Advanced Imputation and Reporting

This notebook demonstrates some of the more advanced features of missingly, including MICE imputation, visualizing the results of imputation, and generating an HTML report.

1. The Dataset

import pandas as pd
import numpy as np
import missingly as mi

np.random.seed(42)

data = {
    'temperature': np.random.normal(100, 5, 100),
    'pressure': np.random.normal(50, 2, 100),
    'humidity': np.random.normal(40, 5, 100)
}
df = pd.DataFrame(data)

# Introduce some missing values
df.loc[df.sample(frac=0.1).index, 'temperature'] = np.nan
df.loc[df.sample(frac=0.15).index, 'pressure'] = np.nan

df.head()

	temperature	pressure	humidity
0	102.483571	47.169259	41.788937
1	99.308678	49.158709	42.803923
2	103.238443	49.314571	45.415256
3	107.615149	NaN	45.269010
4	98.829233	49.677429	33.111653

2. MICE Imputation

df_imputed_mice = mi.impute_mice(df)

3. Visualizing the Imputation

mi.vis_impute_dist(df, df_imputed_mice, 'temperature')

<Axes: title={'center': "Distribution of 'temperature': before vs after imputation"}, xlabel='temperature', ylabel='Count'>

4. Generating an HTML Report

mi.create_report(df, output_path='missingly_report.html')

'/home/runner/work/missingly/missingly/docs/source/examples/missingly_report.html'