Update app.py

app.py

@@ -1,32 +1,34 @@
-import gradio as gr
-import numpy as np
+from tensorflow.keras.models import model_from_json
 import tensorflow as tf
 import joblib
 from tensorflow.keras.preprocessing.sequence import pad_sequences
+import gradio as gr
 
-# Load the trained model
-model = tf.keras.models.load_model("sentiment_model.h5")
+# Load model architecture
+with open("model_architecture.json", "r") as f:
+    model = model_from_json(f.read())
 
-# Load the tokenizer
+# Load weights
+model.load_weights("model_weights.weights.h5")
+
+# Load tokenizer
 tokenizer = joblib.load("tokenizer.joblib")
+
 max_len = 40
 
-# Inference function
 def predict_sentiment(text):
     seq = tokenizer.texts_to_sequences([text])
     padded = pad_sequences(seq, maxlen=max_len, padding='post')
     pred = model.predict(padded)[0][0]
     label = "Positive" if pred >= 0.5 else "Negative"
-    confidence = float(pred) if label == "Positive" else 1 - float(pred)
-    return {label: round(confidence, 4)}
+    return {label: float(pred) if label == "Positive" else 1 - float(pred)}
 
-# Gradio UI
 demo = gr.Interface(
     fn=predict_sentiment,
-    inputs=gr.Textbox(lines=2, placeholder="Enter a tweet here..."),
+    inputs=gr.Textbox(lines=2, placeholder="Enter a tweet..."),
     outputs=gr.Label(num_top_classes=2),
-    title="Tweet Sentiment Analyzer (BiLSTM + Attention)",
-    description="This model was trained from scratch using LSTM + Attention to predict sentiment of tweets (Positive/Negative)."
+    title="Sentiment Analysis on Tweets",
+    description="Enter a tweet and get predicted sentiment (Positive/Negative) and confidence score."
 )
 
 demo.launch()