AI-CodeMate: Titanic Survival Prediction & Financial Chatbot

This project is part of an internship task series involving:

• Exploratory Data Analysis (EDA) on the Titanic dataset.
• Model creation to predict survival using logistic regression.
• A basic rule-based chatbot to answer predefined financial queries.

---

📌 Task Summary

✅ Task 1: EDA on Titanic Dataset

Performed exploratory analysis using pandas, matplotlib, and seaborn to uncover survival patterns.

✅ Task 2: Logistic Regression Model

Built and evaluated a logistic regression model to predict passenger survival based on selected features.

✅ Task 3: Model Deployment (Optional)

Saved the trained model (titanic_logistic_model.pkl) using joblib for later use.

✅ Task 4: Financial Chatbot (Rule-Based)

Created a simple Python chatbot that can answer predefined financial questions like:

• "What is the total revenue?"
• "How has net income changed over the last year?"
• "What is the profit margin?"

This was implemented as a basic script to simulate interaction and demonstrate logic handling with conditional statements.

---

📁 Files

• titanic_task2.ipynb: Notebook containing all tasks including the chatbot implementation.
• titanic.csv: Titanic dataset.
• titanic_logistic_model.pkl: Saved model from Task 2.
• README.md: This file.

---

🚀 Key Learnings

• Exploratory data analysis using pandas and matplotlib.
• Model creation and evaluation using scikit-learn.
• Basics of saving models and creating simple chatbots with Python.

Task 5: Decision Trees & Random Forests

• Objective: Implement classification models using Decision Trees and Random Forests.

• Dataset: Heart Disease Dataset (or Titanic dataset)

• Steps:

  1. Loaded and preprocessed the dataset.
  2. Trained a Decision Tree and visualized it.
  3. Controlled overfitting using max depth and pruning.
  4. Trained a Random Forest classifier.
  5. Compared performance using confusion matrix.
  6. Evaluated with cross-validation.
  7. Displayed feature importances.

• Results:

  • Accuracy: XX% (based on your model)
  • Confusion Matrix used for visual evaluation

🎮 Python Game Project

A simple game developed using Python and Pygame, showcasing fundamental game development concepts.

🚀 Features

• Basic game loop implementation
• Player controls and interactions
• Collision detection
• Score tracking

🛠️ Installation

1. Clone the repository:

   git clone https://github.com/yourusername/your-repo-name.git
   cd your-repo-name