Upload predict.py with huggingface_hub

predict.py

@@ -0,0 +1,79 @@
+import torch
+import numpy as np
+import pandas as pd
+from model import CardiovascularRNN
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+
+class RiskPredictor:
+    def __init__(self, model_path='cardiovascular_rnn_model.pth', csv_path='cardiovascular_risk_dataset.csv'):
+        self.df = pd.read_csv(csv_path)
+        
+        # Determine feature names and order
+        self.feature_names = self.df.drop(['Patient_ID', 'risk_category'], axis=1).columns.tolist()
+        
+        self.le_risk = LabelEncoder()
+        self.le_risk.fit(self.df['risk_category'])
+        
+        self.le_smoking = LabelEncoder()
+        self.le_smoking.fit(self.df['smoking_status'])
+        
+        self.le_family = LabelEncoder()
+        self.le_family.fit(self.df['family_history_heart_disease'])
+        
+        self.scaler = StandardScaler()
+        df_proc = self.df.drop(['Patient_ID', 'risk_category'], axis=1)
+        df_proc['smoking_status'] = self.le_smoking.transform(df_proc['smoking_status'])
+        df_proc['family_history_heart_disease'] = self.le_family.transform(df_proc['family_history_heart_disease'])
+        self.scaler.fit(df_proc.values)
+        
+        self.input_size = 1
+        self.hidden_size = 64
+        self.num_layers = 2
+        self.num_classes = len(self.le_risk.classes_)
+        
+        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        self.model = CardiovascularRNN(self.input_size, self.hidden_size, self.num_layers, self.num_classes).to(self.device)
+        self.model.load_state_dict(torch.load(model_path, map_location=self.device))
+        self.model.eval()
+        print(f"Model initialized with features: {self.feature_names}")
+
+    def predict_single(self, data_dict):
+        # Convert dictionary to DataFrame with explicit column order
+        input_df = pd.DataFrame([data_dict])[self.feature_names]
+        
+        # Transform categorical
+        input_df['smoking_status'] = self.le_smoking.transform(input_df['smoking_status'])
+        input_df['family_history_heart_disease'] = self.le_family.transform(input_df['family_history_heart_disease'])
+        
+        # Scale
+        input_scaled = self.scaler.transform(input_df.values)
+        input_tensor = torch.FloatTensor(input_scaled).reshape(1, -1, 1).to(self.device)
+        
+        # Predict
+        with torch.no_grad():
+            output = self.model(input_tensor)
+            probs = torch.softmax(output, dim=1)
+            _, predicted = torch.max(output, 1)
+            predicted_label = self.le_risk.inverse_transform([predicted.item()])[0]
+            
+        print(f"Prediction: {predicted_label} | Probabilities: {probs.cpu().numpy()}")
+        return predicted_label
+
+def predict():
+    predictor = RiskPredictor()
+    print("Model loaded successfully.")
+
+    # Take a sample from the dataset for prediction
+    df = pd.read_csv('cardiovascular_risk_dataset.csv')
+    sample_row = df.drop(['Patient_ID', 'risk_category'], axis=1).iloc[0]
+    sample_dict = sample_row.to_dict()
+    true_label = df['risk_category'].iloc[0]
+    
+    predicted_label = predictor.predict_single(sample_dict)
+    
+    print(f"\nSample Data: {sample_dict}")
+    print(f"True Risk Category: {true_label}")
+    print(f"Predicted Risk Category: {predicted_label}")
+
+if __name__ == "__main__":
+    predict()