missingly: Comprehensive Missing Data Analysis¶
missingly is a Python package for comprehensive analysis, visualization, and imputation of missing data. Inspired by the R naniar package, it provides intuitive tools for understanding and handling missing data patterns in pandas DataFrames.
Features¶
Summary Statistics: Quick overviews of missing data patterns
Rich Visualizations: Matrix plots, bar charts, dendrograms, upset plots, and more
Statistical Tests: Little’s MCAR test and observed-data missingness diagnostics
Multiple Imputation Methods: From simple mean imputation to advanced MICE
Automated Reporting: Generate comprehensive HTML reports
Custom Missing Values: Handle non-standard missing indicators
Quick Start¶
import pandas as pd
import numpy as np
import missingly as mi
# Create sample data
data = {'A': [1, np.nan, 3], 'B': [4, 5, np.nan]}
df = pd.DataFrame(data)
# Analyze missing patterns
mi.miss_var_summary(df)
mi.matrix(df)
mi.dendrogram(df)
# Generate report
mi.create_report(df, "report.html")
Contents¶
Documentation: