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
+h8dsft_P1M2_AlselloDM.ipynb filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,179 @@
+import streamlit as st
+import pandas as pd
+import joblib
+from bs4 import BeautifulSoup
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from imblearn.pipeline import Pipeline as imbpipe
+
+
+
+APP_ICON_URL = "credit-card.png"
+
+# Setup web page
+st.set_page_config(
+     page_title="CREDIT CARD APPROVAL APP",
+     page_icon=APP_ICON_URL,
+     layout="wide",
+     )
+
+st.markdown("""
+    <style type="text/css">
+    blockquote {
+        margin: 1em 0px 1em -1px;
+        padding: 0px 0px 0px 1.2em;
+        font-size: 20px;
+        border-left: 5px solid rgb(230, 234, 241);
+        # background-color: rgb(129, 164, 182);
+    }
+    blockquote p {
+        font-size: 30px;
+        color: #FFFFFF;
+    }
+    [data-testid=stSidebar] {
+        background-color: rgb(129, 164, 182);
+        color: #FFFFFF;
+    }
+    [aria-selected="true"] {
+         color: #000000;
+    }
+    </style>
+""", unsafe_allow_html=True)
+with st.container():
+    col1,col2,_,_ = st.columns([1,14,1,1],gap="large")
+    with col1:
+        st.image(APP_ICON_URL, width=80)
+    with col2:
+        st.header(f"Credit Card Prediction App")
+st.caption(f"App developed by [Alsello](https://github.com/AlselloDM)")
+st.write(f"This application predicts whether your credit card application is **Approved** or **Not Approved**.")
+st.markdown("___")
+
+@st.cache_data
+def fetch_data():
+    df = pd.read_csv('Application_Data.csv')
+    return df
+
+df = fetch_data()
+
+st.sidebar.title("Approval App 📋")
+st.sidebar.write('Please choose the page')
+#make two pages for EDA and Prediction
+page = st.sidebar.selectbox('Choose a page', ['EDA', 'Approval Form📋'])
+if page == 'EDA':
+    
+    st.subheader('Approval Status')
+    st.write('Approval Status is the target variable with value of 0 (not approved) and 1 (approved).')
+    sns.countplot(x='Status', data=df)
+    plt.xticks([0, 1])
+    st.pyplot(plt)
+    st.write('The data is imbalanced.')
+
+    st.subheader('Correlation between Years Employed and Total Income')
+    st.write('Years Employed and Total Income usually has correlation.')
+    plt.figure(figsize=(8, 6))
+    plt.scatter(df['Years_of_Working'], df['Total_Income'], alpha=0.5)
+    plt.xlabel('Years Employed')
+    plt.ylabel('Total Income')
+    plt.title('Correlation between Years Employed and Total Income')
+    st.pyplot(plt)
+    st.write('We can see that the longer the Years Employed, it does not increase the Total Income.')
+    st.write('')
+
+    st.subheader('Correlation of the Features')
+    st.write("One of the many Feature Selection Methods is Pearson's Heatmap Correlation Method.")
+    plt.figure(figsize=(15,15))
+    sns.heatmap(df.corr(), annot=True)
+    plt.show()
+    st.pyplot(plt)
+    st.write("There are no good enough features to choose so I used another method called 'SelectKBest'.")
+    st.write('')
+
+
+else:
+    st.sidebar.title("Applicant's Profile")
+    st.sidebar.write('Please enter the needed profile here')
+    def user_input_features():
+        # Applicant ID
+        id = st.number_input("ID of the applicant (7 Digits of your ID)")
+        # Male or Female
+        sex = st.selectbox('Gender',('M','F'))
+        # Car Ownership
+        car_ownership = st.selectbox('Car Ownership (1 : Yes | 0 : No)',(1,0))
+        # Property Ownership
+        property_ownership = st.selectbox('Property Ownership (1 : Yes | 0 : No)',(1,0))
+        # Total Children
+        total_children = st.slider('Number of Children?',0,5,0)
+        # Income
+        income = st.number_input('Yearly Income',27000,1575000)
+        # Income Type
+        income_type = st.selectbox("Employment Status",('Working','Commercial associate ','State servant','Pensioner','Student'))
+        # Education Level
+        education = st.selectbox("Education Level",('Lower secondary','Secondary / secondary special','Incomplete higher ','Higher education ','Academic degree'))
+        # Marriage Status
+        marriage_status = st.selectbox("Marriage Status",('Single / not married','Married','Civil marriage','Separated','Widow'))
+        # Residence
+        residence = st.selectbox('Residency',('House / apartment','With parents','Municipal apartment','Rented apartment','Office apartment','Co-op apartment'))
+        # Mobile Phone Ownership
+        mobile_phone = st.selectbox('Mobile Phone Ownership (1 : True | 0 : False)',(1,0))
+        # Work Phone Ownership
+        work_phone = st.selectbox('Work Phone Ownership (1 : True | 0 : False)',(1,0))
+        # Phone Ownership
+        phone = st.selectbox('Phone Ownership (1 : True | 0 : False)',(1,0))
+        # Email Ownership
+        email = st.selectbox('Email Ownership (1 : True | 0 : False)',(1,0))
+        # Job Title
+        job_title = st.selectbox('Job Title',('Laborers','Core staff','Sales staff','Managers','Drivers','High skill tech staff','Accountants','Medicine staff','Cooking staff','Security staff','Cleaning staff','Private service staff','Low-skill Laborers','Waiters/barmen staff','Secretaries','HR staff','Realty agents','IT staff'))
+        # Total Family Member
+        total_family = st.slider('Number of Family Member',1,7,1)
+        # Applicant Age
+        age = st.number_input("Age")
+        # Years of Working
+        years_of_working = st.number_input("Years of Work")
+        # Total Bad Debt
+        total_bad_debt = st.slider('Total of Bad Debt',0,49,0)\
+        # Total Good Debt
+        total_good_debt = st.slider('Total of Good Debt',1,61,1)
+        
+
+
+
+        data = {'Applicant_ID': id,'Applicant_Gender':sex,'Owned_Car':car_ownership,
+                'Owned_Realty':property_ownership,'Total_Children':total_children,
+                'Total_Income':income,'Income_Type':income_type,
+                'Education_Type':education,'Family_Status':marriage_status,
+                'Housing_Type':residence,'Owned_Mobile_Phone':mobile_phone,'Owned_Work_Phone':work_phone,
+                'Owned_Phone':phone,'Owned_Email':email,'Job_Title':job_title,'Total_Family_Members':total_family,
+                'Applicant_Age':age,'Years_of_Working':years_of_working,
+                'Total_Bad_Debt':total_bad_debt,'Total_Good_Debt':total_good_debt}
+        # 
+        features = pd.DataFrame(data,index=[0])
+        return features
+
+    input_df = user_input_features()
+
+    st.subheader('Applicant Data📋')
+    st.write(input_df)
+
+    load_model = joblib.load("model")
+
+
+    if st.button('Predict'):
+        try:
+            prediction = load_model.predict(input_df)
+            prediction_proba = load_model.predict_proba(input_df)
+
+            st.subheader('APPROVAL')
+            for i in range(len(prediction)):
+                if prediction[i] == 0:
+                    st.error("This applicant is not **Approved**")
+                else:
+                    st.success("This applicant is **Approved**")
+
+            st.subheader('Probability')
+            st.write("0 : No | 1 : Yes")
+            st.write(prediction_proba)
+
+        except ValueError:
+            st.header("Insufficient Applicant Data")

h8dsft_P1M2_AlselloDM.ipynb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7814b40a00ac7b609b62352d4f87419c9a30ce614a096a622960656ba31228
+size 36101976

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+pandas
+matplotlib
+joblib
+seaborn
+imblearn
+scikit-learn==1.1.1
+feature_engine==1.5.2