Update app.py

app.py

@@ -1,85 +1,107 @@
-# Import necessary libraries
+import gradio as gr
 import pandas as pd
-import seaborn as sns
-import matplotlib.pyplot as plt
-from sklearn.model_selection import train_test_split
-from sklearn.linear_model import LogisticRegression
-from sklearn.metrics import confusion_matrix, roc_curve, auc
-from sklearn.preprocessing import StandardScaler, LabelEncoder
-import joblib
-import os
-
-# File path
-file_path = "heart.csv"
-
-# Step 1: Data Cleaning and Encoding
-# Load data
-data = pd.read_csv(file_path)
-
-# Handle missing values (example: filling with median)
-data = data.fillna(data.median())
-
-# Encode categorical variables
-label_encoders = {}
-for column in data.select_dtypes(include=['object']).columns:
-    le = LabelEncoder()
-    data[column] = le.fit_transform(data[column])
-    label_encoders[column] = le
-
-# Step 2: Plotting the Dependency Matrix
-plt.figure(figsize=(12, 8))
-correlation_matrix = data.corr()
-sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm')
-plt.title('Correlation Matrix')
-plt.show()
-
-# Step 3: Supervised Learning Model for Prediction
-# Define features and target
-X = data.drop('target', axis=1)  # Assuming 'target' is the target variable
-y = data['target']
-
-# Split the data
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-
-# Standardize the data
-scaler = StandardScaler()
-X_train = scaler.fit_transform(X_train)
-X_test = scaler.transform(X_test)
-
-# Train the model
-model = LogisticRegression()
-model.fit(X_train, y_train)
-
-# Make predictions
-y_pred = model.predict(X_test)
-y_pred_prob = model.predict_proba(X_test)[:, 1]
-
-# Step 4: Evaluation Using Confusion Matrix and Plotting ROC Curve
-# Confusion Matrix
-conf_matrix = confusion_matrix(y_test, y_pred)
-sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues')
-plt.title('Confusion Matrix')
-plt.xlabel('Predicted')
-plt.ylabel('Actual')
-plt.show()
-
-# ROC Curve
-fpr, tpr, _ = roc_curve(y_test, y_pred_prob)
-roc_auc = auc(fpr, tpr)
-plt.figure()
-plt.plot(fpr, tpr, color='darkorange', lw=2, label=f'ROC curve (area = {roc_auc:0.2f})')
-plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
-plt.xlim([0.0, 1.0])
-plt.ylim([0.0, 1.05])
-plt.xlabel('False Positive Rate')
-plt.ylabel('True Positive Rate')
-plt.title('Receiver Operating Characteristic (ROC) Curve')
-plt.legend(loc='lower right')
-plt.show()
-
-# Ensure the directory exists before saving the model
-model_directory = './models'
-os.makedirs(model_directory, exist_ok=True)
-model_filename = os.path.join(model_directory, 'logistic_regression_model.sav')
-joblib.dump(model, model_filename)
-print(f"Model saved to {model_filename}")
+import numpy as np
+import joblib, os
+
+script_dir = os.path.dirname(os.path.abspath(__file__))
+pipeline_path = os.path.join(script_dir, 'toolkit', 'pipeline.joblib')
+model_path = os.path.join(script_dir, 'toolkit', 'Random Forest Classifier.joblib')
+
+# Load transformation pipeline and model
+pipeline = joblib.load(pipeline_path)
+model = joblib.load(model_path)
+
+# Update predict function to handle new parameters
+def predict(age, sex, cp, trestbps, chol, fbs, restecg, thalach, exang, oldpeak, slope, ca, thal):
+    # Create a dataframe with the input data
+    input_df = pd.DataFrame({
+        'age': [age],
+        'sex': [sex],
+        'cp': [cp],
+        'trestbps': [trestbps],
+        'chol': [chol],
+        'fbs': [fbs],
+        'restecg': [restecg],
+        'thalach': [thalach],
+        'exang': [exang],
+        'oldpeak': [oldpeak],
+        'slope': [slope],
+        'ca': [ca],
+        'thal': [thal]
+    })
+
+    # Process input data using the pipeline
+    X_processed = pipeline.transform(input_df)
+
+    # Make predictions using the model
+    prediction_probs = model.predict_proba(X_processed)[0]
+    prediction_label = {
+        "Prediction: CHURN 🔴": prediction_probs[1],
+        "Prediction: STAY ✅": prediction_probs[0]
+    }
+
+    return prediction_label
+
+input_interface = []
+
+with gr.Blocks(theme=gr.themes.Soft()) as app:
+
+    Title = gr.Label('Customer Churn Prediction App')
+
+    with gr.Row():
+        Title
+
+    with gr.Row():
+        gr.Markdown("This app predicts likelihood of a customer to leave or stay with the company")
+
+    with gr.Row():
+        with gr.Column():
+            input_interface_column_1 = [
+                gr.components.Slider(label='Age', minimum=0, maximum=120, step=1),
+                gr.components.Radio([0, 1], label='Sex'),
+                gr.components.Slider(label='Chest Pain Type', minimum=0, maximum=3, step=1),
+                gr.components.Slider(label='Resting Blood Pressure', minimum=0, maximum=200, step=1),
+                gr.components.Slider(label='Cholesterol', minimum=0, maximum=600, step=1),
+                gr.components.Radio([0, 1], label='Fasting Blood Sugar > 120 mg/dl')
+            ]
+
+        with gr.Column():
+            input_interface_column_2 = [
+                gr.components.Slider(label='Resting ECG', minimum=0, maximum=2, step=1),
+                gr.components.Slider(label='Max Heart Rate Achieved', minimum=60, maximum=220, step=1),
+                gr.components.Radio([0, 1], label='Exercise Induced Angina'),
+                gr.components.Slider(label='ST Depression Induced by Exercise', minimum=0.0, maximum=10.0, step=0.1),
+                gr.components.Slider(label='Slope of Peak Exercise ST Segment', minimum=0, maximum=2, step=1),
+                gr.components.Slider(label='Number of Major Vessels (0-3)', minimum=0, maximum=3, step=1),
+                gr.components.Slider(label='Thalassemia (0-3)', minimum=0, maximum=3, step=1)
+            ]
+
+    with gr.Row():
+        input_interface.extend(input_interface_column_1)
+        input_interface.extend(input_interface_column_2)
+
+    with gr.Row():
+        predict_btn = gr.Button('Predict')
+        output_interface = gr.Label(label="churn")
+    
+    with gr.Accordion("Open for information on inputs", open=False):
+        gr.Markdown("""This app receives the following as inputs and processes them to return the prediction on whether a customer, will churn or not.
+                    
+                    - age: Age of the customer
+                    - sex: Sex of the customer (0: Female, 1: Male)
+                    - cp: Chest Pain Type (0: typical angina, 1: atypical angina, 2: non-anginal pain, 3: asymptomatic)
+                    - trestbps: Resting Blood Pressure (in mm Hg on admission to the hospital)
+                    - chol: Serum Cholesterol in mg/dl
+                    - fbs: Fasting Blood Sugar > 120 mg/dl (0: No, 1: Yes)
+                    - restecg: Resting Electrocardiographic results (0: normal, 1: having ST-T wave abnormality, 2: showing probable or definite left ventricular hypertrophy)
+                    - thalach: Maximum Heart Rate Achieved
+                    - exang: Exercise Induced Angina (0: No, 1: Yes)
+                    - oldpeak: ST depression induced by exercise relative to rest
+                    - slope: The slope of the peak exercise ST segment
+                    - ca: Number of major vessels (0-3) colored by fluoroscopy
+                    - thal: Thalassemia (0: normal, 1: fixed defect, 2: reversible defect, 3: unknown)
+                    """)
+
+    predict_btn.click(fn=predict, inputs=input_interface, outputs=output_interface)
+        
+app.launch(share=True)