRSKJBSsYlYjPQ+AAAAINkIpFJATvZvqX0KoQoIpAAAAICkI5BKoREpWU8JdAAAACDpCKRSQHZ2lm0YlKLgBAAAAOAAgVSKyCksOMGIFAAAAJBsBFIpoho35QUAAADcIJBKsREpUvsAAACA5COQShHVsjek9hWQ2gcAAABYpgdSBQUFNmLECOvSpYu1adPG+vbta3Pnzi11+SVLltgVV1xh7du3tw4dOthNN91kubm5lu5yNqT2MSIFAAAAJF/SA6mRI0fa2LFj7ZZbbrFx48aFwKpPnz62bt26Epfv37+/zZkzx5544gm777777N1337Ubb7zRMqUEOsUmAAAAgAwPpBQsjRo1KgRHXbt2tZYtW9qwYcNswYIFNmHChGLLf/rpp/bxxx/bnXfeaXvssYd16tTJbr75ZnvppZds4cKFls4oNgEAAAD4kdRAasaMGbZq1aoQEEXq169vu+++u02ePLnY8lOmTLHtt9/edt1118LHlN6XlZVln3zyiWVCsYkly9faqjV5FosxMgUAAIDUtWbdepv38wr7/NtFtmTFGks11ZL54hp5ksaNGxd5vGHDhoW/i6dRp8Rla9SoYdtss43Nnz+/Um3Iy/stKPniiy8s2dSO7Oxsa1RnvTWsXTRQarJ/Pctbv9WGn1abxqeyorv0llNWvtm/3v+lCluc3tQfH0/9OtnNyHj0gx/0hQ/0gw/0gx/0RSr1Q8w0FhDbsHz8uMCShdnWoH5NSzbFBhqkcR9IRUUiFAzFq1mzpi1btqzE5ROXjZZfu3ZtpdoQrajyrrDNKWpDrZrFu6VOrepJaBEAAACQObKyslIjkKpVq1bhXKno/6KgqHbt2iUuX1IRCi1fp06dSrWhbdu2lfo7AAAAAJkrqXOkojS9n3/+ucjj+nmHHXYotnyjRo2KLavAaunSpSEdEAAAAADSPpBSlb66devapEmTCh9bvny5TZs2LdwnKpEe09wplT+PqIqf7LPPPluo1QAAAAAyXVJT+zTfqUePHnb33XdbgwYNrEmTJjZ06NAw8tStWzfLz8+3xYsXW7169UJaX+vWra1du3Y2cODAcO+o1atX2/XXX28nnHBCiSNYAAAAALA5ZMWSXEdbwdK9995rzz//vK1ZsyaMOik4atq0qc2bN88OPfRQu+OOO+ykk04Ky//6669200032b///e9QZKJ79+42aNCg8H8AAAAAyIhACgAAAABSTVLnSAEAAABAKiKQAgAAAIAKIpACAAAAgAoikAIAAACACiKQAgAAAIAKIpACAAAAgAoikAIAAACACiKQ2oIKCgpsxIgR1qVLF2vTpo317dvX5s6dW+ryS5YssSuuuCLcpLhDhw7hRsS5ublbtM3pqqJ98fLLL1uLFi2Kfemm0agaDz/8sPXs2bPMZdgn/PQF+8TmsXTp0nBT+gMPPNDatWtnZ555pk2ZMqXU5bW+zz///LBs586dbfjw4eFG99iy/fDggw+WuD9g0/3666921VVX2X777Wdt27a1fv362XfffVfq8nxO+OiHlzPkM6JashuQSUaOHGljx461IUOGWKNGjWzo0KHWp08fe+WVV6xGjRrFlu/fv3/Y+Z944glbvny5XXfddbZ69Wq78847k9L+TO6LmTNnhgPyvffeW+TxBg0abMFWp68xY8aEE8B99923zOXYJ/z0BfvE5nH55ZfbokWLwnrdbrvtbPTo0XbeeefZCy+8YLvsskuRZfPy8sLvmjVrZuPGjbP//ve/YZ/Izs4O+wq2TD9E+8Pxxx8fTjRRtS6++OJw8fORRx6xrbbayu677z7r3bu3TZgwwWrXrl1seT4nfPTDzEz5jIhhi1i7dm2sbdu2sTFjxhQ+tmzZstjee+8de+WVV4otP3Xq1Nhuu+0WmzVrVuFj//73v2MtWrSILViwYIu1Ox1VtC+kT58+sVtuuWULtjIzaFs+//zzY23atIl179491qNHj1KXZZ/w0xfCPlH1Zs+eHbbxKVOmFD5WUFAQO+yww2LDhw8vtryOV3vuuWds6dKlhY+NGzcu1q5du3Ccw5bpBznyyCNjjz/++BZsZWbQtn355ZfHZs6cWfjY9OnTQ/98/vnnxZbnc8JHP2TSZwSpfVvIjBkzbNWqVdapU6fCx+rXr2+77767TZ48udjySiHYfvvtbddddy18TJF9VlaWffLJJ1us3emoon0RXVmJ7wtUja+//tqqV68eUgBat25d5rLsE376Qtgnqt62224brvbutddehY9p+9aXrqyXtE/ssccetvXWWxc+prSblStX2vTp07dYuzO9H9atW2ezZ88ucaQKm0bb9j333GO77bZb+Hnx4sVhpEmZJM2bNy+2PJ8TPvohkz4jCKS2kAULFoTvjRs3LvJ4w4YNC38Xb+HChcWWVcrZNttsY/Pnz9/MrU1vFe2LZcuWhf7QAfrYY48N8xAuuugi++GHH7ZYm9PVIYccYvfff7/tuOOOG12WfcJPX7BPbB66oHPQQQcVSS9+4403bM6cOWE+ZyIdr3Qik3gcE/aJLdcPs2bNCvPStMwRRxxhXbt2DSl+P//88xZueXr7y1/+Ei6Avvbaa3bbbbdZnTp1ii3D54SPfliWQZ8RBFJbSDTRMXH+Tc2aNW3t2rUlLl/SXJ3Slsfm64tvv/02fI/FYnbHHXeE+SNa7qyzzrJffvllC7Ua7BN+sE9sGVOnTrVBgwZZt27dwsl5ojVr1pR4HBP2iS3XD9988034rnkimjeik8vvv//ezj777NBHqBq9evWy5557zo455pgwX0ej6In4nPDRD99m0GcExSa2kFq1ahWmAET/F21YJU3S0zJaNpGWLyn6x+brC026//DDD0O6h9ID5IEHHggfqM8//3yoXIPNj33CD/aJzW/ixIl25ZVXhopxd999d7n3iehkkX1iy/XDCSecEKr7xU+i/+Mf/xgee/vtt+2oo47agi1OX1EKmQLVzz//3J566qlwkh6Pzwkf/bBvBn1GMCK1hURDzYlD/fp5hx12KLa80jUSl9XBQSVZo9QNbJm+EH1ARgcDUcDVtGnTMHSNLYN9whf2ic1HJyaXXnqpHXzwwfbQQw8VjjKVZ5+Ifi7tWIaq74eSKpHpmKR0spLSxVF+moujFLL169cXPqaqlDqZLyl1ks8JH/2QSZ8RBFJbSMuWLa1u3bo2adKkwsc0aXXatGnhXgeJ9JgOwMrJjnz88cfh+z777LOFWp2eKtoXTz/9tHXs2DGUT41oMrcmF5c2yRJVj33CD/aJzUe3ZbjlllvsT3/6UygbXFKaUvw+oeOW1n3ko48+CqWJdZzDlumHYcOGhblRSmOK6F45up8R+8OmURqYStFrdCO+7L+2+5IKGfA54aMfns6gzwgCqS1EB+EePXqE1IC33norVI4bOHBguHqivGtNVNU9K6J8alXNUiqBlvniiy/Ch6NuDqgUAq40btm+UHqG7p1w9dVXh7zfL7/8Mlyl1NWWk046KdlvJ22xT/jBPrFlaCL27bffbocffni4ya5OXrTe9bVixYpwZV3/j1KXDjvssFChbMCAAeE4pjQ0nfSfe+65ZZ74o2r7Qcv9+OOPduONN4a/VfVX7Q86XpVUnALlpypxOt7ceuutYb1qPtq1114bLn7qHkZ8TvjshwMz6TMi2fXXM8n69etjd911V2y//fYL92rp27dvbO7cueF3+q56/M8991zh8r/88kvs0ksvDct27NgxdsMNN8TWrFmTxHeQuX3x1Vdfxc4555zYPvvsE+7Ron756aefkvgO0s8111xT5N5F7BO++4J9ouo9+OCDYT2X9KU++eijj8L/9T3+nkfqh7322ivWuXPncJ+j/Pz8pL6PTOyHDz74IHb66aeHY1OHDh1igwYNKnJ/L1Te8uXLw7H+gAMOCPd7PPfcc2PffPNN+B2fE3774asM+YzI0j/JDuYAAAAAIJWQ2gcAAAAAFUQgBQAAAAAVRCAFAAAAABVEIAUAAAAAFUQgBQAAAAAVRCAFAAAAABVUraJ/AABAptIdQ7KyspLdDADABg8//LC9//77Nnr0aCuPSZMm2dlnn13i75o2bWpvvfWWlRcjUgAAt3r27GktWrSwM844o9RlBg4cGJa59tprw8/6//3331/lbfnkk0+sX79+Vf68AIDKGTNmjA0fPrxCf9O2bdsQeMV/PfDAA+Ei2UUXXVSh52JECgDgWnZ2tn322We2YMECa9SoUZHfrV692t55550ijz399NPFlqsKzzzzjH333XdV/rwAgIpZuHCh3XDDDWF0qVmzZhX62xo1atj2229f5HPkjjvusBNPPNFOPvnkCj0XI1IAANd23313q1mzpv3zn/8s9jsFUbVr17Yddtih8LE2bdpslkAKAODD119/bdWrV7eXX37ZWrduXeJnw0knnWR77723HX744WHUat26dSU+10MPPWS5ubl2zTXXVLgdBFIAANfq1KljBx10UImB1Pjx4+2II46watX+l2ARn9qnq5X6+cMPP7Rzzz03fOAecMABNnToUMvPzw/LzJs3Lyzz/PPPF3lupQoecsghhf9/4YUX7Mcffyyy7IoVK8KVzMMOO8z22msvO+aYY+zZZ58t8jxfffWV9erVy/bZZ5+QUtK7d+8wwgYAqBwdm3Wc33HHHYv97r333rMBAwbYaaedZq+++moYuXr99dftqquuKrbs4sWL7YknnrALLrjAttlmmwq3g0AKAODeUUcdVZjeF1m5cmX4wFTwsjFXXnllCGR05VHL/+1vfwupeuWlvHkFc0oHUepg165dbc2aNXbWWWfZK6+8Yn369LGRI0eG17juuuvC60Rt1O+23Xbb8KE/bNiwcOXzvPPOC0EYAKBq6firIEpza3faaSfr3Lmz3XTTTeFinC6cxRs7dqzVq1fPTj/99Eq9FnOkAADuKXBRCp8+CDWiI2+++aZtt912IXjZmFNPPdUuvvji8P9OnTrZxIkT7V//+leZRSzi6cO4QYMGIbdeqYPRB/A333xj48aNCyNN0qVLF1u/fn0IqvTcs2fPtiVLloQKUe3atQvL7LLLLiEYW7VqVfgABwBUnWnTptkXX3xRJDtAFVdF81xVmS/y4osv2gknnGC1atWq1GsRSAEA3NOHnFI54gOp1157zY488shylSOPAp2I5lBpgvGm+Pjjj61JkybFnvu4444LH+Cff/657bvvviEAU9pI9+7dQ6Cl1MKSUkwAAJuuoKAgZAKoeESi+CITM2bMsLlz59qxxx5b6dcitQ8AkBIUNEXpfRrl0byno48+ulx/m3i1UZUAoyuUlbVs2bIiH8qR3/3ud+H78uXLbauttgrleZUWqBz9Sy65JIyIXX/99aVOfAYAVN4f//hH++GHH+wPf/hD4Zc+N+66666QCRCZMmVKyGpo2bJlpV+LESkAQEo48MADQ2CiUSkVoFB6xp577rnJzxuNaEXFJyIbG7Haeuutbc6cOcUeX7RoUfiueVFRKl9U3ELpJi+99JL9/e9/D+mCumoKAKg6ffv2DcUmdG8oXWxTEKW5q/rMiL/4pRRAFQ/aFIxIAQBSguYnqTreG2+8EUZ3yjsatTF169YtvC9JJC8vLwQ9iaNY8dq3bx+q+H366adFHlc5XpXlVdldBX377bdfCK5ycnJCGuCNN95o9evXt59++qlK2g8A+B+lUauwj+bCKm1PqdQqOKHAKp6Oy5Wp1BePESkAQEpV7zv//PNDUDN48OAqeU6NLCnAGT16dEgB0c9PPvlkqMqnka+Igp9ffvnF3n33XWvVqlW4R4kKTqiIRf/+/cPVzrffftuee+65kMKn5VVgQvn6WqZfv35hRE1BoCr2devWrUraDwCZbMiQISWmguurLI8++ugmvzYjUgCAlLH//vuHAEU58LvuumuVfhArTVDB2aBBg2yPPfYI936Kp8BJxSUUFKnSk6oIKvg6+OCD7b777rMLL7zQPvnkE7vtttvs0ksvDX/TsGHDUGpd1fmUWqIgUDeSVCl0jVQBAFJXVmxTZ9sCAAAAQIZhRAoAAAAAKohACgAAAAAqiEAKAAAAACqIQAoAAAAAKohACgAAAAAqiEAKAAAAACqIQAoAAAAAKohACgAAAAAqiEAKAAAAACqIQAoAAAAAKohACgAAAAAqiEAKAAAAAKxi/h/4eAi4knIK8AAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "#Parte 5: Análisis exploratorio de datos (EDA) con visualizaciones\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "\n", + "# Estilo general para los gráficos\n", + "sns.set(style='whitegrid')\n", + "plt.rcParams['figure.figsize'] = (10, 6)\n", + "\n", + "# --- 1. Distribución del rating de usuarios\n", + "plt.figure()\n", + "sns.histplot(df_final['rating'].dropna(), bins=30, kde=True)\n", + "plt.title('Distribución del rating de los usuarios')\n", + "plt.xlabel('Rating')\n", + "plt.ylabel('Frecuencia')\n", + "plt.show()\n", + "\n", + "# --- 2. Top 10 países con más participantes\n", + "plt.figure()\n", + "top_countries = df_final['country'].value_counts().head(10)\n", + "sns.barplot(x=top_countries.values, y=top_countries.index, palette='viridis')\n", + "plt.title('Top 10 países con más participantes')\n", + "plt.xlabel('Cantidad de usuarios')\n", + "plt.ylabel('País')\n", + "plt.show()\n", + "\n", + "# --- 3. Relación entre problemas resueltos y rating alcanzado\n", + "df_final['problems_solved'] = df_final[[col for col in df_final.columns if col.startswith('finished_')]].sum(axis=1)\n", + "\n", + "plt.figure()\n", + "sns.scatterplot(data=df_final, x='problems_solved', y='rating_achieved', alpha=0.5)\n", + "plt.title('Relación entre problemas resueltos y rating alcanzado')\n", + "plt.xlabel('Problemas resueltos')\n", + "plt.ylabel('Rating alcanzado (suma de ratings)')\n", + "plt.show()\n", + "\n", + "# --- 4. Lenguajes de programación más usados (en el primer problema)\n", + "plt.figure()\n", + "language_counts = df_final['1_language'].value_counts().head(10)\n", + "sns.barplot(x=language_counts.values, y=language_counts.index, palette='coolwarm')\n", + "plt.title('Lenguajes más usados en el primer problema')\n", + "plt.xlabel('Cantidad de envíos')\n", + "plt.ylabel('Lenguaje')\n", + "plt.show()\n", + "\n", + "# --- 5. Tiempo promedio para resolver el primer problema\n", + "plt.figure()\n", + "sns.histplot(df_final['time_to_answer_1'].dropna() / 60, bins=30, kde=True) # en minutos\n", + "plt.title('Tiempo promedio para resolver el primer problema (en minutos)')\n", + "plt.xlabel('Minutos')\n", + "plt.ylabel('Frecuencia')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3260500c-85f4-4b8a-ae16-22080f9d5bbf", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [conda env:Tarea1]", + "language": "python", + "name": "conda-env-Tarea1-py" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.11" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/homework/hw2/259359_hw2_2025_1/.ipynb_checkpoints/Tarea2-checkpoint.ipynb b/homework/hw2/259359_hw2_2025_1/.ipynb_checkpoints/Tarea2-checkpoint.ipynb new file mode 100644 index 000000000..a59fc6a77 --- /dev/null +++ b/homework/hw2/259359_hw2_2025_1/.ipynb_checkpoints/Tarea2-checkpoint.ipynb @@ -0,0 +1,1311 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 3, + "id": "8c3503f3-f7a1-4c6b-91ae-3bb44c115305", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "🧠 Concursos válidos encontrados: 57\n", + "\n", + "🔍 Procesando: 2053 - Good Bye 2024: 2025 is NEAR\n", + "\n", + "🔍 Procesando: 2043 - Educational Codeforces Round 173 (Rated for Div. 2)\n", + "\n", + "🔍 Procesando: 2051 - Codeforces Round 995 (Div. 3)\n", + "\n", + "🔍 Procesando: 2049 - Codeforces Round 994 (Div. 2)\n", + "\n", + "🔍 Procesando: 2048 - Codeforces Global Round 28\n", + "\n", + "🔍 Procesando: 2044 - Codeforces Round 993 (Div. 4)\n", + "\n", + "🔍 Procesando: 2040 - Codeforces Round 992 (Div. 2)\n", + "\n", + "🔍 Procesando: 2050 - Codeforces Round 991 (Div. 3)\n", + "\n", + "🔍 Procesando: 2046 - Codeforces Round 990 (Div. 1)\n", + "\n", + "🔍 Procesando: 2047 - Codeforces Round 990 (Div. 2)\n", + "\n", + "🔍 Procesando: 2042 - Educational Codeforces Round 172 (Rated for Div. 2)\n", + "\n", + "🔍 Procesando: 2034 - Rayan Programming Contest 2024 - Selection (Codeforces Round 989, Div. 1 + Div. 2)\n", + "\n", + "🔍 Procesando: 2039 - CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!)\n", + "\n", + "🔍 Procesando: 2037 - Codeforces Round 988 (Div. 3)\n", + "\n", + "🔍 Procesando: 2031 - Codeforces Round 987 (Div. 2)\n", + "\n", + "🔍 Procesando: 2028 - Codeforces Round 986 (Div. 2)\n", + "\n", + "🔍 Procesando: 2029 - Refact.ai Match 1 (Codeforces Round 985)\n", + "\n", + "🔍 Procesando: 2036 - Codeforces Round 984 (Div. 3)\n", + "\n", + "🔍 Procesando: 2032 - Codeforces Round 983 (Div. 2)\n", + "\n", + "🔍 Procesando: 2026 - Educational Codeforces Round 171 (Rated for Div. 2)\n", + "\n", + "🔍 Procesando: 2035 - Codeforces Global Round 27\n", + "\n", + "🔍 Procesando: 2027 - Codeforces Round 982 (Div. 2)\n", + "\n", + "🔍 Procesando: 2033 - Codeforces Round 981 (Div. 3)\n", + "\n", + "🔍 Procesando: 2023 - Codeforces Round 980 (Div. 1)\n", + "\n", + "🔍 Procesando: 2024 - Codeforces Round 980 (Div. 2)\n", + "\n", + "🔍 Procesando: 2030 - Codeforces Round 979 (Div. 2)\n", + "\n", + "🔍 Procesando: 2025 - Educational Codeforces Round 170 (Rated for Div. 2)\n", + "\n", + "🔍 Procesando: 2022 - Codeforces Round 978 (Div. 2)\n", + "\n", + "🔍 Procesando: 2021 - Codeforces Round 977 (Div. 2, based on COMPFEST 16 - Final Round)\n", + "\n", + "🔍 Procesando: 2020 - Codeforces Round 976 (Div. 2) and Divide By Zero 9.0\n", + "\n", + "🔍 Procesando: 2018 - Codeforces Round 975 (Div. 1)\n", + "\n", + "🔍 Procesando: 2019 - Codeforces Round 975 (Div. 2)\n", + "\n", + "🔍 Procesando: 2014 - Codeforces Round 974 (Div. 3)\n", + "\n", + "🔍 Procesando: 2013 - Codeforces Round 973 (Div. 2)\n", + "\n", + "🔍 Procesando: 2005 - Codeforces Round 972 (Div. 2)\n", + "\n", + "🔍 Procesando: 2009 - Codeforces Round 971 (Div. 4)\n", + "\n", + "🔍 Procesando: 2008 - Codeforces Round 970 (Div. 3)\n", + "\n", + "🔍 Procesando: 2006 - Codeforces Round 969 (Div. 1)\n", + "\n", + "🔍 Procesando: 2007 - Codeforces Round 969 (Div. 2)\n", + "\n", + "🔍 Procesando: 2010 - Testing Round 19 (Div. 3)\n", + "\n", + "🔍 Procesando: 2003 - Codeforces Round 968 (Div. 2)\n", + "\n", + "🔍 Procesando: 2001 - Codeforces Round 967 (Div. 2)\n", + "\n", + "🔍 Procesando: 2004 - Educational Codeforces Round 169 (Rated for Div. 2)\n", + "\n", + "🔍 Procesando: 2000 - Codeforces Round 966 (Div. 3)\n", + "\n", + "🔍 Procesando: 2002 - EPIC Institute of Technology Round August 2024 (Div. 1 + Div. 2)\n", + "\n", + "🔍 Procesando: 1998 - Codeforces Round 965 (Div. 2)\n", + "\n", + "🔍 Procesando: 1999 - Codeforces Round 964 (Div. 4)\n", + "\n", + "🔍 Procesando: 1993 - Codeforces Round 963 (Div. 2)\n", + "\n", + "🔍 Procesando: 1997 - Educational Codeforces Round 168 (Rated for Div. 2)\n", + "\n", + "🔍 Procesando: 1991 - Pinely Round 4 (Div. 1 + Div. 2)\n", + "\n", + "🔍 Procesando: 1996 - Codeforces Round 962 (Div. 3)\n", + "\n", + "🔍 Procesando: 1995 - Codeforces Round 961 (Div. 2)\n", + "\n", + "🔍 Procesando: 1990 - Codeforces Round 960 (Div. 2)\n", + "\n", + "🔍 Procesando: 1994 - Codeforces Round 959 sponsored by NEAR (Div. 1 + Div. 2)\n", + "\n", + "🔍 Procesando: 1988 - Codeforces Round 958 (Div. 2)\n", + "\n", + "🔍 Procesando: 1992 - Codeforces Round 957 (Div. 3)\n", + "\n", + "🔍 Procesando: 1983 - Codeforces Round 956 (Div. 2) and ByteRace 2024\n", + "\n", + "✅ Data extraída exitosamente. Muestra:\n", + " handle contest_id contest_name \\\n", + "0 tourist 2053 Good Bye 2024: 2025 is NEAR \n", + "1 benq 2053 Good Bye 2024: 2025 is NEAR \n", + "2 Radewoosh 2053 Good Bye 2024: 2025 is NEAR \n", + "3 tourist 2043 Educational Codeforces Round 173 (Rated for Di... \n", + "4 benq 2043 Educational Codeforces Round 173 (Rated for Di... \n", + "\n", + " start_time rating_before rating_after finished_A \\\n", + "0 2024-12-28 09:35:00 NaN NaN False \n", + "1 2024-12-28 09:35:00 NaN NaN True \n", + "2 2024-12-28 09:35:00 3410.0 3456.0 True \n", + "3 2024-12-24 09:35:00 NaN NaN False \n", + "4 2024-12-24 09:35:00 NaN NaN False \n", + "\n", + " relative_time_A time_to_answer_A A_language finished_B \\\n", + "0 NaN NaN None False \n", + "1 86.0 86.0 C++23 (GCC 14-64, msys2) True \n", + "2 138.0 138.0 C++20 (GCC 13-64) True \n", + "3 NaN NaN None False \n", + "4 NaN NaN None False \n", + "\n", + " relative_time_B time_to_answer_B B_language finished_C \\\n", + "0 NaN NaN None False \n", + "1 337.0 251.0 C++23 (GCC 14-64, msys2) True \n", + "2 352.0 214.0 C++20 (GCC 13-64) True \n", + "3 NaN NaN None False \n", + "4 NaN NaN None False \n", + "\n", + " relative_time_C time_to_answer_C C_language \n", + "0 NaN NaN None \n", + "1 539.0 202.0 C++23 (GCC 14-64, msys2) \n", + "2 562.0 210.0 C++20 (GCC 13-64) \n", + "3 NaN NaN None \n", + "4 NaN NaN None \n" + ] + } + ], + "source": [ + "# --------------------- Extracción de Datos de Codeforces -----------------------\n", + "import requests\n", + "import pandas as pd\n", + "from datetime import datetime\n", + "import time\n", + "\n", + "# --- Parámetros base ---\n", + "USER_HANDLES = [\"tourist\", \"benq\", \"Radewoosh\"] # Handles a analizar\n", + "START_DATE = datetime(2024, 7, 1).timestamp()\n", + "END_DATE = datetime(2024, 12, 31).timestamp()\n", + "KEYWORDS = [\"Hello\", \"Round\", \"Good Bye\"]\n", + "\n", + "# --- Paso 1: Obtener lista de concursos válidos ---\n", + "def get_filtered_contests():\n", + " url = \"https://codeforces.com/api/contest.list\"\n", + " res = requests.get(url).json()\n", + " if res[\"status\"] != \"OK\":\n", + " raise Exception(\"Error al obtener la lista de concursos.\")\n", + " \n", + " contests = res[\"result\"]\n", + " filtered = [\n", + " c for c in contests\n", + " if c[\"phase\"] == \"FINISHED\"\n", + " and START_DATE <= c[\"startTimeSeconds\"] <= END_DATE\n", + " and any(keyword in c[\"name\"] for keyword in KEYWORDS)\n", + " ]\n", + " return filtered\n", + "\n", + "# --- Paso 2: Obtener información de cada concurso con standings y problemas ---\n", + "def get_contest_details(contest_id):\n", + " url = f\"https://codeforces.com/api/contest.standings?contestId={contest_id}&from=1&count=1\"\n", + " res = requests.get(url).json()\n", + " if res[\"status\"] != \"OK\":\n", + " print(f\"⚠️ Falló standings para contest {contest_id}\")\n", + " return None\n", + " return res[\"result\"][\"contest\"], res[\"result\"][\"problems\"]\n", + "\n", + "# --- Paso 3: Obtener lista de usuarios que participaron (solo rated) ---\n", + "def get_rated_users():\n", + " url = \"https://codeforces.com/api/user.ratedList?activeOnly=false\"\n", + " res = requests.get(url).json()\n", + " if res[\"status\"] != \"OK\":\n", + " raise Exception(\"Error al obtener rated users.\")\n", + " return res[\"result\"]\n", + "\n", + "# --- Paso 4: Obtener envíos de un usuario en un concurso específico ---\n", + "def get_user_submissions(contest_id, handle):\n", + " url = f\"https://codeforces.com/api/contest.status?contestId={contest_id}&handle={handle}\"\n", + " res = requests.get(url).json()\n", + " return res[\"result\"] if res[\"status\"] == \"OK\" else []\n", + "\n", + "# --- Paso 5: Obtener cambios de rating por concurso ---\n", + "def get_rating_changes(contest_id):\n", + " url = f\"https://codeforces.com/api/contest.ratingChanges?contestId={contest_id}\"\n", + " res = requests.get(url).json()\n", + " return res[\"result\"] if res[\"status\"] == \"OK\" else []\n", + "\n", + "# --- Ejecutar todo lo anterior ---\n", + "contests = get_filtered_contests()\n", + "print(f\"\\n🧠 Concursos válidos encontrados: {len(contests)}\")\n", + "\n", + "all_data = []\n", + "\n", + "for contest in contests:\n", + " cid = contest[\"id\"]\n", + " cname = contest[\"name\"]\n", + " ctime = datetime.fromtimestamp(contest[\"startTimeSeconds\"]).strftime('%Y-%m-%d %H:%M:%S')\n", + " \n", + " print(f\"\\n🔍 Procesando: {cid} - {cname}\")\n", + " contest_info, problems = get_contest_details(cid)\n", + " rating_changes = get_rating_changes(cid)\n", + " rating_map = {r['handle']: r for r in rating_changes}\n", + " \n", + " for handle in USER_HANDLES:\n", + " submissions = get_user_submissions(cid, handle)\n", + " time.sleep(0.5) # Respetar la API\n", + " \n", + " entry = {\n", + " \"handle\": handle,\n", + " \"contest_id\": cid,\n", + " \"contest_name\": cname,\n", + " \"start_time\": ctime,\n", + " \"rating_before\": rating_map.get(handle, {}).get(\"oldRating\", None),\n", + " \"rating_after\": rating_map.get(handle, {}).get(\"newRating\", None),\n", + " }\n", + "\n", + " # Datos por problema (A, B, C...)\n", + " problem_letters = [\"A\", \"B\", \"C\"]\n", + " accepted = sorted([s for s in submissions if s.get(\"verdict\") == \"OK\"], key=lambda s: s[\"relativeTimeSeconds\"])\n", + " prev_time = 0\n", + "\n", + " for p in problem_letters:\n", + " prob_subs = [s for s in accepted if s['problem']['index'] == p]\n", + " if prob_subs:\n", + " first = prob_subs[0]\n", + " rel_time = first['relativeTimeSeconds']\n", + " entry[f\"finished_{p}\"] = True\n", + " entry[f\"relative_time_{p}\"] = rel_time\n", + " entry[f\"time_to_answer_{p}\"] = rel_time - prev_time if prev_time else rel_time\n", + " entry[f\"{p}_language\"] = first.get('programmingLanguage', 'Unknown')\n", + " prev_time = rel_time\n", + " else:\n", + " entry[f\"finished_{p}\"] = False\n", + " entry[f\"relative_time_{p}\"] = None\n", + " entry[f\"time_to_answer_{p}\"] = None\n", + " entry[f\"{p}_language\"] = None\n", + "\n", + " all_data.append(entry)\n", + "\n", + "# --- Convertir a DataFrame ---\n", + "df = pd.DataFrame(all_data)\n", + "print(\"\\n✅ Data extraída exitosamente. Muestra:\")\n", + "print(df.head())\n", + "\n", + "#Solo considera concursos válidos entre julio y diciembre de 2024.\n", + "\n", + "#Solo incluye concursos que contienen \"Hello\", \"Round\" o \"Good Bye\".\n", + "\n", + "#Extrae:\n", + "\n", + "#Info del concurso y problemas (contest.standings)\n", + "\n", + "#Cambios de rating (contest.ratingChanges)\n", + "\n", + "#Submissions por usuario (contest.status)\n", + "\n", + "#Procesa problemas por letra (A, B, C) con relative_time y time_to_answer." + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "5ee09943-a454-42a5-ba87-781cb4d9aed2", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['author_handle', 'contest_id', 'contest_name', 'contest_start_time', 'rating_achieved', 'rating', 'max_rating', 'finished_A', 'A_language', 'relative_time_A', 'time_to_answer_A', 'finished_B', 'B_language', 'relative_time_B', 'time_to_answer_B', 'finished_C', 'C_language', 'relative_time_C', 'time_to_answer_C']\n" + ] + } + ], + "source": [ + "print(df.columns.tolist())" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "efe6029f-ae1e-4cd8-8d63-e7952fa2c755", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "✅ Wrangling completado. Muestra:\n", + " author_handle contest_id \\\n", + "0 tourist 2053 \n", + "1 tourist 2043 \n", + "2 tourist 2051 \n", + "3 tourist 2049 \n", + "4 tourist 2048 \n", + "\n", + " contest_name contest_start_time \\\n", + "0 Good Bye 2024: 2025 is NEAR 2024-12-28 09:35:00 \n", + "1 Educational Codeforces Round 173 (Rated for Di... 2024-12-24 09:35:00 \n", + "2 Codeforces Round 995 (Div. 3) 2024-12-22 09:35:00 \n", + "3 Codeforces Round 994 (Div. 2) 2024-12-20 09:35:00 \n", + "4 Codeforces Global Round 28 2024-12-19 09:35:00 \n", + "\n", + " rating_achieved rating max_rating finished_A A_language \\\n", + "0 NaN NaN NaN False NaN \n", + "1 NaN NaN NaN False NaN \n", + "2 NaN NaN NaN False NaN \n", + "3 NaN NaN NaN False NaN \n", + "4 NaN NaN NaN False NaN \n", + "\n", + " relative_time_A time_to_answer_A finished_B B_language relative_time_B \\\n", + "0 NaN NaN False NaN NaN \n", + "1 NaN NaN False NaN NaN \n", + "2 NaN NaN False NaN NaN \n", + "3 NaN NaN False NaN NaN \n", + "4 NaN NaN False NaN NaN \n", + "\n", + " time_to_answer_B finished_C C_language relative_time_C time_to_answer_C \n", + "0 NaN False NaN NaN NaN \n", + "1 NaN False NaN NaN NaN \n", + "2 NaN False NaN NaN NaN \n", + "3 NaN False NaN NaN NaN \n", + "4 NaN False NaN NaN NaN \n" + ] + } + ], + "source": [ + "# ------------------- Data Wrangling: Recolección, limpieza y transformación -------------------\n", + "import pandas as pd\n", + "\n", + "# Asumimos que el DataFrame original ya está en df\n", + "\n", + "# ------------------ LIMPIEZA BÁSICA ------------------\n", + "# Asegurarnos de que columnas clave estén bien tipadas\n", + "df['contest_start_time'] = pd.to_datetime(df['contest_start_time']) # Convertir timestamps a datetime\n", + "\n", + "# Convertir ratings a numéricos (por si hay valores None o vacíos)\n", + "df['rating'] = pd.to_numeric(df['rating'], errors='coerce')\n", + "df['max_rating'] = pd.to_numeric(df['max_rating'], errors='coerce')\n", + "df['rating_achieved'] = pd.to_numeric(df['rating_achieved'], errors='coerce')\n", + "\n", + "# ------------------ VARIABLES DERIVADAS POR PROBLEMA ------------------\n", + "problem_letters = ['A', 'B', 'C']\n", + "\n", + "# Aseguramos que cada usuario y concurso tenga un cálculo correcto\n", + "for handle in df['author_handle'].unique():\n", + " for cid in df['contest_id'].unique():\n", + " subset = df[(df['author_handle'] == handle) & (df['contest_id'] == cid)]\n", + "\n", + " if len(subset) == 1:\n", + " idx = subset.index[0]\n", + " prev_time = 0\n", + "\n", + " for p in problem_letters:\n", + " rt_col = f'relative_time_{p}'\n", + " tt_col = f'time_to_answer_{p}'\n", + "\n", + " rel_time = df.at[idx, rt_col]\n", + "\n", + " if pd.notna(rel_time):\n", + " if prev_time == 0:\n", + " df.at[idx, tt_col] = rel_time\n", + " else:\n", + " df.at[idx, tt_col] = rel_time - prev_time\n", + " prev_time = rel_time\n", + " else:\n", + " df.at[idx, tt_col] = None\n", + "\n", + "# Convertimos finished_n a booleano\n", + "for p in problem_letters:\n", + " df[f'finished_{p}'] = df[f'finished_{p}'].astype(bool)\n", + "\n", + "# ------------------ RESULTADO ------------------\n", + "print(\"✅ Wrangling completado. Muestra:\")\n", + "print(df.head())" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "ba00dd58-ed9d-4630-8a02-92b23ef8a059", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
author_handlecontest_idcontest_namecontest_start_timerating_achievedratingmax_ratingfinished_AA_languagerelative_time_Atime_to_answer_Afinished_BB_languagerelative_time_Btime_to_answer_Bfinished_CC_languagerelative_time_Ctime_to_answer_C
11tourist2034Rayan Programming Contest 2024 - Selection (Co...2024-11-30 09:35:003985.03993.03993.0TrueC++20 (GCC 13-64)56.056.0TrueC++20 (GCC 13-64)138.082.0TrueC++20 (GCC 13-64)631.0493.0
12tourist2039CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!)2024-11-23 09:35:003993.04009.04009.0TrueC++20 (GCC 13-64)51.051.0TrueC++20 (GCC 13-64)188.0137.0FalseNaNNaNNaN
37tourist2006Codeforces Round 969 (Div. 1)2024-08-30 09:35:004009.03947.03947.0TrueC++20 (GCC 13-64)287.0287.0TrueC++20 (GCC 13-64)812.0525.0TrueC++20 (GCC 13-64)1184.0372.0
49tourist1991Pinely Round 4 (Div. 1 + Div. 2)2024-07-28 09:35:003947.03880.03880.0TrueC++20 (GCC 13-64)46.046.0TrueC++20 (GCC 13-64)147.0101.0TrueC++20 (GCC 13-64)354.0207.0
53tourist1994Codeforces Round 959 sponsored by NEAR (Div. 1...2024-07-18 09:35:003880.03803.03803.0TrueC++20 (GCC 13-64)124.0124.0TrueC++20 (GCC 13-64)223.099.0TrueC++20 (GCC 13-64)373.0150.0
\n", + "
" + ], + "text/plain": [ + " author_handle contest_id \\\n", + "11 tourist 2034 \n", + "12 tourist 2039 \n", + "37 tourist 2006 \n", + "49 tourist 1991 \n", + "53 tourist 1994 \n", + "\n", + " contest_name contest_start_time \\\n", + "11 Rayan Programming Contest 2024 - Selection (Co... 2024-11-30 09:35:00 \n", + "12 CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!) 2024-11-23 09:35:00 \n", + "37 Codeforces Round 969 (Div. 1) 2024-08-30 09:35:00 \n", + "49 Pinely Round 4 (Div. 1 + Div. 2) 2024-07-28 09:35:00 \n", + "53 Codeforces Round 959 sponsored by NEAR (Div. 1... 2024-07-18 09:35:00 \n", + "\n", + " rating_achieved rating max_rating finished_A A_language \\\n", + "11 3985.0 3993.0 3993.0 True C++20 (GCC 13-64) \n", + "12 3993.0 4009.0 4009.0 True C++20 (GCC 13-64) \n", + "37 4009.0 3947.0 3947.0 True C++20 (GCC 13-64) \n", + "49 3947.0 3880.0 3880.0 True C++20 (GCC 13-64) \n", + "53 3880.0 3803.0 3803.0 True C++20 (GCC 13-64) \n", + "\n", + " relative_time_A time_to_answer_A finished_B B_language \\\n", + "11 56.0 56.0 True C++20 (GCC 13-64) \n", + "12 51.0 51.0 True C++20 (GCC 13-64) \n", + "37 287.0 287.0 True C++20 (GCC 13-64) \n", + "49 46.0 46.0 True C++20 (GCC 13-64) \n", + "53 124.0 124.0 True C++20 (GCC 13-64) \n", + "\n", + " relative_time_B time_to_answer_B finished_C C_language \\\n", + "11 138.0 82.0 True C++20 (GCC 13-64) \n", + "12 188.0 137.0 False NaN \n", + "37 812.0 525.0 True C++20 (GCC 13-64) \n", + "49 147.0 101.0 True C++20 (GCC 13-64) \n", + "53 223.0 99.0 True C++20 (GCC 13-64) \n", + "\n", + " relative_time_C time_to_answer_C \n", + "11 631.0 493.0 \n", + "12 NaN NaN \n", + "37 1184.0 372.0 \n", + "49 354.0 207.0 \n", + "53 373.0 150.0 " + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Muestra con datos \n", + "df1 = df[df['rating_achieved'].notna()]\n", + "df1.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "c2bbae22-a83a-465a-9bfe-7b0c0339fb91", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "#Visualizaciones y Análisis\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "\n", + "# --- Histograma del rating logrado ---\n", + "plt.figure(figsize=(8, 5))\n", + "sns.histplot(df['rating_achieved'].dropna(), kde=True, bins=10, color='skyblue')\n", + "plt.title(\"Distribución del Rating Alcanzado\")\n", + "plt.xlabel(\"Rating\")\n", + "plt.ylabel(\"Frecuencia\")\n", + "plt.show()\n", + "\n", + "# --- Boxplot: Lenguaje más usado vs. tiempo de respuesta (problema A) ---\n", + "plt.figure(figsize=(10, 6))\n", + "sns.boxplot(x='A_language', y='time_to_answer_A', data=df)\n", + "plt.xticks(rotation=45)\n", + "plt.title(\"Tiempo para Resolver Problema A según Lenguaje\")\n", + "plt.show()\n", + "\n", + "# --- Scatterplot: Rating vs Tiempo para resolver problema B ---\n", + "plt.figure(figsize=(8, 5))\n", + "sns.scatterplot(x='rating', y='time_to_answer_B', data=df)\n", + "sns.regplot(x='rating', y='time_to_answer_B', data=df, scatter=False, color='red')\n", + "plt.title(\"Rating vs. Tiempo para Resolver Problema B\")\n", + "plt.xlabel(\"Rating\")\n", + "plt.ylabel(\"Tiempo para Responder (s)\")\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "c86ecaf8-40c3-48e8-bf71-b4579c3c9b8a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting statsmodels\n", + " Downloading statsmodels-0.14.4-cp311-cp311-win_amd64.whl.metadata (9.5 kB)\n", + "Requirement already satisfied: numpy<3,>=1.22.3 in c:\\users\\fabrizio\\anaconda3\\envs\\tarea1\\lib\\site-packages (from statsmodels) (1.26.4)\n", + "Collecting scipy!=1.9.2,>=1.8 (from statsmodels)\n", + " Downloading scipy-1.15.2-cp311-cp311-win_amd64.whl.metadata (60 kB)\n", + "Requirement already satisfied: pandas!=2.1.0,>=1.4 in c:\\users\\fabrizio\\anaconda3\\envs\\tarea1\\lib\\site-packages (from statsmodels) (2.2.0)\n", + "Collecting patsy>=0.5.6 (from statsmodels)\n", + " Downloading patsy-1.0.1-py2.py3-none-any.whl.metadata (3.3 kB)\n", + "Requirement already satisfied: packaging>=21.3 in c:\\users\\fabrizio\\anaconda3\\envs\\tarea1\\lib\\site-packages (from statsmodels) (24.2)\n", + "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\fabrizio\\anaconda3\\envs\\tarea1\\lib\\site-packages (from pandas!=2.1.0,>=1.4->statsmodels) (2.9.0.post0)\n", + "Requirement already satisfied: pytz>=2020.1 in c:\\users\\fabrizio\\anaconda3\\envs\\tarea1\\lib\\site-packages (from pandas!=2.1.0,>=1.4->statsmodels) (2025.2)\n", + "Requirement already satisfied: tzdata>=2022.7 in c:\\users\\fabrizio\\anaconda3\\envs\\tarea1\\lib\\site-packages (from pandas!=2.1.0,>=1.4->statsmodels) (2025.2)\n", + "Requirement already satisfied: six>=1.5 in c:\\users\\fabrizio\\anaconda3\\envs\\tarea1\\lib\\site-packages (from python-dateutil>=2.8.2->pandas!=2.1.0,>=1.4->statsmodels) (1.17.0)\n", + "Downloading statsmodels-0.14.4-cp311-cp311-win_amd64.whl (9.9 MB)\n", + " ---------------------------------------- 0.0/9.9 MB ? eta -:--:--\n", + " - -------------------------------------- 0.3/9.9 MB ? eta -:--:--\n", + " -- ------------------------------------- 0.5/9.9 MB 1.2 MB/s eta 0:00:08\n", + " -- ------------------------------------- 0.5/9.9 MB 1.2 MB/s eta 0:00:08\n", + " --- ------------------------------------ 0.8/9.9 MB 1.0 MB/s eta 0:00:09\n", + " ---- ----------------------------------- 1.0/9.9 MB 1.0 MB/s eta 0:00:09\n", + " ----- ---------------------------------- 1.3/9.9 MB 1.0 MB/s eta 0:00:09\n", + " ------ --------------------------------- 1.6/9.9 MB 1.0 MB/s eta 0:00:09\n", + " ------ --------------------------------- 1.6/9.9 MB 1.0 MB/s eta 0:00:09\n", + " ------- -------------------------------- 1.8/9.9 MB 987.4 kB/s eta 0:00:09\n", + " -------- ------------------------------- 2.1/9.9 MB 987.1 kB/s eta 0:00:08\n", + " --------- ------------------------------ 2.4/9.9 MB 986.9 kB/s eta 0:00:08\n", + " ---------- ----------------------------- 2.6/9.9 MB 987.2 kB/s eta 0:00:08\n", + " ---------- ----------------------------- 2.6/9.9 MB 987.2 kB/s eta 0:00:08\n", + " ----------- ---------------------------- 2.9/9.9 MB 987.0 kB/s eta 0:00:08\n", + " ------------ --------------------------- 3.1/9.9 MB 997.8 kB/s eta 0:00:07\n", + " ------------- -------------------------- 3.4/9.9 MB 991.7 kB/s eta 0:00:07\n", + " -------------- ------------------------- 3.7/9.9 MB 995.9 kB/s eta 0:00:07\n", + " -------------- ------------------------- 3.7/9.9 MB 995.9 kB/s eta 0:00:07\n", + " --------------- ------------------------ 3.9/9.9 MB 987.1 kB/s eta 0:00:06\n", + " --------------- ------------------------ 3.9/9.9 MB 987.1 kB/s eta 0:00:06\n", + " ----------------- ---------------------- 4.2/9.9 MB 949.8 kB/s eta 0:00:06\n", + " ------------------ --------------------- 4.5/9.9 MB 969.1 kB/s eta 0:00:06\n", + " ------------------ --------------------- 4.5/9.9 MB 969.1 kB/s eta 0:00:06\n", + " ------------------- -------------------- 4.7/9.9 MB 947.6 kB/s eta 0:00:06\n", + " --------------------- ------------------ 5.2/9.9 MB 974.9 kB/s eta 0:00:05\n", + " --------------------- ------------------ 5.2/9.9 MB 974.9 kB/s eta 0:00:05\n", + " ---------------------- ----------------- 5.5/9.9 MB 964.3 kB/s eta 0:00:05\n", + " ----------------------- ---------------- 5.8/9.9 MB 962.8 kB/s eta 0:00:05\n", + " ----------------------- ---------------- 5.8/9.9 MB 962.8 kB/s eta 0:00:05\n", + " ------------------------ --------------- 6.0/9.9 MB 956.3 kB/s eta 0:00:04\n", + " ------------------------- -------------- 6.3/9.9 MB 948.2 kB/s eta 0:00:04\n", + " ------------------------- -------------- 6.3/9.9 MB 948.2 kB/s eta 0:00:04\n", + " -------------------------- ------------- 6.6/9.9 MB 945.2 kB/s eta 0:00:04\n", + " --------------------------- ------------ 6.8/9.9 MB 938.4 kB/s eta 0:00:04\n", + " --------------------------- ------------ 6.8/9.9 MB 938.4 kB/s eta 0:00:04\n", + " ---------------------------- ----------- 7.1/9.9 MB 934.0 kB/s eta 0:00:03\n", + " ---------------------------- ----------- 7.1/9.9 MB 934.0 kB/s eta 0:00:03\n", + " ---------------------------- ----------- 7.1/9.9 MB 934.0 kB/s eta 0:00:03\n", + " ---------------------------- ----------- 7.1/9.9 MB 934.0 kB/s eta 0:00:03\n", + " ----------------------------- ---------- 7.3/9.9 MB 869.5 kB/s eta 0:00:03\n", + " ----------------------------- ---------- 7.3/9.9 MB 869.5 kB/s eta 0:00:03\n", + " ----------------------------- ---------- 7.3/9.9 MB 869.5 kB/s eta 0:00:03\n", + " ------------------------------ --------- 7.6/9.9 MB 824.2 kB/s eta 0:00:03\n", + " ------------------------------ --------- 7.6/9.9 MB 824.2 kB/s eta 0:00:03\n", + " ------------------------------- -------- 7.9/9.9 MB 810.9 kB/s eta 0:00:03\n", + " ------------------------------- -------- 7.9/9.9 MB 810.9 kB/s eta 0:00:03\n", + " -------------------------------- ------- 8.1/9.9 MB 814.4 kB/s eta 0:00:03\n", + " ---------------------------------- ----- 8.4/9.9 MB 815.3 kB/s eta 0:00:02\n", + " ---------------------------------- ----- 8.4/9.9 MB 815.3 kB/s eta 0:00:02\n", + " ----------------------------------- ---- 8.7/9.9 MB 809.8 kB/s eta 0:00:02\n", + " ----------------------------------- ---- 8.7/9.9 MB 809.8 kB/s eta 0:00:02\n", + " ------------------------------------ --- 8.9/9.9 MB 809.5 kB/s eta 0:00:02\n", + " ------------------------------------ --- 8.9/9.9 MB 809.5 kB/s eta 0:00:02\n", + " ------------------------------------- -- 9.2/9.9 MB 798.9 kB/s eta 0:00:01\n", + " ------------------------------------- -- 9.2/9.9 MB 798.9 kB/s eta 0:00:01\n", + " ------------------------------------- -- 9.2/9.9 MB 798.9 kB/s eta 0:00:01\n", + " ------------------------------------- -- 9.2/9.9 MB 798.9 kB/s eta 0:00:01\n", + " -------------------------------------- - 9.4/9.9 MB 768.6 kB/s eta 0:00:01\n", + " -------------------------------------- - 9.4/9.9 MB 768.6 kB/s eta 0:00:01\n", + " -------------------------------------- - 9.4/9.9 MB 768.6 kB/s eta 0:00:01\n", + " -------------------------------------- - 9.4/9.9 MB 768.6 kB/s eta 0:00:01\n", + " -------------------------------------- - 9.4/9.9 MB 768.6 kB/s eta 0:00:01\n", + " -------------------------------------- - 9.4/9.9 MB 768.6 kB/s eta 0:00:01\n", + " -------------------------------------- - 9.4/9.9 MB 768.6 kB/s eta 0:00:01\n", + " -------------------------------------- - 9.4/9.9 MB 768.6 kB/s eta 0:00:01\n", + " --------------------------------------- 9.7/9.9 MB 686.3 kB/s eta 0:00:01\n", + " --------------------------------------- 9.7/9.9 MB 686.3 kB/s eta 0:00:01\n", + " --------------------------------------- 9.7/9.9 MB 686.3 kB/s eta 0:00:01\n", + " --------------------------------------- 9.7/9.9 MB 686.3 kB/s eta 0:00:01\n", + " --------------------------------------- 9.7/9.9 MB 686.3 kB/s eta 0:00:01\n", + " --------------------------------------- 9.7/9.9 MB 686.3 kB/s eta 0:00:01\n", + " --------------------------------------- 9.7/9.9 MB 686.3 kB/s eta 0:00:01\n", + " ---------------------------------------- 9.9/9.9 MB 634.1 kB/s eta 0:00:00\n", + "Downloading patsy-1.0.1-py2.py3-none-any.whl (232 kB)\n", + "Downloading scipy-1.15.2-cp311-cp311-win_amd64.whl (41.2 MB)\n", + " ---------------------------------------- 0.0/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.0/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.0/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.0/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.0/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.0/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.3/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.3/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.3/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.3/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.3/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.3/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.3/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.3/41.2 MB ? eta -:--:--\n", + " ---------------------------------------- 0.3/41.2 MB ? eta -:--:--\n", + " --------------------------------------- 0.5/41.2 MB 128.1 kB/s eta 0:05:18\n", + " --------------------------------------- 0.5/41.2 MB 128.1 kB/s eta 0:05:18\n", + " --------------------------------------- 0.5/41.2 MB 128.1 kB/s eta 0:05:18\n", + " --------------------------------------- 0.5/41.2 MB 128.1 kB/s eta 0:05:18\n", + " --------------------------------------- 0.5/41.2 MB 128.1 kB/s eta 0:05:18\n", + " --------------------------------------- 0.8/41.2 MB 176.6 kB/s eta 0:03:49\n", + " --------------------------------------- 0.8/41.2 MB 176.6 kB/s eta 0:03:49\n", + " - -------------------------------------- 1.0/41.2 MB 222.7 kB/s eta 0:03:01\n", + " - -------------------------------------- 1.0/41.2 MB 222.7 kB/s eta 0:03:01\n", + " - -------------------------------------- 1.0/41.2 MB 222.7 kB/s eta 0:03:01\n", + " - -------------------------------------- 1.3/41.2 MB 258.1 kB/s eta 0:02:35\n", + " - -------------------------------------- 1.3/41.2 MB 258.1 kB/s eta 0:02:35\n", + " - -------------------------------------- 1.6/41.2 MB 290.3 kB/s eta 0:02:17\n", + " - -------------------------------------- 1.6/41.2 MB 290.3 kB/s eta 0:02:17\n", + " - -------------------------------------- 1.8/41.2 MB 317.6 kB/s eta 0:02:05\n", + " - -------------------------------------- 1.8/41.2 MB 317.6 kB/s eta 0:02:05\n", + " -- ------------------------------------- 2.1/41.2 MB 346.5 kB/s eta 0:01:53\n", + " -- ------------------------------------- 2.1/41.2 MB 346.5 kB/s eta 0:01:53\n", + " -- ------------------------------------- 2.1/41.2 MB 346.5 kB/s eta 0:01:53\n", + " -- ------------------------------------- 2.1/41.2 MB 346.5 kB/s eta 0:01:53\n", + " -- ------------------------------------- 2.1/41.2 MB 346.5 kB/s eta 0:01:53\n", + " -- ------------------------------------- 2.4/41.2 MB 331.4 kB/s eta 0:01:58\n", + " -- ------------------------------------- 2.4/41.2 MB 331.4 kB/s eta 0:01:58\n", + " -- ------------------------------------- 2.4/41.2 MB 331.4 kB/s eta 0:01:58\n", + " -- ------------------------------------- 2.4/41.2 MB 331.4 kB/s eta 0:01:58\n", + " -- ------------------------------------- 2.6/41.2 MB 326.1 kB/s eta 0:01:59\n", + " -- ------------------------------------- 2.6/41.2 MB 326.1 kB/s eta 0:01:59\n", + " -- ------------------------------------- 2.6/41.2 MB 326.1 kB/s eta 0:01:59\n", + " -- ------------------------------------- 2.6/41.2 MB 326.1 kB/s eta 0:01:59\n", + " -- ------------------------------------- 2.9/41.2 MB 324.5 kB/s eta 0:01:59\n", + " -- ------------------------------------- 2.9/41.2 MB 324.5 kB/s eta 0:01:59\n", + " -- ------------------------------------- 2.9/41.2 MB 324.5 kB/s eta 0:01:59\n", + " --- ------------------------------------ 3.1/41.2 MB 327.2 kB/s eta 0:01:57\n", + " --- ------------------------------------ 3.1/41.2 MB 327.2 kB/s eta 0:01:57\n", + " --- ------------------------------------ 3.1/41.2 MB 327.2 kB/s eta 0:01:57\n", + " --- ------------------------------------ 3.4/41.2 MB 335.5 kB/s eta 0:01:53\n", + " --- ------------------------------------ 3.4/41.2 MB 335.5 kB/s eta 0:01:53\n", + " --- ------------------------------------ 3.7/41.2 MB 347.3 kB/s eta 0:01:49\n", + " --- ------------------------------------ 3.7/41.2 MB 347.3 kB/s eta 0:01:49\n", + " --- ------------------------------------ 3.9/41.2 MB 358.6 kB/s eta 0:01:44\n", + " --- ------------------------------------ 3.9/41.2 MB 358.6 kB/s eta 0:01:44\n", + " --- ------------------------------------ 3.9/41.2 MB 358.6 kB/s eta 0:01:44\n", + " --- ------------------------------------ 3.9/41.2 MB 358.6 kB/s eta 0:01:44\n", + " --- ------------------------------------ 3.9/41.2 MB 358.6 kB/s eta 0:01:44\n", + " --- ------------------------------------ 3.9/41.2 MB 358.6 kB/s eta 0:01:44\n", + " --- ------------------------------------ 3.9/41.2 MB 358.6 kB/s eta 0:01:44\n", + " ---- ----------------------------------- 4.2/41.2 MB 338.2 kB/s eta 0:01:50\n", + " ---- ----------------------------------- 4.2/41.2 MB 338.2 kB/s eta 0:01:50\n", + " ---- ----------------------------------- 4.2/41.2 MB 338.2 kB/s eta 0:01:50\n", + " ---- ----------------------------------- 4.5/41.2 MB 337.2 kB/s eta 0:01:50\n", + " ---- ----------------------------------- 4.5/41.2 MB 337.2 kB/s eta 0:01:50\n", + " ---- ----------------------------------- 4.5/41.2 MB 337.2 kB/s eta 0:01:50\n", + " ---- ----------------------------------- 4.5/41.2 MB 337.2 kB/s eta 0:01:50\n", + " ---- ----------------------------------- 4.7/41.2 MB 335.6 kB/s eta 0:01:49\n", + " ---- ----------------------------------- 4.7/41.2 MB 335.6 kB/s eta 0:01:49\n", + " ---- ----------------------------------- 4.7/41.2 MB 335.6 kB/s eta 0:01:49\n", + " ---- ----------------------------------- 4.7/41.2 MB 335.6 kB/s eta 0:01:49\n", + " ---- ----------------------------------- 5.0/41.2 MB 336.7 kB/s eta 0:01:48\n", + " ---- ----------------------------------- 5.0/41.2 MB 336.7 kB/s eta 0:01:48\n", + " ---- ----------------------------------- 5.0/41.2 MB 336.7 kB/s eta 0:01:48\n", + " ----- ---------------------------------- 5.2/41.2 MB 340.2 kB/s eta 0:01:46\n", + " ----- ---------------------------------- 5.2/41.2 MB 340.2 kB/s eta 0:01:46\n", + " ----- ---------------------------------- 5.5/41.2 MB 345.6 kB/s eta 0:01:44\n", + " ----- ---------------------------------- 5.5/41.2 MB 345.6 kB/s eta 0:01:44\n", + " ----- ---------------------------------- 5.8/41.2 MB 352.7 kB/s eta 0:01:41\n", + " ----- ---------------------------------- 5.8/41.2 MB 352.7 kB/s eta 0:01:41\n", + " ----- ---------------------------------- 5.8/41.2 MB 352.7 kB/s eta 0:01:41\n", + " ----- ---------------------------------- 5.8/41.2 MB 352.7 kB/s eta 0:01:41\n", + " ----- ---------------------------------- 5.8/41.2 MB 352.7 kB/s eta 0:01:41\n", + " ----- ---------------------------------- 5.8/41.2 MB 352.7 kB/s eta 0:01:41\n", + " ----- ---------------------------------- 6.0/41.2 MB 340.8 kB/s eta 0:01:44\n", + " ----- ---------------------------------- 6.0/41.2 MB 340.8 kB/s eta 0:01:44\n", + " ----- ---------------------------------- 6.0/41.2 MB 340.8 kB/s eta 0:01:44\n", + " ------ --------------------------------- 6.3/41.2 MB 345.5 kB/s eta 0:01:42\n", + " ------ --------------------------------- 6.3/41.2 MB 345.5 kB/s eta 0:01:42\n", + " ------ --------------------------------- 6.6/41.2 MB 353.2 kB/s eta 0:01:39\n", + " ------ --------------------------------- 6.6/41.2 MB 353.2 kB/s eta 0:01:39\n", + " ------ --------------------------------- 6.8/41.2 MB 356.1 kB/s eta 0:01:37\n", + " ------ --------------------------------- 6.8/41.2 MB 356.1 kB/s eta 0:01:37\n", + " ------ --------------------------------- 6.8/41.2 MB 356.1 kB/s eta 0:01:37\n", + " ------ --------------------------------- 6.8/41.2 MB 356.1 kB/s eta 0:01:37\n", + " ------ --------------------------------- 6.8/41.2 MB 356.1 kB/s eta 0:01:37\n", + " ------ --------------------------------- 6.8/41.2 MB 356.1 kB/s eta 0:01:37\n", + " ------ --------------------------------- 7.1/41.2 MB 349.3 kB/s eta 0:01:38\n", + " ------ --------------------------------- 7.1/41.2 MB 349.3 kB/s eta 0:01:38\n", + " ------ --------------------------------- 7.1/41.2 MB 349.3 kB/s eta 0:01:38\n", + " ------- -------------------------------- 7.3/41.2 MB 350.1 kB/s eta 0:01:37\n", + " ------- -------------------------------- 7.3/41.2 MB 350.1 kB/s eta 0:01:37\n", + " ------- -------------------------------- 7.3/41.2 MB 350.1 kB/s eta 0:01:37\n", + " ------- -------------------------------- 7.6/41.2 MB 352.7 kB/s eta 0:01:36\n", + " ------- -------------------------------- 7.6/41.2 MB 352.7 kB/s eta 0:01:36\n", + " ------- -------------------------------- 7.6/41.2 MB 352.7 kB/s eta 0:01:36\n", + " ------- -------------------------------- 7.6/41.2 MB 352.7 kB/s eta 0:01:36\n", + " ------- -------------------------------- 7.6/41.2 MB 352.7 kB/s eta 0:01:36\n", + " ------- -------------------------------- 7.9/41.2 MB 347.0 kB/s eta 0:01:37\n", + " ------- -------------------------------- 7.9/41.2 MB 347.0 kB/s eta 0:01:37\n", + " ------- -------------------------------- 7.9/41.2 MB 347.0 kB/s eta 0:01:37\n", + " ------- -------------------------------- 8.1/41.2 MB 349.5 kB/s eta 0:01:35\n", + " -------- ------------------------------- 8.4/41.2 MB 354.8 kB/s eta 0:01:33\n", + " -------- ------------------------------- 8.4/41.2 MB 354.8 kB/s eta 0:01:33\n", + " -------- ------------------------------- 8.4/41.2 MB 354.8 kB/s eta 0:01:33\n", + " -------- ------------------------------- 8.7/41.2 MB 359.1 kB/s eta 0:01:31\n", + " -------- ------------------------------- 8.7/41.2 MB 359.1 kB/s eta 0:01:31\n", + " -------- ------------------------------- 8.9/41.2 MB 361.6 kB/s eta 0:01:30\n", + " -------- ------------------------------- 8.9/41.2 MB 361.6 kB/s eta 0:01:30\n", + " -------- ------------------------------- 9.2/41.2 MB 365.4 kB/s eta 0:01:28\n", + " -------- ------------------------------- 9.2/41.2 MB 365.4 kB/s eta 0:01:28\n", + " --------- ------------------------------ 9.4/41.2 MB 369.3 kB/s eta 0:01:27\n", + " --------- ------------------------------ 9.4/41.2 MB 369.3 kB/s eta 0:01:27\n", + " --------- ------------------------------ 9.7/41.2 MB 374.4 kB/s eta 0:01:25\n", + " --------- ------------------------------ 9.7/41.2 MB 374.4 kB/s eta 0:01:25\n", + " --------- ------------------------------ 10.0/41.2 MB 380.1 kB/s eta 0:01:23\n", + " --------- ------------------------------ 10.0/41.2 MB 380.1 kB/s eta 0:01:23\n", + " --------- ------------------------------ 10.0/41.2 MB 380.1 kB/s eta 0:01:23\n", + " --------- ------------------------------ 10.2/41.2 MB 380.4 kB/s eta 0:01:22\n", + " --------- ------------------------------ 10.2/41.2 MB 380.4 kB/s eta 0:01:22\n", + " ---------- ----------------------------- 10.5/41.2 MB 382.2 kB/s eta 0:01:21\n", + " ---------- ----------------------------- 10.5/41.2 MB 382.2 kB/s eta 0:01:21\n", + " ---------- ----------------------------- 10.5/41.2 MB 382.2 kB/s eta 0:01:21\n", + " ---------- ----------------------------- 10.7/41.2 MB 382.8 kB/s eta 0:01:20\n", + " ---------- ----------------------------- 11.0/41.2 MB 389.7 kB/s eta 0:01:18\n", + " ---------- ----------------------------- 11.0/41.2 MB 389.7 kB/s eta 0:01:18\n", + " ---------- ----------------------------- 11.3/41.2 MB 394.8 kB/s eta 0:01:16\n", + " ---------- ----------------------------- 11.3/41.2 MB 394.8 kB/s eta 0:01:16\n", + " ----------- ---------------------------- 11.5/41.2 MB 398.6 kB/s eta 0:01:15\n", + " ----------- ---------------------------- 11.8/41.2 MB 402.9 kB/s eta 0:01:14\n", + " ----------- ---------------------------- 11.8/41.2 MB 402.9 kB/s eta 0:01:14\n", + " ----------- ---------------------------- 11.8/41.2 MB 402.9 kB/s eta 0:01:14\n", + " ----------- ---------------------------- 11.8/41.2 MB 402.9 kB/s eta 0:01:14\n", + " ----------- ---------------------------- 12.1/41.2 MB 401.8 kB/s eta 0:01:13\n", + " ----------- ---------------------------- 12.1/41.2 MB 401.8 kB/s eta 0:01:13\n", + " ----------- ---------------------------- 12.1/41.2 MB 401.8 kB/s eta 0:01:13\n", + " ----------- ---------------------------- 12.1/41.2 MB 401.8 kB/s eta 0:01:13\n", + " ----------- ---------------------------- 12.1/41.2 MB 401.8 kB/s eta 0:01:13\n", + " ----------- ---------------------------- 12.3/41.2 MB 416.2 kB/s eta 0:01:10\n", + " ----------- ---------------------------- 12.3/41.2 MB 416.2 kB/s eta 0:01:10\n", + " ----------- ---------------------------- 12.3/41.2 MB 416.2 kB/s eta 0:01:10\n", + " ----------- ---------------------------- 12.3/41.2 MB 416.2 kB/s eta 0:01:10\n", + " ----------- ---------------------------- 12.3/41.2 MB 416.2 kB/s eta 0:01:10\n", + " ----------- ---------------------------- 12.3/41.2 MB 416.2 kB/s eta 0:01:10\n", + " ------------ --------------------------- 12.6/41.2 MB 406.4 kB/s eta 0:01:11\n", + " ------------ --------------------------- 12.6/41.2 MB 406.4 kB/s eta 0:01:11\n", + " ------------ --------------------------- 12.6/41.2 MB 406.4 kB/s eta 0:01:11\n", + " ------------ --------------------------- 12.6/41.2 MB 406.4 kB/s eta 0:01:11\n", + " ------------ --------------------------- 12.6/41.2 MB 406.4 kB/s eta 0:01:11\n", + " ------------ --------------------------- 12.8/41.2 MB 404.9 kB/s eta 0:01:11\n", + " ------------ --------------------------- 12.8/41.2 MB 404.9 kB/s eta 0:01:11\n", + " ------------ --------------------------- 12.8/41.2 MB 404.9 kB/s eta 0:01:11\n", + " ------------ --------------------------- 13.1/41.2 MB 404.1 kB/s eta 0:01:10\n", + " ------------ --------------------------- 13.1/41.2 MB 404.1 kB/s eta 0:01:10\n", + " ------------ --------------------------- 13.4/41.2 MB 404.3 kB/s eta 0:01:09\n", + " ------------ --------------------------- 13.4/41.2 MB 404.3 kB/s eta 0:01:09\n", + " ------------- -------------------------- 13.6/41.2 MB 404.3 kB/s eta 0:01:09\n", + " ------------- -------------------------- 13.6/41.2 MB 404.3 kB/s eta 0:01:09\n", + " ------------- -------------------------- 13.9/41.2 MB 405.3 kB/s eta 0:01:08\n", + " ------------- -------------------------- 14.2/41.2 MB 404.9 kB/s eta 0:01:07\n", + " ------------- -------------------------- 14.2/41.2 MB 404.9 kB/s eta 0:01:07\n", + " ------------- -------------------------- 14.4/41.2 MB 414.7 kB/s eta 0:01:05\n", + " ------------- -------------------------- 14.4/41.2 MB 414.7 kB/s eta 0:01:05\n", + " ------------- -------------------------- 14.4/41.2 MB 414.7 kB/s eta 0:01:05\n", + " ------------- -------------------------- 14.4/41.2 MB 414.7 kB/s eta 0:01:05\n", + " ------------- -------------------------- 14.4/41.2 MB 414.7 kB/s eta 0:01:05\n", + " ------------- -------------------------- 14.4/41.2 MB 414.7 kB/s eta 0:01:05\n", + " -------------- ------------------------- 14.7/41.2 MB 408.1 kB/s eta 0:01:06\n", + " -------------- ------------------------- 14.7/41.2 MB 408.1 kB/s eta 0:01:06\n", + " -------------- ------------------------- 14.7/41.2 MB 408.1 kB/s eta 0:01:06\n", + " -------------- ------------------------- 14.9/41.2 MB 411.2 kB/s eta 0:01:04\n", + " -------------- ------------------------- 14.9/41.2 MB 411.2 kB/s eta 0:01:04\n", + " -------------- ------------------------- 15.2/41.2 MB 413.9 kB/s eta 0:01:03\n", + " -------------- ------------------------- 15.2/41.2 MB 413.9 kB/s eta 0:01:03\n", + " -------------- ------------------------- 15.2/41.2 MB 413.9 kB/s eta 0:01:03\n", + " --------------- ------------------------ 15.5/41.2 MB 415.5 kB/s eta 0:01:02\n", + " --------------- ------------------------ 15.5/41.2 MB 415.5 kB/s eta 0:01:02\n", + " --------------- ------------------------ 15.5/41.2 MB 415.5 kB/s eta 0:01:02\n", + " --------------- ------------------------ 15.7/41.2 MB 415.5 kB/s eta 0:01:02\n", + " --------------- ------------------------ 15.7/41.2 MB 415.5 kB/s eta 0:01:02\n", + " --------------- ------------------------ 15.7/41.2 MB 415.5 kB/s eta 0:01:02\n", + " --------------- ------------------------ 16.0/41.2 MB 413.9 kB/s eta 0:01:01\n", + " --------------- ------------------------ 16.0/41.2 MB 413.9 kB/s eta 0:01:01\n", + " --------------- ------------------------ 16.3/41.2 MB 412.6 kB/s eta 0:01:01\n", + " --------------- ------------------------ 16.3/41.2 MB 412.6 kB/s eta 0:01:01\n", + " ---------------- ----------------------- 16.5/41.2 MB 426.0 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 16.5/41.2 MB 426.0 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 16.5/41.2 MB 426.0 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 16.5/41.2 MB 426.0 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 16.5/41.2 MB 426.0 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 16.8/41.2 MB 421.9 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 16.8/41.2 MB 421.9 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 16.8/41.2 MB 421.9 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 17.0/41.2 MB 423.0 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 17.0/41.2 MB 423.0 kB/s eta 0:00:58\n", + " ---------------- ----------------------- 17.3/41.2 MB 427.5 kB/s eta 0:00:56\n", + " ---------------- ----------------------- 17.3/41.2 MB 427.5 kB/s eta 0:00:56\n", + " ---------------- ----------------------- 17.3/41.2 MB 427.5 kB/s eta 0:00:56\n", + " ----------------- ---------------------- 17.6/41.2 MB 429.3 kB/s eta 0:00:56\n", + " ----------------- ---------------------- 17.6/41.2 MB 429.3 kB/s eta 0:00:56\n", + " ----------------- ---------------------- 17.8/41.2 MB 433.1 kB/s eta 0:00:55\n", + " ----------------- ---------------------- 17.8/41.2 MB 433.1 kB/s eta 0:00:55\n", + " ----------------- ---------------------- 18.1/41.2 MB 435.2 kB/s eta 0:00:54\n", + " ----------------- ---------------------- 18.1/41.2 MB 435.2 kB/s eta 0:00:54\n", + " ----------------- ---------------------- 18.4/41.2 MB 436.9 kB/s eta 0:00:53\n", + " ----------------- ---------------------- 18.4/41.2 MB 436.9 kB/s eta 0:00:53\n", + " ------------------ --------------------- 18.6/41.2 MB 438.5 kB/s eta 0:00:52\n", + " ------------------ --------------------- 18.6/41.2 MB 438.5 kB/s eta 0:00:52\n", + " ------------------ --------------------- 18.9/41.2 MB 438.5 kB/s eta 0:00:51\n", + " ------------------ --------------------- 18.9/41.2 MB 438.5 kB/s eta 0:00:51\n", + " ------------------ --------------------- 18.9/41.2 MB 438.5 kB/s eta 0:00:51\n", + " ------------------ --------------------- 18.9/41.2 MB 438.5 kB/s eta 0:00:51\n", + " ------------------ --------------------- 18.9/41.2 MB 438.5 kB/s eta 0:00:51\n", + " ------------------ --------------------- 18.9/41.2 MB 438.5 kB/s eta 0:00:51\n", + " ------------------ --------------------- 18.9/41.2 MB 438.5 kB/s eta 0:00:51\n", + " ------------------ --------------------- 18.9/41.2 MB 438.5 kB/s eta 0:00:51\n", + " ------------------ --------------------- 18.9/41.2 MB 438.5 kB/s eta 0:00:51\n", + " ------------------ --------------------- 19.1/41.2 MB 430.6 kB/s eta 0:00:52\n", + " ------------------ --------------------- 19.1/41.2 MB 430.6 kB/s eta 0:00:52\n", + " ------------------ --------------------- 19.4/41.2 MB 430.4 kB/s eta 0:00:51\n", + " ------------------- -------------------- 19.7/41.2 MB 434.5 kB/s eta 0:00:50\n", + " ------------------- -------------------- 19.7/41.2 MB 434.5 kB/s eta 0:00:50\n", + " ------------------- -------------------- 19.9/41.2 MB 438.3 kB/s eta 0:00:49\n", + " ------------------- -------------------- 19.9/41.2 MB 438.3 kB/s eta 0:00:49\n", + " ------------------- -------------------- 19.9/41.2 MB 438.3 kB/s eta 0:00:49\n", + " ------------------- -------------------- 20.2/41.2 MB 445.5 kB/s eta 0:00:48\n", + " ------------------- -------------------- 20.2/41.2 MB 445.5 kB/s eta 0:00:48\n", + " ------------------- -------------------- 20.2/41.2 MB 445.5 kB/s eta 0:00:48\n", + " ------------------- -------------------- 20.2/41.2 MB 445.5 kB/s eta 0:00:48\n", + " ------------------- -------------------- 20.4/41.2 MB 441.7 kB/s eta 0:00:48\n", + " ------------------- -------------------- 20.4/41.2 MB 441.7 kB/s eta 0:00:48\n", + " ------------------- -------------------- 20.4/41.2 MB 441.7 kB/s eta 0:00:48\n", + " ------------------- -------------------- 20.4/41.2 MB 441.7 kB/s eta 0:00:48\n", + " -------------------- ------------------- 20.7/41.2 MB 438.5 kB/s eta 0:00:47\n", + " -------------------- ------------------- 20.7/41.2 MB 438.5 kB/s eta 0:00:47\n", + " -------------------- ------------------- 20.7/41.2 MB 438.5 kB/s eta 0:00:47\n", + " -------------------- ------------------- 20.7/41.2 MB 438.5 kB/s eta 0:00:47\n", + " -------------------- ------------------- 20.7/41.2 MB 438.5 kB/s eta 0:00:47\n", + " -------------------- ------------------- 20.7/41.2 MB 438.5 kB/s eta 0:00:47\n", + " -------------------- ------------------- 20.7/41.2 MB 438.5 kB/s eta 0:00:47\n", + " -------------------- ------------------- 21.0/41.2 MB 433.8 kB/s eta 0:00:47\n", + " -------------------- ------------------- 21.0/41.2 MB 433.8 kB/s eta 0:00:47\n", + " -------------------- ------------------- 21.0/41.2 MB 433.8 kB/s eta 0:00:47\n", + " -------------------- ------------------- 21.2/41.2 MB 430.9 kB/s eta 0:00:47\n", + " -------------------- ------------------- 21.5/41.2 MB 432.9 kB/s eta 0:00:46\n", + " -------------------- ------------------- 21.5/41.2 MB 432.9 kB/s eta 0:00:46\n", + " --------------------- ------------------ 21.8/41.2 MB 435.2 kB/s eta 0:00:45\n", + " --------------------- ------------------ 21.8/41.2 MB 435.2 kB/s eta 0:00:45\n", + " --------------------- ------------------ 21.8/41.2 MB 435.2 kB/s eta 0:00:45\n", + " --------------------- ------------------ 21.8/41.2 MB 435.2 kB/s eta 0:00:45\n", + " --------------------- ------------------ 22.0/41.2 MB 428.2 kB/s eta 0:00:45\n", + " --------------------- ------------------ 22.0/41.2 MB 428.2 kB/s eta 0:00:45\n", + " --------------------- ------------------ 22.0/41.2 MB 428.2 kB/s eta 0:00:45\n", + " --------------------- ------------------ 22.0/41.2 MB 428.2 kB/s eta 0:00:45\n", + " --------------------- ------------------ 22.3/41.2 MB 421.0 kB/s eta 0:00:45\n", + " --------------------- ------------------ 22.3/41.2 MB 421.0 kB/s eta 0:00:45\n", + " --------------------- ------------------ 22.5/41.2 MB 418.1 kB/s eta 0:00:45\n", + " --------------------- ------------------ 22.5/41.2 MB 418.1 kB/s eta 0:00:45\n", + " --------------------- ------------------ 22.5/41.2 MB 418.1 kB/s eta 0:00:45\n", + " ---------------------- ----------------- 22.8/41.2 MB 420.3 kB/s eta 0:00:44\n", + " ---------------------- ----------------- 22.8/41.2 MB 420.3 kB/s eta 0:00:44\n", + " ---------------------- ----------------- 23.1/41.2 MB 421.8 kB/s eta 0:00:44\n", + " ---------------------- ----------------- 23.1/41.2 MB 421.8 kB/s eta 0:00:44\n", + " ---------------------- ----------------- 23.1/41.2 MB 421.8 kB/s eta 0:00:44\n", + " ---------------------- ----------------- 23.1/41.2 MB 421.8 kB/s eta 0:00:44\n", + " ---------------------- ----------------- 23.1/41.2 MB 421.8 kB/s eta 0:00:44\n", + " ---------------------- ----------------- 23.3/41.2 MB 405.1 kB/s eta 0:00:45\n", + " ---------------------- ----------------- 23.3/41.2 MB 405.1 kB/s eta 0:00:45\n", + " ---------------------- ----------------- 23.6/41.2 MB 404.7 kB/s eta 0:00:44\n", + " ----------------------- ---------------- 23.9/41.2 MB 404.9 kB/s eta 0:00:43\n", + " ----------------------- ---------------- 24.1/41.2 MB 411.8 kB/s eta 0:00:42\n", + " ----------------------- ---------------- 24.1/41.2 MB 411.8 kB/s eta 0:00:42\n", + " ----------------------- ---------------- 24.4/41.2 MB 415.7 kB/s eta 0:00:41\n", + " ----------------------- ---------------- 24.6/41.2 MB 419.9 kB/s eta 0:00:40\n", + " ----------------------- ---------------- 24.6/41.2 MB 419.9 kB/s eta 0:00:40\n", + " ------------------------ --------------- 24.9/41.2 MB 430.4 kB/s eta 0:00:38\n", + " ------------------------ --------------- 25.2/41.2 MB 435.9 kB/s eta 0:00:37\n", + " ------------------------ --------------- 25.4/41.2 MB 440.6 kB/s eta 0:00:36\n", + " ------------------------ --------------- 25.7/41.2 MB 456.9 kB/s eta 0:00:34\n", + " ------------------------ --------------- 25.7/41.2 MB 456.9 kB/s eta 0:00:34\n", + " ------------------------ --------------- 25.7/41.2 MB 456.9 kB/s eta 0:00:34\n", + " ------------------------ --------------- 25.7/41.2 MB 456.9 kB/s eta 0:00:34\n", + " ------------------------ --------------- 25.7/41.2 MB 456.9 kB/s eta 0:00:34\n", + " ------------------------ --------------- 25.7/41.2 MB 456.9 kB/s eta 0:00:34\n", + " ------------------------ --------------- 25.7/41.2 MB 456.9 kB/s eta 0:00:34\n", + " ------------------------- -------------- 26.0/41.2 MB 451.5 kB/s eta 0:00:34\n", + " ------------------------- -------------- 26.0/41.2 MB 451.5 kB/s eta 0:00:34\n", + " ------------------------- -------------- 26.0/41.2 MB 451.5 kB/s eta 0:00:34\n", + " ------------------------- -------------- 26.2/41.2 MB 448.9 kB/s eta 0:00:34\n", + " ------------------------- -------------- 26.2/41.2 MB 448.9 kB/s eta 0:00:34\n", + " ------------------------- -------------- 26.5/41.2 MB 454.2 kB/s eta 0:00:33\n", + " ------------------------- -------------- 26.5/41.2 MB 454.2 kB/s eta 0:00:33\n", + " ------------------------- -------------- 26.7/41.2 MB 455.1 kB/s eta 0:00:32\n", + " ------------------------- -------------- 26.7/41.2 MB 455.1 kB/s eta 0:00:32\n", + " -------------------------- ------------- 27.0/41.2 MB 457.7 kB/s eta 0:00:32\n", + " -------------------------- ------------- 27.3/41.2 MB 459.9 kB/s eta 0:00:31\n", + " -------------------------- ------------- 27.3/41.2 MB 459.9 kB/s eta 0:00:31\n", + " -------------------------- ------------- 27.5/41.2 MB 464.1 kB/s eta 0:00:30\n", + " -------------------------- ------------- 27.8/41.2 MB 464.6 kB/s eta 0:00:29\n", + " -------------------------- ------------- 27.8/41.2 MB 464.6 kB/s eta 0:00:29\n", + " --------------------------- ------------ 28.0/41.2 MB 465.8 kB/s eta 0:00:29\n", + " --------------------------- ------------ 28.3/41.2 MB 465.8 kB/s eta 0:00:28\n", + " --------------------------- ------------ 28.3/41.2 MB 465.8 kB/s eta 0:00:28\n", + " --------------------------- ------------ 28.6/41.2 MB 482.2 kB/s eta 0:00:27\n", + " --------------------------- ------------ 28.6/41.2 MB 482.2 kB/s eta 0:00:27\n", + " --------------------------- ------------ 28.8/41.2 MB 482.4 kB/s eta 0:00:26\n", + " --------------------------- ------------ 28.8/41.2 MB 482.4 kB/s eta 0:00:26\n", + " --------------------------- ------------ 28.8/41.2 MB 482.4 kB/s eta 0:00:26\n", + " --------------------------- ------------ 28.8/41.2 MB 482.4 kB/s eta 0:00:26\n", + " --------------------------- ------------ 28.8/41.2 MB 482.4 kB/s eta 0:00:26\n", + " --------------------------- ------------ 28.8/41.2 MB 482.4 kB/s eta 0:00:26\n", + " --------------------------- ------------ 28.8/41.2 MB 482.4 kB/s eta 0:00:26\n", + " --------------------------- ------------ 28.8/41.2 MB 482.4 kB/s eta 0:00:26\n", + " ---------------------------- ----------- 29.1/41.2 MB 465.3 kB/s eta 0:00:27\n", + " ---------------------------- ----------- 29.1/41.2 MB 465.3 kB/s eta 0:00:27\n", + " ---------------------------- ----------- 29.4/41.2 MB 467.5 kB/s eta 0:00:26\n", + " ---------------------------- ----------- 29.4/41.2 MB 467.5 kB/s eta 0:00:26\n", + " ---------------------------- ----------- 29.6/41.2 MB 468.5 kB/s eta 0:00:25\n", + " ---------------------------- ----------- 29.6/41.2 MB 468.5 kB/s eta 0:00:25\n", + " ---------------------------- ----------- 29.6/41.2 MB 468.5 kB/s eta 0:00:25\n", + " ----------------------------- ---------- 29.9/41.2 MB 467.5 kB/s eta 0:00:25\n", + " ----------------------------- ---------- 29.9/41.2 MB 467.5 kB/s eta 0:00:25\n", + " ----------------------------- ---------- 30.1/41.2 MB 470.7 kB/s eta 0:00:24\n", + " ----------------------------- ---------- 30.4/41.2 MB 474.8 kB/s eta 0:00:23\n", + " ----------------------------- ---------- 30.7/41.2 MB 477.6 kB/s eta 0:00:23\n", + " ----------------------------- ---------- 30.7/41.2 MB 477.6 kB/s eta 0:00:23\n", + " ------------------------------ --------- 30.9/41.2 MB 482.1 kB/s eta 0:00:22\n", + " ------------------------------ --------- 30.9/41.2 MB 482.1 kB/s eta 0:00:22\n", + " ------------------------------ --------- 30.9/41.2 MB 482.1 kB/s eta 0:00:22\n", + " ------------------------------ --------- 30.9/41.2 MB 482.1 kB/s eta 0:00:22\n", + " ------------------------------ --------- 31.2/41.2 MB 485.9 kB/s eta 0:00:21\n", + " ------------------------------ --------- 31.2/41.2 MB 485.9 kB/s eta 0:00:21\n", + " ------------------------------ --------- 31.2/41.2 MB 485.9 kB/s eta 0:00:21\n", + " ------------------------------ --------- 31.2/41.2 MB 485.9 kB/s eta 0:00:21\n", + " ------------------------------ --------- 31.5/41.2 MB 480.9 kB/s eta 0:00:21\n", + " ------------------------------ --------- 31.5/41.2 MB 480.9 kB/s eta 0:00:21\n", + " ------------------------------ --------- 31.5/41.2 MB 480.9 kB/s eta 0:00:21\n", + " ------------------------------ --------- 31.5/41.2 MB 480.9 kB/s eta 0:00:21\n", + " ------------------------------ --------- 31.7/41.2 MB 474.1 kB/s eta 0:00:21\n", + " ------------------------------ --------- 31.7/41.2 MB 474.1 kB/s eta 0:00:21\n", + " ------------------------------- -------- 32.0/41.2 MB 476.3 kB/s eta 0:00:20\n", + " ------------------------------- -------- 32.2/41.2 MB 478.3 kB/s eta 0:00:19\n", + " ------------------------------- -------- 32.2/41.2 MB 478.3 kB/s eta 0:00:19\n", + " ------------------------------- -------- 32.2/41.2 MB 478.3 kB/s eta 0:00:19\n", + " ------------------------------- -------- 32.5/41.2 MB 477.3 kB/s eta 0:00:19\n", + " ------------------------------- -------- 32.8/41.2 MB 480.6 kB/s eta 0:00:18\n", + " ------------------------------- -------- 32.8/41.2 MB 480.6 kB/s eta 0:00:18\n", + " -------------------------------- ------- 33.0/41.2 MB 481.6 kB/s eta 0:00:18\n", + " -------------------------------- ------- 33.0/41.2 MB 481.6 kB/s eta 0:00:18\n", + " -------------------------------- ------- 33.3/41.2 MB 482.6 kB/s eta 0:00:17\n", + " -------------------------------- ------- 33.3/41.2 MB 482.6 kB/s eta 0:00:17\n", + " -------------------------------- ------- 33.6/41.2 MB 506.7 kB/s eta 0:00:16\n", + " -------------------------------- ------- 33.6/41.2 MB 506.7 kB/s eta 0:00:16\n", + " -------------------------------- ------- 33.6/41.2 MB 506.7 kB/s eta 0:00:16\n", + " -------------------------------- ------- 33.6/41.2 MB 506.7 kB/s eta 0:00:16\n", + " -------------------------------- ------- 33.6/41.2 MB 506.7 kB/s eta 0:00:16\n", + " -------------------------------- ------- 33.8/41.2 MB 496.6 kB/s eta 0:00:15\n", + " -------------------------------- ------- 33.8/41.2 MB 496.6 kB/s eta 0:00:15\n", + " -------------------------------- ------- 33.8/41.2 MB 496.6 kB/s eta 0:00:15\n", + " --------------------------------- ------ 34.1/41.2 MB 492.7 kB/s eta 0:00:15\n", + " --------------------------------- ------ 34.1/41.2 MB 492.7 kB/s eta 0:00:15\n", + " --------------------------------- ------ 34.1/41.2 MB 492.7 kB/s eta 0:00:15\n", + " --------------------------------- ------ 34.3/41.2 MB 481.9 kB/s eta 0:00:15\n", + " --------------------------------- ------ 34.3/41.2 MB 481.9 kB/s eta 0:00:15\n", + " --------------------------------- ------ 34.6/41.2 MB 484.9 kB/s eta 0:00:14\n", + " --------------------------------- ------ 34.6/41.2 MB 484.9 kB/s eta 0:00:14\n", + " --------------------------------- ------ 34.6/41.2 MB 484.9 kB/s eta 0:00:14\n", + " --------------------------------- ------ 34.9/41.2 MB 492.4 kB/s eta 0:00:13\n", + " ---------------------------------- ----- 35.1/41.2 MB 496.6 kB/s eta 0:00:13\n", + " ---------------------------------- ----- 35.4/41.2 MB 501.7 kB/s eta 0:00:12\n", + " ---------------------------------- ----- 35.4/41.2 MB 501.7 kB/s eta 0:00:12\n", + " ---------------------------------- ----- 35.9/41.2 MB 516.2 kB/s eta 0:00:11\n", + " ----------------------------------- ---- 36.2/41.2 MB 521.8 kB/s eta 0:00:10\n", + " ----------------------------------- ---- 36.4/41.2 MB 527.0 kB/s eta 0:00:10\n", + " ----------------------------------- ---- 36.4/41.2 MB 527.0 kB/s eta 0:00:10\n", + " ----------------------------------- ---- 36.4/41.2 MB 527.0 kB/s eta 0:00:10\n", + " ----------------------------------- ---- 36.4/41.2 MB 527.0 kB/s eta 0:00:10\n", + " ----------------------------------- ---- 36.7/41.2 MB 538.9 kB/s eta 0:00:09\n", + " ----------------------------------- ---- 36.7/41.2 MB 538.9 kB/s eta 0:00:09\n", + " ----------------------------------- ---- 37.0/41.2 MB 538.6 kB/s eta 0:00:08\n", + " ----------------------------------- ---- 37.0/41.2 MB 538.6 kB/s eta 0:00:08\n", + " ------------------------------------ --- 37.2/41.2 MB 542.3 kB/s eta 0:00:08\n", + " ------------------------------------ --- 37.5/41.2 MB 546.6 kB/s eta 0:00:07\n", + " ------------------------------------ --- 37.7/41.2 MB 551.9 kB/s eta 0:00:07\n", + " ------------------------------------ --- 38.0/41.2 MB 554.3 kB/s eta 0:00:06\n", + " ------------------------------------- -- 38.3/41.2 MB 559.8 kB/s eta 0:00:06\n", + " ------------------------------------- -- 38.8/41.2 MB 569.5 kB/s eta 0:00:05\n", + " ------------------------------------- -- 39.1/41.2 MB 583.8 kB/s eta 0:00:04\n", + " ------------------------------------- -- 39.1/41.2 MB 583.8 kB/s eta 0:00:04\n", + " ------------------------------------- -- 39.1/41.2 MB 583.8 kB/s eta 0:00:04\n", + " -------------------------------------- - 39.3/41.2 MB 583.7 kB/s eta 0:00:04\n", + " -------------------------------------- - 39.3/41.2 MB 583.7 kB/s eta 0:00:04\n", + " -------------------------------------- - 39.6/41.2 MB 587.1 kB/s eta 0:00:03\n", + " -------------------------------------- - 39.6/41.2 MB 587.1 kB/s eta 0:00:03\n", + " -------------------------------------- - 39.6/41.2 MB 587.1 kB/s eta 0:00:03\n", + " -------------------------------------- - 39.8/41.2 MB 586.8 kB/s eta 0:00:03\n", + " -------------------------------------- - 40.1/41.2 MB 589.1 kB/s eta 0:00:02\n", + " -------------------------------------- - 40.1/41.2 MB 589.1 kB/s eta 0:00:02\n", + " --------------------------------------- 40.4/41.2 MB 593.2 kB/s eta 0:00:02\n", + " --------------------------------------- 40.4/41.2 MB 593.2 kB/s eta 0:00:02\n", + " --------------------------------------- 40.4/41.2 MB 593.2 kB/s eta 0:00:02\n", + " --------------------------------------- 40.4/41.2 MB 593.2 kB/s eta 0:00:02\n", + " --------------------------------------- 40.4/41.2 MB 593.2 kB/s eta 0:00:02\n", + " --------------------------------------- 40.6/41.2 MB 591.2 kB/s eta 0:00:01\n", + " --------------------------------------- 40.6/41.2 MB 591.2 kB/s eta 0:00:01\n", + " --------------------------------------- 40.6/41.2 MB 591.2 kB/s eta 0:00:01\n", + " --------------------------------------- 40.9/41.2 MB 590.1 kB/s eta 0:00:01\n", + " --------------------------------------- 40.9/41.2 MB 590.1 kB/s eta 0:00:01\n", + " --------------------------------------- 40.9/41.2 MB 590.1 kB/s eta 0:00:01\n", + " --------------------------------------- 41.2/41.2 MB 582.5 kB/s eta 0:00:01\n", + " ---------------------------------------- 41.2/41.2 MB 580.6 kB/s eta 0:00:00\n", + "Installing collected packages: scipy, patsy, statsmodels\n", + "Successfully installed patsy-1.0.1 scipy-1.15.2 statsmodels-0.14.4\n" + ] + } + ], + "source": [ + "#!pip install statsmodels" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "537f2ffb-487d-4005-86fa-ad4b63045ffd", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: time_to_answer_B R-squared: 0.005\n", + "Model: OLS Adj. R-squared: -0.050\n", + "Method: Least Squares F-statistic: 0.08829\n", + "Date: Mon, 14 Apr 2025 Prob (F-statistic): 0.770\n", + "Time: 23:09:26 Log-Likelihood: -137.79\n", + "No. Observations: 20 AIC: 279.6\n", + "Df Residuals: 18 BIC: 281.6\n", + "Df Model: 1 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -55.4718 1231.942 -0.045 0.965 -2643.686 2532.743\n", + "rating 0.0997 0.335 0.297 0.770 -0.605 0.804\n", + "==============================================================================\n", + "Omnibus: 24.372 Durbin-Watson: 2.320\n", + "Prob(Omnibus): 0.000 Jarque-Bera (JB): 33.592\n", + "Skew: 2.235 Prob(JB): 5.08e-08\n", + "Kurtosis: 7.509 Cond. No. 8.08e+04\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", + "[2] The condition number is large, 8.08e+04. This might indicate that there are\n", + "strong multicollinearity or other numerical problems.\n" + ] + } + ], + "source": [ + "#import statsmodels.api as sm\n", + "\n", + "#data = df[['rating', 'time_to_answer_B']].dropna()\n", + "#X = sm.add_constant(data['rating'])\n", + "#y = data['time_to_answer_B']\n", + "#model = sm.OLS(y, X).fit()\n", + "#print(model.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "24a62c6b-bd78-4cef-936a-0bec173e1982", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [conda env:Tarea1]", + "language": "python", + "name": "conda-env-Tarea1-py" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.11" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/homework/hw2/259359_hw2_2025_1/Tarea 2 VF.ipynb b/homework/hw2/259359_hw2_2025_1/Tarea 2 VF.ipynb new file mode 100644 index 000000000..ec35b8436 --- /dev/null +++ b/homework/hw2/259359_hw2_2025_1/Tarea 2 VF.ipynb @@ -0,0 +1,1303 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 3, + "id": "466ae9b3-3bb6-4118-a26b-2660b02ec0b2", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Concursos seleccionados:\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idnamestartTime
482053Good Bye 2024: 2025 is NEAR2024-12-28 14:35:00
492043Educational Codeforces Round 173 (Rated for Di...2024-12-24 14:35:00
512051Codeforces Round 995 (Div. 3)2024-12-22 14:35:00
522049Codeforces Round 994 (Div. 2)2024-12-20 14:35:00
532048Codeforces Global Round 282024-12-19 14:35:00
542044Codeforces Round 993 (Div. 4)2024-12-15 14:35:00
562040Codeforces Round 992 (Div. 2)2024-12-08 14:35:00
572050Codeforces Round 991 (Div. 3)2024-12-05 14:35:00
582046Codeforces Round 990 (Div. 1)2024-12-03 06:25:00
592047Codeforces Round 990 (Div. 2)2024-12-03 06:25:00
602042Educational Codeforces Round 172 (Rated for Di...2024-12-02 14:35:00
622034Rayan Programming Contest 2024 - Selection (Co...2024-11-30 14:35:00
642039CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!)2024-11-23 14:35:00
662037Codeforces Round 988 (Div. 3)2024-11-17 14:35:00
672031Codeforces Round 987 (Div. 2)2024-11-15 12:35:00
682028Codeforces Round 986 (Div. 2)2024-11-10 15:35:00
692029Refact.ai Match 1 (Codeforces Round 985)2024-11-09 14:35:00
702036Codeforces Round 984 (Div. 3)2024-11-02 14:35:00
712032Codeforces Round 983 (Div. 2)2024-11-01 14:35:00
722026Educational Codeforces Round 171 (Rated for Di...2024-10-28 14:35:00
732035Codeforces Global Round 272024-10-27 14:35:00
742027Codeforces Round 982 (Div. 2)2024-10-26 14:35:00
752033Codeforces Round 981 (Div. 3)2024-10-24 14:35:00
762023Codeforces Round 980 (Div. 1)2024-10-20 09:05:00
772024Codeforces Round 980 (Div. 2)2024-10-20 09:05:00
782030Codeforces Round 979 (Div. 2)2024-10-19 14:05:00
792025Educational Codeforces Round 170 (Rated for Di...2024-10-14 14:35:00
802022Codeforces Round 978 (Div. 2)2024-10-13 19:35:00
812021Codeforces Round 977 (Div. 2, based on COMPFES...2024-10-06 06:05:00
832020Codeforces Round 976 (Div. 2) and Divide By Ze...2024-09-29 15:35:00
842018Codeforces Round 975 (Div. 1)2024-09-27 13:35:00
852019Codeforces Round 975 (Div. 2)2024-09-27 13:35:00
862014Codeforces Round 974 (Div. 3)2024-09-21 14:45:00
872013Codeforces Round 973 (Div. 2)2024-09-20 14:35:00
902005Codeforces Round 972 (Div. 2)2024-09-14 14:35:00
912009Codeforces Round 971 (Div. 4)2024-09-03 14:35:00
922008Codeforces Round 970 (Div. 3)2024-09-01 14:35:00
932006Codeforces Round 969 (Div. 1)2024-08-30 14:35:00
942007Codeforces Round 969 (Div. 2)2024-08-30 14:35:00
952010Testing Round 19 (Div. 3)2024-08-28 20:35:00
962003Codeforces Round 968 (Div. 2)2024-08-25 14:35:00
972001Codeforces Round 967 (Div. 2)2024-08-20 14:35:00
982004Educational Codeforces Round 169 (Rated for Di...2024-08-15 14:35:00
992000Codeforces Round 966 (Div. 3)2024-08-13 14:40:00
1002002EPIC Institute of Technology Round August 2024...2024-08-11 14:35:00
1011998Codeforces Round 965 (Div. 2)2024-08-10 14:35:00
1021999Codeforces Round 964 (Div. 4)2024-08-06 14:35:00
1031993Codeforces Round 963 (Div. 2)2024-08-04 14:35:00
1041997Educational Codeforces Round 168 (Rated for Di...2024-07-30 14:35:00
1051991Pinely Round 4 (Div. 1 + Div. 2)2024-07-28 14:35:00
1061996Codeforces Round 962 (Div. 3)2024-07-26 14:35:00
1071995Codeforces Round 961 (Div. 2)2024-07-23 14:35:00
1081990Codeforces Round 960 (Div. 2)2024-07-20 14:35:00
1091994Codeforces Round 959 sponsored by NEAR (Div. 1...2024-07-18 14:35:00
1101988Codeforces Round 958 (Div. 2)2024-07-15 14:35:00
1111992Codeforces Round 957 (Div. 3)2024-07-11 14:35:00
1121983Codeforces Round 956 (Div. 2) and ByteRace 20242024-07-07 14:35:00
\n", + "
" + ], + "text/plain": [ + " id name \\\n", + "48 2053 Good Bye 2024: 2025 is NEAR \n", + "49 2043 Educational Codeforces Round 173 (Rated for Di... \n", + "51 2051 Codeforces Round 995 (Div. 3) \n", + "52 2049 Codeforces Round 994 (Div. 2) \n", + "53 2048 Codeforces Global Round 28 \n", + "54 2044 Codeforces Round 993 (Div. 4) \n", + "56 2040 Codeforces Round 992 (Div. 2) \n", + "57 2050 Codeforces Round 991 (Div. 3) \n", + "58 2046 Codeforces Round 990 (Div. 1) \n", + "59 2047 Codeforces Round 990 (Div. 2) \n", + "60 2042 Educational Codeforces Round 172 (Rated for Di... \n", + "62 2034 Rayan Programming Contest 2024 - Selection (Co... \n", + "64 2039 CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!) \n", + "66 2037 Codeforces Round 988 (Div. 3) \n", + "67 2031 Codeforces Round 987 (Div. 2) \n", + "68 2028 Codeforces Round 986 (Div. 2) \n", + "69 2029 Refact.ai Match 1 (Codeforces Round 985) \n", + "70 2036 Codeforces Round 984 (Div. 3) \n", + "71 2032 Codeforces Round 983 (Div. 2) \n", + "72 2026 Educational Codeforces Round 171 (Rated for Di... \n", + "73 2035 Codeforces Global Round 27 \n", + "74 2027 Codeforces Round 982 (Div. 2) \n", + "75 2033 Codeforces Round 981 (Div. 3) \n", + "76 2023 Codeforces Round 980 (Div. 1) \n", + "77 2024 Codeforces Round 980 (Div. 2) \n", + "78 2030 Codeforces Round 979 (Div. 2) \n", + "79 2025 Educational Codeforces Round 170 (Rated for Di... \n", + "80 2022 Codeforces Round 978 (Div. 2) \n", + "81 2021 Codeforces Round 977 (Div. 2, based on COMPFES... \n", + "83 2020 Codeforces Round 976 (Div. 2) and Divide By Ze... \n", + "84 2018 Codeforces Round 975 (Div. 1) \n", + "85 2019 Codeforces Round 975 (Div. 2) \n", + "86 2014 Codeforces Round 974 (Div. 3) \n", + "87 2013 Codeforces Round 973 (Div. 2) \n", + "90 2005 Codeforces Round 972 (Div. 2) \n", + "91 2009 Codeforces Round 971 (Div. 4) \n", + "92 2008 Codeforces Round 970 (Div. 3) \n", + "93 2006 Codeforces Round 969 (Div. 1) \n", + "94 2007 Codeforces Round 969 (Div. 2) \n", + "95 2010 Testing Round 19 (Div. 3) \n", + "96 2003 Codeforces Round 968 (Div. 2) \n", + "97 2001 Codeforces Round 967 (Div. 2) \n", + "98 2004 Educational Codeforces Round 169 (Rated for Di... \n", + "99 2000 Codeforces Round 966 (Div. 3) \n", + "100 2002 EPIC Institute of Technology Round August 2024... \n", + "101 1998 Codeforces Round 965 (Div. 2) \n", + "102 1999 Codeforces Round 964 (Div. 4) \n", + "103 1993 Codeforces Round 963 (Div. 2) \n", + "104 1997 Educational Codeforces Round 168 (Rated for Di... \n", + "105 1991 Pinely Round 4 (Div. 1 + Div. 2) \n", + "106 1996 Codeforces Round 962 (Div. 3) \n", + "107 1995 Codeforces Round 961 (Div. 2) \n", + "108 1990 Codeforces Round 960 (Div. 2) \n", + "109 1994 Codeforces Round 959 sponsored by NEAR (Div. 1... \n", + "110 1988 Codeforces Round 958 (Div. 2) \n", + "111 1992 Codeforces Round 957 (Div. 3) \n", + "112 1983 Codeforces Round 956 (Div. 2) and ByteRace 2024 \n", + "\n", + " startTime \n", + "48 2024-12-28 14:35:00 \n", + "49 2024-12-24 14:35:00 \n", + "51 2024-12-22 14:35:00 \n", + "52 2024-12-20 14:35:00 \n", + "53 2024-12-19 14:35:00 \n", + "54 2024-12-15 14:35:00 \n", + "56 2024-12-08 14:35:00 \n", + "57 2024-12-05 14:35:00 \n", + "58 2024-12-03 06:25:00 \n", + "59 2024-12-03 06:25:00 \n", + "60 2024-12-02 14:35:00 \n", + "62 2024-11-30 14:35:00 \n", + "64 2024-11-23 14:35:00 \n", + "66 2024-11-17 14:35:00 \n", + "67 2024-11-15 12:35:00 \n", + "68 2024-11-10 15:35:00 \n", + "69 2024-11-09 14:35:00 \n", + "70 2024-11-02 14:35:00 \n", + "71 2024-11-01 14:35:00 \n", + "72 2024-10-28 14:35:00 \n", + "73 2024-10-27 14:35:00 \n", + "74 2024-10-26 14:35:00 \n", + "75 2024-10-24 14:35:00 \n", + "76 2024-10-20 09:05:00 \n", + "77 2024-10-20 09:05:00 \n", + "78 2024-10-19 14:05:00 \n", + "79 2024-10-14 14:35:00 \n", + "80 2024-10-13 19:35:00 \n", + "81 2024-10-06 06:05:00 \n", + "83 2024-09-29 15:35:00 \n", + "84 2024-09-27 13:35:00 \n", + "85 2024-09-27 13:35:00 \n", + "86 2024-09-21 14:45:00 \n", + "87 2024-09-20 14:35:00 \n", + "90 2024-09-14 14:35:00 \n", + "91 2024-09-03 14:35:00 \n", + "92 2024-09-01 14:35:00 \n", + "93 2024-08-30 14:35:00 \n", + "94 2024-08-30 14:35:00 \n", + "95 2024-08-28 20:35:00 \n", + "96 2024-08-25 14:35:00 \n", + "97 2024-08-20 14:35:00 \n", + "98 2024-08-15 14:35:00 \n", + "99 2024-08-13 14:40:00 \n", + "100 2024-08-11 14:35:00 \n", + "101 2024-08-10 14:35:00 \n", + "102 2024-08-06 14:35:00 \n", + "103 2024-08-04 14:35:00 \n", + "104 2024-07-30 14:35:00 \n", + "105 2024-07-28 14:35:00 \n", + "106 2024-07-26 14:35:00 \n", + "107 2024-07-23 14:35:00 \n", + "108 2024-07-20 14:35:00 \n", + "109 2024-07-18 14:35:00 \n", + "110 2024-07-15 14:35:00 \n", + "111 2024-07-11 14:35:00 \n", + "112 2024-07-07 14:35:00 " + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "#Parte 1: Extracción de Datos desde la API de Codeforces\n", + "#Carga las librerías necesarias.\n", + "\n", + "#Hace una solicitud al endpoint contest.list de Codeforces.\n", + "\n", + "#Convierte la respuesta en un DataFrame.\n", + "\n", + "#Filtra los concursos que se realizaron entre julio y diciembre de 2024, y cuyo nombre contiene “Hello”, “Round” o “Good Bye”.\n", + "\n", + "#Muestra los concursos seleccionados para trabajar con ellos en las siguientes etapas.\n", + "#-----------------------------------------------------------------------------------------------------------------------------# \n", + "# Importamos las librerías necesarias\n", + "import requests\n", + "import pandas as pd\n", + "from datetime import datetime\n", + "\n", + "# Esta función convierte un timestamp a una fecha legible\n", + "def timestamp_to_date(timestamp):\n", + " return datetime.utcfromtimestamp(timestamp)\n", + "\n", + "# 1. Obtenemos la lista de concursos desde el endpoint contest.list\n", + "url_contests = \"https://codeforces.com/api/contest.list\"\n", + "response = requests.get(url_contests)\n", + "contests_data = response.json()\n", + "\n", + "# Verificamos que la respuesta haya sido exitosa\n", + "assert contests_data['status'] == 'OK', \"No se pudo obtener la lista de concursos\"\n", + "\n", + "# Convertimos los datos a un DataFrame para filtrarlos fácilmente\n", + "df_contests = pd.DataFrame(contests_data['result'])\n", + "\n", + "# Convertimos los timestamps a fechas legibles\n", + "df_contests['startTime'] = df_contests['startTimeSeconds'].apply(timestamp_to_date)\n", + "\n", + "# Filtramos los concursos por:\n", + "# - Fechas entre julio y diciembre 2024\n", + "# - Nombre que contenga 'Hello', 'Round' o 'Good Bye'\n", + "df_contests_filtered = df_contests[\n", + " (df_contests['startTime'] >= datetime(2024, 7, 1)) &\n", + " (df_contests['startTime'] <= datetime(2024, 12, 31)) &\n", + " (df_contests['name'].str.contains('Hello|Round|Good Bye', case=False, na=False))\n", + "].copy()\n", + "\n", + "# Mostramos los concursos seleccionados\n", + "print(\"Concursos seleccionados:\")\n", + "display(df_contests_filtered[['id', 'name', 'startTime']])" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "e3755325-e639-4e03-8f87-95925eebab2e", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "📥 Extrayendo datos para el concurso: Good Bye 2024: 2025 is NEAR (ID: 2053)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 173 (Rated for Div. 2) (ID: 2043)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 995 (Div. 3) (ID: 2051)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 994 (Div. 2) (ID: 2049)\n", + "📥 Extrayendo datos para el concurso: Codeforces Global Round 28 (ID: 2048)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 993 (Div. 4) (ID: 2044)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 992 (Div. 2) (ID: 2040)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 991 (Div. 3) (ID: 2050)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 990 (Div. 1) (ID: 2046)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 990 (Div. 2) (ID: 2047)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 172 (Rated for Div. 2) (ID: 2042)\n", + "📥 Extrayendo datos para el concurso: Rayan Programming Contest 2024 - Selection (Codeforces Round 989, Div. 1 + Div. 2) (ID: 2034)\n", + "📥 Extrayendo datos para el concurso: CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!) (ID: 2039)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 988 (Div. 3) (ID: 2037)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 987 (Div. 2) (ID: 2031)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 986 (Div. 2) (ID: 2028)\n", + "📥 Extrayendo datos para el concurso: Refact.ai Match 1 (Codeforces Round 985) (ID: 2029)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 984 (Div. 3) (ID: 2036)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 983 (Div. 2) (ID: 2032)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 171 (Rated for Div. 2) (ID: 2026)\n", + "📥 Extrayendo datos para el concurso: Codeforces Global Round 27 (ID: 2035)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 982 (Div. 2) (ID: 2027)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 981 (Div. 3) (ID: 2033)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 980 (Div. 1) (ID: 2023)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 980 (Div. 2) (ID: 2024)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 979 (Div. 2) (ID: 2030)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 170 (Rated for Div. 2) (ID: 2025)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 978 (Div. 2) (ID: 2022)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 977 (Div. 2, based on COMPFEST 16 - Final Round) (ID: 2021)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 976 (Div. 2) and Divide By Zero 9.0 (ID: 2020)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 975 (Div. 1) (ID: 2018)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 975 (Div. 2) (ID: 2019)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 974 (Div. 3) (ID: 2014)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 973 (Div. 2) (ID: 2013)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 972 (Div. 2) (ID: 2005)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 971 (Div. 4) (ID: 2009)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 970 (Div. 3) (ID: 2008)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 969 (Div. 1) (ID: 2006)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 969 (Div. 2) (ID: 2007)\n", + "📥 Extrayendo datos para el concurso: Testing Round 19 (Div. 3) (ID: 2010)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 968 (Div. 2) (ID: 2003)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 967 (Div. 2) (ID: 2001)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 169 (Rated for Div. 2) (ID: 2004)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 966 (Div. 3) (ID: 2000)\n", + "📥 Extrayendo datos para el concurso: EPIC Institute of Technology Round August 2024 (Div. 1 + Div. 2) (ID: 2002)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 965 (Div. 2) (ID: 1998)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 964 (Div. 4) (ID: 1999)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 963 (Div. 2) (ID: 1993)\n", + "📥 Extrayendo datos para el concurso: Educational Codeforces Round 168 (Rated for Div. 2) (ID: 1997)\n", + "📥 Extrayendo datos para el concurso: Pinely Round 4 (Div. 1 + Div. 2) (ID: 1991)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 962 (Div. 3) (ID: 1996)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 961 (Div. 2) (ID: 1995)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 960 (Div. 2) (ID: 1990)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 959 sponsored by NEAR (Div. 1 + Div. 2) (ID: 1994)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 958 (Div. 2) (ID: 1988)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 957 (Div. 3) (ID: 1992)\n", + "📥 Extrayendo datos para el concurso: Codeforces Round 956 (Div. 2) and ByteRace 2024 (ID: 1983)\n", + "✅ Extracción completa de todos los concursos.\n" + ] + } + ], + "source": [ + "#Parte 2: Extracción de Datos por Concurso\n", + "import time\n", + "\n", + "# Definimos funciones para cada endpoint\n", + "\n", + "# 1. Obtener standings y problemas\n", + "def get_standings(contest_id):\n", + " url = f\"https://codeforces.com/api/contest.standings?contestId={contest_id}&from=1&count=5000\"\n", + " res = requests.get(url)\n", + " data = res.json()\n", + " if data['status'] == 'OK':\n", + " return data['result']\n", + " return None\n", + "\n", + "# 2. Obtener submissions\n", + "def get_submissions(contest_id):\n", + " url = f\"https://codeforces.com/api/contest.status?contestId={contest_id}\"\n", + " res = requests.get(url)\n", + " data = res.json()\n", + " if data['status'] == 'OK':\n", + " return data['result']\n", + " return None\n", + "\n", + "# 3. Obtener cambios de rating\n", + "def get_rating_changes(contest_id):\n", + " url = f\"https://codeforces.com/api/contest.ratingChanges?contestId={contest_id}\"\n", + " res = requests.get(url)\n", + " data = res.json()\n", + " if data['status'] == 'OK':\n", + " return data['result']\n", + " return None\n", + "\n", + "# 4. Obtener usuarios calificados (solo una vez)\n", + "def get_rated_users():\n", + " url = \"https://codeforces.com/api/user.ratedList?activeOnly=false\"\n", + " res = requests.get(url)\n", + " data = res.json()\n", + " if data['status'] == 'OK':\n", + " return data['result']\n", + " return None\n", + "\n", + "# Creamos un diccionario para almacenar toda la información\n", + "contest_details = {}\n", + "\n", + "# Iteramos sobre los concursos filtrados anteriormente\n", + "for _, row in df_contests_filtered.iterrows():\n", + " contest_id = row['id']\n", + " print(f\"📥 Extrayendo datos para el concurso: {row['name']} (ID: {contest_id})\")\n", + "\n", + " contest_details[contest_id] = {\n", + " 'name': row['name'],\n", + " 'start_time': row['startTime'],\n", + " 'standings': get_standings(contest_id),\n", + " 'submissions': get_submissions(contest_id),\n", + " 'rating_changes': get_rating_changes(contest_id)\n", + " }\n", + " \n", + " # Esperamos 1 segundo entre llamadas para no sobrecargar la API\n", + " time.sleep(1)\n", + "\n", + "# Obtenemos la lista completa de usuarios calificados (solo una vez)\n", + "rated_users = get_rated_users()\n", + "\n", + "print(\"✅ Extracción completa de todos los concursos.\")" + ] + }, + { + "cell_type": "markdown", + "id": "a7e95826-262b-4586-bbce-ed4aeb0f43b2", + "metadata": {}, + "source": [ + "Link para la carpeta con los archivos csv descargados:\n", + "https://drive.google.com/drive/folders/1NzMFkL1a1KvoV67B9lratY2uCsLblTyV?usp=sharing" + ] + }, + { + "cell_type": "markdown", + "id": "ab80da29-b19a-4c2f-8038-5b67ce4abe32", + "metadata": {}, + "source": [ + "#Código para guardar los archivos .csv por concurso\n", + "import os\n", + "\n", + "# Creamos una carpeta para almacenar los CSVs\n", + "base_folder = \"codeforces_data\"\n", + "os.makedirs(base_folder, exist_ok=True)\n", + "\n", + "for contest_id, data in contest_details.items():\n", + " folder_name = os.path.join(base_folder, f\"contest_{contest_id}\")\n", + " os.makedirs(folder_name, exist_ok=True)\n", + "\n", + " # Guardamos standings (solo rows, no problems)\n", + " if data['standings'] and 'rows' in data['standings']:\n", + " df_standings = pd.json_normalize(data['standings']['rows'])\n", + " df_standings.to_csv(os.path.join(folder_name, \"standings.csv\"), index=False)\n", + "\n", + " # Guardamos submissions\n", + " if data['submissions']:\n", + " df_submissions = pd.json_normalize(data['submissions'])\n", + " df_submissions.to_csv(os.path.join(folder_name, \"submissions.csv\"), index=False)\n", + "\n", + " # Guardamos cambios de rating\n", + " if data['rating_changes']:\n", + " df_rating = pd.DataFrame(data['rating_changes'])\n", + " df_rating.to_csv(os.path.join(folder_name, \"rating_changes.csv\"), index=False)\n", + "\n", + "# También exportamos la lista de usuarios calificados\n", + "if rated_users:\n", + " df_users = pd.DataFrame(rated_users)\n", + " df_users.to_csv(os.path.join(base_folder, \"rated_users.csv\"), index=False)\n", + "\n", + "print(\"✅ Archivos CSV guardados con éxito.\")" + ] + }, + { + "cell_type": "markdown", + "id": "7176043e-b79e-41ab-9761-e7b466904b97", + "metadata": {}, + "source": [ + "## Parte 3: Descripción del Dataset\n", + "## 📄 Descripción del Dataset\n", + "\n", + "### 🔗 Endpoints de la API utilizados:\n", + "\n", + "- `contest.list`: Lista de todos los concursos públicos en Codeforces.\n", + "- `contest.standings`: Información sobre los problemas de un concurso y la clasificación de los usuarios.\n", + "- `contest.status`: Todas las submissions de un concurso.\n", + "- `contest.ratingChanges`: Cambios de rating de los usuarios después del concurso.\n", + "- `user.ratedList`: Lista de todos los usuarios con rating en Codeforces.\n", + "\n", + "### 🧱 Estructura del dataset\n", + "\n", + "Para cada concurso se extrajeron tres tablas:\n", + "\n", + "1. **Standings (`standings.csv`)**\n", + " - `party.members[0].handle`: Usuario.\n", + " - `problemResults`: Lista con información sobre cada problema (puntos, tiempo, etc.).\n", + " - `rank`, `points`, `successfulHackCount`, etc.\n", + "\n", + "2. **Submissions (`submissions.csv`)**\n", + " - `id`: ID de la submission.\n", + " - `creationTimeSeconds`: Fecha y hora de envío (en timestamp).\n", + " - `relativeTimeSeconds`: Tiempo desde el inicio del concurso.\n", + " - `verdict`: Resultado de la solución (OK, Wrong Answer, etc.).\n", + " - `programmingLanguage`: Lenguaje usado.\n", + " - `problem.index` y `problem.rating`: Información del problema resuelto.\n", + "\n", + "3. **Rating Changes (`rating_changes.csv`)**\n", + " - `handle`: Usuario.\n", + " - `oldRating`, `newRating`: Puntos antes y después del concurso.\n", + " - `rank`: Posición en el concurso.\n", + "\n", + "4. **Usuarios (`rated_users.csv`)**\n", + " - `handle`: Nombre del usuario.\n", + " - `country`, `city`, `rating`, `maxRating`, etc.\n", + "\n", + "### 📌 Variables clave para el análisis posterior\n", + "\n", + "- `finished_n`: Si el usuario resolvió el problema `n`.\n", + "- `n_language`: Lenguaje usado para resolver el problema `n`.\n", + "- `relative_time_n`: Tiempo desde el inicio del concurso hasta la solución del problema `n`.\n", + "- `time_to_answer_n`: Diferencia de tiempo entre problemas resueltos.\n", + "- `rating_n`: Dificultad del problema.\n", + "- `rating_achieved`: Suma de los ratings de los problemas resueltos por el usuario.\n", + "- `contest_name`, `contest_start_time`: Contexto del concurso.\n", + "- `country`, `city`, `rating`, `max_rating`: Información del perfil del usuario." + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "c4d47475-dd97-46e4-bc23-15efa52f7cf9", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "100%|██████████| 57/57 [02:19<00:00, 2.45s/it]\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "✅ Dataset final con 264595 filas y 64 columnas.\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
author_handlecontest_idcontest_namecontest_start_timecountrycityratingmax_ratingrating_achievedrating_1...rating_10finished_10relative_time_1010_languagetime_to_answer_10rating_11finished_11relative_time_1111_languagetime_to_answer_11
0jiangly2053Good Bye 2024: 2025 is NEAR1735396500ChinaChongqing3710.04039.022900800...3500.0True2.147484e+09C++23 (GCC 14-64, msys2)2.147479e+09NaNNaNNaNNaNNaN
1ecnerwala2053Good Bye 2024: 2025 is NEAR1735396500United StatesCupertino3627.03668.015900800...3500.0FalseNaNNoneNaNNaNNaNNaNNaNNaN
2Benq2053Good Bye 2024: 2025 is NEAR1735396500United StatesPrinceton3539.03833.022900800...3500.0True2.147484e+09C++23 (GCC 14-64, msys2)2.147479e+09NaNNaNNaNNaNNaN
3Egor2053Good Bye 2024: 2025 is NEAR1735396500GermanyAugsburg2937.03235.016000800...3500.0FalseNaNNoneNaNNaNNaNNaNNaNNaN
4Radewoosh2053Good Bye 2024: 2025 is NEAR1735396500PolandWarsaw3463.03759.019400800...3500.0FalseNaNNoneNaNNaNNaNNaNNaNNaN
\n", + "

5 rows × 64 columns

\n", + "
" + ], + "text/plain": [ + " author_handle contest_id contest_name contest_start_time \\\n", + "0 jiangly 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "1 ecnerwala 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "2 Benq 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "3 Egor 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "4 Radewoosh 2053 Good Bye 2024: 2025 is NEAR 1735396500 \n", + "\n", + " country city rating max_rating rating_achieved rating_1 \\\n", + "0 China Chongqing 3710.0 4039.0 22900 800 \n", + "1 United States Cupertino 3627.0 3668.0 15900 800 \n", + "2 United States Princeton 3539.0 3833.0 22900 800 \n", + "3 Germany Augsburg 2937.0 3235.0 16000 800 \n", + "4 Poland Warsaw 3463.0 3759.0 19400 800 \n", + "\n", + " ... rating_10 finished_10 relative_time_10 10_language \\\n", + "0 ... 3500.0 True 2.147484e+09 C++23 (GCC 14-64, msys2) \n", + "1 ... 3500.0 False NaN None \n", + "2 ... 3500.0 True 2.147484e+09 C++23 (GCC 14-64, msys2) \n", + "3 ... 3500.0 False NaN None \n", + "4 ... 3500.0 False NaN None \n", + "\n", + " time_to_answer_10 rating_11 finished_11 relative_time_11 11_language \\\n", + "0 2.147479e+09 NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN NaN \n", + "2 2.147479e+09 NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN NaN \n", + "\n", + " time_to_answer_11 \n", + "0 NaN \n", + "1 NaN \n", + "2 NaN \n", + "3 NaN \n", + "4 NaN \n", + "\n", + "[5 rows x 64 columns]" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Parte 4: Código para limpieza y creación de variables\n", + "from collections import defaultdict\n", + "from tqdm import tqdm\n", + "import pandas as pd\n", + "\n", + "# Crear diccionario para acceder fácilmente a los datos de cada usuario\n", + "# Esto evita tener que buscar a cada usuario en la lista de rated_users una y otra vez\n", + "users_dict = {user['handle']: user for user in rated_users}\n", + "\n", + "# Estructura para almacenar todo el dataset limpio\n", + "final_data = []\n", + "\n", + "# Recorremos cada concurso\n", + "for contest_id, data in tqdm(contest_details.items()):\n", + " contest_name = data['name']\n", + " contest_start = data['standings']['contest']['startTimeSeconds']\n", + " problems = data['standings']['problems']\n", + " \n", + " # Crear diccionario de problemas (para acceder por problem.index)\n", + " problem_info = {p['index']: p for p in problems}\n", + " \n", + " # Creamos un mapeo de handle -> cambios de rating\n", + " ratings = {r['handle']: r for r in data.get('rating_changes', [])}\n", + " \n", + " # Agrupar submissions por usuario y problema\n", + " submissions_by_user = defaultdict(lambda: defaultdict(list))\n", + " for sub in data['submissions']:\n", + " if 'author' in sub and 'members' in sub['author']:\n", + " handle = sub['author']['members'][0]['handle']\n", + " problem_index = sub['problem']['index']\n", + " submissions_by_user[handle][problem_index].append(sub)\n", + "\n", + " # Procesamos cada fila del standings (un usuario)\n", + " for row in data['standings']['rows']:\n", + " handle = row['party']['members'][0]['handle']\n", + " user_data = {\n", + " 'author_handle': handle,\n", + " 'contest_id': contest_id,\n", + " 'contest_name': contest_name,\n", + " 'contest_start_time': contest_start,\n", + " }\n", + "\n", + " # Añadir país, ciudad, rating actual y máximo (si tenemos)\n", + " if handle in users_dict:\n", + " user = users_dict[handle]\n", + " user_data.update({\n", + " 'country': user.get('country'),\n", + " 'city': user.get('city'),\n", + " 'rating': user.get('rating'),\n", + " 'max_rating': user.get('maxRating'),\n", + " })\n", + "\n", + " # Añadir rating_achieved\n", + " rating_change = ratings.get(handle)\n", + " if rating_change:\n", + " user_data['rating_achieved'] = rating_change['newRating']\n", + " else:\n", + " user_data['rating_achieved'] = None\n", + "\n", + " # Variables por problema\n", + " total_rating = 0\n", + " prev_time = 0\n", + " for i, prob in enumerate(problems, 1):\n", + " p_index = prob['index']\n", + " p_rating = prob.get('rating')\n", + " user_data[f'rating_{i}'] = p_rating\n", + "\n", + " # Revisamos si el usuario envió un \"OK\" para este problema\n", + " subs = submissions_by_user[handle].get(p_index, [])\n", + " solved = False\n", + " min_time = None\n", + " lang = None\n", + " for sub in subs:\n", + " if sub.get('verdict') == 'OK':\n", + " solved = True\n", + " if min_time is None or sub['relativeTimeSeconds'] < min_time:\n", + " min_time = sub['relativeTimeSeconds']\n", + " lang = sub.get('programmingLanguage')\n", + " user_data[f'finished_{i}'] = solved\n", + " user_data[f'relative_time_{i}'] = min_time\n", + " user_data[f'{i}_language'] = lang\n", + "\n", + " # Sumar rating logrado\n", + " if solved and p_rating:\n", + " total_rating += p_rating\n", + "\n", + " # Calcular tiempo entre respuestas (si hay min_time)\n", + " if min_time is not None:\n", + " user_data[f'time_to_answer_{i}'] = min_time - prev_time\n", + " prev_time = min_time\n", + " else:\n", + " user_data[f'time_to_answer_{i}'] = None\n", + "\n", + " user_data['rating_achieved'] = total_rating\n", + " final_data.append(user_data)\n", + "\n", + "# Convertimos a DataFrame\n", + "df_final = pd.DataFrame(final_data)\n", + "\n", + "print(f\"✅ Dataset final con {df_final.shape[0]} filas y {df_final.shape[1]} columnas.\")\n", + "df_final.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "9668f163-bb6b-4d6c-8588-073e0f55debe", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Fabrizio\\AppData\\Local\\Temp\\ipykernel_30260\\767654638.py:20: FutureWarning: \n", + "\n", + "Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `y` variable to `hue` and set `legend=False` for the same effect.\n", + "\n", + " sns.barplot(x=top_countries.values, y=top_countries.index, palette='viridis')\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Fabrizio\\AppData\\Local\\Temp\\ipykernel_30260\\767654638.py:39: FutureWarning: \n", + "\n", + "Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `y` variable to `hue` and set `legend=False` for the same effect.\n", + "\n", + " sns.barplot(x=language_counts.values, y=language_counts.index, palette='coolwarm')\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "#Parte 5: Análisis exploratorio de datos (EDA) con visualizaciones\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "\n", + "# Estilo general para los gráficos\n", + "sns.set(style='whitegrid')\n", + "plt.rcParams['figure.figsize'] = (10, 6)\n", + "\n", + "# --- 1. Distribución del rating de usuarios\n", + "plt.figure()\n", + "sns.histplot(df_final['rating'].dropna(), bins=30, kde=True)\n", + "plt.title('Distribución del rating de los usuarios')\n", + "plt.xlabel('Rating')\n", + "plt.ylabel('Frecuencia')\n", + "plt.show()\n", + "\n", + "# --- 2. Top 10 países con más participantes\n", + "plt.figure()\n", + "top_countries = df_final['country'].value_counts().head(10)\n", + "sns.barplot(x=top_countries.values, y=top_countries.index, palette='viridis')\n", + "plt.title('Top 10 países con más participantes')\n", + "plt.xlabel('Cantidad de usuarios')\n", + "plt.ylabel('País')\n", + "plt.show()\n", + "\n", + "# --- 3. Relación entre problemas resueltos y rating alcanzado\n", + "df_final['problems_solved'] = df_final[[col for col in df_final.columns if col.startswith('finished_')]].sum(axis=1)\n", + "\n", + "plt.figure()\n", + "sns.scatterplot(data=df_final, x='problems_solved', y='rating_achieved', alpha=0.5)\n", + "plt.title('Relación entre problemas resueltos y rating alcanzado')\n", + "plt.xlabel('Problemas resueltos')\n", + "plt.ylabel('Rating alcanzado (suma de ratings)')\n", + "plt.show()\n", + "\n", + "# --- 4. Lenguajes de programación más usados (en el primer problema)\n", + "plt.figure()\n", + "language_counts = df_final['1_language'].value_counts().head(10)\n", + "sns.barplot(x=language_counts.values, y=language_counts.index, palette='coolwarm')\n", + "plt.title('Lenguajes más usados en el primer problema')\n", + "plt.xlabel('Cantidad de envíos')\n", + "plt.ylabel('Lenguaje')\n", + "plt.show()\n", + "\n", + "# --- 5. Tiempo promedio para resolver el primer problema\n", + "plt.figure()\n", + "sns.histplot(df_final['time_to_answer_1'].dropna() / 60, bins=30, kde=True) # en minutos\n", + "plt.title('Tiempo promedio para resolver el primer problema (en minutos)')\n", + "plt.xlabel('Minutos')\n", + "plt.ylabel('Frecuencia')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3260500c-85f4-4b8a-ae16-22080f9d5bbf", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [conda env:Tarea1]", + "language": "python", + "name": "conda-env-Tarea1-py" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.11" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/homework/hw2/259359_hw2_2025_1/requirements.txt b/homework/hw2/259359_hw2_2025_1/requirements.txt new file mode 100644 index 000000000..0172a010d --- /dev/null +++ b/homework/hw2/259359_hw2_2025_1/requirements.txt @@ -0,0 +1,10 @@ +beautifulsoup4==4.12 +html5lib==1.1 +ipykernel==6.29 +ipywidgets==8.1 +jupyter==1.1 +lxml==5.3 +openpyxl==3.1 +pandas==2.2 +selenium==4.28 +tqdm==4.67 \ No newline at end of file diff --git a/homework/hw2/259359_hw2_2025_1/valid_contests.csv b/homework/hw2/259359_hw2_2025_1/valid_contests.csv new file mode 100644 index 000000000..e2899d205 --- /dev/null +++ b/homework/hw2/259359_hw2_2025_1/valid_contests.csv @@ -0,0 +1,58 @@ +id,name,start_time,phase +2053,Good Bye 2024: 2025 is NEAR,2024-12-28 14:35:00,FINISHED +2043,Educational Codeforces Round 173 (Rated for Div. 2),2024-12-24 14:35:00,FINISHED +2051,Codeforces Round 995 (Div. 3),2024-12-22 14:35:00,FINISHED +2049,Codeforces Round 994 (Div. 2),2024-12-20 14:35:00,FINISHED +2048,Codeforces Global Round 28,2024-12-19 14:35:00,FINISHED +2044,Codeforces Round 993 (Div. 4),2024-12-15 14:35:00,FINISHED +2040,Codeforces Round 992 (Div. 2),2024-12-08 14:35:00,FINISHED +2050,Codeforces Round 991 (Div. 3),2024-12-05 14:35:00,FINISHED +2046,Codeforces Round 990 (Div. 1),2024-12-03 06:25:00,FINISHED +2047,Codeforces Round 990 (Div. 2),2024-12-03 06:25:00,FINISHED +2042,Educational Codeforces Round 172 (Rated for Div. 2),2024-12-02 14:35:00,FINISHED +2034,"Rayan Programming Contest 2024 - Selection (Codeforces Round 989, Div. 1 + Div. 2)",2024-11-30 14:35:00,FINISHED +2039,"CodeTON Round 9 (Div. 1 + Div. 2, Rated, Prizes!)",2024-11-23 14:35:00,FINISHED +2037,Codeforces Round 988 (Div. 3),2024-11-17 14:35:00,FINISHED +2031,Codeforces Round 987 (Div. 2),2024-11-15 12:35:00,FINISHED +2028,Codeforces Round 986 (Div. 2),2024-11-10 15:35:00,FINISHED +2029,Refact.ai Match 1 (Codeforces Round 985),2024-11-09 14:35:00,FINISHED +2036,Codeforces Round 984 (Div. 3),2024-11-02 14:35:00,FINISHED +2032,Codeforces Round 983 (Div. 2),2024-11-01 14:35:00,FINISHED +2026,Educational Codeforces Round 171 (Rated for Div. 2),2024-10-28 14:35:00,FINISHED +2035,Codeforces Global Round 27,2024-10-27 14:35:00,FINISHED +2027,Codeforces Round 982 (Div. 2),2024-10-26 14:35:00,FINISHED +2033,Codeforces Round 981 (Div. 3),2024-10-24 14:35:00,FINISHED +2023,Codeforces Round 980 (Div. 1),2024-10-20 09:05:00,FINISHED +2024,Codeforces Round 980 (Div. 2),2024-10-20 09:05:00,FINISHED +2030,Codeforces Round 979 (Div. 2),2024-10-19 14:05:00,FINISHED +2025,Educational Codeforces Round 170 (Rated for Div. 2),2024-10-14 14:35:00,FINISHED +2022,Codeforces Round 978 (Div. 2),2024-10-13 19:35:00,FINISHED +2021,"Codeforces Round 977 (Div. 2, based on COMPFEST 16 - Final Round)",2024-10-06 06:05:00,FINISHED +2020,Codeforces Round 976 (Div. 2) and Divide By Zero 9.0,2024-09-29 15:35:00,FINISHED +2018,Codeforces Round 975 (Div. 1),2024-09-27 13:35:00,FINISHED +2019,Codeforces Round 975 (Div. 2),2024-09-27 13:35:00,FINISHED +2014,Codeforces Round 974 (Div. 3),2024-09-21 14:45:00,FINISHED +2013,Codeforces Round 973 (Div. 2),2024-09-20 14:35:00,FINISHED +2005,Codeforces Round 972 (Div. 2),2024-09-14 14:35:00,FINISHED +2009,Codeforces Round 971 (Div. 4),2024-09-03 14:35:00,FINISHED +2008,Codeforces Round 970 (Div. 3),2024-09-01 14:35:00,FINISHED +2006,Codeforces Round 969 (Div. 1),2024-08-30 14:35:00,FINISHED +2007,Codeforces Round 969 (Div. 2),2024-08-30 14:35:00,FINISHED +2010,Testing Round 19 (Div. 3),2024-08-28 20:35:00,FINISHED +2003,Codeforces Round 968 (Div. 2),2024-08-25 14:35:00,FINISHED +2001,Codeforces Round 967 (Div. 2),2024-08-20 14:35:00,FINISHED +2004,Educational Codeforces Round 169 (Rated for Div. 2),2024-08-15 14:35:00,FINISHED +2000,Codeforces Round 966 (Div. 3),2024-08-13 14:40:00,FINISHED +2002,EPIC Institute of Technology Round August 2024 (Div. 1 + Div. 2),2024-08-11 14:35:00,FINISHED +1998,Codeforces Round 965 (Div. 2),2024-08-10 14:35:00,FINISHED +1999,Codeforces Round 964 (Div. 4),2024-08-06 14:35:00,FINISHED +1993,Codeforces Round 963 (Div. 2),2024-08-04 14:35:00,FINISHED +1997,Educational Codeforces Round 168 (Rated for Div. 2),2024-07-30 14:35:00,FINISHED +1991,Pinely Round 4 (Div. 1 + Div. 2),2024-07-28 14:35:00,FINISHED +1996,Codeforces Round 962 (Div. 3),2024-07-26 14:35:00,FINISHED +1995,Codeforces Round 961 (Div. 2),2024-07-23 14:35:00,FINISHED +1990,Codeforces Round 960 (Div. 2),2024-07-20 14:35:00,FINISHED +1994,Codeforces Round 959 sponsored by NEAR (Div. 1 + Div. 2),2024-07-18 14:35:00,FINISHED +1988,Codeforces Round 958 (Div. 2),2024-07-15 14:35:00,FINISHED +1992,Codeforces Round 957 (Div. 3),2024-07-11 14:35:00,FINISHED +1983,Codeforces Round 956 (Div. 2) and ByteRace 2024,2024-07-07 14:35:00,FINISHED