Upload app.py

app.py

@@ -21,41 +21,22 @@ from datasets import load_dataset
 
 #Read data training data.
 
-x1 = load_dataset("mertkarabacak/NCDB-GBM", data_files="6m_data_train.csv", use_auth_token = HF_TOKEN)
+x1 = load_dataset("mertkarabacak/NCDB-GBM", data_files="6m_data_resampled.csv", use_auth_token = HF_TOKEN)
 x1 = pd.DataFrame(x1['train'])
 x1 = x1.iloc[:, 1:]
 
-x2 = load_dataset("mertkarabacak/NCDB-GBM", data_files="12m_data_train.csv", use_auth_token = HF_TOKEN)
+x2 = load_dataset("mertkarabacak/NCDB-GBM", data_files="12m_data_resampled.csv", use_auth_token = HF_TOKEN)
 x2 = pd.DataFrame(x2['train'])
 x2 = x2.iloc[:, 1:]
 
-x3 = load_dataset("mertkarabacak/NCDB-GBM", data_files="18m_data_train.csv", use_auth_token = HF_TOKEN)
+x3 = load_dataset("mertkarabacak/NCDB-GBM", data_files="18m_data_resampled.csv", use_auth_token = HF_TOKEN)
 x3 = pd.DataFrame(x3['train'])
 x3 = x3.iloc[:, 1:]
 
-x4 = load_dataset("mertkarabacak/NCDB-GBM", data_files="24m_data_train.csv", use_auth_token = HF_TOKEN)
+x4 = load_dataset("mertkarabacak/NCDB-GBM", data_files="24m_data_resampled.csv", use_auth_token = HF_TOKEN)
 x4 = pd.DataFrame(x4['train'])
 x4 = x4.iloc[:, 1:]
 
-#Read validation data.
-
-x1_valid = load_dataset("mertkarabacak/NCDB-GBM", data_files="6m_data_valid.csv", use_auth_token = HF_TOKEN)
-x1_valid = pd.DataFrame(x1_valid['train'])
-x1_valid = x1_valid.iloc[:, 1:]
-
-x2_valid = load_dataset("mertkarabacak/NCDB-GBM", data_files="12m_data_valid.csv", use_auth_token = HF_TOKEN)
-x2_valid = pd.DataFrame(x2_valid['train'])
-x2_valid = x2_valid.iloc[:, 1:]
-
-x3_valid = load_dataset("mertkarabacak/NCDB-GBM", data_files="18m_data_valid.csv", use_auth_token = HF_TOKEN)
-x3_valid = pd.DataFrame(x3_valid['train'])
-x3_valid = x3_valid.iloc[:, 1:]
-
-x4_valid = load_dataset("mertkarabacak/NCDB-GBM", data_files="24m_data_valid.csv", use_auth_token = HF_TOKEN)
-x4_valid = pd.DataFrame(x4_valid['train'])
-x4_valid = x4_valid.iloc[:, 1:]
-
-
 #Define feature names.
 f1_names = list(x1.columns)
 f1_names = [f1.replace('__', ' - ') for f1 in f1_names]
@@ -95,7 +76,7 @@ tabpfn = TabPFNClassifier(device='cuda', N_ensemble_configurations=1)
 y1_model = tabpfn
 y1_model = y1_model.fit(x1, y1, overwrite_warning=True)
 
-y1_calib_model = CalibratedClassifierCV(y1_model, method='sigmoid', cv='prefit')
+y1_calib_model = CalibratedClassifierCV(y1_model, method='isotonic', cv='prefit')
 y1_calib_model = y1_calib_model.fit(x1, y1)
 
 y1_explainer = shap.Explainer(y1_model.predict, x1)
@@ -107,7 +88,7 @@ tabpfn = TabPFNClassifier(device='cuda', N_ensemble_configurations=1)
 y2_model = tabpfn
 y2_model = y2_model.fit(x2, y2, overwrite_warning=True)
 
-y2_calib_model = CalibratedClassifierCV(y2_model, method='sigmoid', cv='prefit')
+y2_calib_model = CalibratedClassifierCV(y2_model, method='isotonic', cv='prefit')
 y2_calib_model = y2_calib_model.fit(x2, y2)
 
 y2_explainer = shap.Explainer(y2_model.predict, x2)
@@ -409,7 +390,7 @@ with gr.Blocks(title = "NCDB-Meningioma") as demo:
                     """
                     <center> <h2>6-Month Survival</h2> </center>
                     <br/>
-                    <center> This model uses the Random Forest algorithm.</center>
+                    <center> This model uses the TabPFN algorithm.</center>
                     <br/>
                     """
                     )
@@ -453,7 +434,7 @@ with gr.Blocks(title = "NCDB-Meningioma") as demo:
                     """
                     <center> <h2>12-Month Survival</h2> </center>
                     <br/>
-                    <center> This model uses the Random Forest algorithm.</center>
+                    <center> This model uses the TabPFN algorithm.</center>
                     <br/>
                     """
                     )