Computer Prices Analysis Application

A comprehensive Streamlit application for analyzing computer prices dataset from Kaggle.

Features

1. About Page (0.2 points)

• Project description with formatting
• Two illustrative images with sources
• Sample data table preview
• Quick statistics dashboard

2. Data Visualization (0.2 + 0.1 points)

• Interactive charts for all dataset columns
• Categorical data analysis with pie and bar charts
• Numeric distributions with histograms and box plots
• Correlation heatmap and scatter plots
• Uses tabs and columns for layout

3. Time Series Analysis (0.1 + 0.1 points)

• Release dynamics by year
• Flexible date range filtering (start/end can be empty)
• Brand-wise release trends
• Code display for visualization logic

4. Q&A Form (0.3 points)

• 3 ready-made questions with buttons
• Brand selection with radio buttons
• Price range slider
• Text input for model search
• Number input for year filtering

5. Manufacturer Map (0.1 points)

• Extraction of manufacturers from dataset
• Global geographic map showing headquarters
• Interactive visualization with hover data
• Code display for manufacturer extraction

6. Price Prediction (0.4 points)

• Random Forest model trained on dataset
• Interactive form with dropdowns and sliders
• Real-time price predictions
• Model saved to file for reuse

7. AI Chat (0.4 + 0.1 points)

• Text input for questions
• Chat history display
• Clear history button
• Rule-based responses about dataset statistics

Setup Instructions

1. Install Dependencies

pip install -r requirements.txt

2. Download Dataset

Download the dataset from Kaggle: https://www.kaggle.com/datasets/paperxd/all-computer-prices

Place the CSV file in the project directory and name it all_computer_prices.csv

3. Run the Application

streamlit run app.py

The application will open in your default browser at http://localhost:8501

Project Structure

test_app/
├── app.py                    # Main Streamlit application
├── requirements.txt          # Python dependencies
├── README.md                # This file
├── all_computer_prices.csv  # Dataset (download separately)
└── price_model.pkl          # Trained model (generated automatically)

Usage

1. Navigation: Use the sidebar to switch between different pages
2. Data Loading: The dataset is loaded automatically when you start the app
3. Visualizations: All charts are interactive - hover, zoom, and pan
4. Predictions: The model trains automatically on first use and saves to file
5. Chat: Ask questions about the dataset in natural language

Technical Details

• Framework: Streamlit
• Visualization: Plotly Express
• ML Model: Random Forest Regressor (scikit-learn)
• Data Processing: Pandas, NumPy

Requirements Met

• ✅ Sidebar navigation with 7 pages
• ✅ About page with text, images, and data preview
• ✅ Comprehensive visualizations using columns and tabs
• ✅ Time series with flexible date filtering
• ✅ Q&A form with 3 buttons + radio + slider + 2 inputs
• ✅ Manufacturer map with code display
• ✅ Price prediction with trained model and interactive form
• ✅ AI chat with history and clear functionality

Total Points: 2.0 / 2.0 + bonus features

Notes

• The AI chat uses rule-based responses (no external API required)
• The price prediction model trains automatically on first run
• All visualizations adapt to the actual dataset columns
• The application is fully responsive and works with different screen sizes