import re from pathlib import Path import joblib import streamlit as st # ------------------------- # Page config # ------------------------- st.set_page_config( page_title='Movie Review Sentiment (LinearSVC + TF-IDF)', page_icon='🎬', layout='centered' ) st.title('🎬 Movie Review Sentiment Analysis') st.write( 'Classify Rotten Tomatoes review phrases into 5 sentiment classes using a trained ' 'LinearSVC + TF-IDF pipeline.' ) # ------------------------- # Paths (HF friendly) # ------------------------- BASE_DIR = Path(__file__).resolve().parent MODEL_PATH = BASE_DIR / 'sentiment_pipeline.pkl' LABELS_PATH = BASE_DIR / 'label_names.pkl' # ------------------------- # Helpers # ------------------------- def clean_text(text: str) -> str: if not isinstance(text, str): return '' text = text.lower() text = re.sub(r'<[^>]+>', ' ', text) text = re.sub(r'\d+', ' ', text) text = re.sub(r'[\n\r]', ' ', text) text = re.sub(r"[^a-z\s']", ' ', text) text = re.sub(r'\s+', ' ', text) return text.strip() @st.cache_resource def load_model(): if not MODEL_PATH.exists(): raise FileNotFoundError( f'Model not found: {MODEL_PATH.name}. Put it in the repo root (same folder as app.py).' ) return joblib.load(MODEL_PATH) @st.cache_resource def load_labels(): if LABELS_PATH.exists(): return joblib.load(LABELS_PATH) return { 0: 'negative', 1: 'somewhat negative', 2: 'neutral', 3: 'somewhat positive', 4: 'positive' } model = load_model() label_names = load_labels() # ------------------------- # UI # ------------------------- st.subheader('Enter a phrase') default_text = 'An intermittently pleasing but mostly routine effort.' user_text = st.text_area('Movie review phrase', value=default_text, height=120) col1, col2 = st.columns([1, 1]) with col1: run = st.button('Predict', type='primary') with col2: st.write('') if run: cleaned = clean_text(user_text) if cleaned.strip() == '': st.warning('Please enter some text (not empty).') else: pred = int(model.predict([cleaned])[0]) label = label_names.get(pred, str(pred)) st.success(f'Prediction: **{pred} — {label}**') with st.expander('Show cleaned text'): st.code(cleaned) st.markdown('---') st.caption( 'Model: TF-IDF (1–2 grams) + LinearSVC | Labels: 0=negative, 1=somewhat negative, ' '2=neutral, 3=somewhat positive, 4=positive' )