Update app.py

app.py

@@ -1,56 +1,42 @@
 import gradio as gr
 import pandas as pd
-from transformers import TabularTransformerForSequenceClassification, TabularTransformerConfig
-from transformers import Trainer, TrainingArguments
-from datasets import Dataset
-import torch
+from pytorch_tabular import TabularModel
+from pytorch_tabular.config import DataConfig, ModelConfig, TrainerConfig
 
 # Sample Data
 data = {
     'feature1': [0.5, 0.3, 0.7, 0.2],
     'feature2': [1, 0, 1, 1],
     'feature3': [0.6, 0.1, 0.8, 0.4],
-    'label': [0, 1, 0, 1]  # Binary classification
+    'target': [0, 1, 0, 1]  # Binary classification target
 }
 df = pd.DataFrame(data)
-dataset = Dataset.from_pandas(df)
 
-# Configure the Model
-config = TabularTransformerConfig(
-    num_labels=2,  # Binary classification
-    numerical_features=['feature1', 'feature2', 'feature3']
+# Configure pytorch_tabular
+data_config = DataConfig(
+    target=["target"],
+    continuous_cols=["feature1", "feature2", "feature3"]
 )
-model = TabularTransformerForSequenceClassification(config)
-
-# Define Training Arguments
-training_args = TrainingArguments(
-    output_dir="./results",
-    evaluation_strategy="epoch",
-    learning_rate=2e-5,
-    per_device_train_batch_size=4,
-    num_train_epochs=3
-)
-
-# Define Trainer
-trainer = Trainer(
-    model=model,
-    args=training_args,
-    train_dataset=dataset,
-    eval_dataset=dataset
+model_config = ModelConfig(task="classification", num_classes=2)
+trainer_config = TrainerConfig(max_epochs=10)
+
+# Initialize and train model
+tabular_model = TabularModel(
+    data_config=data_config,
+    model_config=model_config,
+    trainer_config=trainer_config
 )
-
-# Train the model
-trainer.train()
+tabular_model.fit(df)
 
 # Define Inference Function
 def classify(feature1, feature2, feature3):
-    input_data = {'feature1': feature1, 'feature2': feature2, 'feature3': feature3}
-    input_df = pd.DataFrame([input_data])
-    test_dataset = Dataset.from_pandas(input_df)
-    with torch.no_grad():
-        logits = model(**test_dataset[:][0]).logits
-        prediction = torch.argmax(logits, dim=1).item()
-        return "Class 1" if prediction == 1 else "Class 0"
+    input_data = pd.DataFrame({
+        "feature1": [feature1],
+        "feature2": [feature2],
+        "feature3": [feature3]
+    })
+    prediction = tabular_model.predict(input_data)["prediction"].iloc[0]
+    return "Class 1" if prediction == 1 else "Class 0"
 
 # Gradio Interface
 iface = gr.Interface(
@@ -61,8 +47,9 @@ iface = gr.Interface(
         gr.inputs.Slider(0, 1, step=0.1, label="Feature 3")
     ],
     outputs="text",
-    title="Tabular Classification with Hugging Face",
+    title="Tabular Classification with PyTorch Tabular",
     description="Classify entries based on tabular data"
 )
 
 iface.launch()
+