Final: Enhanced app's loading times (#196)

Author: hoangsonww

MovieVerse-Middleware/machine-learning/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Son Nguyen Hoang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

MovieVerse-Middleware/machine-learning/README.md

@@ -21,29 +21,71 @@ The `Machine-Learning` directory contains Python scripts that leverage machine l
 
 This script uses machine learning models to classify movies into genres based on their descriptions, titles, and other metadata. It helps in categorizing movies accurately within the app database.
 
+To run the genre classifier, execute the following command:
+
+```bash
+python genre-classifier.py
+```
+
 ### Movie Recommendation (`movie-recommendation.py`)
 
 This script is responsible for generating movie recommendations for users based on their viewing history, preferences, and ratings. It uses collaborative filtering and content-based methods to provide personalized recommendations.
 
+To run, execute the following command:
+
+```bash
+python movie-recommendation.py
+```
+
 ### Movie Reviews Analysis (`movie-reviews.py`)
 
 This script processes and analyzes movie reviews, extracting insights and useful information. It might use natural language processing (NLP) techniques to understand user sentiments, key themes, and overall opinions about movies.
 
+To get started, you can run the following command:
+
+```bash
+python movie-reviews.py
+```
+
+Then, follow the instructions provided by the script to analyze movie reviews and extract valuable information.
+
 ### Plot Summarizer (`plot-summarizer.py`)
 
 `plot-summarizer.py` utilizes NLP and text summarization algorithms to create concise summaries of movie plots. This assists users in quickly grasping the essence of a movie without spoilers.
 
+To get started, you can run the following command:
+
+```bash
+python plot-summarizer.py
+```
+
+Then, follow the instructions by Streamlit to view the plot summarizer web application. For example, you may receive the following instructions:
+
+```
+Warning: to view this Streamlit app on a browser, run it with the following command:
+
+streamlit run /Users/davidnguyen/WebstormProjects/The-MovieVerse-Database/MovieVerse-Backend/machine-learning/plot-summarizer.py [ARGUMENTS]
+```
+
+In this case, simply copy and run the provided `streamlit run` command in your terminal to view the plot summarizer web application.
+
 ### Sentiment Analysis (`sentiment_analysis.py`)
 
 This script performs sentiment analysis on user reviews and comments. It determines the overall sentiment (positive, negative, neutral) expressed in the text, helping in gauging audience reception of movies.
 
+To run, simply execute the following command:
+
+```bash
+python sentiment_analysis.py
+```
+
 ## Using these Scripts
 
 To run these scripts:
 
 1. Ensure you have Python installed on your system.
 2. Install necessary libraries using pip: `pip install -r requirements.txt` (assuming a `requirements.txt` file is present).
-3. Execute each script as needed, e.g., `python genre-classifier.py`.
+3. Execute each script as needed, following the instructions above.
 
 ## Customization and Adaptation
 

MovieVerse-Middleware/machine-learning/genre_classifier.py

@@ -5,6 +5,7 @@
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import classification_report
 
+
 class GenreClassifier:
     def __init__(self):
         self.pipeline = Pipeline([
@@ -26,6 +27,7 @@ def predict_genre(self, description: str) -> str:
     def predict_genres(self, descriptions: List[str]) -> List[str]:
         return self.pipeline.predict(descriptions)
 
+
 # Example usage
 if __name__ == "__main__":
     # Example data

MovieVerse-Middleware/machine-learning/movie-recommendation.py

@@ -6,7 +6,8 @@
 
 # Load movie data
 movies_df = pd.read_csv('movies.csv', usecols=['movieId', 'title'], dtype={'movieId': 'int32', 'title': 'str'})
-ratings_df = pd.read_csv('ratings.csv', usecols=['userId', 'movieId', 'rating'], dtype={'userId': 'int32', 'movieId': 'int32', 'rating': 'float32'})
+ratings_df = pd.read_csv('ratings.csv', usecols=['userId', 'movieId', 'rating'],
+                         dtype={'userId': 'int32', 'movieId': 'int32', 'rating': 'float32'})
 
 # Preprocessing
 # Create a user-movie matrix
@@ -24,6 +25,7 @@
 all_user_predicted_ratings = np.dot(np.dot(U, sigma), Vt) + mean_user_rating.values.reshape(-1, 1)
 preds_df = pd.DataFrame(all_user_predicted_ratings, columns=user_movie_df.columns)
 
+
 # Recommend Movies
 def recommend_movies(predictions_df, userID, movies_df, original_ratings_df, num_recommendations=5):
     user_row_number = userID - 1
@@ -45,6 +47,7 @@ def recommend_movies(predictions_df, userID, movies_df, original_ratings_df, num
 
     return user_full, recommendations
 
+
 # Test the recommendation system for a user
 user_id = 1
 rated_movies, recommendations = recommend_movies(preds_df, user_id, movies_df, ratings_df, 10)

MovieVerse-Middleware/machine-learning/plot-summarizer.py

@@ -1,4 +1,3 @@
-import torch
 import logging
 from transformers import BartTokenizer, BartForConditionalGeneration
 import streamlit as st
@@ -7,6 +6,7 @@
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
+
 class MoviePlotSummarizer:
     def __init__(self, model_name='facebook/bart-large-cnn'):
         self.tokenizer = BartTokenizer.from_pretrained(model_name)
@@ -24,13 +24,16 @@ def summarize(self, plot_text, max_length=130, min_length=30, style='default'):
                 min_length //= 2
 
             # Tokenize and generate summary
-            inputs = self.tokenizer.encode("summarize: " + plot_text, return_tensors="pt", max_length=1024, truncation=True)
-            summary_ids = self.model.generate(inputs, max_length=max_length, min_length=min_length, length_penalty=2.0, num_beams=4, early_stopping=True)
+            inputs = self.tokenizer.encode("summarize: " + plot_text, return_tensors="pt", max_length=1024,
+                                           truncation=True)
+            summary_ids = self.model.generate(inputs, max_length=max_length, min_length=min_length, length_penalty=2.0,
+                                              num_beams=4, early_stopping=True)
             return self.tokenizer.decode(summary_ids[0], skip_special_tokens=True)
         except Exception as e:
             logger.error(f"Error in summarizing plot: {e}")
             return "Error in summarization process."
 
+
 # Streamlit UI
 def main():
     st.title("Movie Plot Summarizer")
@@ -49,17 +52,17 @@ def main():
 
     if st.button("About"):
         st.subheader("About")
-        st.write("This is a simple movie plot summarizer built using the HuggingFace Transformers library. It uses the BART model to generate the summaries.")
-        st.write("The model was trained on the CNN/Daily Mail dataset, which contains news articles and their summaries. The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
-        st.write("The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
-        st.write("The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
-        st.write("The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
-        st.write("The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
-        st.write("The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
-        st.write("The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
-        st.write("The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
-        st.write("The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
-        st.write("The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
+        st.write(
+            "This is a simple movie plot summarizer built using the HuggingFace Transformers library. It uses the "
+            "BART model to generate the summaries.")
+        st.write(
+            "The model was trained on the CNN/Daily Mail dataset, which contains news articles and their summaries. "
+            "The model was fine-tuned on the XSUM dataset, which contains summaries of BBC articles.")
+        st.write("You can adjust the length of the summary and the style of summarization (default, verbose, concise).")
+        st.write("The model may not always provide accurate summaries, especially for longer or complex plots.")
+        st.write("Feel free to experiment with different movie plots and summarization settings! Enjoy!")
+        st.write("Note: The model might take a few seconds to generate the summary, so please be patient.")
+
 
 if __name__ == "__main__":
     main()

MovieVerse-Middleware/machine-learning/sentiment_analysis.py

@@ -6,6 +6,7 @@
 # Ensure you have the necessary NLTK components
 nltk.download('vader_lexicon')
 
+
 class SentimentAnalyzer:
     def __init__(self):
         self.analyzer = SentimentIntensityAnalyzer()
@@ -54,19 +55,6 @@ def analyze_review(self, review: str) -> str:
         sentiment = self.predict_sentiment(review)
         return sentiment
 
-    def analyze_reviews(self, reviews: List[str]) -> pd.DataFrame:
-        results = {'Review': [], 'Sentiment': []}
-
-        for review in reviews:
-            sentiment = self.predict_sentiment(review)
-            results['Review'].append(review)
-            results['Sentiment'].append(sentiment)
-
-        return pd.DataFrame(results)
-
-    def analyze_review(self, review: str) -> str:
-        sentiment = self.predict_sentiment(review)
-        return sentiment
 
 if __name__ == "__main__":
     reviews = [

MovieVerse-Middleware/middleware.js

@@ -89,4 +89,4 @@ app.use(errorHandler);
 const PORT = process.env.PORT || 3000;
 app.listen(PORT, () => {
     console.log(`Server is running on port ${PORT}`);
-});
+});