Movie_Details
تفاصيل العمل
? Movie Revenue Predictor
A machine learning application that predicts movie revenue based on various features like budget, popularity, runtime, and more. Built with Streamlit and trained on movie dataset analysis.
? Features
Revenue Prediction: Predict movie revenue using trained machine learning models
Interactive Web Interface: User-friendly Streamlit application
Data Analysis: Explore movie dataset statistics and visualizations
Model Information: Detailed information about the trained models and their performance
? Model Performance
Based on the analysis in movie_predict.ipynb:
Model Train R² Test R²
Random Forest 0.8581 0.8165
Gradient Boosting 0.8929 0.8362
Linear Regression (Polynomial) 0.8162 0.8020
?️ Installation & Setup
Prerequisites
Python 3.8 or higher
pip package manager
1. Clone the Repository
git clone <repository-url>
cd movie-revenue-predictor
2. Install Dependencies
pip install -r requirements.txt
3. Prepare Model Files
Ensure you have the following model files in your project directory:
ValueClassifier - Trained Random Forest model
encode - Categorical encoder
scaler - Feature scaler
outlier_bounds - Outlier detection bounds
These files are generated when you run the movie_predict.ipynb notebook.
4. Prepare Data Files
Ensure you have the following CSV files:
movie_details.csv - Main movie dataset
companies.csv - Company information
countries.csv - Country information
genres.csv - Genre information
langs.csv - Language information
? Running the Application
Start the Streamlit App
streamlit run deploymen.py
The application will open in your default web browser at http://localhost:8501
? Application Features
? Home Page
Input form for movie details
Real-time revenue prediction
ROI calculation
Formatted output (B/M for billions/millions)
? Data Analysis Page
Dataset statistics
Sample data display
Generated visualizations
Interactive data exploration
? Model Info Page
Model details and parameters
Feature information
Preprocessing steps
Performance metrics