Update README.md

README.md

@@ -19,24 +19,46 @@ The sentiment analysis model is trained using a Support Vector Machine (SVM) cla
 
 from huggingface_hub import hf_hub_download
 import joblib
+from sklearn.preprocessing import LabelEncoder
+
+# Download the sentiment analysis model
 model = joblib.load(
-	hf_hub_download("DineshKumar1329/Sentiment_Analysis", "sklearn_model.joblib")
+    hf_hub_download("DineshKumar1329/Sentiment_Analysis", "sklearn_model.joblib")
 )
-tfidf_vectorizer = joblib.load('/content/vectorizer_model.joblib')  # Replace with your actual filename
+
+# Load the TF-IDF vectorizer
+tfidf_vectorizer = joblib.load('/content/vectorizer_model.joblib')  # Replace with your path
+
+def clean_text(text):
+  # Implement your text cleaning logic here (e.g., lowercase, remove punctuation, etc.)
+  # This example simply lowercases the text
+  return text.lower()
+
+def predict_sentiment(user_input):
+  """Predicts sentiment for a given user input."""
+  cleaned_text = clean_text(user_input)
+  input_matrix = tfidf_vectorizer.transform([cleaned_text])
+  prediction = model.predict(input_matrix)[0]
+
+  if isinstance(model.classes_, LabelEncoder):
+    prediction = model.classes_.inverse_transform([prediction])[0]
+
+  return prediction
+
+# Get user input
 user_input = input("Enter a sentence: ")
-cleaned_input = clean_text(user_input)
-input_matrix = tfidf_vectorizer.transform([cleaned_input])
-prediction = model.predict(input_matrix)[0]
-print(f"Predicted Sentiment: {prediction}")
-df_result = pd.DataFrame({'User_Input': [user_input], 'Predicted_Sentiment': [prediction]})
-excel_filename = '/content/output_predictions.xlsx'  # Replace with your desired filename
-try:
-    # Load existing predictions from the Excel file
-    df_existing = pd.read_excel(excel_filename)
 
-    # Append the new predictions to the existing DataFrame
-    df_combined = pd.concat([df_existing, df_result], ignore_index=True)
+# Predict sentiment
+predicted_sentiment = predict_sentiment(user_input)
+
+print(f"Predicted Sentiment: {predicted_sentiment}")
+
+# Optional: Save predictions (modify paths as needed)
+try:
+  df_existing = pd.read_excel('/content/output_predictions.xlsx')
 except FileNotFoundError:
-    # If the file doesn't exist, create a new DataFrame
-    df_combined = df_result
-df_combined.to_excel(excel_filename, index=False)
+  df_existing = pd.DataFrame()
+
+new_prediction = pd.DataFrame({'User_Input': [user_input], 'Predicted_Sentiment': [predicted_sentiment]})
+df_combined = pd.concat([df_existing, new_prediction], ignore_index=True)
+df_combined.to_excel('/content/output_predictions.xlsx', index=False)