How harshavardhannayaka20072007-png/movie-success-rate-prediction works
This repository is a notebook-based movie-success analysis and prediction project. Its documented workflow prepares movie data, explores and visualizes financial relationships, predicts worldwide revenue, and classifies movies against a megahit threshold while comparing approaches. The notebook and CSVs are the only runtime artifacts shown in the tree; source excerpts were unavailable, so links reflect documented activity rather than inspected code-level calls.
Main entry points: Top_Movies_Cleaned_Data.csv Cleaned Movie Data · Untitled.ipynb Revenue Regression · Top Movies Data.csv Original Movie Data
Components 10
Data Preparation
- Original Movie Data
Top Movies Data.csv - Clean Data
Untitled.ipynb - Cleaned Movie Data
Top_Movies_Cleaned_Data.csv
Exploration
- Explore Relationships
Untitled.ipynb - Financial Visualizations
Untitled.ipynb
Prediction
- Revenue Regression
Untitled.ipynb - Megahit Classification
Untitled.ipynb - Model Comparison
Untitled.ipynb - Movie Predictions
Untitled.ipynb
Other components
- Analyst
Connections 11
- Analyst → Clean Data: runs notebook
- Original Movie Data → Clean Data: input data
- Clean Data → Cleaned Movie Data: prepares data
- Cleaned Movie Data → Explore Relationships: explores data
- Explore Relationships → Financial Visualizations: visualizes relationships
- Cleaned Movie Data → Revenue Regression: predicts revenue
- Cleaned Movie Data → Megahit Classification: classifies success
- Revenue Regression → Model Comparison: compared with
- Megahit Classification → Model Comparison: compared with
- Revenue Regression → Movie Predictions: estimates revenue
- Megahit Classification → Movie Predictions: classifies threshold