README.md

---
license: mit
language:
- en
metrics:
- accuracy
library_name: sklearn
pipeline_tag: text-classification
tags:
- code
---


## Model Training

The sentiment analysis model is trained using a Support Vector Machine (SVM) classifier with a linear kernel. The cleaned text data is transformed into a bag-of-words representation using the CountVectorizer. The trained model is saved as `Sentiment_classifier_model.joblib`, and the corresponding TF-IDF vectorizer is saved as `vectorizer_model.joblib`.






- 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")
)

# 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: ")

# 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:
  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)