employee_future_.py

# -*- coding: utf-8 -*-
"""Employee Future .ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1qrkFNfcXzUi3JoqFT-2P_Ilcs5PmKA3A
"""

!pip install xgboost
!pip install scikit-learn

import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from xgboost import XGBClassifier

X_train = pd.read_csv('/content/drive/MyDrive/229/Lab07/Employee.csv')
X_train

X_train['JoiningYear'].unique()

y_train = X_train.pop("LeaveOrNot")

# Names of numerical features
num_col = X_train.select_dtypes(include=['int64', 'float64']).columns
# Names of categorical features
cat_col = X_train.select_dtypes(include=['object', 'bool']).columns

#find tpe of column
print(num_col)
print(cat_col)

preprocessor = ColumnTransformer([("scaler", StandardScaler(), num_col),
                                  ("onehot", OneHotEncoder(sparse=False), cat_col)])

model = Pipeline(steps=[('preprocessor', preprocessor),
                        ('classifier', XGBClassifier())])

model.fit(X_train, y_train)

import joblib  #function save model

joblib.dump(model, 'model.joblib')

unique_values = {col:X_train[col].unique() for col in cat_col}
joblib.dump(unique_values, 'unique_values.joblib')

unique_values

import joblib
import pandas as pd
import streamlit as st


model = joblib.load('model.joblib')
unique_values = joblib.load('unique_values.joblib')

unique_Education =  unique_values["Education"]
unique_JoiningYear =  unique_values["JoiningYear"]
unique_City =  unique_values["City"]
unique_PaymentTier =  unique_values["PaymentTier"]
unique_Age=  unique_values["Age"]
unique_Gender =  unique_values["Gender"]
unique_EverBenched = unique_values["EverBenched"]
unique_ExperienceInCurrentDomain =  unique_values["ExperienceInCurrentDomain"]


def main():
    st.title("Employee Future Analysis")

    with st.form("questionaire"):
        Age = st.slider("Age", min_value=15, max_value=80)
        Gender = st.selectbox("Gender", unique_Gender)
        Education = st.selectbox("Education", unique_Education)
        JoiningYear = st.slider("JoiningYear", min_value=2010, max_value=2020)
        City = st.selectbox("City", unique_City)
        PaymentTier = st.slider("PaymentTier (1: HIGHEST , 2: MID LEVEL , 3: LOWEST)", min_value=1, max_value=3)
        EverBenched = st.selectbox("EverBenched", unique_EverBenched)
        ExperienceInCurrentDomain = st.slider("ExperienceInCurrentDomain", min_value=0, max_value=7)



        clicked = st.form_submit_button("Employee Future")
        if clicked:
            result=model.predict(pd.DataFrame({"Age": [Age],
                                               "Gender": [Gender],
                                               "Education": [Education],
                                               "JoiningYear": [JoiningYear],
                                               "City": [City],
                                               "PaymentTier": [PaymentTier],
                                               "EverBenched": [EverBenched],
                                               "ExperienceInCurrentDomain" : [ExperienceInCurrentDomain]}))
            result =  '0' if result[0] == 0 else '1'
            st.success('The predicted Heart Disease is {}'.format(result))

if __name__=='__main__':
    main()