Upload eda.py

eda.py

@@ -30,8 +30,19 @@ def run():
     # Show dataframe
     st.write('### Dataset')
     df = pd.read_csv('df_ori.csv')
+
+    # data cleaning
+    #drop unused columns
+    df = df.drop(columns='Unnamed: 0')
+    # replace "6" as "5" in "education_level" column
+    df['education_level'] = df['education_level'].replace(6, 5)
+    # replace "0.0" as "-1.0" in "pay_[i]" column
+    df[['pay_0', 'pay_2', 'pay_3', 'pay_4', 'pay_5', 'pay_6']] = df[['pay_0', 'pay_2', 'pay_3', 'pay_4', 'pay_5', 'pay_6']].replace(0.0, -1.0)
+
+    # show cleaned dataset
     st.dataframe(df)
 
+    # make border
     st.write('')
     st.markdown('---')
     st.write('')