Prediction

- pandas - scikit-learn

import pandas as pd import warnings warnings.filterwarnings("ignore") from pyodide.http import open_url from sklearn.ensemble import GradientBoostingClassifier depressed_data=pd.read_csv(open_url("https://raw.githubusercontent.com/knavee12345/knavee12345/main/Certifications/b_depressed.csv")) depressed_data.fillna(method='ffill',inplace=True) depressed_data['Number_children']=depressed_data['Number_children'].apply(lambda x: str(x)+" children") depressed_data['education_level']=depressed_data['education_level'].apply(lambda x: str(x)+" education level") depressed_data['total_members']=depressed_data['total_members'].apply(lambda x: str(x)+" family members") depressed_data=depressed_data[['sex', 'Age', 'Married', 'Number_children', 'education_level', 'total_members','depressed']] temp = pd.get_dummies(depressed_data[['Number_children']],drop_first=False) depressed_data = pd.concat([depressed_data,temp],axis=1) depressed_data.drop('Number_children',axis=1,inplace=True) temp = pd.get_dummies(depressed_data[['education_level']],drop_first=False) depressed_data = pd.concat([depressed_data,temp],axis=1) depressed_data.drop('education_level',axis=1,inplace=True) temp = pd.get_dummies(depressed_data[['total_members']],drop_first=False) depressed_data = pd.concat([depressed_data,temp],axis=1) depressed_data.drop('total_members',axis=1,inplace=True) new_data=depressed_data.groupby('depressed',group_keys=None).apply(lambda x: x.sample(238)) x = new_data.drop('depressed',axis=1) y = new_data['depressed'] Model_best=GradientBoostingClassifier(learning_rate=0.3, max_depth=10, max_features=0.2,min_samples_leaf=60, random_state=100) Model_best.fit(x,y) print()

Loading.....!

Gender :

Relationship Status :

Revenue Status :

Age :

Valid.

Please fill out this field.

Education Level :

Valid.

Please fill out this field.

No of Children :

Valid.

Please fill out this field.

Total Family Members :

Valid.

Please fill out this field.

pyscript.write("status","Enter Your Details") def data(*args, **kwargs): gender=Element("gender").value age=Element("age").value married=Element("relation").value children=Element("children").value members=Element("members").value education=Element("education").value my_data={'sex':gender, 'Age':age, 'Married':married, '0 children':0, '1 children':0, '10 children':0, '11 children':0, '2 children':0, '3 children':0, '4 children':0, '5 children':0, '6 children':0, '7 children':0, '8 children':0, '9 children':0, '1 education level':0, '10 education level':0, '11 education level':0, '12 education level':0, '13 education level':0, '14 education level':0, '16 education level':0, '17 education level':0, '18 education level':0, '19 education level':0, '2 education level':0, '3 education level':0, '4 education level':0, '5 education level':0, '6 education level':0, '7 education level':0, '8 education level':0, '9 education level':0, '1 family members':0, '10 family members':0, '11 family members':0, '12 family members':0, '2 family members':0, '3 family members':0, '4 family members':0, '5 family members':0, '6 family members':0, '7 family members':0, '8 family members':0, '9 family members':0} my_df=pd.DataFrame(data=my_data.values(),index=my_data.keys()).T my_df[[f"{children} children"]]=1 my_df[[f"{education} education level"]]=1 my_df[[f"{members} family members"]]=1 pyscript.write("result","Result") if Model_best.predict(my_df)[0]==0: pyscript.write("out1","Not Depressed") else: pyscript.write("out1","Depressed")