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.
Usage :
from huggingface_hub import hf_hub_download import joblib from sklearn.preprocessing import LabelEncoder
model = joblib.load( hf_hub_download("DineshKumar1329/Sentiment_Analysis", "sklearn_model.joblib") )
tfidf_vectorizer = joblib.load('/content/vectorizer_model.joblib') # Replace with your path
def clean_text(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
user_input = input("Enter a sentence: ")
predicted_sentiment = predict_sentiment(user_input)
print(f"Predicted Sentiment: {predicted_sentiment}")
from transformers import AutoTokenizer, AutoModelForSequenceClassification from sklearn.preprocessing import LabelEncoder import joblib
def load_model_and_tokenizer(model_name="DineshKumar1329/Sentiment_Analysis"): """Loads the sentiment analysis model and tokenizer from Hugging Face Hub."""
# Replace with desired model name if using a different model
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
return model, tokenizer
def clean_text(text): """Converts the input text to lowercase for case-insensitive processing.""" return text.lower()
def predict_sentiment(user_input, model, tokenizer): """Predicts sentiment for a given user input."""
cleaned_text = clean_text(user_input)
encoded_text = tokenizer(cleaned_text, return_tensors="pt")
with torch.no_grad():
outputs = model(**encoded_text)
logits = outputs.logits
prediction = torch.argmax(logits, dim=-1).item()
if isinstance(model.config.label_list, LabelEncoder):
prediction = model.config.label_list.inverse_transform([prediction])[0]
return prediction
if name == "main": model, tokenizer = load_model_and_tokenizer()
user_input = input("Enter a sentence: ")
predicted_sentiment = predict_sentiment(user_input, model, tokenizer)
print(f"Predicted Sentiment: {predicted_sentiment}")