CLN: reorg type inference & introspection

closes pandas-dev#12503

Author: Jeff Reback <[email protected]>

Closes pandas-dev#13147 from jreback/types and squashes the following commits:

244649a [Jeff Reback] CLN: reorg type inference & introspection

Author: jreback

ci/lint.sh

@@ -8,7 +8,7 @@ RET=0
 
 if [ "$LINT" ]; then
     echo "Linting"
-    for path in 'core' 'indexes' 'types' 'formats' 'io' 'stats' 'compat' 'sparse' 'tools' 'tseries' 'tests' 'computation' 'util'
+    for path in 'api' 'core' 'indexes' 'types' 'formats' 'io' 'stats' 'compat' 'sparse' 'tools' 'tseries' 'tests' 'computation' 'util'
     do
         echo "linting -> pandas/$path"
         flake8 pandas/$path --filename '*.py'

doc/source/whatsnew/v0.19.0.txt

@@ -10,6 +10,7 @@ users upgrade to this version.
 Highlights include:
 
 - :func:`merge_asof` for asof-style time-series joining, see :ref:`here <whatsnew_0190.enhancements.asof_merge>`
+- pandas development api, see :ref:`here <whatsnew_0190.dev_api>`
 
 .. contents:: What's new in v0.18.2
     :local:
@@ -20,6 +21,25 @@ Highlights include:
 New features
 ~~~~~~~~~~~~
 
+.. _whatsnew_0190.dev_api:
+
+pandas development API
+^^^^^^^^^^^^^^^^^^^^^^
+
+As part of making pandas APi more uniform and accessible in the future, we have created a standard
+sub-package of pandas, ``pandas.api`` to hold public API's. We are starting by exposing type
+introspection functions in ``pandas.api.types``. More sub-packages and officially sanctioned API's
+will be published in future versions of pandas.
+
+The following are now part of this API:
+
+.. ipython:: python
+
+   import pprint
+   from pandas.api import types
+   funcs = [ f for f in dir(types) if not f.startswith('_') ]
+   pprint.pprint(funcs)
+
 .. _whatsnew_0190.enhancements.asof_merge:
 
 :func:`merge_asof` for asof-style time-series joining
@@ -227,7 +247,7 @@ Other enhancements
 - Consistent with the Python API, ``pd.read_csv()`` will now interpret ``+inf`` as positive infinity (:issue:`13274`)
 - The ``DataFrame`` constructor will now respect key ordering if a list of ``OrderedDict`` objects are passed in (:issue:`13304`)
 - ``pd.read_html()`` has gained support for the ``decimal`` option (:issue:`12907`)
-- A top-level function :func:`union_categorical` has been added for combining categoricals, see :ref:`Unioning Categoricals<categorical.union>` (:issue:`13361`)
+- A function :func:`union_categorical` has been added for combining categoricals, see :ref:`Unioning Categoricals<categorical.union>` (:issue:`13361`)
 - ``Series`` has gained the properties ``.is_monotonic``, ``.is_monotonic_increasing``, ``.is_monotonic_decreasing``, similar to ``Index`` (:issue:`13336`)
 
 .. _whatsnew_0190.api:

pandas/__init__.py

@@ -16,7 +16,7 @@
 
 if missing_dependencies:
     raise ImportError("Missing required dependencies {0}".format(missing_dependencies))
-
+del hard_dependencies, dependency, missing_dependencies
 
 # numpy compat
 from pandas.compat.numpy import *

pandas/api/__init__.py

@@ -0,0 +1 @@
+""" public toolkit API """

pandas/api/tests/__init__.py

@@ -0,0 +1,213 @@
+# -*- coding: utf-8 -*-
+
+import pandas as pd
+from pandas.core import common as com
+from pandas import api
+from pandas.api import types
+from pandas.util import testing as tm
+
+_multiprocess_can_split_ = True
+
+
+class Base(object):
+
+    def check(self, namespace, expected, ignored=None):
+        # see which names are in the namespace, minus optional
+        # ignored ones
+        # compare vs the expected
+
+        result = sorted([f for f in dir(namespace) if not f.startswith('_')])
+        if ignored is not None:
+            result = sorted(list(set(result) - set(ignored)))
+
+        expected = sorted(expected)
+        tm.assert_almost_equal(result, expected)
+
+
+class TestPDApi(Base, tm.TestCase):
+
+    # these are optionally imported based on testing
+    # & need to be ignored
+    ignored = ['tests', 'rpy', 'sandbox', 'locale']
+
+    # top-level sub-packages
+    lib = ['api', 'compat', 'computation', 'core',
+           'indexes', 'formats', 'pandas',
+           'test', 'tools', 'tseries',
+           'types', 'util', 'options', 'io']
+
+    # top-level packages that are c-imports, should rename to _*
+    # to avoid naming conflicts
+    lib_to_rename = ['algos', 'hashtable', 'tslib', 'msgpack', 'sparse',
+                     'json', 'lib', 'index', 'parser']
+
+    # these are already deprecated; awaiting removal
+    deprecated_modules = ['ols', 'stats']
+
+    # misc
+    misc = ['IndexSlice', 'NaT']
+
+    # top-level classes
+    classes = ['Categorical', 'CategoricalIndex', 'DataFrame', 'DateOffset',
+               'DatetimeIndex', 'ExcelFile', 'ExcelWriter', 'Float64Index',
+               'Grouper', 'HDFStore', 'Index', 'Int64Index', 'MultiIndex',
+               'Period', 'PeriodIndex', 'RangeIndex',
+               'Series', 'SparseArray', 'SparseDataFrame',
+               'SparseSeries', 'TimeGrouper', 'Timedelta',
+               'TimedeltaIndex', 'Timestamp']
+
+    # these are already deprecated; awaiting removal
+    deprecated_classes = ['SparsePanel', 'TimeSeries', 'WidePanel',
+                          'SparseTimeSeries']
+
+    # these should be deperecated in the future
+    deprecated_classes_in_future = ['Panel', 'Panel4D',
+                                    'SparseList', 'Term']
+
+    # these should be removed from top-level namespace
+    remove_classes_from_top_level_namespace = ['Expr']
+
+    # external modules exposed in pandas namespace
+    modules = ['np', 'datetime', 'datetools']
+
+    # top-level functions
+    funcs = ['bdate_range', 'concat', 'crosstab', 'cut',
+             'date_range', 'eval',
+             'factorize', 'get_dummies', 'get_store',
+             'infer_freq', 'isnull', 'lreshape',
+             'match', 'melt', 'notnull', 'offsets',
+             'merge', 'merge_ordered', 'merge_asof',
+             'period_range',
+             'pivot', 'pivot_table', 'plot_params', 'qcut',
+             'scatter_matrix',
+             'show_versions', 'timedelta_range', 'unique',
+             'value_counts', 'wide_to_long']
+
+    # top-level option funcs
+    funcs_option = ['reset_option', 'describe_option', 'get_option',
+                    'option_context', 'set_option',
+                    'set_eng_float_format']
+
+    # top-level read_* funcs
+    funcs_read = ['read_clipboard', 'read_csv', 'read_excel', 'read_fwf',
+                  'read_gbq', 'read_hdf', 'read_html', 'read_json',
+                  'read_msgpack', 'read_pickle', 'read_sas', 'read_sql',
+                  'read_sql_query', 'read_sql_table', 'read_stata',
+                  'read_table']
+
+    # top-level to_* funcs
+    funcs_to = ['to_datetime', 'to_msgpack',
+                'to_numeric', 'to_pickle', 'to_timedelta']
+
+    # these should be deperecated in the future
+    deprecated_funcs_in_future = ['pnow', 'groupby', 'info']
+
+    # these are already deprecated; awaiting removal
+    deprecated_funcs = ['ewma', 'ewmcorr', 'ewmcov', 'ewmstd', 'ewmvar',
+                        'ewmvol', 'expanding_apply', 'expanding_corr',
+                        'expanding_count', 'expanding_cov', 'expanding_kurt',
+                        'expanding_max', 'expanding_mean', 'expanding_median',
+                        'expanding_min', 'expanding_quantile',
+                        'expanding_skew', 'expanding_std', 'expanding_sum',
+                        'expanding_var', 'fama_macbeth', 'rolling_apply',
+                        'rolling_corr', 'rolling_count', 'rolling_cov',
+                        'rolling_kurt', 'rolling_max', 'rolling_mean',
+                        'rolling_median', 'rolling_min', 'rolling_quantile',
+                        'rolling_skew', 'rolling_std', 'rolling_sum',
+                        'rolling_var', 'rolling_window', 'ordered_merge']
+
+    def test_api(self):
+
+        self.check(pd,
+                   self.lib + self.lib_to_rename + self.misc +
+                   self.modules + self.deprecated_modules +
+                   self.classes + self.deprecated_classes +
+                   self.deprecated_classes_in_future +
+                   self.remove_classes_from_top_level_namespace +
+                   self.funcs + self.funcs_option +
+                   self.funcs_read + self.funcs_to +
+                   self.deprecated_funcs +
+                   self.deprecated_funcs_in_future,
+                   self.ignored)
+
+
+class TestApi(Base, tm.TestCase):
+
+    allowed = ['tests', 'types']
+
+    def test_api(self):
+
+        self.check(api, self.allowed)
+
+
+class TestTypes(Base, tm.TestCase):
+
+    allowed = ['is_any_int_dtype', 'is_bool', 'is_bool_dtype',
+               'is_categorical', 'is_categorical_dtype', 'is_complex',
+               'is_complex_dtype', 'is_datetime64_any_dtype',
+               'is_datetime64_dtype', 'is_datetime64_ns_dtype',
+               'is_datetime64tz_dtype', 'is_datetimetz', 'is_dtype_equal',
+               'is_extension_type', 'is_float', 'is_float_dtype',
+               'is_floating_dtype', 'is_int64_dtype', 'is_integer',
+               'is_integer_dtype', 'is_number', 'is_numeric_dtype',
+               'is_object_dtype', 'is_scalar', 'is_sparse',
+               'is_string_dtype', 'is_timedelta64_dtype',
+               'is_timedelta64_ns_dtype',
+               'is_re', 'is_re_compilable',
+               'is_dict_like', 'is_iterator',
+               'is_list_like', 'is_hashable',
+               'is_named_tuple', 'is_sequence',
+               'pandas_dtype']
+
+    def test_types(self):
+
+        self.check(types, self.allowed)
+
+    def check_deprecation(self, fold, fnew):
+        with tm.assert_produces_warning(FutureWarning):
+            try:
+                result = fold('foo')
+                expected = fnew('foo')
+                self.assertEqual(result, expected)
+            except TypeError:
+                self.assertRaises(TypeError,
+                                  lambda: fnew('foo'))
+            except AttributeError:
+                self.assertRaises(AttributeError,
+                                  lambda: fnew('foo'))
+
+    def test_deprecation_core_common(self):
+
+        # test that we are in fact deprecating
+        # the pandas.core.common introspectors
+        for t in self.allowed:
+            self.check_deprecation(getattr(com, t), getattr(types, t))
+
+    def test_deprecation_core_common_moved(self):
+
+        # these are in pandas.types.common
+        l = ['is_datetime_arraylike',
+             'is_datetime_or_timedelta_dtype',
+             'is_datetimelike',
+             'is_datetimelike_v_numeric',
+             'is_datetimelike_v_object',
+             'is_datetimetz',
+             'is_int_or_datetime_dtype',
+             'is_period_arraylike',
+             'is_string_like',
+             'is_string_like_dtype']
+
+        from pandas.types import common as c
+        for t in l:
+            self.check_deprecation(getattr(com, t), getattr(c, t))
+
+    def test_removed_from_core_common(self):
+
+        for t in ['is_null_datelike_scalar',
+                  'ensure_float']:
+            self.assertRaises(AttributeError, lambda: getattr(com, t))
+
+if __name__ == '__main__':
+    import nose
+    nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
+                   exit=False)

pandas/api/tests/test_api.py

@@ -0,0 +1,4 @@
+""" public toolkit API """
+
+from pandas.types.api import *  # noqa
+del np  # noqa

pandas/api/types/__init__.py

@@ -21,7 +21,8 @@
 from numpy import ndarray
 from pandas.util.validators import (validate_args, validate_kwargs,
                                     validate_args_and_kwargs)
-from pandas.core.common import is_bool, is_integer, UnsupportedFunctionCall
+from pandas.core.common import UnsupportedFunctionCall
+from pandas.types.common import is_integer, is_bool
 from pandas.compat import OrderedDict
 
 

pandas/compat/numpy/function.py

@@ -7,11 +7,11 @@
 
 import numpy as np
 
+from pandas.types.common import is_list_like, is_scalar
 import pandas as pd
 from pandas.compat import PY3, string_types, text_type
 import pandas.core.common as com
 from pandas.formats.printing import pprint_thing, pprint_thing_encoded
-import pandas.lib as lib
 from pandas.core.base import StringMixin
 from pandas.computation.common import _ensure_decoded, _result_type_many
 from pandas.computation.scope import _DEFAULT_GLOBALS
@@ -100,7 +100,7 @@ def update(self, value):
 
     @property
     def isscalar(self):
-        return lib.isscalar(self._value)
+        return is_scalar(self._value)
 
     @property
     def type(self):
@@ -229,7 +229,7 @@ def _in(x, y):
     try:
         return x.isin(y)
     except AttributeError:
-        if com.is_list_like(x):
+        if is_list_like(x):
             try:
                 return y.isin(x)
             except AttributeError:
@@ -244,7 +244,7 @@ def _not_in(x, y):
     try:
         return ~x.isin(y)
     except AttributeError:
-        if com.is_list_like(x):
+        if is_list_like(x):
             try:
                 return ~y.isin(x)
             except AttributeError:

pandas/computation/ops.py

@@ -7,6 +7,8 @@
 from datetime import datetime, timedelta
 import numpy as np
 import pandas as pd
+
+from pandas.types.common import is_list_like
 import pandas.core.common as com
 from pandas.compat import u, string_types, DeepChainMap
 from pandas.core.base import StringMixin
@@ -127,7 +129,7 @@ def pr(left, right):
 
     def conform(self, rhs):
         """ inplace conform rhs """
-        if not com.is_list_like(rhs):
+        if not is_list_like(rhs):
             rhs = [rhs]
         if isinstance(rhs, np.ndarray):
             rhs = rhs.ravel()