Update app.py

app.py

@@ -9,34 +9,21 @@ import pickle
 with open('label_encoder.pkl', 'rb') as f:
     label_encoder = pickle.load(f)
 
-# Load the ColumnTransformer (ensure that you have this preprocessing object)
-with open('column_transformer.pkl', 'rb') as f:
-    ct = pickle.load(f)
-
-# Define the dropdown options based on data (assuming 'df' is your DataFrame)
-# You need to load 'df' or replace it with a dataset source.
-# Example:
-# df = pd.read_csv('your_data.csv')  # Adjust this line as necessary
-
-# Define dropdown values dynamically from your dataset
-# Example for 'Race' and 'Cyp2C9 genotypes'
-race_options = list(dict(df['Race (Reported)'].value_counts()).keys())
-age_options = list(dict(df['Age'].value_counts()).keys())
-cyp2c9_genotypes_options = list(dict(df['Cyp2C9 genotypes'].value_counts()).keys())
-vkorc1_genotypes_options = list(dict(df['VKORC1 genotype: -1639 G>A (3673); chr16:31015190; rs9923231; C/T'].value_counts()).keys())
+# Assuming 'ct' is your ColumnTransformer (replace this with the actual loading code for your preprocessor)
+# Make sure that 'ct' is properly loaded, or use the same transformation logic here.
 
 # UI Components for user input
 input_Gender = gr.Radio(["male", "female"], label="Gender")
-input_Race = gr.Dropdown(race_options, label="Race")
-input_Age = gr.Dropdown(age_options, label='Age')
+input_Race = gr.Dropdown(list(dict(df['Race (Reported)'].value_counts()).keys()), label="Race")
+input_Age = gr.Dropdown(list(dict(df['Age'].value_counts())), label='Age')
 input_Height = gr.Number(label='Height (cm)')
 input_Weight = gr.Number(label='Weight (kg)')
 input_Diabetes = gr.Radio([0.0, 1.0], label='Diabetes')
 input_Simvastatin = gr.Radio([0.0, 1.0], label='Simvastatin (Zocor)')
 input_Amiodarone = gr.Radio([0.0, 1.0], label='Amiodarone (Cordarone)')
 input_INR_reported = gr.Number(label='INR on Reported Therapeutic Dose of Warfarin')
-input_Cyp2C9_genotypes = gr.Dropdown(cyp2c9_genotypes_options, label='Cyp2C9 genotypes')
-input_VKORC1_genotypes = gr.Dropdown(vkorc1_genotypes_options, label='VKORC1 genotypes')
+input_Cyp2C9_genotypes = gr.Dropdown(list(dict(df['Cyp2C9 genotypes'].value_counts())), label='Cyp2C9 genotypes')
+input_VKORC1_genotypes = gr.Radio(list(dict(df['VKORC1 genotype: -1639 G>A (3673); chr16:31015190; rs9923231; C/T'].value_counts())), label='VKORC1 genotypes')
 input_model = gr.Dropdown(['Decision Tree Regression', 'Support Vector Regression', 'Random Forest Regression', 'Deep Learning'], label='Model Selection')
 
 # Output textbox to display predicted dose
@@ -44,6 +31,17 @@ output_warfarin_dosage = gr.Textbox(label='Therapeutic Dose of Warfarin')
 
 # Prediction function with renamed input variables
 def predict_dosage(gender, race, age, height, weight, diabetes, simvastatin, amiodarone, inr, cyp2c9, vkorc1, selected_model):
+    import numpy as np
+    from joblib import load
+    from tensorflow.keras.models import load_model
+    import tensorflow as tf
+
+    # Optional debug function to inspect data before prediction
+    def print_input_debug(transformed_input, final_array):
+        print("Transformed input shape:", transformed_input.shape)
+        print("Final input shape:", final_array.shape)
+        print("Input data type:", final_array.dtype)
+
     try:
         # Load the selected model
         if selected_model == 'Deep Learning':
@@ -92,6 +90,7 @@ def predict_dosage(gender, race, age, height, weight, diabetes, simvastatin, ami
 
         # Convert to NumPy array for model input
         input_array = np.array(transformed_input, dtype=np.float32)
+        print_input_debug(transformed_input, input_array)
 
         # Predict using appropriate model type
         if selected_model == 'Deep Learning':