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.
Model Usage :
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("DineshKumar1329/Sentiment_Analysis", "sklearn_model.joblib") )
only load pickle files from sources you trust
read more about it here https://skops.readthedocs.io/en/stable/persistence.html
Load the TF-IDF vectorizer used during training
tfidf_vectorizer = joblib.load('/content/vectorizer_model.joblib') # Replace with your actual filename
Take user input
user_input = input("Enter a sentence: ")
Clean the user input
cleaned_input = clean_text(user_input)
Transform the cleaned text data using the TF-IDF vectorizer
input_matrix = tfidf_vectorizer.transform([cleaned_input])
Make prediction
prediction = model.predict(input_matrix)[0]
Display the prediction
print(f"Predicted Sentiment: {prediction}")
Create a DataFrame with the results
df_result = pd.DataFrame({'User_Input': [user_input], 'Predicted_Sentiment': [prediction]})
Save the DataFrame to an Excel file (append if the file already exists)
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)
except FileNotFoundError: # If the file doesn't exist, create a new DataFrame df_combined = df_result
Save the combined DataFrame to the Excel file
df_combined.to_excel(excel_filename, index=False)