TST: add method/dtype coverage to str-accessor; precursor to #23167

pandas/conftest.py

@@ -1,3 +1,5 @@
+from datetime import date, time, timedelta
+from decimal import Decimal
 import importlib
 import os
 
@@ -8,7 +10,7 @@
 import pytest
 from pytz import utc
 
-from pandas.compat import PY3
+from pandas.compat import PY3, u
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -513,6 +515,84 @@ def any_numpy_dtype(request):
     return request.param
 
 
+# categoricals are handled separately
+_any_skipna_inferred_dtype = [
+    ('string', ['a', np.nan, 'c']),
+    ('unicode' if not PY3 else 'string', [u('a'), np.nan, u('c')]),
+    ('bytes' if PY3 else 'string', [b'a', np.nan, b'c']),
+    ('empty', [np.nan, np.nan, np.nan]),
+    ('empty', []),
+    ('mixed-integer', ['a', np.nan, 2]),
+    ('mixed', ['a', np.nan, 2.0]),
+    ('floating', [1.0, np.nan, 2.0]),
+    ('integer', [1, np.nan, 2]),
+    ('mixed-integer-float', [1, np.nan, 2.0]),
+    ('decimal', [Decimal(1), np.nan, Decimal(2)]),
+    ('boolean', [True, np.nan, False]),
+    ('datetime64', [np.datetime64('2013-01-01'), np.nan,
+                    np.datetime64('2018-01-01')]),
+    ('datetime', [pd.Timestamp('20130101'), np.nan, pd.Timestamp('20180101')]),
+    ('date', [date(2013, 1, 1), np.nan, date(2018, 1, 1)]),
+    # The following two dtypes are commented out due to GH 23554
+    # ('complex', [1 + 1j, np.nan, 2 + 2j]),
+    # ('timedelta64', [np.timedelta64(1, 'D'),
+    #                  np.nan, np.timedelta64(2, 'D')]),
+    ('timedelta', [timedelta(1), np.nan, timedelta(2)]),
+    ('time', [time(1), np.nan, time(2)]),
+    ('period', [pd.Period(2013), pd.NaT, pd.Period(2018)]),
+    ('interval', [pd.Interval(0, 1), np.nan, pd.Interval(0, 2)])]
+ids, _ = zip(*_any_skipna_inferred_dtype)  # use inferred type as fixture-id
+
+
+@pytest.fixture(params=_any_skipna_inferred_dtype, ids=ids)
+def any_skipna_inferred_dtype(request):
+    """
+    Fixture for all inferred dtypes from _libs.lib.infer_dtype
+
+    The covered (inferred) types are:
+    * 'string'
+    * 'unicode' (if PY2)
+    * 'empty'
+    * 'bytes' (if PY3)
+    * 'mixed'
+    * 'mixed-integer'
+    * 'mixed-integer-float'
+    * 'floating'
+    * 'integer'
+    * 'decimal'
+    * 'boolean'
+    * 'datetime64'
+    * 'datetime'
+    * 'date'
+    * 'timedelta'
+    * 'time'
+    * 'period'
+    * 'interval'
+
+    Returns
+    -------
+    inferred_dtype : str
+        The string for the inferred dtype from _libs.lib.infer_dtype
+    values : np.ndarray
+        An array of object dtype that will be inferred to have
+        `inferred_dtype`
+
+    Examples
+    --------
+    >>> import pandas._libs.lib as lib
+    >>>
+    >>> def test_something(any_skipna_inferred_dtype):
+    ...     inferred_dtype, values = any_skipna_inferred_dtype
+    ...     # will pass
+    ...     assert lib.infer_dtype(values, skipna=True) == inferred_dtype
+    """
+    inferred_dtype, values = request.param
+    values = np.array(values, dtype=object)  # object dtype to avoid casting
+
+    # correctness of inference tested in tests/dtypes/test_inference.py
+    return inferred_dtype, values
+
+
 @pytest.fixture
 def mock():
     """

pandas/tests/dtypes/test_inference.py

@@ -495,6 +495,13 @@ class TestTypeInference(object):
     class Dummy():
         pass
 
+    def test_inferred_dtype_fixture(self, any_skipna_inferred_dtype):
+        # see pandas/conftest.py
+        inferred_dtype, values = any_skipna_inferred_dtype
+
+        # make sure the inferred dtype of the fixture is as requested
+        assert inferred_dtype == lib.infer_dtype(values, skipna=True)
+
     def test_length_zero(self):
         result = lib.infer_dtype(np.array([], dtype='i4'))
         assert result == 'integer'

pandas/tests/series/test_api.py

@@ -602,82 +602,6 @@ def f():
                                       ordered=True))
         tm.assert_series_equal(result, expected)
 
-    def test_str_accessor_api_for_categorical(self):
-        # https://github.com/pandas-dev/pandas/issues/10661
-        from pandas.core.strings import StringMethods
-        s = Series(list('aabb'))
-        s = s + " " + s
-        c = s.astype('category')
-        assert isinstance(c.str, StringMethods)
-
-        # str functions, which need special arguments
-        special_func_defs = [
-            ('cat', (list("zyxw"),), {"sep": ","}),
-            ('center', (10,), {}),
-            ('contains', ("a",), {}),
-            ('count', ("a",), {}),
-            ('decode', ("UTF-8",), {}),
-            ('encode', ("UTF-8",), {}),
-            ('endswith', ("a",), {}),
-            ('extract', ("([a-z]*) ",), {"expand": False}),
-            ('extract', ("([a-z]*) ",), {"expand": True}),
-            ('extractall', ("([a-z]*) ",), {}),
-            ('find', ("a",), {}),
-            ('findall', ("a",), {}),
-            ('index', (" ",), {}),
-            ('ljust', (10,), {}),
-            ('match', ("a"), {}),  # deprecated...
-            ('normalize', ("NFC",), {}),
-            ('pad', (10,), {}),
-            ('partition', (" ",), {"expand": False}),  # not default
-            ('partition', (" ",), {"expand": True}),  # default
-            ('repeat', (3,), {}),
-            ('replace', ("a", "z"), {}),
-            ('rfind', ("a",), {}),
-            ('rindex', (" ",), {}),
-            ('rjust', (10,), {}),
-            ('rpartition', (" ",), {"expand": False}),  # not default
-            ('rpartition', (" ",), {"expand": True}),  # default
-            ('slice', (0, 1), {}),
-            ('slice_replace', (0, 1, "z"), {}),
-            ('split', (" ",), {"expand": False}),  # default
-            ('split', (" ",), {"expand": True}),  # not default
-            ('startswith', ("a",), {}),
-            ('wrap', (2,), {}),
-            ('zfill', (10,), {})
-        ]
-        _special_func_names = [f[0] for f in special_func_defs]
-
-        # * get, join: they need a individual elements of type lists, but
-        #   we can't make a categorical with lists as individual categories.
-        #   -> `s.str.split(" ").astype("category")` will error!
-        # * `translate` has different interfaces for py2 vs. py3
-        _ignore_names = ["get", "join", "translate"]
-
-        str_func_names = [f for f in dir(s.str) if not (
-            f.startswith("_") or
-            f in _special_func_names or
-            f in _ignore_names)]
-
-        func_defs = [(f, (), {}) for f in str_func_names]
-        func_defs.extend(special_func_defs)
-
-        for func, args, kwargs in func_defs:
-            res = getattr(c.str, func)(*args, **kwargs)
-            exp = getattr(s.str, func)(*args, **kwargs)
-
-            if isinstance(res, DataFrame):
-                tm.assert_frame_equal(res, exp)
-            else:
-                tm.assert_series_equal(res, exp)
-
-        invalid = Series([1, 2, 3]).astype('category')
-        msg = "Can only use .str accessor with string"
-
-        with pytest.raises(AttributeError, match=msg):
-            invalid.str
-        assert not hasattr(invalid, 'str')
-
     def test_dt_accessor_api_for_categorical(self):
         # https://github.com/pandas-dev/pandas/issues/10661
         from pandas.core.indexes.accessors import Properties