Find out the percentage of missing values in each column in the given dataset

Question

import pandas as pd
df = pd.read_csv(\'https://query.data.world/s/Hfu_PsEuD1Z_yJHmGaxWTxvkz7W_b0\')
percent= 100*(len(df.loc[:,df.isnull().sum(axis=0)>=1 ].index) / l         


        

Answer 1

import numpy as np
import pandas as pd

raw_data = {'first_name': ['Jason', np.nan, 'Tina', 'Jake', 'Amy'], 
        'last_name': ['Miller', np.nan, np.nan, 'Milner', 'Cooze'], 
        'age': [22, np.nan, 23, 24, 25], 
        'sex': ['m', np.nan, 'f', 'm', 'f'], 
        'Test1_Score': [4, np.nan, 0, 0, 0],
        'Test2_Score': [25, np.nan, np.nan, 0, 0]}
results = pd.DataFrame(raw_data, columns = ['first_name', 'last_name', 'age', 'sex', 'Test1_Score', 'Test2_Score'])


results 

  first_name last_name   age  sex  Test1_Score  Test2_Score
0      Jason    Miller  22.0    m          4.0         25.0
1        NaN       NaN   NaN  NaN          NaN          NaN
2       Tina       NaN  23.0    f          0.0          NaN
3       Jake    Milner  24.0    m          0.0          0.0
4        Amy     Cooze  25.0    f          0.0          0.0

You can use following function, which will give you output in Dataframe

• Zero Values
• Missing Values
• % of Total Values
• Total Zero Missing Values
• % Total Zero Missing Values
• Data Type

Just copy and paste following function and call it by passing your pandas Dataframe

def missing_zero_values_table(df):
        zero_val = (df == 0.00).astype(int).sum(axis=0)
        mis_val = df.isnull().sum()
        mis_val_percent = 100 * df.isnull().sum() / len(df)
        mz_table = pd.concat([zero_val, mis_val, mis_val_percent], axis=1)
        mz_table = mz_table.rename(
        columns = {0 : 'Zero Values', 1 : 'Missing Values', 2 : '% of Total Values'})
        mz_table['Total Zero Missing Values'] = mz_table['Zero Values'] + mz_table['Missing Values']
        mz_table['% Total Zero Missing Values'] = 100 * mz_table['Total Zero Missing Values'] / len(df)
        mz_table['Data Type'] = df.dtypes
        mz_table = mz_table[
            mz_table.iloc[:,1] != 0].sort_values(
        '% of Total Values', ascending=False).round(1)
        print ("Your selected dataframe has " + str(df.shape[1]) + " columns and " + str(df.shape[0]) + " Rows.\n"      
            "There are " + str(mz_table.shape[0]) +
              " columns that have missing values.")
#         mz_table.to_excel('D:/sampledata/missing_and_zero_values.xlsx', freeze_panes=(1,0), index = False)
        return mz_table

missing_zero_values_table(results)

Output

Your selected dataframe has 6 columns and 5 Rows.
There are 6 columns that have missing values.

             Zero Values  Missing Values  % of Total Values  Total Zero Missing Values  % Total Zero Missing Values Data Type
last_name              0               2               40.0                          2                         40.0    object
Test2_Score            2               2               40.0                          4                         80.0   float64
first_name             0               1               20.0                          1                         20.0    object
age                    0               1               20.0                          1                         20.0   float64
sex                    0               1               20.0                          1                         20.0    object
Test1_Score            3               1               20.0                          4                         80.0   float64

If you want to keep it simple then you can use following function to get missing values in %

def missing(dff):
    print (round((dff.isnull().sum() * 100/ len(dff)),2).sort_values(ascending=False))


missing(results)

Test2_Score    40.0
last_name      40.0
Test1_Score    20.0
sex            20.0
age            20.0
first_name     20.0
dtype: float64