asf

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.preprocessing import LabelEncoder, StandardScaler
from sklearn.metrics import confusion_matrix

# Load dataset
file_path = "healthcare-dataset-stroke-data.csv"
data = pd.read_csv(file_path)

# Handle missing values
data['bmi'] = data['bmi'].fillna(data['bmi'].mean())

# Drop unnecessary column
data = data.drop(['id'], axis=1)

# Encode categorical columns
label_encoders = {}
for column in ['gender', 'ever_married', 'work_type', 'Residence_type', 'smoking_status']:
    le = LabelEncoder()
    data[column] = le.fit_transform(data[column])
    label_encoders[column] = le

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

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

# Split into training and testing data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42, stratify=y)

# Initialize and train Naive Bayes model
model = GaussianNB()
model.fit(X_train, y_train)

# Predict the test data
y_pred = model.predict(X_test)

# Calculate confusion matrix
Confusion_Matrix = confusion_matrix(y_test, y_pred)
print("The confusion matrix is as follows: ")
print(Confusion_Matrix)

# Extract True Positives, False Positives, False Negatives, True Negatives
True_positives = Confusion_Matrix[1, 1]
False_positives = Confusion_Matrix[0, 1]
False_negatives = Confusion_Matrix[1, 0]
True_negatives = Confusion_Matrix[0, 0]

# Print confusion matrix values
print("True Positives:", True_positives)
print("False Positives:", False_positives)
print("False Negatives:", False_negatives)
print("True Negatives:", True_negatives)

# Calculate Precision
Precision = True_positives / (True_positives + False_positives) if (True_positives + False_positives) > 0 else 0
print("Precision:", Precision)

# Calculate Recall
Recall = True_positives / (True_positives + False_negatives) if (True_positives + False_negatives) > 0 else 0
print("Recall:", Recall)

# Calculate F1-Score
F1_Score = 2 * (Precision * Recall) / (Precision + Recall) if (Precision + Recall) > 0 else 0
print("F1-Score:", F1_Score)