Upload 6 files

app.py

@@ -0,0 +1,10 @@
+import streamlit as st
+import eda
+import prediction
+
+page = st.sidebar.selectbox('Choose page : ', ('EDA', 'Prediction'))
+
+if page == 'EDA' : 
+    eda.run()
+else:
+    prediction.run()

eda.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px
+
+
+def run():
+    #Membuat title
+    st.title('Credit Default Predictor - Exploratory Data Analysis')
+
+    #Membuat subheader
+    st.subheader('Exploratory Data Analysis of the model Credit Default Predictor')
+
+    #Membuat garis
+    st.markdown('----')
+
+    #Masukkan pandas dataframe
+
+    #Show dataframe
+    df = pd.read_csv('https://raw.githubusercontent.com/AdeWT/AdeWT-Hacktiv8-things/main/BigQuery_credit_card_default_27_12_2023.csv')
+    st.dataframe(df)
+
+    #Membuat bar plot
+    st.write('### Spread of default and non-default in the dataset')
+    fig = plt.figure(figsize=(15,5))
+    sns.countplot(x='default_payment_next_month', data = df)
+    st.pyplot(fig)
+
+    #Membuat histogram
+    st.write('### Distribution plot of limit balance')
+    fig = plt.figure(figsize=(15,5))
+    sns.histplot(df['limit_balance'], bins = 30, kde = True)
+    st.pyplot(fig)
+    #tambah penjelas
+
+    #membuat histogram berdasarkan inputan user
+    st.write('### Choose which data to see spread of')
+    option = st.selectbox('Choose data : ', ('sex', 'education_level', 'marital_status'))
+    fig = plt.figure(figsize= (15,5))
+    sns.countplot(x=option, data=df)
+    st.pyplot(fig)
+    st.write(f'#### sex = 1 is male, 2 is female')
+    st.write('#### education_level =')
+    st.write('#### 1 is graduate school')
+    st.write('#### 2 is university')
+    st.write('#### 3 is high school')
+    st.write('#### 4 is others')
+    st.write('#### 5 and 6 are unknown')
+    st.write('#### marital_status =')
+    st.write('#### 1 is married')
+    st.write('#### 2 is single')
+    st.write('#### 3 is others')
+
+    #Membuat Plotly plot
+
+    st.write('### Plotly Plot - Education Level on Default Payment Next Month')
+    fig = px.scatter(df, x = 'education_level', y = 'default_payment_next_month', hover_data = ['limit_balance',
+                                                                                                'education_level',
+                                                                                                'marital_status',
+                                                                                                'age'])
+    st.plotly_chart(fig)
+    st.write('#### 1 is default while 0 is no default')
+if __name__ == '__main__':
+    run()

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbeffa7344ec24c9af95777df0a3ae533686af36282cc1b6bc45086cfb412f1a
+size 184229

prediction.py

@@ -0,0 +1,98 @@
+# learn stremlit, this one for the predictions
+
+#import libs
+import streamlit as st
+import pandas as pd
+import pickle
+
+#open related files/load files
+with open('scaler.pkl', 'rb') as file_1:
+  scaler = pickle.load(file_1)
+
+with open('model.pkl', 'rb') as file_2:
+  model = pickle.load(file_2)
+
+
+def run():
+    #Make the input form for the user to input data?
+    with st.form('Form_CreditDefaultPredictor'):
+        #Field limit balance
+        limit_balance = st.number_input('limit_balance',min_value=10000, max_value=1000000)
+        #Field age
+        age = st.number_input('age', min_value= 21, max_value = 70, step = 1, help = 'Age of borrower')
+        #Field education level
+        education_level = st.slider('education_level', 1, 4, 2)
+        st.write('#### - 1 is graduate school')
+        st.write('#### - 2 is university')
+        st.write('#### - 3 is high school')
+        st.write('#### - 4 is others')
+        #Field marital status
+        marital_status = st.slider('marital_status', 1, 3, 2)
+        st.write('#### - 1 is married')
+        st.write('#### - 2 is single')
+        st.write('#### - 3 is others')
+        #Field pay_0
+        pay_0 = st.slider('pay_0', -2, 9, -1 )
+        st.write('### latest month payment status')
+        st.write('#### - -2: pay early')
+        st.write('#### - -1 = pay on deadline')
+        st.write('#### - 0 : pay delayed for 0 month')                    
+        st.write('#### - 1 = payment delayed for one month')
+        st.write('#### - 2 = payment delayed for two months')
+        st.write('#### ...')
+        st.write('#### - 8 = payment delayed for 8 months')
+        st.write('#### - 9 = payment delayed for 9 months')
+        #Field pay_2
+        pay_2 = st.slider('pay_1', -2, 9, -1, key=2 )
+        st.write('#### 1 months before latest month payment status, same scale as above')
+        #Field pay_3
+        pay_3 = st.slider('pay_2', -2, 9, -1, key=3 )
+        st.write('#### 2 months before latest month payment status, same scale as above')
+        #Field pay_4
+        pay_4 = st.slider('pay_3', -2, 9, -1, key=4 )
+        st.write('#### 3 months before latest month payment status, same scale as above')
+        #Field pay_5
+        pay_5 = st.slider('pay_4', -2, 9, -1, key=5 )
+        st.write('#### 4 months before latest month payment status, same scale as above')
+        #Field pay_6
+        pay_6 = st.slider('pay_5', -2, 9, -1, key=6 )
+        st.write('#### 5 months before latest month payment status, same scale as above')
+        # bikin batasan
+        st.markdown('---------')
+        #bikin submit button
+        submitted = st.form_submit_button('Predict!')
+
+    #inference/satuin data supaya bisa masuk model
+    # nama col ('Name',etc) harus sama dengan di model
+    # keys dari col harus sama dengan nama variable di form streamlit
+    data_inf = {
+        'limit_balance' : limit_balance,
+        'education_level' : education_level,
+        'marital_status' : marital_status,
+        'age': age,
+        'pay_0' : pay_0,
+        'pay_2' : pay_2,
+        'pay_3' : pay_3,
+        'pay_4' : pay_4,
+        'pay_5' : pay_5,
+        'pay_6' : pay_6,
+    }
+
+    #turn to dataframe for model
+    data_inf = pd.DataFrame([data_inf])
+    #aslo show the input from user
+    st.dataframe(data_inf)
+
+    #what happen when predict button is pushed/clicked:
+    if submitted: #ketika si submitted itu punya value, maka
+        #scale 
+        data_inf_scaled = scaler.transform(data_inf)
+        
+        # predict using linear reg model
+        y_pred_inf = model.predict(data_inf_scaled)
+
+        #kasih tau hasilnya apa
+        st.write('## Prediction of whether the borrower will default : ',str(int(y_pred_inf)))
+        st.write('###1 = will default, 0 = will not default')
+if __name__ == '__main__':
+    run()

requirements.txt

@@ -0,0 +1,8 @@
+streamlit==1.29.0
+pandas==2.1.1
+seaborn==0.12.2
+matplotlib==3.8
+numpy==1.26.2
+plotly==5.9.0
+Pillow==9.4.0
+scikit-learn==1.3.0

scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f37a2f6cc2ccb76aa8797beab0a1735236223787a5a483f198412cc7d1bd04
+size 1073