Create app.py

app.py

@@ -0,0 +1,80 @@
+from datasets import load_dataset
+from transformers import DistilBertTokenizer, DistilBertForSequenceClassification, Trainer, TrainingArguments
+import torch
+import numpy as np
+from sklearn.metrics import accuracy_score, f1_score
+
+# Step 2: Load dataset
+dataset = load_dataset("amazon_polarity")
+train_dataset = dataset["train"].shuffle(seed=42).select(range(10000))
+test_dataset = dataset["test"].shuffle(seed=42).select(range(2000))
+
+# Step 3: Tokenize dataset
+tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased")
+def tokenize_function(examples):
+    text = [title + " " + content for title, content in zip(examples["title"], examples["content"])]
+    return tokenizer(text, padding="max_length", truncation=True, max_length=512)
+tokenized_train = train_dataset.map(tokenize_function, batched=True)
+tokenized_test = test_dataset.map(tokenize_function, batched=True)
+tokenized_train = tokenized_train.remove_columns(["title", "content"])
+tokenized_test = tokenized_test.remove_columns(["title", "content"])
+tokenized_train.set_format("torch", columns=["input_ids", "attention_mask", "label"])
+tokenized_test.set_format("torch", columns=["input_ids", "attention_mask", "label"])
+
+# Step 4: Fine-tune model
+model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased", num_labels=2)
+def compute_metrics(pred):
+    labels = pred.label_ids
+    preds = pred.predictions.argmax(-1)
+    acc = accuracy_score(labels, preds)
+    f1 = f1_score(labels, preds, average="weighted")
+    return {"accuracy": acc, "f1": f1}
+training_args = TrainingArguments(
+    output_dir="./results",
+    num_train_epochs=3,
+    per_device_train_batch_size=16,
+    per_device_eval_batch_size=16,
+    warmup_steps=500,
+    weight_decay=0.01,
+    logging_dir="./logs",
+    logging_steps=10,
+    eval_strategy="epoch",
+    save_strategy="epoch",
+    load_best_model_at_end=True,
+)
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_train,
+    eval_dataset=tokenized_test,
+    compute_metrics=compute_metrics,
+)
+trainer.train()
+
+# Step 5: Evaluate and predict
+eval_results = trainer.evaluate()
+print("Evaluation results:", eval_results)
+model.save_pretrained("./fine_tuned_distilbert")
+tokenizer.save_pretrained("./fine_tuned_distilbert")
+def predict_sentiment(text):
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    inputs = {key: val.to(device) for key, val in inputs.items()}
+    model.to(device)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    logits = outputs.logits
+    predicted_class = torch.argmax(logits, dim=1).item()
+    return "Positive" if predicted_class == 1 else "Negative"
+example_reviews = [
+    "Great product! Fast shipping and works perfectly as described.",
+    "Terrible quality, broke after one use. Very disappointed.",
+    "The item is okay, not amazing but does the job for the price."
+]
+for review in example_reviews:
+    sentiment = predict_sentiment(review)
+    print(f"Review: {review}\nPredicted Sentiment: {sentiment}\n")
+
+# Create Gradio interface
+interface = gr.Interface(fn=predict_sentiment, inputs="text", outputs="text", title="Amazon Sentiment Analysis Demo")
+interface.launch()