Submit Model

app.py

@@ -0,0 +1,12 @@
+import streamlit as st
+import eda
+import prediction
+
+
+navigation = st.sidebar.selectbox('Pilih Halaman', ('EDA', 'Predict'))
+
+
+if navigation == 'EDA':
+    eda.run()
+else:
+    prediction.run()

eda.py

@@ -0,0 +1,101 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px
+
+st.set_page_config(page_title='Wine Quality Dataset Analysis', layout='wide', initial_sidebar_state='expanded')
+
+def run():
+
+    # Buat Title
+    st.title('EDA Dataset Wine Quality')
+
+    # Buat Deskripsi
+    st.subheader('Written by Franciscus Andrew Sunanda, FTDS-RMT-018')
+
+    st.markdown('---')
+
+    
+    st.write('Dataset         : Wine Quality Data Set')
+
+    st.write('Objective       : Dapat memprediksi grade quality sebuah Wine')
+
+    st.write('Evaluasi nya menggunakan Accuracy Score')
+    
+
+    st.markdown('---')
+
+    st.write('## Dataset')
+    data = pd.read_csv('winequalityN.csv')
+
+    # Rename nama column agar lebih mudah digunakan
+
+    data = data.rename(columns={'fixed acidity' : 'fixed_acidity', 'volatile acidity' : 'volatile_acidity', 'citric acid':'citric_acid', 'residual sugar' : 'residual_sugar',
+                   'free sulfur dioxide' : 'free_sulfur_dioxide', 'total sulfur dioxide' : 'total_sulfur_dioxide'})
+    data.drop_duplicates(inplace=True)
+    data.dropna(inplace=True, axis=0)
+
+    st.dataframe(data)
+
+    
+    st.markdown('---')
+
+    st.write('## Checking Balance / Imbalance')
+
+    quality = data['quality'].value_counts()
+
+    fig = plt.figure()
+    quality.plot(kind='bar',
+            color='blue')
+
+    plt.title('Perbandingan Jumlah Quality Wine')
+    plt.xlabel('Quality')
+    plt.ylabel('Count')
+    st.pyplot(fig)
+
+
+    st.markdown('---')
+
+    st.write('## Each Features Correlation with Wine Quality')
+
+    red = data[data['type'] == 'red'].corrwith(data['quality'])
+    white = data[data['type'] == 'white'].corrwith(data['quality'])
+    fig = plt.figure()
+    sns.heatmap(red.to_frame(), cmap='RdYlGn', annot=True, vmin=-1,vmax=1)
+    plt.title('Red Wine')
+    st.pyplot(fig)
+
+    fig = plt.figure()
+    sns.heatmap(white.to_frame(), cmap='RdYlGn', annot=True, vmin=-1,vmax=1)
+    plt.title('White Wine')
+    st.pyplot(fig)
+
+    st.write('Semakin tinggi level sulphates dan citric acid dalam red wine akan menghasilkan red wine yang semakin bagus')
+    st.write('Sebaliknya, sulphates dan citric acid tidak terlalu berpengaruh pada white wine, tetapi level density yang semakin rendah akan menghasilkan white wine yang baik')
+
+    st.markdown('---')
+
+    st.write('## Alcohol and Volatile Acidity')
+
+    fig = plt.figure()
+    sns.scatterplot(x='alcohol', y='volatile_acidity', data=data, hue='quality', palette='coolwarm')
+    plt.title('Perbandingan Level Alcohol dan Volatile Acidity dengan Kualitas suatu Wine')
+    st.pyplot(fig)
+
+    st.markdown('---')
+
+    st.write('## Citric Acid')
+
+    fig = plt.figure()
+    sns.scatterplot(x='quality', y='citric_acid', data=data, hue='type')
+    plt.title('Perbandingan Kematian dengan Lama Follow-up period')
+    st.pyplot(fig)
+
+    
+    st.markdown('---')
+
+    
+if __name__ == '__main__':
+    run()

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ee0ff3fe56eb4acb018e634850e719906fe35dcec41aa3be33164160367e25
+size 555794

prediction.py

@@ -0,0 +1,62 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+import json
+
+
+# Load All Files
+
+with open('model.pkl', 'rb') as file_1:
+  pipeline = pickle.load(file_1)
+
+def run():
+
+    st.title('Wine Quality Prediction')
+
+
+    with st.form(key='form_heart_failure'):
+        type = st.selectbox('Red/White Wine?', ('red','white'))
+        fixed = st.number_input('Level of Fixed Acidity', min_value=3.0, max_value=20., value=5.,step=.1)
+        volatile = st.number_input('Level of Volatile Acidity', min_value=.01, max_value=2., value=1.,step=.01)
+        citric = st.number_input('Level of Citric Acid', min_value=.0, max_value=2., value=1.,step=.01)
+        sugar = st.number_input('Level of Residual Sugar', min_value=.1, max_value=80., value=1.,step=.1)
+        chlorides = st.number_input('Level of Chlorides', min_value=.001, max_value=1., value=.001,step=.001)
+        free = st.number_input('Level of Free Sulfur Dioxide', min_value=1, max_value=300, value=20,step=1)
+        total = st.number_input('Level of Total Sullfur Dioxide', min_value=5, max_value=450, value=100,step=1)
+        density = st.number_input('Level of Density', min_value=.8, max_value=1.2, value=.9,step=.001)
+        pH = st.number_input('Level of pH', min_value=2., max_value=5., value=2.5,step=.1)
+        sulphates = st.number_input('Level of Sulphates', min_value=.1, max_value=3., value=1.,step=.1)
+        alcohol = st.number_input('Level of Alcohol', min_value=5., max_value=20., value=10., step=.1)
+        
+        submitted = st.form_submit_button('Predict')
+
+
+    data_inf = {
+        'type': type,
+        'fixed_acidity': fixed,
+        'volatile_acidity': volatile,
+        'citric_acid': citric,
+        'residual_sugar' : sugar,
+        'chlorides': chlorides,
+        'free_sulfur_dioxide': free,
+        'total_sulfur_dioxide': total,
+        'density': density,
+        'pH': pH,
+        'sulphates': sulphates,
+        'alcohol': alcohol 
+        }
+
+    data_inf = pd.DataFrame([data_inf])
+    st.dataframe(data_inf)
+
+    if submitted:
+        # Predict using Model
+
+        y_pred_inf = pipeline.predict(data_inf)
+        st.write('Hasil prediksi Model : ', y_pred_inf)
+
+
+
+if __name__ == '__main__':
+    run()

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+pandas
+seaborn
+matplotlib
+numpy
+plotly
+scikit-learn==1.2.1