| import streamlit as st
|
| import pickle
|
| import numpy as np
|
| import re
|
| from gensim.models import Word2Vec
|
| from nltk.corpus import stopwords
|
| import nltk
|
| nltk.download('stopwords')
|
|
|
|
|
|
|
|
|
| class Word2VecVectorizer:
|
| def __init__(self, model):
|
| self.model = model
|
| self.size = model.vector_size
|
|
|
| def fit(self, X, y=None):
|
| return self
|
|
|
| def transform(self, X):
|
| vectors = []
|
| for text in X:
|
| tokens = text.split()
|
| word_vecs = []
|
| for w in tokens:
|
| if w in self.model.wv:
|
| vec = self.model.wv[w]
|
|
|
| vec = vec / np.linalg.norm(vec)
|
| word_vecs.append(vec)
|
| if word_vecs:
|
| vectors.append(np.mean(word_vecs, axis=0))
|
| else:
|
| vectors.append(np.zeros(self.size))
|
| return np.array(vectors)
|
|
|
|
|
|
|
|
|
| st.set_page_config(page_title="🎯 Word2Vec Sentiment Classifier")
|
|
|
| st.title("🎯 Live Sentiment Classifier (Word2Vec + Logistic Regression)")
|
|
|
|
|
|
|
| stop_words = set(stopwords.words('english'))
|
|
|
|
|
|
|
|
|
| with open("text_classification_word2vec.pkl", "rb") as f:
|
| pipeline = pickle.load(f)
|
|
|
|
|
|
|
|
|
| user_input = st.text_area("**Enter a sentence or YouTube comment to analyze:**")
|
|
|
|
|
|
|
|
|
| if st.button("Predict Sentiment"):
|
| if user_input.strip():
|
| prediction = pipeline.predict([user_input])[0]
|
|
|
| st.markdown(f"## ✅ Prediction: `{prediction.capitalize()}`")
|
|
|
| if prediction.lower() == "positive":
|
| st.success("😊 Positive Sentiment")
|
| elif prediction.lower() == "negative":
|
| st.error("😠 Negative Sentiment")
|
| else:
|
| st.info("😐 Neutral Sentiment")
|
| else:
|
| st.warning("⚠️ Please enter some text to analyze.") |
