first commit

eda.py

@@ -0,0 +1,67 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px
+from PIL import Image
+
+st.set_page_config(
+    page_title="FIFA 2022 Player Rating Prediction",
+    layout='wide',
+    initial_sidebar_state='expanded'
+)
+def run(): # Agar bisa dipanggil oleh code main.
+    # Membuat Title
+    st.title('FIFA 2022 Player Rating Prediction')
+
+    # Membuat Sub Header
+    st.subheader('EDA untuk Analisa Dataset FIFA 2022')
+
+    # Membuat Deskripsi
+    st.write('Page ini dibuat oleh *Ardiansyah Arya Salvinia')
+
+    # Menambahkan Gambar
+    image = Image.open('joshua-hoehne-8ZvTRSRdsOA-unsplash.jpg')
+    st.image(image, caption='FIFA 2022')
+
+    # Menambahkan Garis Lurus
+    st.markdown('---')
+
+    # Magic Syntax untuk menuliskan text beberapa baris
+    '''
+    Pada page kali ini, penulis akan melakukan eksplorasi sederhana.
+    Dataset yang digunakan adalah dataset FIFA 2022.
+    Dataset ini berasal dari web sofifa.com.
+    '''
+
+    # Show Dataframe
+    data = pd.read_csv('https://raw.githubusercontent.com/ardhiraka/FSDS_Guidelines/master/p1/v3/w1/P1W1D1PM%20-%20Machine%20Learning%20Problem%20Framing.csv')
+    st.dataframe(data)
+
+    # Membuat BarPlot
+    st.write('### Plot AttackingWorkRate')
+    fig = plt.figure(figsize=(15,5))
+    sns.countplot(x='AttackingWorkRate',data=data)
+    st.pyplot(fig)
+
+    # Membuat Histogram
+    st.write('### Histogram of Rating')
+    fig = plt.figure(figsize=(15,5))
+    sns.histplot(data['Overall'], bins=30, kde=True)
+    st.pyplot(fig)
+
+    # Membuat Histogram Berdasarkan Input User
+    st.write('#### Histogram Berdasarkan Input User')
+    pilihan = st.radio(' Pilih Column : ', ('Age','Weight','Height','ShootingTotal'))
+    fig = plt.figure(figsize=(15,5))
+    sns.histplot(data[pilihan], bins=30, kde=True)
+    st.pyplot(fig)
+
+    # Membuat Plotly Plot
+    st.write('#### Plotly  Plot - ValueEUR dengan Overall')
+    fig = px.scatter(data, x='ValueEUR', y='Overall', hover_data=['Name','Age'])
+    st.plotly_chart(fig)
+
+if __name__ == '__main__': # Agar python bisa dibuka standalone tanpa membuka main.
+    run()

list_cat_cols.txt

@@ -0,0 +1 @@
+["AttackingWorkRate", "DefensiveWorkRate"]

list_num_cols.txt

@@ -0,0 +1 @@
+["Age", "Height", "Weight", "Price", "PaceTotal", "ShootingTotal", "PassingTotal", "DribblingTotal", "DefendingTotal", "PhysicalityTotal"]

main.py

@@ -0,0 +1,11 @@
+# Digunakan sebagai pusat code yang akan digunakan user.
+import streamlit as st
+import eda
+import prediction
+
+navigation = st.sidebar.selectbox('Pilh Halaman : ', ('EDA', 'Predict A Player'))
+
+if navigation == 'EDA':
+    eda.run()
+else:
+    prediction.run()

model_encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0487ce8b546fe0a6b798cb570bf6f876b6f7c687b42a3a1d4e690b791b95fcdb
+size 1361

model_lin_reg.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f34fed46db68589436b95a9f085a5b38f053b2d98dac710a9fe5310bed7328
+size 861

model_scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66a44b8a7e687aae2805b4ea993c7eaf9eefd8b77f5e85b9fd9a1e7d4ee69c1
+size 1590

prediction.py

@@ -0,0 +1,95 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px
+from PIL import Image
+
+# Load All Files
+
+import joblib
+import json
+
+# Load All Files
+with open('model_lin_reg.pkl', 'rb') as file_1:
+  model_lin_reg = joblib.load(file_1)
+
+with open('model_scaler.pkl', 'rb') as file_2:
+  model_scaler = joblib.load(file_2)
+
+with open('model_encoder.pkl', 'rb') as file_3:
+  model_encoder = joblib.load(file_3)
+
+with open('list_num_cols.txt', 'r') as file_4:
+  list_num_cols = json.load(file_4)
+
+with open('list_cat_cols.txt', 'r') as file_5:
+  list_cat_cols = json.load(file_5)
+
+
+def run(): # Agar bisa dipanggil oleh main.
+    # Membuat Form
+    with st.form(key='form_parameters'):
+        name = st.text_input('Name', value='') # Value = nilai default
+        age = st.number_input('Age', min_value=16, max_value=60, value=25, step=1, help='Usia Pemain') # Help deskripsi kolom form
+        weight = st.number_input('Weight', min_value=50, max_value=150, value=70)
+        height = st.number_input('Height',min_value=50, max_value=250, value=170)
+        # Bisa menggunakan untuk slider `price = st.slider('Price', 0,100000000)`
+        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=1)
+        defensive_work_rate = st.selectbox('DefensiveWorkRate', ('Low','Medium','High'), index=2)
+        st.markdown('---')
+
+        pace = st.number_input('Pace', 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')
+
+    data_inf = { # Label harus sama dengan CSV, variabel bebas.
+        'Name' : name,
+        'Age' : age,
+        'Height' : height,
+        'Weight' : weight,
+        'Price' : price,
+        'AttackingWorkRate' : attacking_work_rate,
+        'DefensiveWorkRate' : defensive_work_rate,
+        'PaceTotal' : pace,
+        'ShootingTotal' : shooting,
+        'PassingTotal' : passing,
+        'DribblingTotal' : dribbling,
+        'DefendingTotal' : defending,
+        'PhysicalityTotal' : physicality
+    }
+
+    data_inf = pd.DataFrame([data_inf])
+    st.dataframe(data_inf)
+
+    if submitted:
+        # Split between Numerical Columns and Categorical Columns
+        data_inf_num = data_inf[list_num_cols]
+        data_inf_cat = data_inf[list_cat_cols]
+
+
+        # Feature Scaling and Feature Encoding
+        data_inf_num_scaled = model_scaler.transform(data_inf_num)
+        data_inf_cat_encoded = model_encoder.transform(data_inf_cat)
+
+
+        # Concate Numerical Columns and Categorical Columns
+        data_inf_final = np.concatenate([data_inf_num_scaled, data_inf_cat_encoded], axis=1)
+
+        # Predict using Linear regression
+        y_pred_inf = model_lin_reg.predict(data_inf_final)
+
+        st.write('# Rating : ', str(int(y_pred_inf)))
+
+if __name__ == '__main__': # Agar python bisa dibuka standalone tanpa membuka main.
+    run()

requirement.txt

@@ -0,0 +1,6 @@
+streamlit
+numpy
+seaborn
+matplotlib
+joblib
+scikit-learn==1.0.2