edaprep good first issues (Python)

Wire up Stage.FEATURE_ENGINEERING, currently a reserved no-op about 1 month ago

enhancement help wanted planner

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Duplicate-column, sentinel, whitespace and case-variant detection run on the profiling sample, not the full frame about 1 month ago

bug help wanted profiling

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Plan.without_columns silently drops MISSING/SCALE steps for every column, not just the ones removed about 1 month ago

bug help wanted planner

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Add IsolationForest as an optional outlier detector about 1 month ago

help wanted good first issue transformer

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

TargetEncoder's out-of-fold encoding leaks through a shared global prior about 2 months ago

bug help wanted transformer leakage-safety

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

DataTypeInference's 'stripped' journal count is inflated by every missing value in the column about 2 months ago

bug good first issue transformer

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Add KNN and iterative imputation behind the [advanced] extra about 2 months ago

help wanted good first issue transformer

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

backends/ is exported from the public API and imported by nothing about 2 months ago

help wanted planner backend

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

_rule_impute's rationale is wrong when imputation is planned only because outlier_strategy='impute' may introduce NaN about 2 months ago

bug good first issue planner

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

TextColumnHandler's length_features treats missing text as the string 'nan' instead of missing about 2 months ago

bug good first issue transformer

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

DateTimeExpander's boolean calendar features turn a missing date into False instead of missing about 2 months ago

bug good first issue transformer

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

OrdinalEncoder's dtype parameter is stored but never applied about 2 months ago

bug help wanted transformer

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Config.from_dict doesn't tolerate retired Thresholds or per-column settings, only top-level ones about 2 months ago

bug good first issue

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

missing_fraction in params means two different things depending on the rule about 2 months ago

help wanted good first issue planner

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Implement binary (base-N) categorical encoding about 2 months ago

help wanted good first issue transformer

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Report test coverage in CI 2 months ago

help wanted good first issue docs

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Enforce `ruff format` instead of running it advisory-only 2 months ago

good first issue docs

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Text columns are detected and dropped; add optional vectorisation 2 months ago

enhancement help wanted transformer

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Implement a Polars or Arrow backend 2 months ago

enhancement help wanted performance backend

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Export a fitted Plan as a scikit-learn ColumnTransformer 2 months ago

enhancement help wanted sklearn-interop

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Check in a reproducible benchmark for per-column loop parallelism 2 months ago

documentation help wanted performance

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Missing-indicator and high-missing rules do not see cast-introduced gaps 2 months ago

bug help wanted good first issue

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

Config.n_jobs is accepted but never used 2 months ago

help wanted good first issue performance

bijay-odyssey/edaprep

0

Transparent, leakage-safe EDA and ML preprocessing for pandas, with an explainable planner that shows its reasoning.

Python

#data-cleaning#data-quality#data-science#eda#exploratory-data-analysis#feature-engineering#machine-learning#pandas#preprocessing#python

bijay-odyssey/edaprep

Open Issues Need Help