statskita 0.1.0

Python toolkit for Indonesian official microdata

StatsKita

⚠️ v0.1.0 - Alpha Release: This is an early release. The API may change in future versions. Use in production with caution.

Python toolkit for Indonesian official microdata.

TL;DR

Load → Clean → Analyze → Export Indonesian official microdata (SAKERNAS, SUSENAS, PODES) with proper survey weights, 10x faster than manual workflows, validated against official BPS publications.

Quick Start

import statskita as sk

# Load SAKERNAS data
df = sk.load_sakernas("sakernas_2024.sav")

# Wrangle and harmonize
clean_df = sk.wrangle(df, harmonize=True, source_wave="2024")

# Declare existing survey design
spec = sk.declare_survey(clean_df, weight="survey_weight")

# Calculate indicators
results = sk.calculate_indicators(spec, ["lfpr", "unemployment_rate"])

Installation

pip install statskita

Features

• Complex survey data loading with proper weights and design
• Cross-wave harmonization for longitudinal analysis
• Labor force indicator calculations (Labour Force Participation Rate, Unemployment Rate, etc.)
• Export to multiple formats (Stata, Excel, Parquet)
• Fast processing with Polars backend

See examples/ directory for detailed usage.