Upload 6 files

eda.py

@@ -7,6 +7,185 @@ import matplotlib.pyplot as plt
 def app():
     st.title('Exploratory Data Analysis')
 
-    df = pd.read_csv('P1G5_Set_1_wilson.csv')
-    st.write('dataset overview')
-    st.write(df)
+    df = pd.read_csv('deployment/eda_data.csv')
+    st.write('Dataset Preview')
+    st.write(df)
+
+    st.write('How is the percentage of default payment as education level increases?')
+    vis_1(df)
+
+    st.write('How is the contribution of each gender to default payment?')
+    vis_2(df)
+
+    st.write('Which one got more into default payment, customers with limit balance above or below average?')
+    vis_3(df)
+
+    st.write('How does the average of default payment changes as the total late payment rises?')
+    vis_4(df)
+
+    st.write('How is the contribution of each marital status to default payment?')
+    vis_5(df)
+
+
+def vis_1(df):
+    # make a copy of df
+    df_eda_1 = df.copy()
+
+    # get default payment sum of each education level
+    df_eda_1_grouped_1 = pd.DataFrame(df_eda_1.groupby(by='education_level')['default_payment_next_month'].sum()).reset_index()
+
+    # get row count of each education level
+    df_eda_1_grouped_2 = pd.DataFrame(df_eda_1.groupby(by='education_level')['default_payment_next_month'].count()).reset_index()
+    df_eda_1_grouped_2.rename(columns={'default_payment_next_month' : 'amount'}, inplace=True)
+
+    # get default payment percentage of each educatin level
+    dp_percentage_data = []
+
+    for i in range(len(df_eda_1_grouped_1)):
+        dp_percentage = df_eda_1_grouped_1['default_payment_next_month'][i] / df_eda_1_grouped_2['amount'][i]
+        dp_percentage *= 100 
+        dp_percentage = round(dp_percentage, 2)
+        dp_percentage_data.append(dp_percentage)
+
+    # create dataframe with education level and default payment percentage data
+    df_eda_1_final = pd.DataFrame({
+        'education_level' : df_eda_1_grouped_1['education_level'],
+        'default_payment_percentage' : dp_percentage_data
+    })
+
+    # set plot's title
+    plt.title('Default Payment Percentage for each Education Level')
+
+    # define plot
+    plt.bar(data=df_eda_1_final, x='education_level', height='default_payment_percentage')
+
+    # set y limit
+    ax = plt.gca()
+    ax.set_ylim([0, 100])
+
+    # add axis label
+    ax.set_xlabel('education level')
+    ax.set_ylabel('default payment percentage')
+
+    # edit x ticks and their labels
+    ax.set_xticks([1, 2, 3, 4])
+    ax.set_xticklabels(['graduate_school', 'university', 'highschool', 'others'])
+
+    # add bar label
+    rects = ax.patches
+    for rect in rects:
+        height = rect.get_height()
+        ax.text(rect.get_x() + rect.get_width()/2., 1.05*height,
+                f'{height}%',
+                ha='center', va='bottom')
+
+    # show plot
+    st.pyplot(plt.gcf())
+    plt.clf()
+
+def vis_2(df):
+    # make a copy of df
+    df_eda_2 = df.copy()
+
+    # group df by sex and sum their default_payment
+    df_eda_2_grouped = pd.DataFrame(df_eda_2.groupby(by='sex')['default_payment_next_month'].sum()).reset_index()
+
+    # set plot's title
+    plt.title('Gender Contribution to Default Payment')
+
+    # define plot
+    plt.pie(data=df_eda_2_grouped, x='default_payment_next_month', labels=['male', 'female'], autopct='%1.1f%%')
+
+    # show plot
+    st.pyplot(plt.gcf())
+    plt.clf()
+
+def vis_3(df):
+    # make a copy of df
+    df_eda_3 = df.copy()
+
+    # get the average limit_balance
+    avg_lim = df_eda_3['limit_balance'].mean()
+
+    # get the limit group data, below or above average
+    lim_group = []
+    for lim in df_eda_3['limit_balance']:
+        if lim < avg_lim:
+            lim_group.append('below_average')
+        else:
+            lim_group.append('above_average')
+
+    # add column
+    df_eda_3['limit_group'] = lim_group
+
+    # group df by limit group and sum their default payment count
+    df_eda_3_grouped = pd.DataFrame(df_eda_3.groupby(by='limit_group')['default_payment_next_month'].sum()).reset_index()
+
+    # set plot's title
+    plt.title('Default Payment Amount Categorized by Limit Group')
+
+    # define plot
+    barh = plt.barh(data=df_eda_3_grouped, y='limit_group', width='default_payment_next_month', label='default_payment_next_month')
+
+    # add axis label
+    ax = plt.gca()
+    ax.set_xlabel('default payment amount')
+    ax.set_ylabel('limit balance group')
+
+    # set x limit
+    ax.set_xlim([0, 550])
+
+    # add label
+    ax = plt.gca()
+    ax.bar_label(barh)
+
+    # show plot
+    st.pyplot(plt.gcf())
+    plt.clf()
+
+def vis_4(df):
+    # make a copy of df
+    df_eda_4 = df.copy()
+
+    # get total late payment
+    total_late_payment = pd.Series()
+    for i in range(1, 7):
+        total_late_payment = total_late_payment.add(df_eda_4[f'pay_{i}'], fill_value=0)
+
+    # add column to df
+    df_eda_4['total_late_payment'] = total_late_payment
+
+    # group df by total late payment and sum default payment amount
+    df_eda_4_grouped = pd.DataFrame(df_eda_4.groupby(by='total_late_payment')['default_payment_next_month'].mean()).reset_index()
+
+    # set plot's title
+    plt.title('The Effect of Late Payment to Default Payment')
+
+    # define plot
+    plt.plot(df_eda_4_grouped['total_late_payment'], df_eda_4_grouped['default_payment_next_month'])
+
+    # add axis label
+    ax = plt.gca()
+    ax.set_xlabel('total late payment (month)')
+    ax.set_ylabel('average default payment')
+
+    # show plot
+    st.pyplot(plt.gcf())
+    plt.clf()
+
+def vis_5(df):
+    # make a copy of df
+    df_eda_5 = df.copy()
+
+    # group df by marital status and sum their default_payment
+    df_eda_5_grouped = pd.DataFrame(df_eda_5.groupby(by='marital_status')['default_payment_next_month'].sum()).reset_index()
+
+    # set plot's title
+    plt.title('Contribution to Default Payment by Marital Status ')
+
+    # define plot
+    plt.pie(data=df_eda_5_grouped, x='default_payment_next_month', labels=['others', 'married', 'single', 'divorced'], autopct='%1.1f%%')
+
+    # show plot
+    st.pyplot(plt.gcf())
+    plt.clf()