Create app.py

app.py

@@ -0,0 +1,103 @@
+import pandas as pd
+import tensorflow as tf
+from sklearn.model_selection import train_test_split
+from transformers import T5Tokenizer, TFT5ForConditionalGeneration
+import gradio as gr
+
+# ========== STEP 1: Load and Prepare Dataset ==========
+# NOTE: On Hugging Face Spaces, upload your CSV file in the repo and update path here:
+df = pd.read_csv("/gmustafa413/ABSA_Dataset")  # Make sure this CSV is uploaded in your repo root
+
+# Convert 'aspectTerms' string to list and create input/output pairs
+def format_example(row):
+    input_text = row["raw_text"]
+    try:
+        aspect_terms = eval(row["aspectTerms"])
+    except:
+        aspect_terms = []
+
+    if not aspect_terms or aspect_terms == '[]':
+        output_text = "noaspectterm:none"
+    else:
+        output_text = ", ".join([f"{d['term']}:{d['polarity']}" for d in aspect_terms if d['term']])
+    return input_text, output_text
+
+df["input_text"], df["target_text"] = zip(*df.apply(format_example, axis=1))
+
+# Split data
+train_texts, val_texts, train_labels, val_labels = train_test_split(
+    df["input_text"], df["target_text"], test_size=0.1, random_state=42
+)
+
+# ========== STEP 2: Tokenization ==========
+tokenizer = T5Tokenizer.from_pretrained("t5-base")
+max_input_length = 128
+max_target_length = 64
+
+def tokenize_data(inputs, targets):
+    inputs_enc = tokenizer(
+        list(inputs), padding="max_length", truncation=True,
+        max_length=max_input_length, return_tensors="tf"
+    )
+    targets_enc = tokenizer(
+        list(targets), padding="max_length", truncation=True,
+        max_length=max_target_length, return_tensors="tf"
+    )
+    return inputs_enc.input_ids, targets_enc.input_ids
+
+train_inputs, train_labels = tokenize_data(train_texts, train_labels)
+val_inputs, val_labels = tokenize_data(val_texts, val_labels)
+
+# ========== STEP 3: Create TensorFlow Datasets ==========
+BATCH_SIZE = 8
+
+train_dataset = tf.data.Dataset.from_tensor_slices(({"input_ids": train_inputs}, train_labels))
+val_dataset = tf.data.Dataset.from_tensor_slices(({"input_ids": val_inputs}, val_labels))
+
+train_dataset = train_dataset.shuffle(1000).batch(BATCH_SIZE)
+val_dataset = val_dataset.batch(BATCH_SIZE)
+
+# ========== STEP 4: Model Training ==========
+model = TFT5ForConditionalGeneration.from_pretrained("t5-base")
+optimizer = tf.keras.optimizers.Adam(learning_rate=3e-5)
+model.compile(optimizer=optimizer)
+
+print("🔧 Training started...")
+model.fit(train_dataset, validation_data=val_dataset, epochs=3)
+print("✅ Training complete!")
+
+# Save model and tokenizer (optional here if you want to save locally)
+# model.save_pretrained("t5_absa_tf_model")
+# tokenizer.save_pretrained("t5_absa_tf_model")
+
+# ========== STEP 5: Gradio Interface ==========
+# Using trained model & tokenizer directly from memory
+
+def preprocess_input(text):
+    instruction = """Definition: The output will be the aspects (both implicit and explicit) and the aspect's sentiment polarity. In cases where there are no aspects the output should be noaspectterm:none.
+Positive example:
+input: With the great variety on the menu , I eat here often and never get bored.
+output: menu:positive
+Now complete the following example-
+input: """
+    return instruction + text + "\noutput:"
+
+def predict_aspects(text):
+    processed = preprocess_input(text)
+    inputs = tokenizer(processed, return_tensors="tf", truncation=True, padding=True)
+    outputs = model.generate(
+        input_ids=inputs["input_ids"], attention_mask=inputs["attention_mask"],
+        max_length=64
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+interface = gr.Interface(
+    fn=predict_aspects,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your review here..."),
+    outputs=gr.Textbox(label="Extracted aspect:sentiment pairs"),
+    title="Aspect-Based Sentiment Analysis (ABSA)",
+    description="Fine-tuned T5 model for extracting aspects and their sentiment from review text.",
+)
+
+if __name__ == "__main__":
+    interface.launch()