Update app.py

app.py

@@ -1,20 +1,40 @@
-import nltk
-
-from nltk.sentiment.vader import SentimentIntensityAnalyzer
 
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.metrics import classification_report, accuracy_score
 import gradio as gr
 
+import datasets
+
+df_true = pd.read_csv('training.1600000.processed.noemoticon.csv')
+
+
+
+df['polarity'] = df['polarity'].replace({0: 'negative', 2: 'neutral', 4: 'positive'})
+df = df[['text', 'polarity']]
+
+
+train_data, test_data = train_test_split(df, test_size=0.2, random_state=42)
+
+
+vectorizer = TfidfVectorizer(max_features=5000)
+X_train = vectorizer.fit_transform(train_data['text'])
+y_train = train_data['polarity']
+classifier = MultinomialNB()
+classifier.fit(X_train, y_train)
 
-nltk.download("vader_lexicon")
-sid = SentimentIntensityAnalyzer()
 
-def sentiment_analysis(text):
-    scores = sid.polarity_scores(text)
-    del scores["compound"]
-    return scores
+X_test = vectorizer.transform(test_data['text'])
+y_pred = classifier.predict(X_test)
+print("Accuracy:", accuracy_score(test_data['polarity'], y_pred))
+print("Classification Report:\n", classification_report(test_data['polarity'], y_pred))
 
-iface = gr.Interface(sentiment_analysis, "textbox", "label", interpretation="default")
 
-iface.test_launch()
-if __name__ == "__main__":
-    iface.launch()
+def predict_sentiment(text):
+    text_vectorized = vectorizer.transform([text])
+    prediction = classifier.predict(text_vectorized)[0]
+    return prediction
+iface = gr.Interface(fn=predict_sentiment, inputs="text", outputs="text")
+iface.launch()