Update app.py

app.py

@@ -1,6 +1,4 @@
-
 import gradio as gr
-
 import numpy as np
 import pandas as pd
 import re
@@ -8,6 +6,7 @@ from tensorflow.keras.models import Sequential
 from tensorflow.keras.layers import Dense
 from transformers import BertTokenizer, TFBertModel
 from sklearn.model_selection import train_test_split
+from sklearn.metrics import confusion_matrix, classification_report
 from nltk.corpus import stopwords
 import tensorflow as tf
 import nltk
@@ -45,7 +44,7 @@ X_train, X_test, y_train, y_test = train_test_split(movies_df['review'], movies_
 y_train = tf.convert_to_tensor(y_train.values, dtype=tf.float32)
 y_test = tf.convert_to_tensor(y_test.values, dtype=tf.float32)
 
-# Batch-wise BERT embeddings
+# Compute BERT embeddings
 def bert_embeddings_batch(texts, batch_size=32, max_length=64):
     embeddings = []
     for i in range(0, len(texts), batch_size):
@@ -81,11 +80,10 @@ classifier.fit(X_train_embeddings, y_train, epochs=5, batch_size=32, validation_
 test_loss, test_accuracy = classifier.evaluate(X_test_embeddings, y_test)
 print(f"Test Accuracy: {test_accuracy}")
 
-
 # Predictions and confusion matrix
 y_pred = (classifier.predict(X_test_embeddings) > 0.5).astype("int32")
-conf_matrix = confusion_matrix(y_test, y_pred)
-class_report = classification_report(y_test, y_pred)
+conf_matrix = confusion_matrix(y_test.numpy(), y_pred)
+class_report = classification_report(y_test.numpy(), y_pred)
 
 print("Confusion Matrix:")
 print(conf_matrix)
@@ -95,23 +93,41 @@ print(class_report)
 # Save the trained model to a file
 #classifier.save("movie_sentiment_model.h5")
 
+# Single input BERT embeddings
+def bert_embeddings(text, max_length=64):
+    inputs = tokenizer(
+        [text],
+        return_tensors="tf",
+        padding=True,
+        truncation=True,
+        max_length=max_length
+    )
+    outputs = bert_model(inputs['input_ids'], attention_mask=inputs['attention_mask'])
+    cls_embeddings = outputs.last_hidden_state[:, 0, :]
+    return cls_embeddings.numpy()
+
+# Define Gradio function
 def fn(test_review):
-    review=remove_tags(test_review)
-    review=remove_stop_wrods(review)
-    cls_embeddings = bert_embeddings([review])
-    #loaded_model = load_model("movie_sentiment_model.h5")
+    review = remove_tags(test_review)
+    review = remove_stop_words(review)
+    cls_embeddings = bert_embeddings(review)
     prediction = classifier.predict(cls_embeddings)
     return "Positive" if prediction[0] > 0.5 else "Negative"
-    
-description = "Give a review of a movie that you like(or hate, sarcasm intended XD) and the model will let you know just how much your review truely reflects your emotions. "
+
+# Gradio Interface
+description = "Give a review of a movie that you like (or hate, sarcasm intended XD) and the model will let you know just how much your review truly reflects your emotions."
 input_text = gr.Textbox(label="Enter Text")
 output_text = gr.Textbox(label="Output Text")
-here = gr.Interface(fn,
-                     inputs= input_text,
-                     outputs=output_text,
-                     title="Sentiment analysis of movie reviews",
-                     description=description,
-                     theme="peach",
-                     allow_flagging="auto",
-                     flagging_dir='flagging records')
-here.launch(inline=False)
+
+app = gr.Interface(
+    fn=fn,
+    inputs=input_text,
+    outputs=output_text,
+    title="Sentiment Analysis of Movie Reviews",
+    description=description,
+    allow_flagging="auto",
+    flagging_dir='flagging_records'
+)
+
+app.launch(inline=False)
+