Static code analysis and corrections

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/__init__.py

@@ -0,0 +1,56 @@
+"""Base test suite for extension arrays.
+
+These tests are intended for third-party libraries to subclass to validate
+that their extension arrays and dtypes satisfy the interface. Moving or
+renaming the tests should not be done lightly.
+
+Libraries are expected to implement a few pytest fixtures to provide data
+for the tests. The fixtures may be located in either
+
+* The same module as your test class.
+* A ``conftest.py`` in the same directory as your test class.
+
+The full list of fixtures may be found in the ``conftest.py`` next to this
+file.
+
+.. code-block:: python
+
+   import pytest
+   from pandas.tests.extension.base import BaseDtypeTests
+
+
+   @pytest.fixture
+   def dtype():
+       return MyDtype()
+
+
+   class TestMyDtype(BaseDtypeTests):
+       pass
+
+
+Your class ``TestDtype`` will inherit all the tests defined on
+``BaseDtypeTests``. pytest's fixture discover will supply your ``dtype``
+wherever the test requires it. You're free to implement additional tests.
+
+All the tests in these modules use ``self.assert_frame_equal`` or
+``self.assert_series_equal`` for dataframe or series comparisons. By default,
+they use the usual ``pandas.testing.assert_frame_equal`` and
+``pandas.testing.assert_series_equal``. You can override the checks used
+by defining the staticmethods ``assert_frame_equal`` and
+``assert_series_equal`` on your base test class.
+
+"""
+from .casting import BaseCastingTests  # noqa
+from .constructors import BaseConstructorsTests  # noqa
+from .dtype import BaseDtypeTests  # noqa
+from .getitem import BaseGetitemTests  # noqa
+from .groupby import BaseGroupbyTests  # noqa
+from .interface import BaseInterfaceTests  # noqa
+from .methods import BaseMethodsTests  # noqa
+from .ops import BaseArithmeticOpsTests, BaseComparisonOpsTests, BaseOpsUtil  # noqa
+from .printing import BasePrintingTests  # noqa
+from .reduce import BaseNoReduceTests, BaseNumericReduceTests, BaseBooleanReduceTests  # noqa
+from .missing import BaseMissingTests  # noqa
+from .reshaping import BaseReshapingTests  # noqa
+from .setitem import BaseSetitemTests  # noqa
+from .io import BaseParsingTests  # noqa

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/base.py

@@ -0,0 +1,10 @@
+import pandas.util.testing as tm
+
+
+class BaseExtensionTests(object):
+    assert_equal = staticmethod(tm.assert_equal)
+    assert_series_equal = staticmethod(tm.assert_series_equal)
+    assert_frame_equal = staticmethod(tm.assert_frame_equal)
+    assert_extension_array_equal = staticmethod(
+        tm.assert_extension_array_equal
+    )

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/casting.py

@@ -0,0 +1,23 @@
+import pandas as pd
+from pandas.core.internals import ObjectBlock
+
+from .base import BaseExtensionTests
+
+
+class BaseCastingTests(BaseExtensionTests):
+    """Casting to and from ExtensionDtypes"""
+
+    def test_astype_object_series(self, all_data):
+        ser = pd.Series({"A": all_data})
+        result = ser.astype(object)
+        assert isinstance(result._data.blocks[0], ObjectBlock)
+
+    def test_tolist(self, data):
+        result = pd.Series(data).tolist()
+        expected = list(data)
+        assert result == expected
+
+    def test_astype_str(self, data):
+        result = pd.Series(data[:5]).astype(str)
+        expected = pd.Series(data[:5].astype(str))
+        self.assert_series_equal(result, expected)

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/constructors.py

@@ -0,0 +1,77 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas.core.internals import ExtensionBlock
+
+from .base import BaseExtensionTests
+
+
+class BaseConstructorsTests(BaseExtensionTests):
+
+    def test_from_sequence_from_cls(self, data):
+        result = type(data)._from_sequence(data, dtype=data.dtype)
+        self.assert_extension_array_equal(result, data)
+
+        data = data[:0]
+        result = type(data)._from_sequence(data, dtype=data.dtype)
+        self.assert_extension_array_equal(result, data)
+
+    def test_array_from_scalars(self, data):
+        scalars = [data[0], data[1], data[2]]
+        result = data._from_sequence(scalars)
+        assert isinstance(result, type(data))
+
+    def test_series_constructor(self, data):
+        result = pd.Series(data)
+        assert result.dtype == data.dtype
+        assert len(result) == len(data)
+        assert isinstance(result._data.blocks[0], ExtensionBlock)
+        assert result._data.blocks[0].values is data
+
+        # Series[EA] is unboxed / boxed correctly
+        result2 = pd.Series(result)
+        assert result2.dtype == data.dtype
+        assert isinstance(result2._data.blocks[0], ExtensionBlock)
+
+    @pytest.mark.parametrize("from_series", [True, False])
+    def test_dataframe_constructor_from_dict(self, data, from_series):
+        if from_series:
+            data = pd.Series(data)
+        result = pd.DataFrame({"A": data})
+        assert result.dtypes['A'] == data.dtype
+        assert result.shape == (len(data), 1)
+        assert isinstance(result._data.blocks[0], ExtensionBlock)
+
+    def test_dataframe_from_series(self, data):
+        result = pd.DataFrame(pd.Series(data))
+        assert result.dtypes[0] == data.dtype
+        assert result.shape == (len(data), 1)
+        assert isinstance(result._data.blocks[0], ExtensionBlock)
+
+    def test_series_given_mismatched_index_raises(self, data):
+        msg = 'Length of passed values is 3, index implies 5'
+        with pytest.raises(ValueError, match=msg):
+            pd.Series(data[:3], index=[0, 1, 2, 3, 4])
+
+    def test_from_dtype(self, data):
+        # construct from our dtype & string dtype
+        dtype = data.dtype
+
+        expected = pd.Series(data)
+        result = pd.Series(list(data), dtype=dtype)
+        self.assert_series_equal(result, expected)
+
+        result = pd.Series(list(data), dtype=str(dtype))
+        self.assert_series_equal(result, expected)
+
+    def test_pandas_array(self, data):
+        # pd.array(extension_array) should be idempotent...
+        result = pd.array(data)
+        self.assert_extension_array_equal(result, data)
+
+    def test_pandas_array_dtype(self, data):
+        # ... but specifying dtype will override idempotency
+        result = pd.array(data, dtype=np.dtype(object))
+        expected = pd.arrays.PandasArray(np.asarray(data, dtype=object))
+        self.assert_equal(result, expected)

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/dtype.py

@@ -0,0 +1,91 @@
+import warnings
+
+import numpy as np
+
+import pandas as pd
+
+from .base import BaseExtensionTests
+
+
+class BaseDtypeTests(BaseExtensionTests):
+    """Base class for ExtensionDtype classes"""
+
+    def test_name(self, dtype):
+        assert isinstance(dtype.name, str)
+
+    def test_kind(self, dtype):
+        valid = set('biufcmMOSUV')
+        if dtype.kind is not None:
+            assert dtype.kind in valid
+
+    def test_construct_from_string_own_name(self, dtype):
+        result = dtype.construct_from_string(dtype.name)
+        assert type(result) is type(dtype)
+
+        # check OK as classmethod
+        result = type(dtype).construct_from_string(dtype.name)
+        assert type(result) is type(dtype)
+
+    def test_is_dtype_from_name(self, dtype):
+        result = type(dtype).is_dtype(dtype.name)
+        assert result is True
+
+    def test_is_dtype_unboxes_dtype(self, data, dtype):
+        assert dtype.is_dtype(data) is True
+
+    def test_is_dtype_from_self(self, dtype):
+        result = type(dtype).is_dtype(dtype)
+        assert result is True
+
+    def test_is_not_string_type(self, dtype):
+        return not pd.api.types.is_string_dtype(dtype)
+
+    def test_is_not_object_type(self, dtype):
+        return not pd.api.types.is_object_dtype(dtype)
+
+    def test_eq_with_str(self, dtype):
+        assert dtype == dtype.name
+        assert dtype != dtype.name + '-suffix'
+
+    def test_eq_with_numpy_object(self, dtype):
+        assert dtype != np.dtype('object')
+
+    def test_eq_with_self(self, dtype):
+        assert dtype == dtype
+        assert dtype != object()
+
+    def test_array_type(self, data, dtype):
+        assert dtype.construct_array_type() is type(data)
+
+    def test_check_dtype(self, data):
+        dtype = data.dtype
+
+        # check equivalency for using .dtypes
+        df = pd.DataFrame({'A': pd.Series(data, dtype=dtype),
+                           'B': data,
+                           'C': 'foo', 'D': 1})
+
+        # np.dtype('int64') == 'Int64' == 'int64'
+        # so can't distinguish
+        if dtype.name == 'Int64':
+            expected = pd.Series([True, True, False, True],
+                                 index=list('ABCD'))
+        else:
+            expected = pd.Series([True, True, False, False],
+                                 index=list('ABCD'))
+
+        # XXX: This should probably be *fixed* not ignored.
+        # See libops.scalar_compare
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", DeprecationWarning)
+            result = df.dtypes == str(dtype)
+
+        self.assert_series_equal(result, expected)
+
+        expected = pd.Series([True, True, False, False],
+                             index=list('ABCD'))
+        result = df.dtypes.apply(str) == str(dtype)
+        self.assert_series_equal(result, expected)
+
+    def test_hashable(self, dtype):
+        hash(dtype)  # no error

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/getitem.py

@@ -0,0 +1,248 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+
+from .base import BaseExtensionTests
+
+
+class BaseGetitemTests(BaseExtensionTests):
+    """Tests for ExtensionArray.__getitem__."""
+
+    def test_iloc_series(self, data):
+        ser = pd.Series(data)
+        result = ser.iloc[:4]
+        expected = pd.Series(data[:4])
+        self.assert_series_equal(result, expected)
+
+        result = ser.iloc[[0, 1, 2, 3]]
+        self.assert_series_equal(result, expected)
+
+    def test_iloc_frame(self, data):
+        df = pd.DataFrame({"A": data, 'B':
+                           np.arange(len(data), dtype='int64')})
+        expected = pd.DataFrame({"A": data[:4]})
+
+        # slice -> frame
+        result = df.iloc[:4, [0]]
+        self.assert_frame_equal(result, expected)
+
+        # sequence -> frame
+        result = df.iloc[[0, 1, 2, 3], [0]]
+        self.assert_frame_equal(result, expected)
+
+        expected = pd.Series(data[:4], name='A')
+
+        # slice -> series
+        result = df.iloc[:4, 0]
+        self.assert_series_equal(result, expected)
+
+        # sequence -> series
+        result = df.iloc[:4, 0]
+        self.assert_series_equal(result, expected)
+
+    def test_loc_series(self, data):
+        ser = pd.Series(data)
+        result = ser.loc[:3]
+        expected = pd.Series(data[:4])
+        self.assert_series_equal(result, expected)
+
+        result = ser.loc[[0, 1, 2, 3]]
+        self.assert_series_equal(result, expected)
+
+    def test_loc_frame(self, data):
+        df = pd.DataFrame({"A": data,
+                           'B': np.arange(len(data), dtype='int64')})
+        expected = pd.DataFrame({"A": data[:4]})
+
+        # slice -> frame
+        result = df.loc[:3, ['A']]
+        self.assert_frame_equal(result, expected)
+
+        # sequence -> frame
+        result = df.loc[[0, 1, 2, 3], ['A']]
+        self.assert_frame_equal(result, expected)
+
+        expected = pd.Series(data[:4], name='A')
+
+        # slice -> series
+        result = df.loc[:3, 'A']
+        self.assert_series_equal(result, expected)
+
+        # sequence -> series
+        result = df.loc[:3, 'A']
+        self.assert_series_equal(result, expected)
+
+    def test_getitem_scalar(self, data):
+        result = data[0]
+        assert isinstance(result, data.dtype.type)
+
+        result = pd.Series(data)[0]
+        assert isinstance(result, data.dtype.type)
+
+    def test_getitem_scalar_na(self, data_missing, na_cmp, na_value):
+        result = data_missing[0]
+        assert na_cmp(result, na_value)
+
+    def test_getitem_mask(self, data):
+        # Empty mask, raw array
+        mask = np.zeros(len(data), dtype=bool)
+        result = data[mask]
+        assert len(result) == 0
+        assert isinstance(result, type(data))
+
+        # Empty mask, in series
+        mask = np.zeros(len(data), dtype=bool)
+        result = pd.Series(data)[mask]
+        assert len(result) == 0
+        assert result.dtype == data.dtype
+
+        # non-empty mask, raw array
+        mask[0] = True
+        result = data[mask]
+        assert len(result) == 1
+        assert isinstance(result, type(data))
+
+        # non-empty mask, in series
+        result = pd.Series(data)[mask]
+        assert len(result) == 1
+        assert result.dtype == data.dtype
+
+    def test_getitem_slice(self, data):
+        # getitem[slice] should return an array
+        result = data[slice(0)]  # empty
+        assert isinstance(result, type(data))
+
+        result = data[slice(1)]  # scalar
+        assert isinstance(result, type(data))
+
+    def test_get(self, data):
+        # GH 20882
+        s = pd.Series(data, index=[2 * i for i in range(len(data))])
+        assert s.get(4) == s.iloc[2]
+
+        result = s.get([4, 6])
+        expected = s.iloc[[2, 3]]
+        self.assert_series_equal(result, expected)
+
+        result = s.get(slice(2))
+        expected = s.iloc[[0, 1]]
+        self.assert_series_equal(result, expected)
+
+        assert s.get(-1) is None
+        assert s.get(s.index.max() + 1) is None
+
+        s = pd.Series(data[:6], index=list('abcdef'))
+        assert s.get('c') == s.iloc[2]
+
+        result = s.get(slice('b', 'd'))
+        expected = s.iloc[[1, 2, 3]]
+        self.assert_series_equal(result, expected)
+
+        result = s.get('Z')
+        assert result is None
+
+        assert s.get(4) == s.iloc[4]
+        assert s.get(-1) == s.iloc[-1]
+        assert s.get(len(s)) is None
+
+        # GH 21257
+        s = pd.Series(data)
+        s2 = s[::2]
+        assert s2.get(1) is None
+
+    def test_take_sequence(self, data):
+        result = pd.Series(data)[[0, 1, 3]]
+        assert result.iloc[0] == data[0]
+        assert result.iloc[1] == data[1]
+        assert result.iloc[2] == data[3]
+
+    def test_take(self, data, na_value, na_cmp):
+        result = data.take([0, -1])
+        assert result.dtype == data.dtype
+        assert result[0] == data[0]
+        assert result[1] == data[-1]
+
+        result = data.take([0, -1], allow_fill=True, fill_value=na_value)
+        assert result[0] == data[0]
+        assert na_cmp(result[1], na_value)
+
+        with pytest.raises(IndexError, match="out of bounds"):
+            data.take([len(data) + 1])
+
+    def test_take_empty(self, data, na_value, na_cmp):
+        empty = data[:0]
+
+        result = empty.take([-1], allow_fill=True)
+        assert na_cmp(result[0], na_value)
+
+        with pytest.raises(IndexError):
+            empty.take([-1])
+
+        with pytest.raises(IndexError, match="cannot do a non-empty take"):
+            empty.take([0, 1])
+
+    def test_take_negative(self, data):
+        # https://github.com/pandas-dev/pandas/issues/20640
+        n = len(data)
+        result = data.take([0, -n, n - 1, -1])
+        expected = data.take([0, 0, n - 1, n - 1])
+        self.assert_extension_array_equal(result, expected)
+
+    def test_take_non_na_fill_value(self, data_missing):
+        fill_value = data_missing[1]  # valid
+        na = data_missing[0]
+
+        array = data_missing._from_sequence([na, fill_value, na])
+        result = array.take([-1, 1], fill_value=fill_value, allow_fill=True)
+        expected = array.take([1, 1])
+        self.assert_extension_array_equal(result, expected)
+
+    def test_take_pandas_style_negative_raises(self, data, na_value):
+        with pytest.raises(ValueError):
+            data.take([0, -2], fill_value=na_value, allow_fill=True)
+
+    @pytest.mark.parametrize('allow_fill', [True, False])
+    def test_take_out_of_bounds_raises(self, data, allow_fill):
+        arr = data[:3]
+        with pytest.raises(IndexError):
+            arr.take(np.asarray([0, 3]), allow_fill=allow_fill)
+
+    def test_take_series(self, data):
+        s = pd.Series(data)
+        result = s.take([0, -1])
+        expected = pd.Series(
+            data._from_sequence([data[0], data[len(data) - 1]], dtype=s.dtype),
+            index=[0, len(data) - 1])
+        self.assert_series_equal(result, expected)
+
+    def test_reindex(self, data, na_value):
+        s = pd.Series(data)
+        result = s.reindex([0, 1, 3])
+        expected = pd.Series(data.take([0, 1, 3]), index=[0, 1, 3])
+        self.assert_series_equal(result, expected)
+
+        n = len(data)
+        result = s.reindex([-1, 0, n])
+        expected = pd.Series(
+            data._from_sequence([na_value, data[0], na_value],
+                                dtype=s.dtype),
+            index=[-1, 0, n])
+        self.assert_series_equal(result, expected)
+
+        result = s.reindex([n, n + 1])
+        expected = pd.Series(data._from_sequence([na_value, na_value],
+                                                 dtype=s.dtype),
+                             index=[n, n + 1])
+        self.assert_series_equal(result, expected)
+
+    def test_reindex_non_na_fill_value(self, data_missing):
+        valid = data_missing[1]
+        na = data_missing[0]
+
+        array = data_missing._from_sequence([na, valid])
+        ser = pd.Series(array)
+        result = ser.reindex([0, 1, 2], fill_value=valid)
+        expected = pd.Series(data_missing._from_sequence([na, valid, valid]))
+
+        self.assert_series_equal(result, expected)

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/groupby.py

@@ -0,0 +1,83 @@
+import pytest
+
+import pandas as pd
+import pandas.util.testing as tm
+
+from .base import BaseExtensionTests
+
+
+class BaseGroupbyTests(BaseExtensionTests):
+    """Groupby-specific tests."""
+
+    def test_grouping_grouper(self, data_for_grouping):
+        df = pd.DataFrame({
+            "A": ["B", "B", None, None, "A", "A", "B", "C"],
+            "B": data_for_grouping
+        })
+        gr1 = df.groupby("A").grouper.groupings[0]
+        gr2 = df.groupby("B").grouper.groupings[0]
+
+        tm.assert_numpy_array_equal(gr1.grouper, df.A.values)
+        tm.assert_extension_array_equal(gr2.grouper, data_for_grouping)
+
+    @pytest.mark.parametrize('as_index', [True, False])
+    def test_groupby_extension_agg(self, as_index, data_for_grouping):
+        df = pd.DataFrame({"A": [1, 1, 2, 2, 3, 3, 1, 4],
+                           "B": data_for_grouping})
+        result = df.groupby("B", as_index=as_index).A.mean()
+        _, index = pd.factorize(data_for_grouping, sort=True)
+
+        index = pd.Index(index, name="B")
+        expected = pd.Series([3, 1, 4], index=index, name="A")
+        if as_index:
+            self.assert_series_equal(result, expected)
+        else:
+            expected = expected.reset_index()
+            self.assert_frame_equal(result, expected)
+
+    def test_groupby_extension_no_sort(self, data_for_grouping):
+        df = pd.DataFrame({"A": [1, 1, 2, 2, 3, 3, 1, 4],
+                           "B": data_for_grouping})
+        result = df.groupby("B", sort=False).A.mean()
+        _, index = pd.factorize(data_for_grouping, sort=False)
+
+        index = pd.Index(index, name="B")
+        expected = pd.Series([1, 3, 4], index=index, name="A")
+        self.assert_series_equal(result, expected)
+
+    def test_groupby_extension_transform(self, data_for_grouping):
+        valid = data_for_grouping[~data_for_grouping.isna()]
+        df = pd.DataFrame({"A": [1, 1, 3, 3, 1, 4],
+                           "B": valid})
+
+        result = df.groupby("B").A.transform(len)
+        expected = pd.Series([3, 3, 2, 2, 3, 1], name="A")
+
+        self.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize('op', [
+        lambda x: 1,
+        lambda x: [1] * len(x),
+        lambda x: pd.Series([1] * len(x)),
+        lambda x: x,
+    ], ids=['scalar', 'list', 'series', 'object'])
+    def test_groupby_extension_apply(self, data_for_grouping, op):
+        df = pd.DataFrame({"A": [1, 1, 2, 2, 3, 3, 1, 4],
+                           "B": data_for_grouping})
+        df.groupby("B").apply(op)
+        df.groupby("B").A.apply(op)
+        df.groupby("A").apply(op)
+        df.groupby("A").B.apply(op)
+
+    def test_in_numeric_groupby(self, data_for_grouping):
+        df = pd.DataFrame({"A": [1, 1, 2, 2, 3, 3, 1, 4],
+                           "B": data_for_grouping,
+                           "C": [1, 1, 1, 1, 1, 1, 1, 1]})
+        result = df.groupby("A").sum().columns
+
+        if data_for_grouping.dtype._is_numeric:
+            expected = pd.Index(['B', 'C'])
+        else:
+            expected = pd.Index(['C'])
+
+        tm.assert_index_equal(result, expected)

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/interface.py

@@ -0,0 +1,68 @@
+import numpy as np
+
+from pandas.core.dtypes.common import is_extension_array_dtype
+from pandas.core.dtypes.dtypes import ExtensionDtype
+
+import pandas as pd
+import pandas.util.testing as tm
+
+from .base import BaseExtensionTests
+
+
+class BaseInterfaceTests(BaseExtensionTests):
+    """Tests that the basic interface is satisfied."""
+    # ------------------------------------------------------------------------
+    # Interface
+    # ------------------------------------------------------------------------
+
+    def test_len(self, data):
+        assert len(data) == 100
+
+    def test_ndim(self, data):
+        assert data.ndim == 1
+
+    def test_can_hold_na_valid(self, data):
+        # GH-20761
+        assert data._can_hold_na is True
+
+    def test_memory_usage(self, data):
+        s = pd.Series(data)
+        result = s.memory_usage(index=False)
+        assert result == s.nbytes
+
+    def test_array_interface(self, data):
+        result = np.array(data)
+        assert result[0] == data[0]
+
+        result = np.array(data, dtype=object)
+        expected = np.array(list(data), dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_is_extension_array_dtype(self, data):
+        assert is_extension_array_dtype(data)
+        assert is_extension_array_dtype(data.dtype)
+        assert is_extension_array_dtype(pd.Series(data))
+        assert isinstance(data.dtype, ExtensionDtype)
+
+    def test_no_values_attribute(self, data):
+        # GH-20735: EA's with .values attribute give problems with internal
+        # code, disallowing this for now until solved
+        assert not hasattr(data, 'values')
+        assert not hasattr(data, '_values')
+
+    def test_is_numeric_honored(self, data):
+        result = pd.Series(data)
+        assert result._data.blocks[0].is_numeric is data.dtype._is_numeric
+
+    def test_isna_extension_array(self, data_missing):
+        # If your `isna` returns an ExtensionArray, you must also implement
+        # _reduce. At the *very* least, you must implement any and all
+        na = data_missing.isna()
+        if is_extension_array_dtype(na):
+            assert na._reduce('any')
+            assert na.any()
+
+            assert not na._reduce('all')
+            assert not na.all()
+
+            assert na.dtype._is_boolean

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/io.py

@@ -0,0 +1,23 @@
+import numpy as np
+import pytest
+
+from pandas.compat import StringIO
+
+import pandas as pd
+
+from .base import BaseExtensionTests
+
+
+class BaseParsingTests(BaseExtensionTests):
+
+    @pytest.mark.parametrize('engine', ['c', 'python'])
+    def test_EA_types(self, engine, data):
+        df = pd.DataFrame({
+            'with_dtype': pd.Series(data, dtype=str(data.dtype))
+        })
+        csv_output = df.to_csv(index=False, na_rep=np.nan)
+        result = pd.read_csv(StringIO(csv_output), dtype={
+            'with_dtype': str(data.dtype)
+        }, engine=engine)
+        expected = df
+        self.assert_frame_equal(result, expected)

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/methods.py

@@ -0,0 +1,341 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas.util.testing as tm
+
+from .base import BaseExtensionTests
+
+
+class BaseMethodsTests(BaseExtensionTests):
+    """Various Series and DataFrame methods."""
+
+    @pytest.mark.parametrize('dropna', [True, False])
+    def test_value_counts(self, all_data, dropna):
+        all_data = all_data[:10]
+        if dropna:
+            other = np.array(all_data[~all_data.isna()])
+        else:
+            other = all_data
+
+        result = pd.Series(all_data).value_counts(dropna=dropna).sort_index()
+        expected = pd.Series(other).value_counts(
+            dropna=dropna).sort_index()
+
+        self.assert_series_equal(result, expected)
+
+    def test_count(self, data_missing):
+        df = pd.DataFrame({"A": data_missing})
+        result = df.count(axis='columns')
+        expected = pd.Series([0, 1])
+        self.assert_series_equal(result, expected)
+
+    def test_apply_simple_series(self, data):
+        result = pd.Series(data).apply(id)
+        assert isinstance(result, pd.Series)
+
+    def test_argsort(self, data_for_sorting):
+        result = pd.Series(data_for_sorting).argsort()
+        expected = pd.Series(np.array([2, 0, 1], dtype=np.int64))
+        self.assert_series_equal(result, expected)
+
+    def test_argsort_missing(self, data_missing_for_sorting):
+        result = pd.Series(data_missing_for_sorting).argsort()
+        expected = pd.Series(np.array([1, -1, 0], dtype=np.int64))
+        self.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize('ascending', [True, False])
+    def test_sort_values(self, data_for_sorting, ascending):
+        ser = pd.Series(data_for_sorting)
+        result = ser.sort_values(ascending=ascending)
+        expected = ser.iloc[[2, 0, 1]]
+        if not ascending:
+            expected = expected[::-1]
+
+        self.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize('ascending', [True, False])
+    def test_sort_values_missing(self, data_missing_for_sorting, ascending):
+        ser = pd.Series(data_missing_for_sorting)
+        result = ser.sort_values(ascending=ascending)
+        if ascending:
+            expected = ser.iloc[[2, 0, 1]]
+        else:
+            expected = ser.iloc[[0, 2, 1]]
+        self.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize('ascending', [True, False])
+    def test_sort_values_frame(self, data_for_sorting, ascending):
+        df = pd.DataFrame({"A": [1, 2, 1],
+                           "B": data_for_sorting})
+        result = df.sort_values(['A', 'B'])
+        expected = pd.DataFrame({"A": [1, 1, 2],
+                                 'B': data_for_sorting.take([2, 0, 1])},
+                                index=[2, 0, 1])
+        self.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize('box', [pd.Series, lambda x: x])
+    @pytest.mark.parametrize('method', [lambda x: x.unique(), pd.unique])
+    def test_unique(self, data, box, method):
+        duplicated = box(data._from_sequence([data[0], data[0]]))
+
+        result = method(duplicated)
+
+        assert len(result) == 1
+        assert isinstance(result, type(data))
+        assert result[0] == duplicated[0]
+
+    @pytest.mark.parametrize('na_sentinel', [-1, -2])
+    def test_factorize(self, data_for_grouping, na_sentinel):
+        labels, uniques = pd.factorize(data_for_grouping,
+                                       na_sentinel=na_sentinel)
+        expected_labels = np.array([0, 0, na_sentinel,
+                                   na_sentinel, 1, 1, 0, 2],
+                                   dtype=np.intp)
+        expected_uniques = data_for_grouping.take([0, 4, 7])
+
+        tm.assert_numpy_array_equal(labels, expected_labels)
+        self.assert_extension_array_equal(uniques, expected_uniques)
+
+    @pytest.mark.parametrize('na_sentinel', [-1, -2])
+    def test_factorize_equivalence(self, data_for_grouping, na_sentinel):
+        l1, u1 = pd.factorize(data_for_grouping, na_sentinel=na_sentinel)
+        l2, u2 = data_for_grouping.factorize(na_sentinel=na_sentinel)
+
+        tm.assert_numpy_array_equal(l1, l2)
+        self.assert_extension_array_equal(u1, u2)
+
+    def test_factorize_empty(self, data):
+        labels, uniques = pd.factorize(data[:0])
+        expected_labels = np.array([], dtype=np.intp)
+        expected_uniques = type(data)._from_sequence([], dtype=data[:0].dtype)
+
+        tm.assert_numpy_array_equal(labels, expected_labels)
+        self.assert_extension_array_equal(uniques, expected_uniques)
+
+    def test_fillna_copy_frame(self, data_missing):
+        arr = data_missing.take([1, 1])
+        df = pd.DataFrame({"A": arr})
+
+        filled_val = df.iloc[0, 0]
+        result = df.fillna(filled_val)
+
+        assert df.A.values is not result.A.values
+
+    def test_fillna_copy_series(self, data_missing):
+        arr = data_missing.take([1, 1])
+        ser = pd.Series(arr)
+
+        filled_val = ser[0]
+        result = ser.fillna(filled_val)
+
+        assert ser._values is not result._values
+        assert ser._values is arr
+
+    def test_fillna_length_mismatch(self, data_missing):
+        msg = "Length of 'value' does not match."
+        with pytest.raises(ValueError, match=msg):
+            data_missing.fillna(data_missing.take([1]))
+
+    def test_combine_le(self, data_repeated):
+        # GH 20825
+        # Test that combine works when doing a <= (le) comparison
+        orig_data1, orig_data2 = data_repeated(2)
+        s1 = pd.Series(orig_data1)
+        s2 = pd.Series(orig_data2)
+        result = s1.combine(s2, lambda x1, x2: x1 <= x2)
+        expected = pd.Series([a <= b for (a, b) in
+                              zip(list(orig_data1), list(orig_data2))])
+        self.assert_series_equal(result, expected)
+
+        val = s1.iloc[0]
+        result = s1.combine(val, lambda x1, x2: x1 <= x2)
+        expected = pd.Series([a <= val for a in list(orig_data1)])
+        self.assert_series_equal(result, expected)
+
+    def test_combine_add(self, data_repeated):
+        # GH 20825
+        orig_data1, orig_data2 = data_repeated(2)
+        s1 = pd.Series(orig_data1)
+        s2 = pd.Series(orig_data2)
+        result = s1.combine(s2, lambda x1, x2: x1 + x2)
+        with np.errstate(over='ignore'):
+            expected = pd.Series(
+                orig_data1._from_sequence([a + b for (a, b) in
+                                           zip(list(orig_data1),
+                                               list(orig_data2))]))
+        self.assert_series_equal(result, expected)
+
+        val = s1.iloc[0]
+        result = s1.combine(val, lambda x1, x2: x1 + x2)
+        expected = pd.Series(
+            orig_data1._from_sequence([a + val for a in list(orig_data1)]))
+        self.assert_series_equal(result, expected)
+
+    def test_combine_first(self, data):
+        # https://github.com/pandas-dev/pandas/issues/24147
+        a = pd.Series(data[:3])
+        b = pd.Series(data[2:5], index=[2, 3, 4])
+        result = a.combine_first(b)
+        expected = pd.Series(data[:5])
+        self.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize('frame', [True, False])
+    @pytest.mark.parametrize('periods, indices', [
+        (-2, [2, 3, 4, -1, -1]),
+        (0, [0, 1, 2, 3, 4]),
+        (2, [-1, -1, 0, 1, 2]),
+    ])
+    def test_container_shift(self, data, frame, periods, indices):
+        # https://github.com/pandas-dev/pandas/issues/22386
+        subset = data[:5]
+        data = pd.Series(subset, name='A')
+        expected = pd.Series(subset.take(indices, allow_fill=True), name='A')
+
+        if frame:
+            result = data.to_frame(name='A').assign(B=1).shift(periods)
+            expected = pd.concat([
+                expected,
+                pd.Series([1] * 5, name='B').shift(periods)
+            ], axis=1)
+            compare = self.assert_frame_equal
+        else:
+            result = data.shift(periods)
+            compare = self.assert_series_equal
+
+        compare(result, expected)
+
+    @pytest.mark.parametrize('periods, indices', [
+        [-4, [-1, -1]],
+        [-1, [1, -1]],
+        [0, [0, 1]],
+        [1, [-1, 0]],
+        [4, [-1, -1]]
+    ])
+    def test_shift_non_empty_array(self, data, periods, indices):
+        # https://github.com/pandas-dev/pandas/issues/23911
+        subset = data[:2]
+        result = subset.shift(periods)
+        expected = subset.take(indices, allow_fill=True)
+        self.assert_extension_array_equal(result, expected)
+
+    @pytest.mark.parametrize('periods', [
+        -4, -1, 0, 1, 4
+    ])
+    def test_shift_empty_array(self, data, periods):
+        # https://github.com/pandas-dev/pandas/issues/23911
+        empty = data[:0]
+        result = empty.shift(periods)
+        expected = empty
+        self.assert_extension_array_equal(result, expected)
+
+    def test_shift_fill_value(self, data):
+        arr = data[:4]
+        fill_value = data[0]
+        result = arr.shift(1, fill_value=fill_value)
+        expected = data.take([0, 0, 1, 2])
+        self.assert_extension_array_equal(result, expected)
+
+        result = arr.shift(-2, fill_value=fill_value)
+        expected = data.take([2, 3, 0, 0])
+        self.assert_extension_array_equal(result, expected)
+
+    @pytest.mark.parametrize("as_frame", [True, False])
+    def test_hash_pandas_object_works(self, data, as_frame):
+        # https://github.com/pandas-dev/pandas/issues/23066
+        data = pd.Series(data)
+        if as_frame:
+            data = data.to_frame()
+        a = pd.util.hash_pandas_object(data)
+        b = pd.util.hash_pandas_object(data)
+        self.assert_equal(a, b)
+
+    @pytest.mark.parametrize("as_series", [True, False])
+    def test_searchsorted(self, data_for_sorting, as_series):
+        b, c, a = data_for_sorting
+        arr = type(data_for_sorting)._from_sequence([a, b, c])
+
+        if as_series:
+            arr = pd.Series(arr)
+        assert arr.searchsorted(a) == 0
+        assert arr.searchsorted(a, side="right") == 1
+
+        assert arr.searchsorted(b) == 1
+        assert arr.searchsorted(b, side="right") == 2
+
+        assert arr.searchsorted(c) == 2
+        assert arr.searchsorted(c, side="right") == 3
+
+        result = arr.searchsorted(arr.take([0, 2]))
+        expected = np.array([0, 2], dtype=np.intp)
+
+        tm.assert_numpy_array_equal(result, expected)
+
+        # sorter
+        sorter = np.array([1, 2, 0])
+        assert data_for_sorting.searchsorted(a, sorter=sorter) == 0
+
+    @pytest.mark.parametrize("as_frame", [True, False])
+    def test_where_series(self, data, na_value, as_frame):
+        assert data[0] != data[1]
+        cls = type(data)
+        a, b = data[:2]
+
+        ser = pd.Series(cls._from_sequence([a, a, b, b], dtype=data.dtype))
+        cond = np.array([True, True, False, False])
+
+        if as_frame:
+            ser = ser.to_frame(name='a')
+            cond = cond.reshape(-1, 1)
+
+        result = ser.where(cond)
+        expected = pd.Series(cls._from_sequence([a, a, na_value, na_value],
+                                                dtype=data.dtype))
+
+        if as_frame:
+            expected = expected.to_frame(name='a')
+        self.assert_equal(result, expected)
+
+        # array other
+        cond = np.array([True, False, True, True])
+        other = cls._from_sequence([a, b, a, b], dtype=data.dtype)
+        if as_frame:
+            other = pd.DataFrame({"a": other})
+            cond = pd.DataFrame({"a": cond})
+        result = ser.where(cond, other)
+        expected = pd.Series(cls._from_sequence([a, b, b, b],
+                                                dtype=data.dtype))
+        if as_frame:
+            expected = expected.to_frame(name='a')
+        self.assert_equal(result, expected)
+
+    @pytest.mark.parametrize("use_numpy", [True, False])
+    @pytest.mark.parametrize("as_series", [True, False])
+    @pytest.mark.parametrize("repeats", [0, 1, 2, [1, 2, 3]])
+    def test_repeat(self, data, repeats, as_series, use_numpy):
+        arr = type(data)._from_sequence(data[:3], dtype=data.dtype)
+        if as_series:
+            arr = pd.Series(arr)
+
+        result = np.repeat(arr, repeats) if use_numpy else arr.repeat(repeats)
+
+        repeats = [repeats] * 3 if isinstance(repeats, int) else repeats
+        expected = [x for x, n in zip(arr, repeats) for _ in range(n)]
+        expected = type(data)._from_sequence(expected, dtype=data.dtype)
+        if as_series:
+            expected = pd.Series(expected, index=arr.index.repeat(repeats))
+
+        self.assert_equal(result, expected)
+
+    @pytest.mark.parametrize("use_numpy", [True, False])
+    @pytest.mark.parametrize('repeats, kwargs, error, msg', [
+        (2, dict(axis=1), ValueError, "'axis"),
+        (-1, dict(), ValueError, "negative"),
+        ([1, 2], dict(), ValueError, "shape"),
+        (2, dict(foo='bar'), TypeError, "'foo'")])
+    def test_repeat_raises(self, data, repeats, kwargs, error, msg, use_numpy):
+        with pytest.raises(error, match=msg):
+            if use_numpy:
+                np.repeat(data, repeats, **kwargs)
+            else:
+                data.repeat(repeats, **kwargs)

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/missing.py

@@ -0,0 +1,132 @@
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas.util.testing as tm
+
+from .base import BaseExtensionTests
+
+
+class BaseMissingTests(BaseExtensionTests):
+    def test_isna(self, data_missing):
+        expected = np.array([True, False])
+
+        result = pd.isna(data_missing)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = pd.Series(data_missing).isna()
+        expected = pd.Series(expected)
+        self.assert_series_equal(result, expected)
+
+        # GH 21189
+        result = pd.Series(data_missing).drop([0, 1]).isna()
+        expected = pd.Series([], dtype=bool)
+        self.assert_series_equal(result, expected)
+
+    def test_dropna_array(self, data_missing):
+        result = data_missing.dropna()
+        expected = data_missing[[1]]
+        self.assert_extension_array_equal(result, expected)
+
+    def test_dropna_series(self, data_missing):
+        ser = pd.Series(data_missing)
+        result = ser.dropna()
+        expected = ser.iloc[[1]]
+        self.assert_series_equal(result, expected)
+
+    def test_dropna_frame(self, data_missing):
+        df = pd.DataFrame({"A": data_missing})
+
+        # defaults
+        result = df.dropna()
+        expected = df.iloc[[1]]
+        self.assert_frame_equal(result, expected)
+
+        # axis = 1
+        result = df.dropna(axis='columns')
+        expected = pd.DataFrame(index=[0, 1])
+        self.assert_frame_equal(result, expected)
+
+        # multiple
+        df = pd.DataFrame({"A": data_missing,
+                           "B": [1, np.nan]})
+        result = df.dropna()
+        expected = df.iloc[:0]
+        self.assert_frame_equal(result, expected)
+
+    def test_fillna_scalar(self, data_missing):
+        valid = data_missing[1]
+        result = data_missing.fillna(valid)
+        expected = data_missing.fillna(valid)
+        self.assert_extension_array_equal(result, expected)
+
+    def test_fillna_limit_pad(self, data_missing):
+        arr = data_missing.take([1, 0, 0, 0, 1])
+        result = pd.Series(arr).fillna(method='ffill', limit=2)
+        expected = pd.Series(data_missing.take([1, 1, 1, 0, 1]))
+        self.assert_series_equal(result, expected)
+
+    def test_fillna_limit_backfill(self, data_missing):
+        arr = data_missing.take([1, 0, 0, 0, 1])
+        result = pd.Series(arr).fillna(method='backfill', limit=2)
+        expected = pd.Series(data_missing.take([1, 0, 1, 1, 1]))
+        self.assert_series_equal(result, expected)
+
+    def test_fillna_series(self, data_missing):
+        fill_value = data_missing[1]
+        ser = pd.Series(data_missing)
+
+        result = ser.fillna(fill_value)
+        expected = pd.Series(data_missing._from_sequence(
+            [fill_value, fill_value], dtype=data_missing.dtype))
+        self.assert_series_equal(result, expected)
+
+        # Fill with a series
+        result = ser.fillna(expected)
+        self.assert_series_equal(result, expected)
+
+        # Fill with a series not affecting the missing values
+        result = ser.fillna(ser)
+        self.assert_series_equal(result, ser)
+
+    @pytest.mark.parametrize('method', ['ffill', 'bfill'])
+    def test_fillna_series_method(self, data_missing, method):
+        fill_value = data_missing[1]
+
+        if method == 'ffill':
+            data_missing = data_missing[::-1]
+
+        result = pd.Series(data_missing).fillna(method=method)
+        expected = pd.Series(data_missing._from_sequence(
+            [fill_value, fill_value], dtype=data_missing.dtype))
+
+        self.assert_series_equal(result, expected)
+
+    def test_fillna_frame(self, data_missing):
+        fill_value = data_missing[1]
+
+        result = pd.DataFrame({
+            "A": data_missing,
+            "B": [1, 2]
+        }).fillna(fill_value)
+
+        expected = pd.DataFrame({
+            "A": data_missing._from_sequence([fill_value, fill_value],
+                                             dtype=data_missing.dtype),
+            "B": [1, 2],
+        })
+
+        self.assert_frame_equal(result, expected)
+
+    def test_fillna_fill_other(self, data):
+        result = pd.DataFrame({
+            "A": data,
+            "B": [np.nan] * len(data)
+        }).fillna({"B": 0.0})
+
+        expected = pd.DataFrame({
+            "A": data,
+            "B": [0.0] * len(result),
+        })
+
+        self.assert_frame_equal(result, expected)

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/ops.py

@@ -0,0 +1,166 @@
+import operator
+
+import pytest
+
+import pandas as pd
+from pandas.core import ops
+
+from .base import BaseExtensionTests
+
+
+class BaseOpsUtil(BaseExtensionTests):
+
+    def get_op_from_name(self, op_name):
+        short_opname = op_name.strip('_')
+        try:
+            op = getattr(operator, short_opname)
+        except AttributeError:
+            # Assume it is the reverse operator
+            rop = getattr(operator, short_opname[1:])
+            op = lambda x, y: rop(y, x)
+
+        return op
+
+    def check_opname(self, s, op_name, other, exc=Exception):
+        op = self.get_op_from_name(op_name)
+
+        self._check_op(s, op, other, op_name, exc)
+
+    def _check_op(self, s, op, other, op_name, exc=NotImplementedError):
+        if exc is None:
+            result = op(s, other)
+            expected = s.combine(other, op)
+            self.assert_series_equal(result, expected)
+        else:
+            with pytest.raises(exc):
+                op(s, other)
+
+    def _check_divmod_op(self, s, op, other, exc=Exception):
+        # divmod has multiple return values, so check separatly
+        if exc is None:
+            result_div, result_mod = op(s, other)
+            if op is divmod:
+                expected_div, expected_mod = s // other, s % other
+            else:
+                expected_div, expected_mod = other // s, other % s
+            self.assert_series_equal(result_div, expected_div)
+            self.assert_series_equal(result_mod, expected_mod)
+        else:
+            with pytest.raises(exc):
+                divmod(s, other)
+
+
+class BaseArithmeticOpsTests(BaseOpsUtil):
+    """Various Series and DataFrame arithmetic ops methods.
+
+    Subclasses supporting various ops should set the class variables
+    to indicate that they support ops of that kind
+
+    * series_scalar_exc = TypeError
+    * frame_scalar_exc = TypeError
+    * series_array_exc = TypeError
+    * divmod_exc = TypeError
+    """
+    series_scalar_exc = TypeError
+    frame_scalar_exc = TypeError
+    series_array_exc = TypeError
+    divmod_exc = TypeError
+
+    def test_arith_series_with_scalar(self, data, all_arithmetic_operators):
+        # series & scalar
+        op_name = all_arithmetic_operators
+        s = pd.Series(data)
+        self.check_opname(s, op_name, s.iloc[0], exc=self.series_scalar_exc)
+
+    @pytest.mark.xfail(run=False, reason="_reduce needs implementation")
+    def test_arith_frame_with_scalar(self, data, all_arithmetic_operators):
+        # frame & scalar
+        op_name = all_arithmetic_operators
+        df = pd.DataFrame({'A': data})
+        self.check_opname(df, op_name, data[0], exc=self.frame_scalar_exc)
+
+    def test_arith_series_with_array(self, data, all_arithmetic_operators):
+        # ndarray & other series
+        op_name = all_arithmetic_operators
+        s = pd.Series(data)
+        self.check_opname(s, op_name, pd.Series([s.iloc[0]] * len(s)),
+                          exc=self.series_array_exc)
+
+    def test_divmod(self, data):
+        s = pd.Series(data)
+        self._check_divmod_op(s, divmod, 1, exc=self.divmod_exc)
+        self._check_divmod_op(1, ops.rdivmod, s, exc=self.divmod_exc)
+
+    def test_divmod_series_array(self, data):
+        s = pd.Series(data)
+        self._check_divmod_op(s, divmod, data)
+
+    def test_add_series_with_extension_array(self, data):
+        s = pd.Series(data)
+        result = s + data
+        expected = pd.Series(data + data)
+        self.assert_series_equal(result, expected)
+
+    def test_error(self, data, all_arithmetic_operators):
+        # invalid ops
+        op_name = all_arithmetic_operators
+        with pytest.raises(AttributeError):
+            getattr(data, op_name)
+
+    def test_direct_arith_with_series_returns_not_implemented(self, data):
+        # EAs should return NotImplemented for ops with Series.
+        # Pandas takes care of unboxing the series and calling the EA's op.
+        other = pd.Series(data)
+        if hasattr(data, '__add__'):
+            result = data.__add__(other)
+            assert result is NotImplemented
+        else:
+            raise pytest.skip(
+                "{} does not implement add".format(data.__class__.__name__)
+            )
+
+
+class BaseComparisonOpsTests(BaseOpsUtil):
+    """Various Series and DataFrame comparison ops methods."""
+
+    def _compare_other(self, s, data, op_name, other):
+        op = self.get_op_from_name(op_name)
+        if op_name == '__eq__':
+            assert getattr(data, op_name)(other) is NotImplemented
+            assert not op(s, other).all()
+        elif op_name == '__ne__':
+            assert getattr(data, op_name)(other) is NotImplemented
+            assert op(s, other).all()
+
+        else:
+
+            # array
+            assert getattr(data, op_name)(other) is NotImplemented
+
+            # series
+            s = pd.Series(data)
+            with pytest.raises(TypeError):
+                op(s, other)
+
+    def test_compare_scalar(self, data, all_compare_operators):
+        op_name = all_compare_operators
+        s = pd.Series(data)
+        self._compare_other(s, data, op_name, 0)
+
+    def test_compare_array(self, data, all_compare_operators):
+        op_name = all_compare_operators
+        s = pd.Series(data)
+        other = pd.Series([data[0]] * len(data))
+        self._compare_other(s, data, op_name, other)
+
+    def test_direct_arith_with_series_returns_not_implemented(self, data):
+        # EAs should return NotImplemented for ops with Series.
+        # Pandas takes care of unboxing the series and calling the EA's op.
+        other = pd.Series(data)
+        if hasattr(data, '__eq__'):
+            result = data.__eq__(other)
+            assert result is NotImplemented
+        else:
+            raise pytest.skip(
+                "{} does not implement __eq__".format(data.__class__.__name__)
+            )

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/printing.py

@@ -0,0 +1,44 @@
+import io
+
+import pytest
+
+import pandas as pd
+from pandas import compat
+
+from .base import BaseExtensionTests
+
+
+class BasePrintingTests(BaseExtensionTests):
+    """Tests checking the formatting of your EA when printed."""
+
+    @pytest.mark.parametrize("size", ["big", "small"])
+    def test_array_repr(self, data, size):
+        if size == "small":
+            data = data[:5]
+        else:
+            data = type(data)._concat_same_type([data] * 5)
+
+        result = repr(data)
+        assert data.__class__.__name__ in result
+        assert 'Length: {}'.format(len(data)) in result
+        assert str(data.dtype) in result
+        if size == 'big':
+            assert '...' in result
+
+    def test_array_repr_unicode(self, data):
+        result = compat.text_type(data)
+        assert isinstance(result, compat.text_type)
+
+    def test_series_repr(self, data):
+        ser = pd.Series(data)
+        assert data.dtype.name in repr(ser)
+
+    def test_dataframe_repr(self, data):
+        df = pd.DataFrame({"A": data})
+        repr(df)
+
+    def test_dtype_name_in_info(self, data):
+        buf = io.StringIO()
+        pd.DataFrame({"A": data}).info(buf=buf)
+        result = buf.getvalue()
+        assert data.dtype.name in result

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/reduce.py

@@ -0,0 +1,61 @@
+import warnings
+
+import pytest
+
+import pandas as pd
+import pandas.util.testing as tm
+
+from .base import BaseExtensionTests
+
+
+class BaseReduceTests(BaseExtensionTests):
+    """
+    Reduction specific tests. Generally these only
+    make sense for numeric/boolean operations.
+    """
+    def check_reduce(self, s, op_name, skipna):
+        result = getattr(s, op_name)(skipna=skipna)
+        expected = getattr(s.astype('float64'), op_name)(skipna=skipna)
+        tm.assert_almost_equal(result, expected)
+
+
+class BaseNoReduceTests(BaseReduceTests):
+    """ we don't define any reductions """
+
+    @pytest.mark.parametrize('skipna', [True, False])
+    def test_reduce_series_numeric(self, data, all_numeric_reductions, skipna):
+        op_name = all_numeric_reductions
+        s = pd.Series(data)
+
+        with pytest.raises(TypeError):
+            getattr(s, op_name)(skipna=skipna)
+
+    @pytest.mark.parametrize('skipna', [True, False])
+    def test_reduce_series_boolean(self, data, all_boolean_reductions, skipna):
+        op_name = all_boolean_reductions
+        s = pd.Series(data)
+
+        with pytest.raises(TypeError):
+            getattr(s, op_name)(skipna=skipna)
+
+
+class BaseNumericReduceTests(BaseReduceTests):
+
+    @pytest.mark.parametrize('skipna', [True, False])
+    def test_reduce_series(self, data, all_numeric_reductions, skipna):
+        op_name = all_numeric_reductions
+        s = pd.Series(data)
+
+        # min/max with empty produce numpy warnings
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", RuntimeWarning)
+            self.check_reduce(s, op_name, skipna)
+
+
+class BaseBooleanReduceTests(BaseReduceTests):
+
+    @pytest.mark.parametrize('skipna', [True, False])
+    def test_reduce_series(self, data, all_boolean_reductions, skipna):
+        op_name = all_boolean_reductions
+        s = pd.Series(data)
+        self.check_reduce(s, op_name, skipna)

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/reshaping.py

@@ -0,0 +1,271 @@
+import itertools
+
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas.core.internals import ExtensionBlock
+
+from .base import BaseExtensionTests
+
+
+class BaseReshapingTests(BaseExtensionTests):
+    """Tests for reshaping and concatenation."""
+    @pytest.mark.parametrize('in_frame', [True, False])
+    def test_concat(self, data, in_frame):
+        wrapped = pd.Series(data)
+        if in_frame:
+            wrapped = pd.DataFrame(wrapped)
+        result = pd.concat([wrapped, wrapped], ignore_index=True)
+
+        assert len(result) == len(data) * 2
+
+        if in_frame:
+            dtype = result.dtypes[0]
+        else:
+            dtype = result.dtype
+
+        assert dtype == data.dtype
+        assert isinstance(result._data.blocks[0], ExtensionBlock)
+
+    @pytest.mark.parametrize('in_frame', [True, False])
+    def test_concat_all_na_block(self, data_missing, in_frame):
+        valid_block = pd.Series(data_missing.take([1, 1]), index=[0, 1])
+        na_block = pd.Series(data_missing.take([0, 0]), index=[2, 3])
+        if in_frame:
+            valid_block = pd.DataFrame({"a": valid_block})
+            na_block = pd.DataFrame({"a": na_block})
+        result = pd.concat([valid_block, na_block])
+        if in_frame:
+            expected = pd.DataFrame({"a": data_missing.take([1, 1, 0, 0])})
+            self.assert_frame_equal(result, expected)
+        else:
+            expected = pd.Series(data_missing.take([1, 1, 0, 0]))
+            self.assert_series_equal(result, expected)
+
+    def test_concat_mixed_dtypes(self, data):
+        # https://github.com/pandas-dev/pandas/issues/20762
+        df1 = pd.DataFrame({'A': data[:3]})
+        df2 = pd.DataFrame({"A": [1, 2, 3]})
+        df3 = pd.DataFrame({"A": ['a', 'b', 'c']}).astype('category')
+        dfs = [df1, df2, df3]
+
+        # dataframes
+        result = pd.concat(dfs)
+        expected = pd.concat([x.astype(object) for x in dfs])
+        self.assert_frame_equal(result, expected)
+
+        # series
+        result = pd.concat([x['A'] for x in dfs])
+        expected = pd.concat([x['A'].astype(object) for x in dfs])
+        self.assert_series_equal(result, expected)
+
+        # simple test for just EA and one other
+        result = pd.concat([df1, df2])
+        expected = pd.concat([df1.astype('object'), df2.astype('object')])
+        self.assert_frame_equal(result, expected)
+
+        result = pd.concat([df1['A'], df2['A']])
+        expected = pd.concat([df1['A'].astype('object'),
+                              df2['A'].astype('object')])
+        self.assert_series_equal(result, expected)
+
+    def test_concat_columns(self, data, na_value):
+        df1 = pd.DataFrame({'A': data[:3]})
+        df2 = pd.DataFrame({'B': [1, 2, 3]})
+
+        expected = pd.DataFrame({'A': data[:3], 'B': [1, 2, 3]})
+        result = pd.concat([df1, df2], axis=1)
+        self.assert_frame_equal(result, expected)
+        result = pd.concat([df1['A'], df2['B']], axis=1)
+        self.assert_frame_equal(result, expected)
+
+        # non-aligned
+        df2 = pd.DataFrame({'B': [1, 2, 3]}, index=[1, 2, 3])
+        expected = pd.DataFrame({
+            'A': data._from_sequence(list(data[:3]) + [na_value],
+                                     dtype=data.dtype),
+            'B': [np.nan, 1, 2, 3]})
+
+        result = pd.concat([df1, df2], axis=1)
+        self.assert_frame_equal(result, expected)
+        result = pd.concat([df1['A'], df2['B']], axis=1)
+        self.assert_frame_equal(result, expected)
+
+    def test_align(self, data, na_value):
+        a = data[:3]
+        b = data[2:5]
+        r1, r2 = pd.Series(a).align(pd.Series(b, index=[1, 2, 3]))
+
+        # Assumes that the ctor can take a list of scalars of the type
+        e1 = pd.Series(data._from_sequence(list(a) + [na_value],
+                                           dtype=data.dtype))
+        e2 = pd.Series(data._from_sequence([na_value] + list(b),
+                                           dtype=data.dtype))
+        self.assert_series_equal(r1, e1)
+        self.assert_series_equal(r2, e2)
+
+    def test_align_frame(self, data, na_value):
+        a = data[:3]
+        b = data[2:5]
+        r1, r2 = pd.DataFrame({'A': a}).align(
+            pd.DataFrame({'A': b}, index=[1, 2, 3])
+        )
+
+        # Assumes that the ctor can take a list of scalars of the type
+        e1 = pd.DataFrame({'A': data._from_sequence(list(a) + [na_value],
+                                                    dtype=data.dtype)})
+        e2 = pd.DataFrame({'A': data._from_sequence([na_value] + list(b),
+                                                    dtype=data.dtype)})
+        self.assert_frame_equal(r1, e1)
+        self.assert_frame_equal(r2, e2)
+
+    def test_align_series_frame(self, data, na_value):
+        # https://github.com/pandas-dev/pandas/issues/20576
+        ser = pd.Series(data, name='a')
+        df = pd.DataFrame({"col": np.arange(len(ser) + 1)})
+        r1, r2 = ser.align(df)
+
+        e1 = pd.Series(data._from_sequence(list(data) + [na_value],
+                                           dtype=data.dtype),
+                       name=ser.name)
+
+        self.assert_series_equal(r1, e1)
+        self.assert_frame_equal(r2, df)
+
+    def test_set_frame_expand_regular_with_extension(self, data):
+        df = pd.DataFrame({"A": [1] * len(data)})
+        df['B'] = data
+        expected = pd.DataFrame({"A": [1] * len(data), "B": data})
+        self.assert_frame_equal(df, expected)
+
+    def test_set_frame_expand_extension_with_regular(self, data):
+        df = pd.DataFrame({'A': data})
+        df['B'] = [1] * len(data)
+        expected = pd.DataFrame({"A": data, "B": [1] * len(data)})
+        self.assert_frame_equal(df, expected)
+
+    def test_set_frame_overwrite_object(self, data):
+        # https://github.com/pandas-dev/pandas/issues/20555
+        df = pd.DataFrame({"A": [1] * len(data)}, dtype=object)
+        df['A'] = data
+        assert df.dtypes['A'] == data.dtype
+
+    def test_merge(self, data, na_value):
+        # GH-20743
+        df1 = pd.DataFrame({'ext': data[:3], 'int1': [1, 2, 3],
+                            'key': [0, 1, 2]})
+        df2 = pd.DataFrame({'int2': [1, 2, 3, 4], 'key': [0, 0, 1, 3]})
+
+        res = pd.merge(df1, df2)
+        exp = pd.DataFrame(
+            {'int1': [1, 1, 2], 'int2': [1, 2, 3], 'key': [0, 0, 1],
+             'ext': data._from_sequence([data[0], data[0], data[1]],
+                                        dtype=data.dtype)})
+        self.assert_frame_equal(res, exp[['ext', 'int1', 'key', 'int2']])
+
+        res = pd.merge(df1, df2, how='outer')
+        exp = pd.DataFrame(
+            {'int1': [1, 1, 2, 3, np.nan], 'int2': [1, 2, 3, np.nan, 4],
+             'key': [0, 0, 1, 2, 3],
+             'ext': data._from_sequence(
+                 [data[0], data[0], data[1], data[2], na_value],
+                 dtype=data.dtype)})
+        self.assert_frame_equal(res, exp[['ext', 'int1', 'key', 'int2']])
+
+    def test_merge_on_extension_array(self, data):
+        # GH 23020
+        a, b = data[:2]
+        key = type(data)._from_sequence([a, b], dtype=data.dtype)
+
+        df = pd.DataFrame({"key": key, "val": [1, 2]})
+        result = pd.merge(df, df, on='key')
+        expected = pd.DataFrame({"key": key,
+                                 "val_x": [1, 2],
+                                 "val_y": [1, 2]})
+        self.assert_frame_equal(result, expected)
+
+        # order
+        result = pd.merge(df.iloc[[1, 0]], df, on='key')
+        expected = expected.iloc[[1, 0]].reset_index(drop=True)
+        self.assert_frame_equal(result, expected)
+
+    def test_merge_on_extension_array_duplicates(self, data):
+        # GH 23020
+        a, b = data[:2]
+        key = type(data)._from_sequence([a, b, a], dtype=data.dtype)
+        df1 = pd.DataFrame({"key": key, "val": [1, 2, 3]})
+        df2 = pd.DataFrame({"key": key, "val": [1, 2, 3]})
+
+        result = pd.merge(df1, df2, on='key')
+        expected = pd.DataFrame({
+            "key": key.take([0, 0, 0, 0, 1]),
+            "val_x": [1, 1, 3, 3, 2],
+            "val_y": [1, 3, 1, 3, 2],
+        })
+        self.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize("columns", [
+        ["A", "B"],
+        pd.MultiIndex.from_tuples([('A', 'a'), ('A', 'b')],
+                                  names=['outer', 'inner']),
+    ])
+    def test_stack(self, data, columns):
+        df = pd.DataFrame({"A": data[:5], "B": data[:5]})
+        df.columns = columns
+        result = df.stack()
+        expected = df.astype(object).stack()
+        # we need a second astype(object), in case the constructor inferred
+        # object -> specialized, as is done for period.
+        expected = expected.astype(object)
+
+        if isinstance(expected, pd.Series):
+            assert result.dtype == df.iloc[:, 0].dtype
+        else:
+            assert all(result.dtypes == df.iloc[:, 0].dtype)
+
+        result = result.astype(object)
+        self.assert_equal(result, expected)
+
+    @pytest.mark.parametrize("index", [
+        # Two levels, uniform.
+        pd.MultiIndex.from_product(([['A', 'B'], ['a', 'b']]),
+                                   names=['a', 'b']),
+
+        # non-uniform
+        pd.MultiIndex.from_tuples([('A', 'a'), ('A', 'b'), ('B', 'b')]),
+
+        # three levels, non-uniform
+        pd.MultiIndex.from_product([('A', 'B'), ('a', 'b', 'c'), (0, 1, 2)]),
+        pd.MultiIndex.from_tuples([
+            ('A', 'a', 1),
+            ('A', 'b', 0),
+            ('A', 'a', 0),
+            ('B', 'a', 0),
+            ('B', 'c', 1),
+        ]),
+    ])
+    @pytest.mark.parametrize("obj", ["series", "frame"])
+    def test_unstack(self, data, index, obj):
+        data = data[:len(index)]
+        if obj == "series":
+            ser = pd.Series(data, index=index)
+        else:
+            ser = pd.DataFrame({"A": data, "B": data}, index=index)
+
+        n = index.nlevels
+        levels = list(range(n))
+        # [0, 1, 2]
+        # [(0,), (1,), (2,), (0, 1), (0, 2), (1, 0), (1, 2), (2, 0), (2, 1)]
+        combinations = itertools.chain.from_iterable(
+            itertools.permutations(levels, i) for i in range(1, n)
+        )
+
+        for level in combinations:
+            result = ser.unstack(level=level)
+            assert all(isinstance(result[col].array, type(data))
+                       for col in result.columns)
+            expected = ser.astype(object).unstack(level=level)
+            result = result.astype(object)
+
+            self.assert_frame_equal(result, expected)

utils/venv/lib/python3.6/site-packages/pandas/tests/extension/base/setitem.py

@@ -0,0 +1,189 @@
+import operator
+
+import numpy as np
+import pytest
+
+import pandas as pd
+
+from .base import BaseExtensionTests
+
+
+class BaseSetitemTests(BaseExtensionTests):
+    def test_setitem_scalar_series(self, data, box_in_series):
+        if box_in_series:
+            data = pd.Series(data)
+        data[0] = data[1]
+        assert data[0] == data[1]
+
+    def test_setitem_sequence(self, data, box_in_series):
+        if box_in_series:
+            data = pd.Series(data)
+        original = data.copy()
+
+        data[[0, 1]] = [data[1], data[0]]
+        assert data[0] == original[1]
+        assert data[1] == original[0]
+
+    @pytest.mark.parametrize('as_array', [True, False])
+    def test_setitem_sequence_mismatched_length_raises(self, data, as_array):
+        ser = pd.Series(data)
+        original = ser.copy()
+        value = [data[0]]
+        if as_array:
+            value = data._from_sequence(value)
+
+        xpr = 'cannot set using a {} indexer with a different length'
+        with pytest.raises(ValueError, match=xpr.format('list-like')):
+            ser[[0, 1]] = value
+        # Ensure no modifications made before the exception
+        self.assert_series_equal(ser, original)
+
+        with pytest.raises(ValueError, match=xpr.format('slice')):
+            ser[slice(3)] = value
+        self.assert_series_equal(ser, original)
+
+    def test_setitem_empty_indxer(self, data, box_in_series):
+        if box_in_series:
+            data = pd.Series(data)
+        original = data.copy()
+        data[np.array([], dtype=int)] = []
+        self.assert_equal(data, original)
+
+    def test_setitem_sequence_broadcasts(self, data, box_in_series):
+        if box_in_series:
+            data = pd.Series(data)
+        data[[0, 1]] = data[2]
+        assert data[0] == data[2]
+        assert data[1] == data[2]
+
+    @pytest.mark.parametrize('setter', ['loc', 'iloc'])
+    def test_setitem_scalar(self, data, setter):
+        arr = pd.Series(data)
+        setter = getattr(arr, setter)
+        operator.setitem(setter, 0, data[1])
+        assert arr[0] == data[1]
+
+    def test_setitem_loc_scalar_mixed(self, data):
+        df = pd.DataFrame({"A": np.arange(len(data)), "B": data})
+        df.loc[0, 'B'] = data[1]
+        assert df.loc[0, 'B'] == data[1]
+
+    def test_setitem_loc_scalar_single(self, data):
+        df = pd.DataFrame({"B": data})
+        df.loc[10, 'B'] = data[1]
+        assert df.loc[10, 'B'] == data[1]
+
+    def test_setitem_loc_scalar_multiple_homogoneous(self, data):
+        df = pd.DataFrame({"A": data, "B": data})
+        df.loc[10, 'B'] = data[1]
+        assert df.loc[10, 'B'] == data[1]
+
+    def test_setitem_iloc_scalar_mixed(self, data):
+        df = pd.DataFrame({"A": np.arange(len(data)), "B": data})
+        df.iloc[0, 1] = data[1]
+        assert df.loc[0, 'B'] == data[1]
+
+    def test_setitem_iloc_scalar_single(self, data):
+        df = pd.DataFrame({"B": data})
+        df.iloc[10, 0] = data[1]
+        assert df.loc[10, 'B'] == data[1]
+
+    def test_setitem_iloc_scalar_multiple_homogoneous(self, data):
+        df = pd.DataFrame({"A": data, "B": data})
+        df.iloc[10, 1] = data[1]
+        assert df.loc[10, 'B'] == data[1]
+
+    @pytest.mark.parametrize('as_callable', [True, False])
+    @pytest.mark.parametrize('setter', ['loc', None])
+    def test_setitem_mask_aligned(self, data, as_callable, setter):
+        ser = pd.Series(data)
+        mask = np.zeros(len(data), dtype=bool)
+        mask[:2] = True
+
+        if as_callable:
+            mask2 = lambda x: mask
+        else:
+            mask2 = mask
+
+        if setter:
+            # loc
+            target = getattr(ser, setter)
+        else:
+            # Series.__setitem__
+            target = ser
+
+        operator.setitem(target, mask2, data[5:7])
+
+        ser[mask2] = data[5:7]
+        assert ser[0] == data[5]
+        assert ser[1] == data[6]
+
+    @pytest.mark.parametrize('setter', ['loc', None])
+    def test_setitem_mask_broadcast(self, data, setter):
+        ser = pd.Series(data)
+        mask = np.zeros(len(data), dtype=bool)
+        mask[:2] = True
+
+        if setter:   # loc
+            target = getattr(ser, setter)
+        else:  # __setitem__
+            target = ser
+
+        operator.setitem(target, mask, data[10])
+        assert ser[0] == data[10]
+        assert ser[1] == data[10]
+
+    def test_setitem_expand_columns(self, data):
+        df = pd.DataFrame({"A": data})
+        result = df.copy()
+        result['B'] = 1
+        expected = pd.DataFrame({"A": data, "B": [1] * len(data)})
+        self.assert_frame_equal(result, expected)
+
+        result = df.copy()
+        result.loc[:, 'B'] = 1
+        self.assert_frame_equal(result, expected)
+
+        # overwrite with new type
+        result['B'] = data
+        expected = pd.DataFrame({"A": data, "B": data})
+        self.assert_frame_equal(result, expected)
+
+    def test_setitem_expand_with_extension(self, data):
+        df = pd.DataFrame({"A": [1] * len(data)})
+        result = df.copy()
+        result['B'] = data
+        expected = pd.DataFrame({"A": [1] * len(data), "B": data})
+        self.assert_frame_equal(result, expected)
+
+        result = df.copy()
+        result.loc[:, 'B'] = data
+        self.assert_frame_equal(result, expected)
+
+    def test_setitem_frame_invalid_length(self, data):
+        df = pd.DataFrame({"A": [1] * len(data)})
+        xpr = "Length of values does not match length of index"
+        with pytest.raises(ValueError, match=xpr):
+            df['B'] = data[:5]
+
+    @pytest.mark.xfail(reason="GH#20441: setitem on extension types.")
+    def test_setitem_tuple_index(self, data):
+        s = pd.Series(data[:2], index=[(0, 0), (0, 1)])
+        expected = pd.Series(data.take([1, 1]), index=s.index)
+        s[(0, 1)] = data[1]
+        self.assert_series_equal(s, expected)
+
+    def test_setitem_slice_mismatch_length_raises(self, data):
+        arr = data[:5]
+        with pytest.raises(ValueError):
+            arr[:1] = arr[:2]
+
+    def test_setitem_slice_array(self, data):
+        arr = data[:5].copy()
+        arr[:5] = data[-5:]
+        self.assert_extension_array_equal(arr, data[-5:])
+
+    def test_setitem_scalar_key_sequence_raise(self, data):
+        arr = data[:5].copy()
+        with pytest.raises(ValueError):
+            arr[0] = arr[[0, 1]]