tea-tasting 0.5.0

What's Changed

Breaking changes

• Change defaults: assume non-negative correlation between hypotheses by @e10v in #131
• Set upper boundary for fixed point number formatting… by @e10v in #132

Other changes

• Update docs by @e10v in #130

Full Changelog: v0.4.3...v0.5.0

tea-tasting 0.4.3

What's Changed

• Improve copy to clipboard by @e10v in #125
• Configure scripts by @e10v in #126
• Strip doctest artifacts in docs by @e10v in #127
• Ignore .pdm-build by @e10v in #128
• Update docs and readme by @e10v in #129

Full Changelog: v0.4.2...v0.4.3

tea-tasting 0.4.2

What's Changed

• Change docs fonts by @e10v in #120
• Convert examples to pycon with prompts and add doctest to CI by @e10v in #121
• Round revenue to 2 decimals by @e10v in #122
• Configure scripts by @e10v in #123
• Update dependencies by @e10v in #124

Full Changelog: v0.4.1...v0.4.2

tea-tasting 0.4.1

What's Changed

• Fix: use 1D array if columns is a single string by @e10v in #116
• Fix: sort variants by @e10v in #117
• Add link to release notes by @e10v in #118
• Update badges by @e10v in #119

Full Changelog: v0.4.0...v0.4.1

tea-tasting 0.4.0

What's Changed

• Switch to PyArrow for internal data and remove Pandas dependency by @e10v in #114

Breaking changes

• Pandas is not automatically installed with tea-tasting anymore. Install it explicitly to export an analysis result using to_pandas method.
• The methods make_users_data and make_sessions_data now return a PyArrow Table by default. You can control the return type by using the return_type parameter. The other possible output types are a Pandas DataFrame or a Polars DataFrame. They require Pandas or Polars packages, respectively.

Enhancements

• Switching from Pandas to PyArrow for internal data can speed up calculations in some use cases.
• You can export an analysis result to a PyArrow Table using the to_arrow method.
• You can export an analysis result to a Polars DataFrame using the to_polars method. Polars is not installed automatically. Install it explicitly to use methods that return a Polars DataFrame.
• The methods make_users_data and make_sessions_data can return a Polars DataFrame. Use the return_type parameter.

Full Changelog: v0.3.1...v0.4.0

tea-tasting 0.3.1

What's Changed

• Update docs and readme by @e10v in #109
• Optimize aggregations for pandas-like dataframes by @e10v in #110
• Remove dependencies upper bounds and update versions by @e10v in #111
• Update CI workflow by @e10v in #112
• Update roadmap by @e10v in #113

Full Changelog: v0.3.0...v0.3.1

tea-tasting 0.3.0

What's Changed

Breaking changes

• Delete to_ibis parameter from make_users_data and make_sessions_data by @e10v in #103

Enhancements

• Support more dataframes with Narwhals by @e10v in #102, #104, #105, and #107

Fixes

• Return nan when dividing negative number by zero by @e10v in #106

Full Changelog: v0.2.0...v0.3.0

tea-tasting 0.2.0

What's Changed

• Multiple hypothesis testing by @e10v in #87, #91, #92, and #97
• Cast to float before aggregation by @e10v in #93
• Update docs and readme by @e10v in #85, #95, and #99
• Replace pandas backend usage with ibis.memtable by @e10v in #90
• Support pretty formatting for ExperimentResults by @e10v in #94
• Update versions by @e10v in #96 and #100
• Other minor changes by @e10v in #86

Full Changelog: v0.1.0...v0.2.0

tea-tasting 0.1.0

What's Changed

tea-tasting is currently in beta. However, I consider it ready for important tasks and use it for the analysis of switchback experiments in my work.

• Analysis of power for RatioOfMeans and Mean by @e10v in #68, #70, #71, #72, #75, and #76
• Fix: make sure that k and n for binomtest are integer by @e10v in #73
• Create a guide on how to use tea-tasting with an arbitrary data backend by @e10v in #79
• Create a guide on custom metrics by @e10v in #81
• Update user guides, docstrings, and readme by @e10v in #77, #78, #80, and #82
• Other minor changes by @e10v in #74 and #83

Full Changelog: v0.0.5...v0.1.0

tea-tasting 0.0.5

What's Changed

• Analysis of a statistic using bootstrap resampling by @e10v in #64
• Analysis of quantiles using bootstrap resampling by @e10v in #65
• Update docs by @e10v in #63 and #67

Full Changelog: v0.0.4...v0.0.5