Create sentiment_analysis.py

sentiment_analysis.py

@@ -0,0 +1,47 @@
+import pandas as pd
+import nltk
+from nltk.sentiment import SentimentIntensityAnalyzer
+from textblob import TextBlob
+from transformers import pipeline
+
+class SentimentAnalyzer:
+    def __init__(self):
+        nltk.download('vader_lexicon')
+        self.sia = SentimentIntensityAnalyzer()
+        self.transformer_model = pipeline("sentiment-analysis")
+
+    def analyze(self, data, text_column):
+        # VADER Sentiment Analysis
+        data['vader_sentiment'] = data[text_column].apply(lambda x: self.sia.polarity_scores(x)['compound'])
+        
+        # TextBlob Sentiment Analysis
+        data['textblob_sentiment'] = data[text_column].apply(lambda x: TextBlob(x).sentiment.polarity)
+        
+        # Transformer-based Sentiment Analysis
+        transformer_results = self.transformer_model(data[text_column].tolist())
+        data['transformer_sentiment'] = [result['score'] if result['label'] == 'POSITIVE' else -result['score'] for result in transformer_results]
+        
+        # Aggregate sentiment
+        data['aggregate_sentiment'] = (data['vader_sentiment'] + data['textblob_sentiment'] + data['transformer_sentiment']) / 3
+        
+        return data
+
+    def get_sentiment_summary(self, data):
+        summary = {
+            'positive': (data['aggregate_sentiment'] > 0.05).sum(),
+            'neutral': ((data['aggregate_sentiment'] >= -0.05) & (data['aggregate_sentiment'] <= 0.05)).sum(),
+            'negative': (data['aggregate_sentiment'] < -0.05).sum()
+        }
+        return summary
+
+    def plot_sentiment_distribution(self, data):
+        import matplotlib.pyplot as plt
+        import seaborn as sns
+
+        fig, ax = plt.subplots(figsize=(10, 6))
+        sns.histplot(data['aggregate_sentiment'], kde=True, ax=ax)
+        ax.set_title('Distribution of Sentiment Scores')
+        ax.set_xlabel('Sentiment Score')
+        ax.set_ylabel('Frequency')
+        
+        return fig