microdf-python 0.3.0__tar.gz → 0.4.4__tar.gz

microdf_python-0.4.4/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2019 Max Ghenis
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

microdf_python-0.4.4/PKG-INFO

@@ -0,0 +1,25 @@
+Metadata-Version: 2.4
+Name: microdf-python
+Version: 0.4.4
+Summary: Survey microdata as DataFrames.
+Home-page: http://github.com/PSLmodels/microdf
+Author: Max Ghenis
+Author-email: max@ubicenter.org
+License: MIT
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: pandas
+Provides-Extra: taxcalc
+Requires-Dist: taxcalc; extra == "taxcalc"
+Provides-Extra: charts
+Requires-Dist: seaborn; extra == "charts"
+Requires-Dist: matplotlib; extra == "charts"
+Requires-Dist: matplotlib-label-lines; extra == "charts"
+Dynamic: author
+Dynamic: author-email
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: summary

{microdf-python-0.3.0 → microdf_python-0.4.4}/microdf/chart_utils.py

@@ -1,6 +1,3 @@
-import matplotlib as mpl
-
-
 def dollar_format(suffix=""):
     """Dollar formatter for matplotlib.
 
@@ -19,6 +16,14 @@ def currency_format(currency="USD", suffix=""):
     :returns: FuncFormatter.
 
     """
+    try:
+        import matplotlib as mpl
+    except ImportError:
+        raise ImportError(
+            "The function you've called requires extra dependencies. " +
+            "Please install microdf with the 'charts' extra by running " +
+            "'pip install microdf[charts]'"
+        )
 
     prefix = {"USD": "$", "GBP": "£"}[currency]
 

{microdf-python-0.3.0 → microdf_python-0.4.4}/microdf/charts.py

@@ -1,7 +1,4 @@
-import matplotlib as mpl
-import matplotlib.pyplot as plt
 import numpy as np
-import seaborn as sns
 
 import microdf as mdf
 
@@ -19,6 +16,17 @@ def quantile_pct_chg_plot(df1, df2, col1, col2, w1=None, w2=None, q=None):
     :returns: Axis.
 
     """
+    try:
+        import seaborn as sns
+        import matplotlib as mpl
+        import matplotlib.pyplot as plt
+    except ImportError:
+        raise ImportError(
+            "The function you've called requires extra dependencies. " +
+            "Please install microdf with the 'charts' extra by running " +
+            "'pip install microdf[charts]'"
+        )
+
     if q is None:
         q = np.arange(0.1, 1, 0.1)
     # Calculate weighted quantiles.
@@ -34,7 +42,7 @@ def quantile_pct_chg_plot(df1, df2, col1, col2, w1=None, w2=None, q=None):
     # Plot.
     fig, ax = plt.subplots()
     markerline, stemlines, baseline = ax.stem(
-        df.index_newline, df.pct_chg, use_line_collection=True
+        df.index_newline, df.pct_chg
     )
     plt.setp(baseline, color="gray", linewidth=0)
     ax.yaxis.set_major_locator(mpl.ticker.MaxNLocator(integer=True))

{microdf-python-0.3.0 → microdf_python-0.4.4}/microdf/generic.py

@@ -251,23 +251,24 @@ class MicroSeries(pd.Series):
         ranks = np.array(self.weights.values)[order].cumsum()[inverse_order]
         if pct:
             ranks /= self.weights.values.sum()
+            np.where(ranks > 1.0, 1.0, ranks)
         return pd.Series(ranks, index=self.index)
 
     @vector_function
     def decile_rank(self):
-        return MicroSeries(np.ceil(self.rank(pct=True) * 10))
+        return MicroSeries(np.minimum(np.ceil(self.rank(pct=True) * 10), 10))
 
     @vector_function
     def quintile_rank(self):
-        return MicroSeries(np.ceil(self.rank(pct=True) * 5))
+        return MicroSeries(np.minimum(np.ceil(self.rank(pct=True) * 5), 5))
 
     @vector_function
     def quartile_rank(self):
-        return MicroSeries(np.ceil(self.rank(pct=True) * 4))
+        return MicroSeries(np.minimum(np.ceil(self.rank(pct=True) * 4), 4))
 
     @vector_function
     def percentile_rank(self):
-        return MicroSeries(np.ceil(self.rank(pct=True) * 100))
+        return MicroSeries(np.minimum(np.ceil(self.rank(pct=True) * 100), 100))
 
     def groupby(self, *args, **kwargs):
         gb = super().groupby(*args, **kwargs)
@@ -319,6 +320,48 @@ class MicroSeries(pd.Series):
     def __pow__(self, other):
         return MicroSeries(super().__pow__(other), weights=self.weights)
 
+    def __xor__(self, other):
+        return MicroSeries(super().__xor__(other), weights=self.weights)
+
+    def __and__(self, other):
+        return MicroSeries(super().__and__(other), weights=self.weights)
+
+    def __or__(self, other):
+        return MicroSeries(super().__or__(other), weights=self.weights)
+
+    def __invert__(self):
+        return MicroSeries(super().__invert__(), weights=self.weights)
+
+    def __radd__(self, other):
+        return MicroSeries(super().__radd__(other), weights=self.weights)
+
+    def __rsub__(self, other):
+        return MicroSeries(super().__rsub__(other), weights=self.weights)
+
+    def __rmul__(self, other):
+        return MicroSeries(super().__rmul__(other), weights=self.weights)
+
+    def __rfloordiv__(self, other):
+        return MicroSeries(super().__rfloordiv__(other), weights=self.weights)
+
+    def __rtruediv__(self, other):
+        return MicroSeries(super().__rtruediv__(other), weights=self.weights)
+
+    def __rmod__(self, other):
+        return MicroSeries(super().__rmod__(other), weights=self.weights)
+
+    def __rpow__(self, other):
+        return MicroSeries(super().__rpow__(other), weights=self.weights)
+
+    def __rand__(self, other):
+        return MicroSeries(super().__rand__(other), weights=self.weights)
+
+    def __ror__(self, other):
+        return MicroSeries(super().__ror__(other), weights=self.weights)
+
+    def __rxor__(self, other):
+        return MicroSeries(super().__rxor__(other), weights=self.weights)
+
     # comparators
 
     def __lt__(self, other):
@@ -661,7 +704,9 @@ class MicroDataFrame(pd.DataFrame):
 
     @get_args_as_micro_series()
     def groupby(self, by: Union[str, list], *args, **kwargs):
-        """Returns a GroupBy object with MicroSeriesGroupBy objects for each column
+        """
+        Returns a GroupBy object with MicroSeriesGroupBy objects for
+        each column
 
         :param by: column to group by
         :type by: Union[str, list]
@@ -766,7 +811,9 @@ class MicroDataFrame(pd.DataFrame):
         income: Union[MicroSeries, str],
         threshold: Union[MicroSeries, str],
     ) -> int:
-        """Calculates the number of entities with income below a poverty threshold.
+        """
+        Calculates the number of entities with income below a poverty
+        threshold.
 
         :param income: income array or column name
         :type income: Union[MicroSeries, str]

{microdf-python-0.3.0 → microdf_python-0.4.4}/microdf/io.py

@@ -1,9 +1,15 @@
 import io
 import zipfile
-from urllib.request import urlopen
-
+import requests
 import pandas as pd
 
+HEADER = {
+    "User-Agent":
+    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) " +
+    "AppleWebKit/537.36 (KHTML, like Gecko) " +
+    "Chrome/50.0.2661.102 Safari/537.36"
+    }
+
 
 def read_stata_zip(url: str, **kwargs) -> pd.DataFrame:
     """Reads zipped Stata file by URL.
@@ -19,8 +25,8 @@ def read_stata_zip(url: str, **kwargs) -> pd.DataFrame:
     :returns: DataFrame.
 
     """
-    with urlopen(url) as request:
-        data = io.BytesIO(request.read())
+    r = requests.get(url, headers=HEADER)
+    data = io.BytesIO(r.content)
     with zipfile.ZipFile(data) as archive:
         with archive.open(archive.namelist()[0]) as stata:
             return pd.read_stata(stata, **kwargs)

{microdf-python-0.3.0 → microdf_python-0.4.4}/microdf/style.py

@@ -1,8 +1,3 @@
-import matplotlib as mpl
-import matplotlib.font_manager as fm
-import seaborn as sns
-
-
 TITLE_COLOR = "#212121"
 AXIS_COLOR = "#757575"
 GRID_COLOR = "#eeeeee"  # Previously lighter #f5f5f5.
@@ -16,6 +11,16 @@ def set_plot_style(dpi: int = DPI):
         (200).
     :type dpi: int, optional
     """
+    try:
+        import seaborn as sns
+        import matplotlib as mpl
+        import matplotlib.font_manager as fm
+    except ImportError:
+        raise ImportError(
+            "The function you've called requires extra dependencies. " +
+            "Please install microdf with the 'charts' extra by running " +
+            "'pip install microdf[charts]'"
+        )
 
     sns.set_style("white")
 

microdf_python-0.4.4/microdf_python.egg-info/PKG-INFO

@@ -0,0 +1,25 @@
+Metadata-Version: 2.4
+Name: microdf-python
+Version: 0.4.4
+Summary: Survey microdata as DataFrames.
+Home-page: http://github.com/PSLmodels/microdf
+Author: Max Ghenis
+Author-email: max@ubicenter.org
+License: MIT
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: pandas
+Provides-Extra: taxcalc
+Requires-Dist: taxcalc; extra == "taxcalc"
+Provides-Extra: charts
+Requires-Dist: seaborn; extra == "charts"
+Requires-Dist: matplotlib; extra == "charts"
+Requires-Dist: matplotlib-label-lines; extra == "charts"
+Dynamic: author
+Dynamic: author-email
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: summary

{microdf-python-0.3.0 → microdf_python-0.4.4}/microdf_python.egg-info/SOURCES.txt

@@ -1,3 +1,4 @@
+LICENSE
 README.md
 setup.py
 microdf/__init__.py

{microdf-python-0.3.0 → microdf_python-0.4.4}/microdf_python.egg-info/requires.txt

@@ -1,8 +1,10 @@
-matplotlib
-matplotlib-label-lines
 numpy
 pandas
+
+[charts]
 seaborn
+matplotlib
+matplotlib-label-lines
 
 [taxcalc]
 taxcalc

{microdf-python-0.3.0 → microdf_python-0.4.4}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
     name="microdf-python",
-    version="0.3.0",
+    version="0.4.4",
     description="Survey microdata as DataFrames.",
     url="http://github.com/PSLmodels/microdf",
     author="Max Ghenis",
@@ -10,12 +10,16 @@ setup(
     license="MIT",
     packages=["microdf"],
     install_requires=[
-        "matplotlib",
-        "matplotlib-label-lines",
         "numpy",
         "pandas",
-        "seaborn",
     ],
-    extras_require={"taxcalc": ["taxcalc"]},
+    extras_require={
+      "taxcalc": ["taxcalc"],
+      "charts": [
+        "seaborn",
+        "matplotlib",
+        "matplotlib-label-lines"
+      ]
+    },
     zip_safe=False,
 )

microdf-python-0.3.0/PKG-INFO

@@ -1,11 +0,0 @@
-Metadata-Version: 2.1
-Name: microdf-python
-Version: 0.3.0
-Summary: Survey microdata as DataFrames.
-Home-page: http://github.com/PSLmodels/microdf
-Author: Max Ghenis
-Author-email: max@ubicenter.org
-License: MIT
-Description: UNKNOWN
-Platform: UNKNOWN
-Provides-Extra: taxcalc

microdf-python-0.3.0/microdf_python.egg-info/PKG-INFO

@@ -1,11 +0,0 @@
-Metadata-Version: 2.1
-Name: microdf-python
-Version: 0.3.0
-Summary: Survey microdata as DataFrames.
-Home-page: http://github.com/PSLmodels/microdf
-Author: Max Ghenis
-Author-email: max@ubicenter.org
-License: MIT
-Description: UNKNOWN
-Platform: UNKNOWN
-Provides-Extra: taxcalc