Created
September 1, 2017 21:24
-
-
Save EdMan1022/586a32ac5ecc4ee38a105ebdc8de1ae5 to your computer and use it in GitHub Desktop.
Create a dataframe with null variable columns indicating indices with null values for each column
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
df = pd.DataFrame(data=[[3., 1., np.NaN], [np.NaN, 3., 2.], [4., 1., 3.]], index=[0, 1, 2], | |
columns=['apple', 'carrot', 'pear']) | |
def null_only_categorical_func(data): | |
""" | |
Take a series, and return values of 1. where the series is null | |
:param data: (pandas Series) input column | |
:return: (pandas Series) column of 1s for indices where data is null | |
""" | |
cat_column = pd.Series(0., data.index) | |
cat_column[(data.isnull())] = 1. | |
return cat_column | |
cat_df = df.apply(null_only_categorical_func, axis=0) | |
trimmed_cat_df = cat_df.drop(cat_df.columns[cat_df.sum() == 0.], axis=1) | |
trimmed_cat_df.columns = trimmed_cat_df.columns + '=' | |
output = pd.concat([df.fillna(0.), trimmed_cat_df], axis=1).sort_index(axis=1) | |
print(output) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment