microdf-python 0.4.5__tar.gz → 1.0.0__tar.gz

microdf_python-1.0.0/PKG-INFO

@@ -0,0 +1,75 @@
+Metadata-Version: 2.4
+Name: microdf-python
+Version: 1.0.0
+Summary: Weighted pandas DataFrames and Series for survey microdata
+Author-email: Max Ghenis <max@ubicenter.org>
+License: MIT
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: pandas
+Provides-Extra: dev
+Requires-Dist: codecov; extra == "dev"
+Requires-Dist: flake8; extra == "dev"
+Requires-Dist: flake8-pyproject; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: docformatter; extra == "dev"
+Requires-Dist: isort; extra == "dev"
+Requires-Dist: linecheck; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: setuptools; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: jupyter_book; extra == "docs"
+Dynamic: license-file
+
+[![Build](https://github.com/PolicyEngine/microdf/workflows/Pull%20request/badge.svg)](https://github.com/PolicyEngine/microdf/actions)
+[![Codecov](https://codecov.io/gh/PolicyEngine/microdf/branch/master/graph/badge.svg)](https://codecov.io/gh/PolicyEngine/microdf)
+
+# microdf
+Weighted pandas DataFrames and Series for survey microdata analysis.
+
+## Overview
+microdf provides `MicroDataFrame` and `MicroSeries` classes that extend pandas functionality with integrated weighting support, essential for accurate survey data analysis.
+
+## Key Features
+- **MicroDataFrame**: A pandas DataFrame with an integrated weight column
+- **MicroSeries**: A pandas Series with integrated weights
+- **Weighted operations**: All aggregations (sum, mean, median, etc.) automatically use weights
+- **Inequality metrics**: Built-in Gini coefficient calculation
+- **Poverty analysis**: Integrated poverty rate and gap calculations
+
+## Installation
+Install with:
+
+    pip install microdf-python
+
+Or for development:
+
+    pip install git+https://github.com/PolicyEngine/microdf.git
+
+## Usage
+```python
+import microdf as mdf
+import pandas as pd
+
+# Create sample data with weights
+df = pd.DataFrame({
+    'income': [10_000, 20_000, 30_000, 40_000, 50_000],
+    'weights': [1, 2, 3, 2, 1]
+})
+
+# Create a MicroDataFrame
+mdf_df = mdf.MicroDataFrame(df, weights='weights')
+
+# All operations are weight-aware
+print(mdf_df.income.mean())  # Weighted mean
+print(mdf_df.income.gini())  # Gini coefficient
+```
+
+## Questions
+Contact the maintainer, Max Ghenis (max@policyengine.org).
+
+## Citation
+You may cite the source of your analysis as "microdf release #.#.#, author's calculations."

microdf_python-1.0.0/README.md

@@ -0,0 +1,49 @@
+[![Build](https://github.com/PolicyEngine/microdf/workflows/Pull%20request/badge.svg)](https://github.com/PolicyEngine/microdf/actions)
+[![Codecov](https://codecov.io/gh/PolicyEngine/microdf/branch/master/graph/badge.svg)](https://codecov.io/gh/PolicyEngine/microdf)
+
+# microdf
+Weighted pandas DataFrames and Series for survey microdata analysis.
+
+## Overview
+microdf provides `MicroDataFrame` and `MicroSeries` classes that extend pandas functionality with integrated weighting support, essential for accurate survey data analysis.
+
+## Key Features
+- **MicroDataFrame**: A pandas DataFrame with an integrated weight column
+- **MicroSeries**: A pandas Series with integrated weights
+- **Weighted operations**: All aggregations (sum, mean, median, etc.) automatically use weights
+- **Inequality metrics**: Built-in Gini coefficient calculation
+- **Poverty analysis**: Integrated poverty rate and gap calculations
+
+## Installation
+Install with:
+
+    pip install microdf-python
+
+Or for development:
+
+    pip install git+https://github.com/PolicyEngine/microdf.git
+
+## Usage
+```python
+import microdf as mdf
+import pandas as pd
+
+# Create sample data with weights
+df = pd.DataFrame({
+    'income': [10_000, 20_000, 30_000, 40_000, 50_000],
+    'weights': [1, 2, 3, 2, 1]
+})
+
+# Create a MicroDataFrame
+mdf_df = mdf.MicroDataFrame(df, weights='weights')
+
+# All operations are weight-aware
+print(mdf_df.income.mean())  # Weighted mean
+print(mdf_df.income.gini())  # Gini coefficient
+```
+
+## Questions
+Contact the maintainer, Max Ghenis (max@policyengine.org).
+
+## Citation
+You may cite the source of your analysis as "microdf release #.#.#, author's calculations."

microdf_python-1.0.0/microdf/__init__.py

@@ -0,0 +1,14 @@
+from .microdataframe import MicroDataFrame, MicroDataFrameGroupBy
+from .microseries import MicroSeries, MicroSeriesGroupBy
+
+name = "microdf"
+__version__ = "0.1.0"
+
+__all__ = [
+    # microseries.py
+    "MicroSeries",
+    "MicroSeriesGroupBy",
+    # microdataframe.py
+    "MicroDataFrame",
+    "MicroDataFrameGroupBy",
+]

{microdf_python-0.4.5 → microdf_python-1.0.0}/microdf/tests/test_microseries_dataframe.py

@@ -105,24 +105,6 @@ def test_multiple_groupby() -> None:
     assert (df.groupby(["x", "y"]).z.sum() == np.array([5, 6])).all()
 
 
-def test_concat() -> None:
-    df1 = mdf.MicroDataFrame({"x": [1, 2]}, weights=[3, 4])
-    df2 = mdf.MicroDataFrame({"y": [5, 6]}, weights=[7, 8])
-    # Verify that pd.concat returns DataFrame (probably no way to fix this).
-    pd_long = pd.concat([df1, df2])
-    assert isinstance(pd_long, pd.DataFrame)
-    assert not isinstance(pd_long, mdf.MicroDataFrame)
-    # Verify that mdf.concat works.
-    mdf_long = mdf.concat([df1, df2])
-    assert isinstance(mdf_long, mdf.MicroDataFrame)
-    # Weights should be preserved.
-    assert mdf_long.weights.equals(pd.concat([df1.weights, df2.weights]))
-    # Verify it works horizontally too (take the first set of weights).
-    mdf_wide = mdf.concat([df1, df2], axis=1)
-    assert isinstance(mdf_wide, mdf.MicroDataFrame)
-    assert mdf_wide.weights.equals(df1.weights)
-
-
 def test_set_index() -> None:
     d = mdf.MicroDataFrame(dict(x=[1, 2, 3]), weights=[4, 5, 6])
     assert d.x.__class__ == MicroSeries

microdf_python-1.0.0/microdf_python.egg-info/PKG-INFO

@@ -0,0 +1,75 @@
+Metadata-Version: 2.4
+Name: microdf-python
+Version: 1.0.0
+Summary: Weighted pandas DataFrames and Series for survey microdata
+Author-email: Max Ghenis <max@ubicenter.org>
+License: MIT
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: pandas
+Provides-Extra: dev
+Requires-Dist: codecov; extra == "dev"
+Requires-Dist: flake8; extra == "dev"
+Requires-Dist: flake8-pyproject; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: docformatter; extra == "dev"
+Requires-Dist: isort; extra == "dev"
+Requires-Dist: linecheck; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: setuptools; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: jupyter_book; extra == "docs"
+Dynamic: license-file
+
+[![Build](https://github.com/PolicyEngine/microdf/workflows/Pull%20request/badge.svg)](https://github.com/PolicyEngine/microdf/actions)
+[![Codecov](https://codecov.io/gh/PolicyEngine/microdf/branch/master/graph/badge.svg)](https://codecov.io/gh/PolicyEngine/microdf)
+
+# microdf
+Weighted pandas DataFrames and Series for survey microdata analysis.
+
+## Overview
+microdf provides `MicroDataFrame` and `MicroSeries` classes that extend pandas functionality with integrated weighting support, essential for accurate survey data analysis.
+
+## Key Features
+- **MicroDataFrame**: A pandas DataFrame with an integrated weight column
+- **MicroSeries**: A pandas Series with integrated weights
+- **Weighted operations**: All aggregations (sum, mean, median, etc.) automatically use weights
+- **Inequality metrics**: Built-in Gini coefficient calculation
+- **Poverty analysis**: Integrated poverty rate and gap calculations
+
+## Installation
+Install with:
+
+    pip install microdf-python
+
+Or for development:
+
+    pip install git+https://github.com/PolicyEngine/microdf.git
+
+## Usage
+```python
+import microdf as mdf
+import pandas as pd
+
+# Create sample data with weights
+df = pd.DataFrame({
+    'income': [10_000, 20_000, 30_000, 40_000, 50_000],
+    'weights': [1, 2, 3, 2, 1]
+})
+
+# Create a MicroDataFrame
+mdf_df = mdf.MicroDataFrame(df, weights='weights')
+
+# All operations are weight-aware
+print(mdf_df.income.mean())  # Weighted mean
+print(mdf_df.income.gini())  # Gini coefficient
+```
+
+## Questions
+Contact the maintainer, Max Ghenis (max@policyengine.org).
+
+## Citation
+You may cite the source of your analysis as "microdf release #.#.#, author's calculations."

microdf_python-1.0.0/microdf_python.egg-info/SOURCES.txt

@@ -0,0 +1,13 @@
+LICENSE
+README.md
+pyproject.toml
+microdf/__init__.py
+microdf/microdataframe.py
+microdf/microseries.py
+microdf/tests/conftest.py
+microdf/tests/test_microseries_dataframe.py
+microdf_python.egg-info/PKG-INFO
+microdf_python.egg-info/SOURCES.txt
+microdf_python.egg-info/dependency_links.txt
+microdf_python.egg-info/requires.txt
+microdf_python.egg-info/top_level.txt

{microdf_python-0.4.5 → microdf_python-1.0.0}/microdf_python.egg-info/requires.txt

@@ -9,13 +9,9 @@ black
 docformatter
 isort
 linecheck
-pip
 pytest
 pytest-cov
 setuptools
 
 [docs]
 jupyter_book
-
-[taxcalc]
-taxcalc

{microdf_python-0.4.5 → microdf_python-1.0.0}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "microdf-python"
-version = "0.4.5"
-description = "Survey microdata as DataFrames"
+version = "1.0.0"
+description = "Weighted pandas DataFrames and Series for survey microdata"
 readme = "README.md"
 authors = [
     { name = "Max Ghenis", email = "max@ubicenter.org" }
@@ -26,7 +26,6 @@ dev = [
     "docformatter",
     "isort",
     "linecheck",
-    "pip",
     "pytest",
     "pytest-cov",
     "setuptools",
@@ -34,9 +33,6 @@ dev = [
 docs = [
     "jupyter_book",
 ]
-taxcalc = [
-    "taxcalc",
-]
 
 [tool.setuptools.packages.find]
 where = ["."]
@@ -48,7 +44,7 @@ line_length = 79
 
 [tool.black]
 line-length = 79
-target-version = ["py311"]
+target-version = ["py313"]
 
 [tool.flake8]
 max-line-length = 79

microdf_python-0.4.5/PKG-INFO

@@ -1,47 +0,0 @@
-Metadata-Version: 2.4
-Name: microdf-python
-Version: 0.4.5
-Summary: Survey microdata as DataFrames
-Author-email: Max Ghenis <max@ubicenter.org>
-License: MIT
-Requires-Python: >=3.9
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: numpy
-Requires-Dist: pandas
-Provides-Extra: dev
-Requires-Dist: codecov; extra == "dev"
-Requires-Dist: flake8; extra == "dev"
-Requires-Dist: flake8-pyproject; extra == "dev"
-Requires-Dist: black; extra == "dev"
-Requires-Dist: docformatter; extra == "dev"
-Requires-Dist: isort; extra == "dev"
-Requires-Dist: linecheck; extra == "dev"
-Requires-Dist: pip; extra == "dev"
-Requires-Dist: pytest; extra == "dev"
-Requires-Dist: pytest-cov; extra == "dev"
-Requires-Dist: setuptools; extra == "dev"
-Provides-Extra: docs
-Requires-Dist: jupyter_book; extra == "docs"
-Provides-Extra: taxcalc
-Requires-Dist: taxcalc; extra == "taxcalc"
-Dynamic: license-file
-
-[![Build](https://github.com/PSLmodels/microdf/workflows/Build%20and%20test%20[Python%203.7,%203.8,%203.9]/badge.svg)](https://github.com/PSLmodels/microdf/actions?query=workflow%3A%22Build+and+test+%5BPython+3.7%2C+3.8%2C+3.9%5D%22)
-[![Codecov](https://codecov.io/gh/PSLmodels/microdf/branch/master/graph/badge.svg)](https://codecov.io/gh/PSLmodels/microdf)
-
-# microdf
-Analysis tools for working with survey microdata as DataFrames.
-
-*Disclaimer: `MicroSeries` and `MicroDataFrame` are experimental features and may not consider weights after performing some operations. See open issues.*
-
-## Installation
-Install with:
-
-    pip install git+git://github.com/PSLmodels/microdf.git
-
-## Questions
-Contact the maintainer, Max Ghenis (mghenis@gmail.com).
-
-## Citation
-You may cite the source of your analysis as "microdf release #.#.#, author's calculations."

microdf_python-0.4.5/README.md

@@ -1,18 +0,0 @@
-[![Build](https://github.com/PSLmodels/microdf/workflows/Build%20and%20test%20[Python%203.7,%203.8,%203.9]/badge.svg)](https://github.com/PSLmodels/microdf/actions?query=workflow%3A%22Build+and+test+%5BPython+3.7%2C+3.8%2C+3.9%5D%22)
-[![Codecov](https://codecov.io/gh/PSLmodels/microdf/branch/master/graph/badge.svg)](https://codecov.io/gh/PSLmodels/microdf)
-
-# microdf
-Analysis tools for working with survey microdata as DataFrames.
-
-*Disclaimer: `MicroSeries` and `MicroDataFrame` are experimental features and may not consider weights after performing some operations. See open issues.*
-
-## Installation
-Install with:
-
-    pip install git+git://github.com/PSLmodels/microdf.git
-
-## Questions
-Contact the maintainer, Max Ghenis (mghenis@gmail.com).
-
-## Citation
-You may cite the source of your analysis as "microdf release #.#.#, author's calculations."

microdf_python-0.4.5/microdf/__init__.py

@@ -1,160 +0,0 @@
-from .agg import agg, combine_base_reform, pctchg_base_reform
-from .concat import concat
-from .constants import (
-    BENS,
-    ECI_REMOVE_COLS,
-    HOUSING_CASH_SHARE,
-    MCAID_CASH_SHARE,
-    MCARE_CASH_SHARE,
-    MED_BENS,
-    OTHER_CASH_SHARE,
-    SNAP_CASH_SHARE,
-    SSI_CASH_SHARE,
-    TANF_CASH_SHARE,
-    VET_CASH_SHARE,
-    WIC_CASH_SHARE,
-)
-from .custom_taxes import (
-    CARBON_TAX_INCIDENCE,
-    FTT_INCIDENCE,
-    VAT_INCIDENCE,
-    add_carbon_tax,
-    add_custom_tax,
-    add_ftt,
-    add_vat,
-)
-from .income_measures import cash_income, market_income, tpc_eci
-from .inequality import (
-    bottom_50_pct_share,
-    bottom_x_pct_share,
-    gini,
-    t10_b50,
-    top_0_1_pct_share,
-    top_1_pct_share,
-    top_10_pct_share,
-    top_50_pct_share,
-    top_x_pct_share,
-)
-from .io import read_stata_zip
-from .microdataframe import MicroDataFrame, MicroDataFrameGroupBy
-from .microseries import MicroSeries, MicroSeriesGroupBy
-from .poverty import (
-    deep_poverty_gap,
-    deep_poverty_rate,
-    fpl,
-    poverty_gap,
-    poverty_rate,
-    squared_poverty_gap,
-)
-from .tax import mtr, tax_from_mtrs
-from .taxcalc import (
-    add_weighted_metrics,
-    calc_df,
-    n65,
-    recalculate,
-    static_baseline_calc,
-)
-from .ubi import ubi_or_bens
-from .utils import (
-    cartesian_product,
-    dedup_list,
-    flatten,
-    listify,
-    ordinal_label,
-)
-from .weighted import (
-    add_weighted_quantiles,
-    quantile_chg,
-    weight,
-    weighted_mean,
-    weighted_median,
-    weighted_quantile,
-    weighted_sum,
-)
-
-name = "microdf"
-__version__ = "0.1.0"
-
-__all__ = [
-    # agg.py
-    "combine_base_reform",
-    "pctchg_base_reform",
-    "agg",
-    # concat.py
-    "concat",
-    # constants.py
-    "BENS",
-    "ECI_REMOVE_COLS",
-    "HOUSING_CASH_SHARE",
-    "MCAID_CASH_SHARE",
-    "MCARE_CASH_SHARE",
-    "MED_BENS",
-    "OTHER_CASH_SHARE",
-    "SNAP_CASH_SHARE",
-    "SSI_CASH_SHARE",
-    "TANF_CASH_SHARE",
-    "VET_CASH_SHARE",
-    "WIC_CASH_SHARE",
-    # custom_taxes.py
-    "CARBON_TAX_INCIDENCE",
-    "FTT_INCIDENCE",
-    "VAT_INCIDENCE",
-    "add_custom_tax",
-    "add_vat",
-    "add_carbon_tax",
-    "add_ftt",
-    # income_measures.py
-    "cash_income",
-    "tpc_eci",
-    "market_income",
-    # inequality.py
-    "gini",
-    "top_x_pct_share",
-    "bottom_x_pct_share",
-    "bottom_50_pct_share",
-    "top_10_pct_share",
-    "top_1_pct_share",
-    "top_0_1_pct_share",
-    "top_50_pct_share",
-    "t10_b50",
-    # io.py
-    "read_stata_zip",
-    # poverty.py
-    "fpl",
-    "poverty_rate",
-    "deep_poverty_rate",
-    "poverty_gap",
-    "squared_poverty_gap",
-    "deep_poverty_gap",
-    # tax.py
-    "mtr",
-    "tax_from_mtrs",
-    # taxcalc.py
-    "static_baseline_calc",
-    "add_weighted_metrics",
-    "n65",
-    "calc_df",
-    "recalculate",
-    # ubi.py
-    "ubi_or_bens",
-    # utils.py
-    "ordinal_label",
-    "dedup_list",
-    "listify",
-    "flatten",
-    "cartesian_product",
-    # weighted.py
-    "weight",
-    "weighted_sum",
-    "weighted_mean",
-    "weighted_quantile",
-    "weighted_median",
-    "add_weighted_quantiles",
-    "quantile_chg",
-    # microseries.py
-    "MicroSeries",
-    "MicroSeriesGroupBy",
-    # microdataframe.py
-    "MicroDataFrame",
-    "MicroDataFrameGroupBy",
-]

microdf_python-0.4.5/microdf/_optional.py

@@ -1,85 +0,0 @@
-import distutils.version
-import importlib
-import types
-import warnings
-from typing import Optional, Union
-
-# Adapted from:
-# https://github.com/pandas-dev/pandas/blob/master/pandas/compat/_optional.py
-
-VERSIONS = {
-    "taxcalc": "2.0.0",
-}
-
-
-def _get_version(module: types.ModuleType) -> str:
-    """
-
-    :param module: types.ModuleType:
-    :param module: types.ModuleType:
-
-    """
-    version = getattr(module, "__version__", None)
-    if version is None:
-        # xlrd uses a capitalized attribute name
-        version = getattr(module, "__VERSION__", None)
-
-    if version is None:
-        raise ImportError(f"Can't determine version for {module.__name__}")
-    return version
-
-
-def import_optional_dependency(
-    name: str,
-    extra: Optional[str] = "",
-    raise_on_missing: Optional[bool] = True,
-    on_version: Optional[str] = "raise",
-) -> Union[types.ModuleType, None]:
-    """Import an optional dependency. By default, if a dependency is missing an
-    ImportError with a nice message will be raised. If a dependency is present,
-    but too old, we raise.
-
-    :param name: The module name. This should be top-level only, so that the
-        version may be checked.
-    :type name: str
-    :param extra: Additional text to include in the ImportError message.
-    :type extra: str
-    :param raise_on_missing: Whether to raise if the optional dependency is
-        not found. When False and the module is not present, None is returned.
-    :type raise_on_missing: bool, default True
-    :param on_version: What to do when a dependency's version is too old.
-        * raise : Raise an ImportError
-        * warn : Warn that the version is too old. Returns None
-        * ignore: Return the module, even if the version is too old.
-          It's expected that users validate the version locally when
-    :type on_version: str {'raise', 'warn'}
-    """
-    msg = (
-        f"Missing optional dependency '{name}'. {extra} "
-        f"Use pip or conda to install {name}."
-    )
-    try:
-        module = importlib.import_module(name)
-    except ImportError:
-        if raise_on_missing:
-            raise ImportError(msg) from None
-        else:
-            return None
-
-    minimum_version = VERSIONS.get(name)
-    if minimum_version:
-        version = _get_version(module)
-        if distutils.version.LooseVersion(version) < minimum_version:
-            assert on_version in {"warn", "raise", "ignore"}
-            msg = (
-                f"microdf requires version '{minimum_version}' or newer of "
-                f"'{name}' "
-                f"(version '{version}' currently installed)."
-            )
-            if on_version == "warn":
-                warnings.warn(msg, UserWarning)
-                return None
-            elif on_version == "raise":
-                raise ImportError(msg)
-
-    return module