main.py

# Import necessary libraries
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
from sklearn.tree import DecisionTreeClassifier
from sklearn.naive_bayes import GaussianNB
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

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

# Check for missing values and fill or drop as appropriate
df.fillna(df.mean(), inplace=True)

# Encode categorical features
label_encoder = LabelEncoder()
df['gender'] = label_encoder.fit_transform(df['gender'])
df['ever_married'] = label_encoder.fit_transform(df['ever_married'])
df['work_type'] = label_encoder.fit_transform(df['work_type'])
df['Residence_type'] = label_encoder.fit_transform(df['Residence_type'])
df['smoking_status'] = label_encoder.fit_transform(df['smoking_status'])

# Split the dataset into features and target
X = df.drop('stroke', axis=1)  # Features
y = df['stroke']               # Target variable

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

# Standardize the features
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

### Decision Tree Classifier
dt_model = DecisionTreeClassifier(random_state=42)
dt_model.fit(X_train, y_train)
dt_pred = dt_model.predict(X_test)
print("Decision Tree Accuracy:", accuracy_score(y_test, dt_pred))
print(classification_report(y_test, dt_pred))

### Naive Bayes Classifier
nb_model = GaussianNB()
nb_model.fit(X_train, y_train)
nb_pred = nb_model.predict(X_test)
print("Naive Bayes Accuracy:", accuracy_score(y_test, nb_pred))
print(classification_report(y_test, nb_pred))

### Artificial Neural Network (ANN)
ann_model = Sequential()
ann_model.add(Dense(32, activation='relu', input_shape=(X_train.shape[1],)))
ann_model.add(Dense(16, activation='relu'))
ann_model.add(Dense(1, activation='sigmoid'))

# Compile the model
ann_model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Train the model
ann_model.fit(X_train, y_train, epochs=50, batch_size=32, validation_split=0.2)

# Evaluate the model
ann_pred = (ann_model.predict(X_test) > 0.5).astype("int32")
print("ANN Accuracy:", accuracy_score(y_test, ann_pred))
print(classification_report(y_test, ann_pred))