important

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import StandardScaler

# Convert Potability into category
#data['Potability'] = data['Potability'].astype('category')



# Handle missing values with median
for column in data.columns:
    if data[column].isnull().any():
        data[column].fillna(data[column].median(), inplace=True)

# Separate features and target
X = data.drop('Potability', axis=1)
y = data['Potability']

# Scale the features
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Train a Random Forest model
rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
rf_model.fit(X_scaled, y)

# Get feature importance
feature_importance = pd.DataFrame({
    'Feature': X.columns,
    'Importance': rf_model.feature_importances_
}).sort_values('Importance', ascending=False)

print("Feature Importance for Predicting Water Potability:")
print(feature_importance)

# Calculate and print model accuracy
from sklearn.metrics import accuracy_score, classification_report

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)

# Train the model on training data
rf_model.fit(X_train, y_train)

# Make predictions on test data
y_pred = rf_model.predict(X_test)

print("\nModel Performance:")
print("\nAccuracy Score:", accuracy_score(y_test, y_pred))
print("\nDetailed Classification Report:")
print(classification_report(y_test, y_pred))

# Create feature importance plot
import matplotlib.pyplot as plt
import seaborn as sns

plt.figure(figsize=(10, 6))
sns.barplot(x='Importance', y='Feature', data=feature_importance)
plt.title('Feature Importance for Water Potability Prediction')
plt.xlabel('Importance Score')
plt.ylabel('Features')
plt.tight_layout()
plt.show()