Create app.py

app.py

@@ -0,0 +1,108 @@
+from joblib import load
+import numpy as np
+import pandas as pd
+
+# Load your saved models
+rf = load('best_random_forest_model.joblib')
+dt = load('best_decision_tree_model.joblib')
+mlp = load('best_MLP_classifier_model.joblib')
+knn = load('best_knn_model.joblib')
+
+# Class names
+class_names = ["Low Therapeutic Dose of Warfarin Required", "High Therapeutic Dose of Warfarin Required"]
+
+# Load training data for expected feature names
+training_data = pd.read_csv('/content/dataset_train.csv')
+
+# Drop the 'Unnamed: 0' column if it exists
+if 'Unnamed: 0' in training_data.columns:
+    training_data = training_data.drop(columns=['Unnamed: 0'])
+
+expected_feature_names = training_data.columns.tolist()
+
+# Define the prediction function
+def predict_warfarin_dose(gender, race, age, height, weight, diabetes, simvastatin, amiodarone, genotype, inr, algorithm):
+    # Decode the encoded values
+    gender = "Male" if gender == 1 else "Female"
+    race = race_dict_inverse[race]
+    age = age_dict_inverse[age]
+    genotype = genotype_dict_inverse[genotype]
+
+    # Convert input data to DataFrame for one-hot encoding
+    input_data = pd.DataFrame([[gender, race, age, height, weight, diabetes, simvastatin, amiodarone, genotype, inr]],
+                               columns=['gender', 'race', 'age', 'height', 'weight', 'diabetes', 'simvastatin',
+                                        'amiodarone', 'genotype', 'inr'])
+
+    # One-hot encode categorical features
+    input_data_encoded = pd.get_dummies(input_data, columns=['gender', 'race', 'diabetes', 'simvastatin', 'amiodarone', 'genotype'])
+
+    # Reindex the DataFrame to match expected feature names
+    input_data_encoded = input_data_encoded.reindex(columns=expected_feature_names, fill_value=0)
+
+    # Predict using the selected algorithm
+    if algorithm == 'Random Forest':
+        model = rf
+    elif algorithm == 'Decision Tree':
+        model = dt
+    elif algorithm == 'MLP':
+        model = mlp
+    elif algorithm == 'KNN':
+        model = knn
+    else:
+        raise ValueError("Invalid algorithm selected.")
+
+    y_prob = model.predict_proba(input_data_encoded)
+    class_idx = np.argmax(y_prob)
+
+    preds_dict = {class_names[i]: float(y_prob[0, i]) for i in range(len(class_names))}
+    name = class_names[class_idx]
+
+    return name, preds_dict
+
+race_dict = {
+    "African-American":0,
+    "Asian":1,
+   "Black":2,
+    "Black African":3,"Black Caribbean":4,"Black or African American":5,"Black other":6 ,
+    "Caucasian":7,"Chinese":8,"Han Chinese":9,"Hispanic":10,"Indian":11,"Intermediate":12,
+    "Japanese":13,"Korean":14, "Malay":15, "Other":16, "Other (Black British)":17, "Other (Hungarian)":18, "Other Mixed Race":19, "White":20}
+
+
+age_dict = {
+    "10-19":0,
+    "20-29":1,
+    "30-39":2,
+    "40-49":3,"50-59":4,"60-69":5,"70-79":6,
+   "80-89":7,"90+":8}
+
+genotype_dict = {"A/A":0, "A/G":1, "G/G":2}
+# Invert dictionaries for decoding
+genotype_dict_inverse = {v: k for k, v in genotype_dict.items()}
+race_dict_inverse = {v: k for k, v in race_dict.items()}
+age_dict_inverse = {v: k for k, v in age_dict.items()}
+
+# Create Gradio interface
+gender_choices = [("Male", 1), ("Female", 0)]
+gender_module = gr.Dropdown(choices=gender_choices, label="Gender")
+
+# Assuming race_choices, age_choices, genotype_choices are already defined
+race_module = gr.Dropdown(choices=list(race_dict.items()), label="Race")
+age_module = gr.Dropdown(choices=list(age_dict.items()), label="Age Group")
+genotype_module = gr.Dropdown(choices=list(genotype_dict.items()), label="Genotype")
+
+height_module = gr.Number(label="Height")
+weight_module = gr.Number(label="Weight")
+diabetes_module = gr.Number(label="Diabetes")
+simvastatin_module = gr.Radio(choices=[0, 1], label="Simvastatin")
+amiodarone_module = gr.Radio(choices=[0, 1], label="Amiodarone")
+inr_module = gr.Number(label="INR Reported")
+algorithm_module = gr.Dropdown(choices=["Random Forest", "Decision Tree", "MLP", "KNN"], label="Algorithm")
+output_module1 = gr.Textbox(label="Predicted Class")
+output_module2 = gr.Label(label="Predicted Probability")
+
+iface = gr.Interface(fn=predict_warfarin_dose,
+                     inputs=[gender_module, race_module, age_module, height_module, weight_module, diabetes_module,
+                             simvastatin_module, amiodarone_module, genotype_module, inr_module, algorithm_module],
+                     outputs=[output_module1, output_module2])
+
+iface.launch(debug=True)