Page 170 - FULL REPORT 30012024

return 'Underweight'
elif bmi < 25:
return 'Normal weight'
elif bmi < 30:
return 'Overweight'
else:
return 'Obesity'

# Function to predict stroke risk and identify influential factors
def predict_stroke_risk(gender, age, hypertension, heart_disease, bmi,
smoking_status,
ever_married, work_type, Residence_type):
# Encode categorical variables
gender = le_gender.transform([gender])[0]
smoking_status = le_smoking_status.transform([smoking_status])[0]
ever_married = le_ever_married.transform([ever_married])[0]
work_type = le_work_type.transform([work_type])[0]
Residence_type = le_Residence_type.transform([Residence_type])[0]
age_category = le_age_category.transform([categorize_age(age)])[0]
bmi_category = le_bmi_category.transform([categorize_bmi(bmi)])[0]

# Create input data for prediction
feature_names = ['gender', 'hypertension', 'heart_disease',
'ever_married', 'work_type',
'Residence_type', 'age_category', 'bmi_category',
'smoking_status']
input_df = pd.DataFrame([[gender, hypertension, heart_disease,
ever_married, work_type, Residence_type, age_category,
bmi_category, smoking_status]],
columns=feature_names)

# Predict stroke risk
probability = model.predict_proba(input_df)[:, 1]
stroke_risk = probability[0] * 100

stroke_risk = round(stroke_risk, 2)

# Ensure minimum output is 1
if stroke_risk < 1:
stroke_risk = stroke_risk + 1

return stroke_risk

#delete userdata
@app.route('/delete_user_data/<string:user_id>', methods=['POST'])
def delete_user_data(user_id):

mydb = get_db_connection()
cursor = mydb.cursor()

# Execute the DELETE query
cursor.execute("DELETE FROM userdata WHERE id = %s", (user_id,))
153