Create app.py

app.py

@@ -0,0 +1,131 @@
+import pickle
+import re
+import string
+import contractions
+import gradio as gr
+import nltk
+
+from bs4 import BeautifulSoup
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+
+# --------------------------------------------------
+# NLTK Downloads
+# --------------------------------------------------
+nltk.download('stopwords', quiet=True)
+nltk.download('punkt', quiet=True)
+nltk.download('punkt_tab', quiet=True)
+
+# --------------------------------------------------
+# Load Model and Tokenizer
+# --------------------------------------------------
+MODEL_PATH = "/content/drive/MyDrive/BiLSTM/bilstm_sentiment_model.keras"
+TOKENIZER_PATH = "/content/drive/MyDrive/BiLSTM/BiLSTM_tokenizer.pkl"
+
+loaded_model = load_model(MODEL_PATH)
+
+with open(TOKENIZER_PATH, "rb") as f:
+    loaded_tokenizer = pickle.load(f)
+
+print("✅ Model and Tokenizer loaded successfully")
+
+# --------------------------------------------------
+# Constants
+# --------------------------------------------------
+MAX_LEN = 200
+STOP_WORDS = set(stopwords.words("english"))
+
+# --------------------------------------------------
+# Text Preprocessing
+# --------------------------------------------------
+def preprocess_text(text: str) -> str:
+
+    # Remove HTML
+    text = BeautifulSoup(text, "html.parser").get_text()
+
+    # Remove URLs
+    text = re.sub(r"http\S+|www\.\S+", "", text)
+
+    # Normalize special characters
+    text = text.replace("\u2019", "'").replace("\u2018", "'")
+    text = text.replace("\u201c", '"').replace("\u201d", '"')
+    text = text.replace("\u2013", "-").replace("\u2014", "-")
+    text = text.encode("ascii", errors="ignore").decode("ascii")
+
+    # Expand contractions
+    text = contractions.fix(text)
+
+    # Lowercase
+    text = text.lower()
+
+    # Remove punctuation
+    text = text.translate(str.maketrans("", "", string.punctuation))
+
+    # Remove numbers
+    text = re.sub(r"\b\d+\b", "", text)
+
+    # Remove extra spaces
+    text = re.sub(r"\s+", " ", text).strip()
+
+    # Tokenize and remove stopwords
+    tokens = word_tokenize(text)
+    tokens = [word for word in tokens if word not in STOP_WORDS]
+
+    return " ".join(tokens)
+
+# --------------------------------------------------
+# Prediction Function
+# --------------------------------------------------
+def predict_sentiment(review_text):
+
+    clean_text = preprocess_text(review_text)
+
+    seq = loaded_tokenizer.texts_to_sequences([clean_text])
+
+    padded = pad_sequences(
+        seq,
+        maxlen=MAX_LEN,
+        padding="post",
+        truncating="post"
+    )
+
+    score = float(loaded_model.predict(padded, verbose=0)[0][0])
+
+    if score >= 0.5:
+        sentiment = "Positive 😊"
+        confidence = score * 100
+    else:
+        sentiment = "Negative 😞"
+        confidence = (1 - score) * 100
+
+    return (
+        clean_text,
+        sentiment,
+        f"{confidence:.2f}%",
+        round(score, 4)
+    )
+
+# --------------------------------------------------
+# Gradio UI
+# --------------------------------------------------
+app = gr.Interface(
+    fn=predict_sentiment,
+    inputs=gr.Textbox(
+        lines=5,
+        placeholder="Enter a movie review...",
+        label="Movie Review"
+    ),
+    outputs=[
+        gr.Textbox(label="Cleaned Text"),
+        gr.Textbox(label="Predicted Sentiment"),
+        gr.Textbox(label="Confidence"),
+        gr.Number(label="Raw Score")
+    ],
+    title="🎬 BiLSTM Movie Review Sentiment Analyzer",
+    description="Enter a movie review and the trained BiLSTM model will predict whether the sentiment is positive or negative."
+)
+
+app.launch()