import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import accuracy_score, classification_report

data = pd.read_excel('/Users/apple/Downloads/21092023-July_Sept.xlsx', sheet_name="op")
data = data.dropna()
print(data)

label_encoder = LabelEncoder()
categorical_cols = ['Gender', 'Caste', 'Category', 'Marital Status', 'Blood Group']
for col in categorical_cols:
    data[col] = label_encoder.fit_transform(data[col])

X = data[['Age', 'Gender', 'Caste', 'Category', 'Marital Status']]
y = data['Test Result']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = LogisticRegression()
model.fit(X_train, y_train)

y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
classification_report_result = classification_report(y_test, y_pred)

print(f"Accuracy: {accuracy}")
print("Classification Report:")
print(classification_report_result)