Upload 5 files

README.md

@@ -1,13 +1,12 @@
 ---
-title: Hypertension CVD Detection
-emoji: 📈
-colorFrom: purple
-colorTo: gray
+title: Cardio Vascular Disease Prediction
+emoji: 🐢
+colorFrom: red
+colorTo: purple
 sdk: gradio
-sdk_version: 5.12.0
+sdk_version: 4.44.0
 app_file: app.py
 pinned: false
-license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,230 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+import numpy as np
+from sklearn.metrics import accuracy_score
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Check for missing values
+#Loading Data
+data = pd.read_csv('Cardio_Vascular_Disease_by_Gut_Microbiota.csv')
+print(data.head())
+
+from sklearn.ensemble import RandomForestClassifier
+
+# Define features and target
+X = data.drop(columns=['patient_id', 'CVD_Status'])
+y = data['CVD_Status']
+
+# Train a RandomForest model
+rf = RandomForestClassifier(random_state=42)
+rf.fit(X, y)
+
+# Feature importances
+importances = rf.feature_importances_
+
+# Plot feature importances
+feature_importance_df = pd.DataFrame({'Feature': X.columns, 'Importance': importances})
+feature_importance_df = feature_importance_df.sort_values('Importance', ascending=False)
+
+plt.figure(figsize=(10,6))
+sns.barplot(x='Importance', y='Feature', data=feature_importance_df)
+plt.title('Feature Importance from Random Forest')
+plt.show()
+
+from sklearn.ensemble import GradientBoostingClassifier
+from xgboost import XGBClassifier
+from lightgbm import LGBMClassifier
+from sklearn.metrics import accuracy_score, confusion_matrix
+from sklearn.metrics import accuracy_score, confusion_matrix, r2_score, mean_squared_error, mean_absolute_error
+from math import sqrt
+
+# Initialize the models
+gradient_boosting = GradientBoostingClassifier(random_state=42)
+
+# Split into training and testing sets (80% train, 20% test)
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Train and evaluate Gradient Boosting
+gradient_boosting.fit(X_train, y_train)
+y_pred_gb = gradient_boosting.predict(X_test)
+accuracy_gb = accuracy_score(y_test, y_pred_gb)
+conf_matrix_gb = confusion_matrix(y_test, y_pred_gb)
+
+# Print results
+print(f"Gradient Boosting Accuracy: {accuracy_gb * 100:.2f}%")
+print(f"Confusion Matrix:\n {conf_matrix_gb}\n")
+
+# Predict probabilities
+y_pred_prob_gb = gradient_boosting.predict_proba(X_test)[:, 1] 
+
+# Predict class labels
+y_pred_gb = gradient_boosting.predict(X_test)
+
+# Calculate R² Score, RMSE, MSE, and MAE for Gradient Boosting
+r2_gb = r2_score(y_test, y_pred_prob_gb)
+rmse_gb = sqrt(mean_squared_error(y_test, y_pred_prob_gb))
+mse_gb = mean_squared_error(y_test, y_pred_prob_gb)
+mae_gb = mean_absolute_error(y_test, y_pred_prob_gb)
+
+# Print Accuracy, R², RMSE, MSE, and MAE for Gradient Boosting
+print(f"Gradient Boosting Accuracy: {accuracy_gb * 100:.2f}%")
+print(f"R² Score: {r2_gb:.4f}, RMSE: {rmse_gb:.4f}, MSE: {mse_gb:.4f}, MAE: {mae_gb:.4f}")
+print(f"Confusion Matrix:\n {conf_matrix_gb}\n")
+
+xgboost = XGBClassifier(use_label_encoder=False, eval_metric='logloss', random_state=42)
+
+
+# Train and evaluate XGBoost
+xgboost.fit(X_train, y_train)
+y_pred_xgb = xgboost.predict(X_test)
+accuracy_xgb = accuracy_score(y_test, y_pred_xgb)
+conf_matrix_xgb = confusion_matrix(y_test, y_pred_xgb)
+
+print(f"XGBoost Accuracy: {accuracy_xgb * 100:.2f}%")
+print(f"Confusion Matrix:\n {conf_matrix_xgb}\n")
+
+y_pred_prob_xgb = xgboost.predict_proba(X_test)[:, 1]
+
+y_pred_xgb = xgboost.predict(X_test)
+
+# Calculate R² Score, RMSE, MSE, and MAE for XGBoost
+r2_xgb = r2_score(y_test, y_pred_prob_xgb)
+rmse_xgb = sqrt(mean_squared_error(y_test, y_pred_prob_xgb))
+mse_xgb = mean_squared_error(y_test, y_pred_prob_xgb)
+mae_xgb = mean_absolute_error(y_test, y_pred_prob_xgb)
+
+# Print Accuracy, R², RMSE, MSE, and MAE for XGBoost
+print(f"XGBoost Accuracy: {accuracy_xgb * 100:.2f}%")
+print(f"R² Score: {r2_xgb:.4f}, RMSE: {rmse_xgb:.4f}, MSE: {mse_xgb:.4f}, MAE: {mae_xgb:.4f}")
+print(f"Confusion Matrix:\n {conf_matrix_xgb}\n")
+
+lightgbm = LGBMClassifier(random_state=42)
+
+# Train and evaluate LightGBM
+lightgbm.fit(X_train, y_train)
+y_pred_lgbm = lightgbm.predict(X_test)
+accuracy_lgbm = accuracy_score(y_test, y_pred_lgbm)
+conf_matrix_lgbm = confusion_matrix(y_test, y_pred_lgbm)
+
+
+print(f"LightGBM Accuracy: {accuracy_lgbm * 100:.2f}%")
+print(f"Confusion Matrix:\n {conf_matrix_lgbm}\n")
+
+y_pred_prob_lgbm = lightgbm.predict_proba(X_test)[:, 1]
+
+y_pred_lgbm = lightgbm.predict(X_test)
+
+# Calculate R² Score, RMSE, MSE, and MAE for LightGBM
+r2_lgbm = r2_score(y_test, y_pred_prob_lgbm)
+rmse_lgbm = sqrt(mean_squared_error(y_test, y_pred_prob_lgbm))
+mse_lgbm = mean_squared_error(y_test, y_pred_prob_lgbm)
+mae_lgbm = mean_absolute_error(y_test, y_pred_prob_lgbm)
+
+
+# Print Accuracy, R², RMSE, MSE, and MAE for LightGBM
+print(f"LightGBM Accuracy: {accuracy_lgbm * 100:.2f}%")
+print(f"R² Score: {r2_lgbm:.4f}, RMSE: {rmse_lgbm:.4f}, MSE: {mse_lgbm:.4f}, MAE: {mae_lgbm:.4f}")
+print(f"Confusion Matrix:\n {conf_matrix_lgbm}\n")
+
+import joblib
+
+# Assuming you have already trained the model (e.g., GradientBoostingClassifier, XGBoost, etc.)
+# Example with a Gradient Boosting model (replace with your trained model)
+from sklearn.ensemble import GradientBoostingClassifier
+
+# Assuming you have trained a model
+model = GradientBoostingClassifier(random_state=42)
+model.fit(X_train, y_train)  # Replace this with your actual training code
+
+# Save the trained model as a .pkl file
+joblib.dump(model, 'trained_model.pkl')
+
+print("Model saved successfully as trained_model.pkl")
+
+
+def predict_cvd(Age, Gender, BMI, Blood_pressure, cholesterol, Bacteroides_fragilis, Faecalibacterium_prausnitzii,
+                Akkermansia_muciniphila, Ruminococcus_bromii, Microbiome_Diversity):
+    
+    # Convert Gender to numerical (assuming Male: 0, Female: 1)
+    Gender = 1 if Gender.lower() == 'female' else 0
+    
+    # Prepare the input data as a dataframe
+    input_data = pd.DataFrame({
+        'Age': [Age],
+        'Gender': [Gender],
+        'BMI': [BMI],
+        'Blood_pressure': [Blood_pressure],
+        'cholesterol': [cholesterol],
+        'Bacteroides_fragilis': [Bacteroides_fragilis],
+        'Faecalibacterium_prausnitzii': [Faecalibacterium_prausnitzii],
+        'Akkermansia_muciniphila': [Akkermansia_muciniphila],
+        'Ruminococcus_bromii': [Ruminococcus_bromii],
+        'Microbiome_Diversity': [Microbiome_Diversity]
+    })
+
+    print(input_data)  # Print the input to debug
+
+    # Predict CVD status (0 or 1)
+    prediction = model.predict(input_data)
+    
+    # Return the result
+    return "Cardiovascular Disease Detected" if prediction[0] == 1 else "No Cardiovascular Disease Detected"
+
+import gradio as gr
+import pandas as pd
+import joblib
+
+# Load the pre-trained model
+model = joblib.load('trained_model.pkl')
+
+# Define the prediction function
+def predict_cvd(Age, Gender, BMI, Blood_pressure, Cholesterol, Bacteroides_fragilis, Faecalibacterium_prausnitzii,
+                Akkermansia_muciniphila, Ruminococcus_bromii, Microbiome_Diversity):
+    
+    try:
+        # Convert Gender to numerical (assuming Male: 0, Female: 1)
+        Gender = 1 if Gender.lower() == 'female' else 0
+        
+        # Prepare the input data as a dataframe with correctly capitalized feature names
+        input_data = pd.DataFrame({
+            'Age': [Age],
+            'Gender': [Gender],
+            'BMI': [BMI],
+            'Blood_pressure': [Blood_pressure],
+            'Cholesterol': [Cholesterol],  # Note the capital "C"
+            'Bacteroides_fragilis': [Bacteroides_fragilis],
+            'Faecalibacterium_prausnitzii': [Faecalibacterium_prausnitzii],
+            'Akkermansia_muciniphila': [Akkermansia_muciniphila],
+            'Ruminococcus_bromii': [Ruminococcus_bromii],
+            'Microbiome_Diversity': [Microbiome_Diversity]
+        })
+
+        # Make prediction
+        prediction = model.predict(input_data)
+        
+        # Return result based on prediction
+        return "Cardiovascular Disease Detected" if prediction[0] == 1 else "No Cardiovascular Disease Detected"
+
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+# Define Gradio inputs with proper ranges and selections
+inputs = [
+    gr.Slider(18, 100, step=1, value=50, label="Age"),
+    gr.Dropdown(['Male', 'Female'], label="Gender"),
+    gr.Slider(10.0, 50.0, step=0.1, value=25.0, label="BMI"),
+    gr.Slider(90, 200, step=1, value=120, label="Blood Pressure"),
+    gr.Slider(100, 300, step=1, value=180, label="Cholesterol"),  # Corrected capitalization
+    gr.Slider(0.0, 10.0, step=0.1, value=5.0, label="Bacteroides Fragilis Level"),
+    gr.Slider(0.0, 10.0, step=0.1, value=5.0, label="Faecalibacterium Prausnitzii Level"),
+    gr.Slider(0.0, 10.0, step=0.1, value=5.0, label="Akkermansia Muciniphila Level"),
+    gr.Slider(0.0, 10.0, step=0.1, value=5.0, label="Ruminococcus Bromii Level"),
+    gr.Slider(0.0, 10.0, step=0.1, value=5.0, label="Microbiome Diversity"),
+]
+
+# Define Gradio interface
+iface = gr.Interface(fn=predict_cvd, inputs=inputs, outputs="text", title="Cardiovascular Disease Prediction")
+
+# Launch the interface
+iface.launch()

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,4 @@
+scikit-learn
+seaborn
+xgboost
+lightgbm