Credit 4

Procfile

@@ -0,0 +1 @@
+web: sh setup.sh && streamlit run app.py

Training_Data.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd73a4449456def74f8cd20200b3861bf07451367510ef944199585ea64e73c
+size 7685009

app.py

@@ -0,0 +1,70 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+import base64
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+st.write("""
+# Credit Risk Detection App
+
+""")
+
+url_dataset = f'<a href="Training_Data.csv">Download Dataset CSV File</a>'
+st.markdown(url_dataset, unsafe_allow_html=True)
+
+def user_input_features() :
+    income = st.sidebar.slider('income', 10310, 9999938)
+    age = st.sidebar.slider('age', 21, 79)
+    experience = st.sidebar.slider('experience', 0, 20)
+    married = st.sidebar.slider ('married', 0, 1)
+    house_ownership = st.sidebar.slider ('house_ownership', 0, 2)
+    car_ownership = st.sidebar.slider ('car_ownership', 0, 1)
+    profession = st.sidebar.slider ('profession', 0, 51)
+    current_job_years = st.sidebar.slider('current_job_years', 0, 14)
+    current_house_years = st.sidebar.slider('current_house_years', 10, 14)
+    
+    data = {'income':[income],
+    'age':[age],
+    'experience':[experience],
+    'married': [married],
+    'house_ownership': [house_ownership],
+    'car_ownership': [car_ownership],
+    'profession': [profession],
+    'current_job_years':[current_job_years],
+    'current_house_years':[current_house_years]}
+
+    features = pd.DataFrame(data)
+    return features
+
+input_df = user_input_features()
+
+credit_raw = pd.read_csv('Training_Data.csv')
+credit_raw.fillna(0, inplace=True)
+credit = credit_raw.drop(columns=['risk_flag'])
+df = pd.concat([input_df, credit],axis=0)
+
+df = df[:1] # Selects only the first row (the user input data)
+df.fillna(0, inplace=True)
+
+features = ['income','age','experience','married','house_ownership','car_ownership','profession','current_job_years',
+            'current_house_years']
+
+df = df[features]
+
+
+st.subheader('User Input features')
+st.write(df)
+
+load_clf = pickle.load(open('Training_Data.pkl', 'rb'))
+detection = load_clf.predict(df)
+detection_proba = load_clf.predict_proba(df)
+credit_labels = np.array(['Normal', 'Beresiko'])
+st.subheader('Detection')
+#st.write(detection)
+st.write(credit_labels[int(detection)])
+st.subheader('Detection Probability')
+st.write(detection_proba)
+#df_prob = pd.DataFrame(data=detection_proba, index=['Probability'], columns=credit_labels)
+#st.write(df_prob)

requirements.txt

@@ -0,0 +1,6 @@
+matplotlib==3.5.2
+numpy==1.23.1
+pandas==1.4.3
+seaborn==0.11.2
+streamlit==1.12.0
+sklearn

setup.sh

@@ -0,0 +1,13 @@
+mkdir -p ~/.streamlit/
+
+echo "\
+[general]\n\
+email = \"your-email@domain.com\"\n\
+" > ~/.streamlit/credentials.toml
+
+echo "\
+[server]\n\
+headless = true\n\
+enableCORS=false\n\
+port = $PORT\n\
+" > ~/.streamlit/config.toml