Upload 6 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ranking.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,10 @@
+import streamlit as st
+import prediksi
+import eda
+
+navigation = st.sidebar.selectbox('Pilih halaman: ', ('EDA', 'Predict Player Return'))
+
+if navigation == "EDA":
+    eda.run()
+else:
+    prediksi.run()

best_estimator.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5073c24cb0edd53710d1db71b4352a68ed376131c517d21a4f9555dd2c1028
+size 426485

eda.py

@@ -0,0 +1,76 @@
+import streamlit as st
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt 
+import plotly.express as px
+from PIL import Image
+
+# Set page config
+st.set_page_config(
+    page_title = 'NBA_EDA',
+    layout='wide',
+    initial_sidebar_state='expanded'
+)
+
+# Create function for eda
+def run():
+    # Create title
+    st.title('NBA Player Return Prediction')
+
+
+    # Create sub header
+    st.subheader('EDA untuk Analisis Dataset NBA')
+
+    # Add image
+    st.image('https://pbs.twimg.com/profile_images/1745324889009987584/JGBvQa17_200x200.png'
+             ,caption='NBA Logo')
+    
+    # Create a description
+    st.write('Dibuat Oleh Daffa')
+    st.write('# Deskripsi 1')
+    st.write('## Deskripsi 2')
+    st.write('### Deskripsi 3')
+    
+
+    # Magic Syntax
+    '''
+    Pada page kali ini, penulis akan melakukan eksplorasi sederhana,
+    Dataset yang digunakan adalah NBA dari tahun 2004.
+    Dataset ini berasal dari web kaggle.com
+    '''
+
+    # Create straight line
+    st.markdown('---')
+
+    # Show dataframe
+    df = pd.read_csv('ranking.csv')
+    st.dataframe(df)
+
+    # Create Barplot
+    st.write('### Plot WinPercentage')
+    popularity = df.groupby(['TEAM','G'])['W_PCT'].mean().sort_values().reset_index()
+    fig = plt.figure(figsize=(15,5))
+    sns.barplot(data=popularity, y='TEAM', orient='h', x='G')
+    st.pyplot(fig)
+    # Statement Barchart using Magic Syntax
+    '''
+    Medium ada xxxxx Low ada High ada xxxx...
+    '''
+    #
+    
+    # Create Histogram
+    st.write('### Barplot Berdasarkan Losses')
+    fig = plt.figure(figsize=(15,5))
+    # definisikan popularitas
+    aw = df.groupby(['TEAM','L'])['W_PCT'].mean().sort_values().reset_index()
+    # buat graf dengan filter yang diinginkan
+    sns.barplot(data=aw, y='TEAM', orient='h', x='L')
+    st.pyplot(fig)
+
+    # Statement Histogram
+    '''
+    Age normal distribusi...
+    '''
+
+if __name__ == '__main__':
+    run()

prediksi.py

@@ -0,0 +1,44 @@
+# Import libraries
+import pickle
+import json
+import pandas as pd
+import numpy as np
+import streamlit as st
+
+with open('best_estimator.pkl', 'rb') as file_1:
+  best_estimator = pickle.load(file_1)
+
+def run():
+    with st.form(key = 'NBA Player Return Form'):
+       
+        Teamid = st.number_input('TEAM_ID', min_value=0, max_value=9999999999, value = 0, placeholder="Type a number...", help='Nomor Team')
+        Seasonid = st.number_input('SEASON_ID', min_value=0, max_value=99999,value=0, placeholder="Type a number", help='Nomor Season')
+        Conference = st.text_input('Name of Conference', value= 'West')
+        Team = st.text_input('Name of Team', value= 'Phoenix')
+        Game = st.number_input('Number of Games', min_value=0, value = None, placeholder="Type a number...", help='Berapa Game Dalam Season')
+        Win = st.number_input('Number of Win', min_value=0, value = None, placeholder="Type a number...", help='Berapa Win Dalam Season')
+        Loss = st.number_input('Number of Loss', min_value=0, value = None, placeholder="Type a number...", help='Berapa Loss Dalam Season')
+        WinPercentage =  st.number_input('Win %', min_value=0.01, value = None, placeholder="Type a number...", help='Berapa Win %')
+        submitted = st.form_submit_button('Predict')
+
+    df_inf = {
+        'TEAM_ID': Teamid, 
+        'SEASON_ID': Seasonid, 
+        'CONFERENCE': Conference, 
+        'TEAM': Team, 
+        'G': Game,
+        'W': Win, 
+        'L': Loss,
+        'W_PCT': WinPercentage, 
+        }
+    df_inf = pd.DataFrame([df_inf])
+
+    if submitted:
+        pred = best_estimator.predict(df_inf)
+        if pred == 1:
+          st.write('Will Return')
+        else:
+          st.write('Will not Return')
+
+if __name__ == '__main__':
+  run()

ranking.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b082d15cd46c93bc2e16db29af8708ea0be753c26c6c6f0611fb8f8d26ba92
+size 15446241

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+pandas
+seaborn
+matplotlib
+numpy
+scikit-learn==1.3.0