prediction.py

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

st.set_page_config(
    page_title = 'FIFA 2022',
    layout = 'wide',
    initial_sidebar_state = 'expanded'
)


with open('model.pkl', 'rb') as file_1: #rb =read binary
    model = pickle.load(file_1)

with open('scaler.pkl', 'rb') as file_2:
    scaler = pickle.load(file_2)

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

with open('num.txt', 'r') as file_4:
    num = json.load(file_4)

with open('cat.txt', 'r') as file_5:
   cat = json.load(file_5)


def run():
    # Membuat Form
    with st.form(key='form_fifa_2022_rmt_040'):
        name = st.text_input('Name', value='')
        age = st.number_input('Age', min_value=16, max_value=52, value=24, step=1, help='Usia Pemain')
        weight = st.number_input('Weight', min_value=60, max_value=120, value=68)
        height = st.slider('Height', 160, 250, 180)
        price = st.number_input('Price', min_value=0, max_value=1000000000, value=0)
        st.markdown('---')

        attacking_work_rate = st.selectbox('AttackingWorkRate', ('Low', 'Medium', 'High'), index=0)
        defensive_work_rate = st.radio('DefensiveWorkRate', ('Low', 'Medium', 'High'), index=1)
        st.markdown('---')

        pace = st.number_input('Kecepatan Lari', min_value=0, max_value=100, value=50)
        shooting = st.number_input('Shooting', min_value=0, max_value=100, value=50)
        passing = st.number_input('Passing', min_value=0, max_value=100, value=50)
        dribbling = st.number_input('Dribbling', min_value=0, max_value=100, value=50)
        defending = st.number_input('Defending', min_value=0, max_value=100, value=50)
        physicality = st.number_input('Physicality', min_value=0, max_value=100, value=50)

        submitted = st.form_submit_button('Predict !')
    
    df_inf = {
        'Name': name,
        'Age': age,
        'Height': height,
        'Weight': weight,
        'ValueEUR': price,
        'AttackingWorkRate': attacking_work_rate,
        'DefensiveWorkRate': defensive_work_rate,
        'PaceTotal': pace,
        'ShootingTotal': shooting,
        'PassingTotal': passing,
        'DribblingTotal': dribbling,
        'DefendingTotal': defending,
        'PhysicalityTotal': physicality
    }
    # Convert to Dataframe pandas
    df_inf = pd.DataFrame([df_inf])
    st.dataframe(df_inf)

    df_inf = df_inf.rename(columns= {'ValueEUR':'Price'})

    if submitted:
        # Define num and cat
        df_inf_num = df_inf[num]
        df_inf_cat = df_inf[cat]

        # Feature scaling and encoding
        df_inf_num_scaled = scaler.transform(df_inf_num)
        df_inf_cat_encoded = encoder.transform(df_inf_cat)

        # Concat
        df_inf_final = np.concatenate([df_inf_num_scaled,df_inf_cat_encoded],axis=1)

        # Predict the new data
        prediction = model.predict(df_inf_final)

        st.write('# Rating : ', str(int(prediction)))


if __name__ == '__main__':
    run()