Merge pull request MLEveryday#90 from madefu/master

Author: yyong119

.gitignore

@@ -102,3 +102,5 @@ venv.bak/
 
 # mypy
 .mypy_cache/
+/.idea
+/datasets/*.bak

Code/Day 3_Multiple_Linear_Regression.py

@@ -31,4 +31,4 @@
 
 # regression evaluation
 from sklearn.metrics import r2_score
-print(r2_score(Y_test,y_pred))
+print(r2_score(Y_test, y_pred))

Code/KafkaProducer.py

@@ -0,0 +1,13 @@
+#!/usr/bin/python
+
+from kafka import KafkaProducer
+
+kafkaHosts=["kafka01.paas.longfor.sit:9092"
+            ,"kafka02.paas.longfor.sit:9092"
+            ,"kafka03.paas.longfor.sit:9092"]
+
+producer = KafkaProducer(bootstrap_servers=kafkaHosts);
+
+for _ in range(20):
+    producer.send("testapplog_plm-prototype",b"Hello....")
+producer.flush();

Code/TestKafka.py

@@ -0,0 +1,24 @@
+#!/usr/bin/python
+
+from kafka import KafkaConsumer;
+
+
+kafkaHosts=["kafka01.paas.longfor.sit:9092"
+            ,"kafka02.paas.longfor.sit:9092"
+            ,"kafka03.paas.longfor.sit:9092"]
+
+'''
+earliest 
+当各分区下有已提交的offset时，从提交的offset开始消费；无提交的offset时，从头开始消费 
+latest 
+当各分区下有已提交的offset时，从提交的offset开始消费；无提交的offset时，消费新产生的该分区下的数据 
+none 
+topic各分区都存在已提交的offset时，从offset后开始消费；只要有一个分区不存在已提交的offset，则抛出异常
+'''
+consumer = KafkaConsumer(
+    bootstrap_servers=kafkaHosts,group_id='mdf_group',auto_offset_reset='latest');
+
+consumer.subscribe("testapplog_plm-prototype");
+
+for msg in consumer:
+    print(msg.value)

Code/my/Data_age_salary.csv

@@ -0,0 +1,11 @@
+Age,Salary
+44,72000
+27,48000
+30,54000
+38,61000
+40,78000
+35,58000
+35,52000
+48,79000
+50,83000
+37,67000

Code/my/LinerTest.py

@@ -0,0 +1,6 @@
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+
+dataset = pd.read_csv('Data_age_salary.csv');
+dataset.iloc[:1]

Other Docs/速查手册/2018年数据科学家报告.pdf

@@ -0,0 +1,64 @@
+# 14张速查表，带你玩转 Python 数据科学
+译自 DataCamp 的速查表，有兴趣的朋友可以在这里查看[英文原版](https://www.datacamp.com/community/data-science-cheatsheets)。
+
+欢迎扫描二维码关注我的 **呆鸟的Python数据分析** 公众号，虽然现在内容还比较少，但我会不断增加的。
+
+![呆鸟的Python数据分析](https://upload-images.jianshu.io/upload_images/3240514-6a4349fff3b8b019.jpg?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+一、[Python 基础系列](https://www.jianshu.com/p/4574d95755db)
+
+* [Python数据科学速查表 - Python 基础](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python数据科学速查表%20-%20Python%20基础.pdf)
+![Python数据科学速查表 - Python 基础](https://upload-images.jianshu.io/upload_images/3240514-a4268e27432411b0.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+* [Python数据科学速查表 - 导入数据](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python数据科学速查表%20-%20导入数据.pdf)
+![Python数据科学速查表 - 导入数据](https://upload-images.jianshu.io/upload_images/3240514-d2b38f138e127333.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+* [Python数据科学速查表 - Jupyter Notebook](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python%E6%95%B0%E6%8D%AE%E7%A7%91%E5%AD%A6%E9%80%9F%E6%9F%A5%E8%A1%A8%20-%20Jupyter%20Notebook.pdf)
+![Python数据科学速查表 - Jupyter Notebook](https://upload-images.jianshu.io/upload_images/3240514-111052b862105515.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+二、[数据处理系列（Numpy、Pandas 及 SciPy）](https://www.jianshu.com/p/8d51642dfa26)
+
+* [Python数据科学速查表 - Numpy 基础](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python数据科学速查表%20-%20Numpy%20基础.pdf)
+![Python数据科学速查表 - Numpy 基础](https://upload-images.jianshu.io/upload_images/3240514-811ca5b168b84a75.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+* [Python数据科学速查表 - Pandas 基础](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python数据科学速查表%20-%20Pandas%20基础.pdf)
+![Python数据科学速查表 - Pandas 基础](https://upload-images.jianshu.io/upload_images/3240514-0711ea1cb1d1fcee.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+* [Python数据科学速查表 -  Pandas 进阶](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python数据科学速查表%20-%20Pandas%20进阶.pdf)
+![Python数据科学速查表 -  Pandas 进阶](https://upload-images.jianshu.io/upload_images/3240514-475cfa9174303f60.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+*  [Python数据科学速查表 -  SciPy](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python%E6%95%B0%E6%8D%AE%E7%A7%91%E5%AD%A6%E9%80%9F%E6%9F%A5%E8%A1%A8%20-%20SciPy.pdf)
+![Python数据科学速查表 -  SciPy](https://upload-images.jianshu.io/upload_images/3240514-fc9fa2b69a820041.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+三、[可视化系列（Matplotlib、Bokeh、Seaborn）](https://www.jianshu.com/p/7e186d43d7f1)
+
+* [Python数据科学速查表 - Matplotlib](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python数据科学速查表%20-%20Matplotlib%20绘图.pdf)
+![Python数据科学速查表 - Matplotlib](https://upload-images.jianshu.io/upload_images/3240514-9c57bcf33113cf98.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+* [Python数据科学速查表 - Bokeh](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python数据科学速查表%20-%20Bokeh.pdf)
+![Python数据科学速查表 - Bokeh](https://upload-images.jianshu.io/upload_images/3240514-d87990f4a3f7f0ae.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+* [Python数据科学速查表 - Seaborn](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python%E6%95%B0%E6%8D%AE%E7%A7%91%E5%AD%A6%E9%80%9F%E6%9F%A5%E8%A1%A8%20-%20Seaborn.pdf)
+![Python数据科学速查表 - Seaborn](https://upload-images.jianshu.io/upload_images/3240514-1c2f56b96f841421.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+四、[机器学习系列（Keras、Scikit-learn）](https://www.jianshu.com/p/cba49ff5fc97)
+
+* [Python数据科学速查表 - Keras](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python数据科学速查表%20-%20Keras.pdf)
+![Python数据科学速查表 - Keras](https://upload-images.jianshu.io/upload_images/3240514-ea9657c97b5e0d19.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+* [Python数据科学速查表 - Scikit-learn](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python%E6%95%B0%E6%8D%AE%E7%A7%91%E5%AD%A6%E9%80%9F%E6%9F%A5%E8%A1%A8%20-%20Scikit-Learn.pdf)
+![Python数据科学速查表 - Scikit-learn](https://upload-images.jianshu.io/upload_images/3240514-b8cbecb3a9194b71.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+五、[PySpark系列（SQL与RDD）](https://www.jianshu.com/p/7dea578c56d8)
+
+* [Python数据科学速查表 - Spark SQL 基础](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python%E6%95%B0%E6%8D%AE%E7%A7%91%E5%AD%A6%E9%80%9F%E6%9F%A5%E8%A1%A8%20-%20Spark%20SQL%20%E5%9F%BA%E7%A1%80.pdf)
+![pyspark.png](https://upload-images.jianshu.io/upload_images/3240514-32909e63b67c0837.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+* [Python数据科学速查表 - Spark RDD 基础](https://github.com/jaystone776/python-data-science-cheatsheet/blob/master/Python%E6%95%B0%E6%8D%AE%E7%A7%91%E5%AD%A6%E9%80%9F%E6%9F%A5%E8%A1%A8%20-%20Spark%20RDD%20%E5%9F%BA%E7%A1%80.pdf)
+![RDD.png](https://upload-images.jianshu.io/upload_images/3240514-43308e4ca89d8699.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)
+
+如果喜欢本文，敬请关注我的简书专题 **[呆鸟的Python数据分析](https://www.jianshu.com/c/38980843c0f2)** 
+
+感谢**天善智能**的**Python爱好者社区**公众号一直以来对我的支持，这里也大力推荐，是我学习入门 Python 数据分析入门的引路者，欢迎关注！
+
+![Python爱好者社区](https://upload-images.jianshu.io/upload_images/3240514-29c87337342b0904.jpg?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)

Other Docs/速查手册/Python数据科学速查表 - Bokeh.pdf

@@ -24,3 +24,6 @@ Hours,Scores
 3.8,35
 6.9,76
 7.8,86
+2.1,93
+2.2,93
+2.5,93