Initial code commit

Author: jseabold

.gitignore

@@ -0,0 +1,138 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/

dev-requirements.txt

@@ -0,0 +1,3 @@
+flake8
+pytest
+pytest-cov

pandas_select/__init__.py

@@ -0,0 +1,230 @@
+import inspect
+import operator
+from functools import wraps
+
+import pandas as pd
+from pandas.core.accessor import CachedAccessor
+from pandas.core.indexes.accessors import (CombinedDatetimelikeProperties,
+                                           DatetimeProperties,
+                                           PeriodProperties)
+from pandas.core.strings import StringMethods
+from pandas.util._decorators import doc
+
+_str_boolean_methods = set([
+    'contains',
+    'endswith',
+    'isalnum',
+    'isalpha',
+    'isdecimal',
+    'isdigit',
+    'islower',
+    'isnumeric',
+    'isspace',
+    'istitle',
+    'isupper',
+    'match',
+    'startswith',
+])
+
+_date_boolean_methods = set([
+    'is_leap_year',
+    'is_month_end',
+    'is_month_start',
+    'is_quarter_end',
+    'is_quarter_start',
+    'is_year_end',
+    'is_year_start',
+])
+
+
+class StringSelectMethods(StringMethods):
+    def __init__(self, *args, **kwargs):
+        frame_or_series = args[0]
+
+        # the superclass will override _parent, so we need to use _parent_frame
+        self._parent_frame = frame_or_series._parent
+        self._series = frame_or_series._series
+        super().__init__(self._series, *args[1:], **kwargs)
+
+    def __getattribute__(self, attr):
+        if (not attr.startswith("_") and  # noqa
+                inspect.isroutine(getattr(StringMethods, attr, None))
+            and attr not in _str_boolean_methods):  # noqa
+            raise NotImplementedError("Boolean selection with this method "
+                                      "does not make sense.")
+        else:
+            return super().__getattribute__(attr)
+
+    def _wrap_result(self, *args, **kwargs):
+        # remove methods that don't return boolean index
+        bool_idx = super()._wrap_result(*args, **kwargs)
+        return self._parent_frame.loc[bool_idx]
+
+
+class SelectDatetimeProperties(DatetimeProperties):
+    def __init__(self, parent, *args, **kwargs):
+        # datetime properties holds an attribute _parent
+        # we need to add the parent_frame (or series) to the subclass instances
+        self._parent_frame = parent
+        super().__init__(*args, **kwargs)
+
+    def __getattribute__(self, attr):
+        if (not attr.startswith("_") and  # noqa
+                inspect.isroutine(getattr(DatetimeProperties, attr, None))
+            and attr not in _date_boolean_methods): # noqa
+            raise NotImplementedError("Boolean selection with this method "
+                                      "does not make sense.")
+        elif attr in _date_boolean_methods:
+            idx = super().__getattribute__(attr)
+            return self._parent_frame.loc[idx]
+        else:
+            return super().__getattribute__(attr)
+
+
+class SelectPeriodProperties(PeriodProperties):
+    def __init__(self, parent, *args, **kwargs):
+        self._parent_frame = parent
+        super().__init__(*args, **kwargs)
+
+    @property
+    def is_leap_year(self):
+        return self._parent_frame.loc[super().is_leap_year]
+
+
+class DateSelectMethods(CombinedDatetimelikeProperties):
+    def __new__(cls, series):
+        properties = super().__new__(cls, series._series)
+        if isinstance(properties, DatetimeProperties):
+            return SelectDatetimeProperties(
+                series._parent,
+                properties._parent,
+                properties.orig)
+        elif isinstance(properties, PeriodProperties):
+            return SelectPeriodProperties(
+                series._frame,
+                properties._parent,
+                properties.orig
+            )
+        raise AttributeError("Can only use select.dt accessor on"
+                             "datetimelike and periodlike values.")
+
+
+def selector_wrapper(klass, method_name):
+    method = getattr(klass, method_name)
+
+    @wraps(method)
+    def selector(self, *args, **kwargs):
+        # for a series accessor series and parent are the same thing
+        # for a frame accessor we're indexing on the parent dataframe
+        series = self._series
+        idx = getattr(klass, method_name)(series, *args, **kwargs)
+        return self._parent.loc[idx]
+    return selector
+
+
+class SelectableIndex:
+    def __init__(self, parent):
+        self._parent = parent
+        self._index = parent.index
+
+    def __getattr__(self, attr):
+        return getattr(self._index, attr)
+
+    def __repr__(self):
+        return pd.Index.__repr__(self)
+
+    def _compare(self, op, cmp):
+        idx = op(self._parent.index, cmp)
+        return self._parent.loc[idx]
+
+    def __lt__(self, cmp):
+        return self._compare(operator.lt, cmp)
+
+    def __le__(self, cmp):
+        return self._compare(operator.le, cmp)
+
+    def __eq__(self, cmp):
+        return self._compare(operator.eq, cmp)
+
+    def __ne__(self, cmp):
+        return self._compare(operator.ne, cmp)
+
+    def __gt__(self, cmp):
+        return self._compare(operator.gt, cmp)
+
+    def __ge__(self, cmp):
+        return self._compare(operator.ge, cmp)
+
+    @doc(pd.Index.isna)
+    def isna(self):
+        return self._parent.loc[self._parent.index.isna()]
+
+    @doc(pd.Index.isnull)
+    def isnull(self):
+        return self._parent.loc[self._parent.index.isnull()]
+
+    @doc(pd.Index.isin)
+    def isin(self, values, levels=None):
+        idx = self._parent.index.isin(values, levels)
+        return self._parent.loc[idx]
+
+
+@pd.api.extensions.register_series_accessor("select")
+class SelectableColumn:
+    str = CachedAccessor("str", StringSelectMethods)
+    dt = CachedAccessor("dt", DateSelectMethods)
+
+    __lt__ = selector_wrapper(pd.Series, "__lt__")
+    __le__ = selector_wrapper(pd.Series, "__le__")
+    __eq__ = selector_wrapper(pd.Series, "__eq__")
+    __ne__ = selector_wrapper(pd.Series, "__ne__")
+    __gt__ = selector_wrapper(pd.Series, "__gt__")
+    __ge__ = selector_wrapper(pd.Series, "__ge__")
+    isna = selector_wrapper(pd.Series, "isna")
+    isnull = selector_wrapper(pd.Series, "isnull")
+    isin = selector_wrapper(pd.Series, "isin")
+
+    def __init__(self, parent, series=None):
+        # if accessed as the series accessor, parent is the series
+        # if returned by a selectable dataframe, parent is the frame
+        if series is None:
+            series = parent
+        self._parent = parent
+        self._series = series
+
+    def __getattr__(self, attr):
+        return getattr(self._series, attr)
+
+    def __repr__(self):
+        return pd.Series.__repr__(self)
+
+    @property
+    def index(self):
+        return SelectableIndex(self._parent)
+
+
+@pd.api.extensions.register_dataframe_accessor('select')
+class DataFrameSelectAccessor:
+    def __init__(self, frame):
+        self._frame = frame
+
+    def __repr__(self):
+        return pd.DataFrame.__repr__(self)
+
+    def __dir__(self):
+        return self._frame.columns.tolist() + ['index']
+
+    def __getattr__(self, attr):
+        if attr in self._frame.columns:
+            return SelectableColumn(self._frame, self._frame[attr])
+        return getattr(self._frame, attr)
+
+    def __getitem__(self, key):
+        try:
+            getattr(self, key)
+        except AttributeError:
+            raise KeyError(f"{key}")
+
+    @property
+    def index(self):
+        return SelectableIndex(self._frame)

pandas_select/tests/conftest.py

@@ -0,0 +1,13 @@
+import numpy as np
+import pandas as pd
+import pytest
+
+
+@pytest.fixture
+def dta():
+    return pd.DataFrame.from_dict({
+        'A': np.arange(1, 16),
+        'B': pd.date_range('2020-01-01', periods=15),
+        'C': ['A', 'B', 'C'] * 5,
+        'D': pd.Categorical(['A', 'B', 'C'] * 5)
+    })