prediction.py

import streamlit as st
import pandas as pd
import numpy as np
import pickle
import json

# Load datanya
with open('list_num_columns.txt', 'r') as file_1:
    list_num_cols = json.load(file_1)

with open('list_cat_columns.txt', 'r') as file_2:
    list_cat_cols = json.load(file_2)

with open('model_scaler.pkl', 'rb') as file_3:
    model_scaler = pickle.load(file_3)

with open('model_encoder.pkl', 'rb') as file_4:
    model_encoder = pickle.load(file_4)

with open('model_lin_reg.pkl', 'rb') as file_5:
    model_lin_reg = pickle.load(file_5)

def run():
    with st.form(key='Form Parameter'):
        name = st.text_input('Name', value='')
        age = st.number_input('Age', min_value=0, max_value=70, step=1)
        weight = st.number_input('Weight', min_value=0, max_value=150, step=1)
        height = st.slider('Height', 150, 225, 165)
        price = st.number_input('Price', min_value=0, max_value=1000000000, step=1000)
        st.markdown('---')
        AttackingWorkRate = st.selectbox('Attacking Work Rate', ('Low','Medium','High'),index=0)
        DefensiveWorkRate = st.selectbox('Defensive Work Rate', ('Low','Medium','High'),index=1)
        st.markdown('---')
        pace = st.number_input('Pace', min_value=0, max_value=100, step=1)
        shooting = st.number_input('Shooting Total', min_value=0, max_value=100, step=1)
        passing = st.number_input('Passing', min_value=0, max_value=100, step=1)
        dribbling = st.number_input('Dribbling', min_value=0, max_value=100, step=1)
        defending = st.number_input('Defending', min_value=0, max_value=100, step=1)
        physicality = st.number_input('Physicality', min_value=0, max_value=100, step=1)

        submitted = st.form_submit_button('Predict')

        data_inf = {'Name': name,
        'Age': age,
        'Height': height,
        'Weight': weight,
        'Price': price,
        'AttackRate':AttackingWorkRate,
        'DefenseRate': DefensiveWorkRate,
        'PaceTotal': pace,
        'ShootingTotal':shooting,
        'PassingTotal':passing ,
        'DribblingTotal':dribbling,
        'DefendingTotal': defending,
        'PhysicalityTotal': physicality}

        df = pd.DataFrame([data_inf])
        st.dataframe(df)

        
        if submitted:
            # split antara num and cat column
            data_inf_num = df[list_num_cols]
            data_inf_cat = df[list_cat_cols]

            # scaling and encoding
            data_inf_num_scaled = model_scaler.transform(data_inf_num)
            data_inf_cat_encoded = model_encoder.transform(data_inf_cat)

            # merge
            data_inf_final = np.concatenate([data_inf_num_scaled, data_inf_cat_encoded], axis=1)

            # predict
            y_pred_inf = model_lin_reg.predict(data_inf_final)
            st.write('# Rating: ',str(np.round(y_pred_inf))[1:3])

if __name__ == '__main__':
    run()