How harrish8248/sentiment-analysis-nlp works
This repository classifies movie reviews as positive or negative through two execution paths: an interactive Streamlit app and a CLI training script. Both train a pipeline over the NLTK movie-review corpus using text cleaning, TF-IDF features, and Logistic Regression. The app accepts typed or templated reviews and presents predictions and metrics; the CLI also evaluates the model and generates diagnostic plots. Source excerpts show the CLI pipeline in detail, while the app excerpt omits parts of its training and prediction logic; documented behavior supplements those relationships.
Main entry points: sentiment_analysis.py CLI training pipeline · app.py Cached app training · outputs Diagnostic plots
Components 15
Web experience
- Review app
sentiment-analysis-nlp/app.py - Review input
sentiment-analysis-nlp/app.py - Prediction view
sentiment-analysis-nlp/app.py - Chart dashboard
sentiment-analysis-nlp/app.py
Sentiment modeling
- NLTK reviews
- Cached app training
sentiment-analysis-nlp/app.py - Text cleaning
sentiment-analysis-nlp/sentiment_analysis.py - TF-IDF features
sentiment-analysis-nlp/sentiment_analysis.py - Logistic classifier
sentiment-analysis-nlp/sentiment_analysis.py
CLI diagnostics
- Diagnostic plots
sentiment-analysis-nlp/outputs - CLI training pipeline
sentiment-analysis-nlp/sentiment_analysis.py - Model evaluation
sentiment-analysis-nlp/sentiment_analysis.py - Plot generation
sentiment-analysis-nlp/sentiment_analysis.py - Sample predictions
sentiment-analysis-nlp/sentiment_analysis.py
Other components
- Reviewer
Connections 18
- Reviewer → Review app: uses
- Review app → Cached app training: loads model
sentiment-analysis-nlp/app.py - Reviewer → Review input: enters review
- Review input → Prediction view: requests analysis
sentiment-analysis-nlp/app.py - Cached app training → NLTK reviews: loads reviews
- Cached app training → Text cleaning: cleans text
sentiment-analysis-nlp/app.py - Cached app training → TF-IDF features: fits features
sentiment-analysis-nlp/app.py - Cached app training → Logistic classifier: trains model
sentiment-analysis-nlp/app.py - Prediction view → Chart dashboard: also displays
sentiment-analysis-nlp/app.py - Chart dashboard → Diagnostic plots: reads plots
sentiment-analysis-nlp/app.py - CLI training pipeline → NLTK reviews: loads reviews
sentiment-analysis-nlp/sentiment_analysis.py - CLI training pipeline → Text cleaning: cleans corpus
sentiment-analysis-nlp/sentiment_analysis.py - CLI training pipeline → TF-IDF features: fits features
sentiment-analysis-nlp/sentiment_analysis.py - CLI training pipeline → Logistic classifier: trains model
sentiment-analysis-nlp/sentiment_analysis.py - CLI training pipeline → Model evaluation: evaluates model
sentiment-analysis-nlp/sentiment_analysis.py - CLI training pipeline → Plot generation: generates plots
sentiment-analysis-nlp/sentiment_analysis.py - Plot generation → Diagnostic plots: writes plots
sentiment-analysis-nlp/sentiment_analysis.py - CLI training pipeline → Sample predictions: runs examples
sentiment-analysis-nlp/sentiment_analysis.py