started work on backend

2019-01-21 17:36:00 +01:00
parent a1a8bca34b
commit 9f9a7e4974
4032 changed files with 745079 additions and 0 deletions
@@ -0,0 +1,105 @@
+import decimal
+import numbers
+import random
+import sys
+
+import numpy as np
+
+import pandas as pd
+from pandas.core.arrays import ExtensionArray
+from pandas.core.dtypes.base import ExtensionDtype
+
+
+class DecimalDtype(ExtensionDtype):
+    type = decimal.Decimal
+    name = 'decimal'
+    na_value = decimal.Decimal('NaN')
+
+    @classmethod
+    def construct_from_string(cls, string):
+        if string == cls.name:
+            return cls()
+        else:
+            raise TypeError("Cannot construct a '{}' from "
+                            "'{}'".format(cls, string))
+
+
+class DecimalArray(ExtensionArray):
+    dtype = DecimalDtype()
+
+    def __init__(self, values):
+        assert all(isinstance(v, decimal.Decimal) for v in values)
+        values = np.asarray(values, dtype=object)
+
+        self._data = values
+        # Some aliases for common attribute names to ensure pandas supports
+        # these
+        self._items = self.data = self._data
+        # those aliases are currently not working due to assumptions
+        # in internal code (GH-20735)
+        # self._values = self.values = self.data
+
+    @classmethod
+    def _from_sequence(cls, scalars):
+        return cls(scalars)
+
+    @classmethod
+    def _from_factorized(cls, values, original):
+        return cls(values)
+
+    def __getitem__(self, item):
+        if isinstance(item, numbers.Integral):
+            return self._data[item]
+        else:
+            return type(self)(self._data[item])
+
+    def take(self, indexer, allow_fill=False, fill_value=None):
+        from pandas.api.extensions import take
+
+        data = self._data
+        if allow_fill and fill_value is None:
+            fill_value = self.dtype.na_value
+
+        result = take(data, indexer, fill_value=fill_value,
+                      allow_fill=allow_fill)
+        return self._from_sequence(result)
+
+    def copy(self, deep=False):
+        if deep:
+            return type(self)(self._data.copy())
+        return type(self)(self)
+
+    def __setitem__(self, key, value):
+        if pd.api.types.is_list_like(value):
+            value = [decimal.Decimal(v) for v in value]
+        else:
+            value = decimal.Decimal(value)
+        self._data[key] = value
+
+    def __len__(self):
+        return len(self._data)
+
+    def __repr__(self):
+        return 'DecimalArray({!r})'.format(self._data)
+
+    @property
+    def nbytes(self):
+        n = len(self)
+        if n:
+            return n * sys.getsizeof(self[0])
+        return 0
+
+    def isna(self):
+        return np.array([x.is_nan() for x in self._data], dtype=bool)
+
+    @property
+    def _na_value(self):
+        return decimal.Decimal('NaN')
+
+    @classmethod
+    def _concat_same_type(cls, to_concat):
+        return cls(np.concatenate([x._data for x in to_concat]))
+
+
+def make_data():
+    return [decimal.Decimal(random.random()) for _ in range(100)]
@@ -0,0 +1,185 @@
+import decimal
+
+import numpy as np
+import pandas as pd
+import pandas.util.testing as tm
+import pytest
+
+from pandas.tests.extension import base
+
+from .array import DecimalDtype, DecimalArray, make_data
+
+
+@pytest.fixture
+def dtype():
+    return DecimalDtype()
+
+
+@pytest.fixture
+def data():
+    return DecimalArray(make_data())
+
+
+@pytest.fixture
+def data_missing():
+    return DecimalArray([decimal.Decimal('NaN'), decimal.Decimal(1)])
+
+
+@pytest.fixture
+def data_for_sorting():
+    return DecimalArray([decimal.Decimal('1'),
+                         decimal.Decimal('2'),
+                         decimal.Decimal('0')])
+
+
+@pytest.fixture
+def data_missing_for_sorting():
+    return DecimalArray([decimal.Decimal('1'),
+                         decimal.Decimal('NaN'),
+                         decimal.Decimal('0')])
+
+
+@pytest.fixture
+def na_cmp():
+    return lambda x, y: x.is_nan() and y.is_nan()
+
+
+@pytest.fixture
+def na_value():
+    return decimal.Decimal("NaN")
+
+
+@pytest.fixture
+def data_for_grouping():
+    b = decimal.Decimal('1.0')
+    a = decimal.Decimal('0.0')
+    c = decimal.Decimal('2.0')
+    na = decimal.Decimal('NaN')
+    return DecimalArray([b, b, na, na, a, a, b, c])
+
+
+class BaseDecimal(object):
+
+    def assert_series_equal(self, left, right, *args, **kwargs):
+
+        left_na = left.isna()
+        right_na = right.isna()
+
+        tm.assert_series_equal(left_na, right_na)
+        return tm.assert_series_equal(left[~left_na],
+                                      right[~right_na],
+                                      *args, **kwargs)
+
+    def assert_frame_equal(self, left, right, *args, **kwargs):
+        # TODO(EA): select_dtypes
+        tm.assert_index_equal(
+            left.columns, right.columns,
+            exact=kwargs.get('check_column_type', 'equiv'),
+            check_names=kwargs.get('check_names', True),
+            check_exact=kwargs.get('check_exact', False),
+            check_categorical=kwargs.get('check_categorical', True),
+            obj='{obj}.columns'.format(obj=kwargs.get('obj', 'DataFrame')))
+
+        decimals = (left.dtypes == 'decimal').index
+
+        for col in decimals:
+            self.assert_series_equal(left[col], right[col],
+                                     *args, **kwargs)
+
+        left = left.drop(columns=decimals)
+        right = right.drop(columns=decimals)
+        tm.assert_frame_equal(left, right, *args, **kwargs)
+
+
+class TestDtype(BaseDecimal, base.BaseDtypeTests):
+    pass
+
+
+class TestInterface(BaseDecimal, base.BaseInterfaceTests):
+    pass
+
+
+class TestConstructors(BaseDecimal, base.BaseConstructorsTests):
+    pass
+
+
+class TestReshaping(BaseDecimal, base.BaseReshapingTests):
+    pass
+
+
+class TestGetitem(BaseDecimal, base.BaseGetitemTests):
+
+    def test_take_na_value_other_decimal(self):
+        arr = DecimalArray([decimal.Decimal('1.0'),
+                            decimal.Decimal('2.0')])
+        result = arr.take([0, -1], allow_fill=True,
+                          fill_value=decimal.Decimal('-1.0'))
+        expected = DecimalArray([decimal.Decimal('1.0'),
+                                 decimal.Decimal('-1.0')])
+        self.assert_extension_array_equal(result, expected)
+
+
+class TestMissing(BaseDecimal, base.BaseMissingTests):
+    pass
+
+
+class TestMethods(BaseDecimal, base.BaseMethodsTests):
+    @pytest.mark.parametrize('dropna', [True, False])
+    @pytest.mark.xfail(reason="value_counts not implemented yet.")
+    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()
+
+        tm.assert_series_equal(result, expected)
+
+
+class TestCasting(BaseDecimal, base.BaseCastingTests):
+    pass
+
+
+class TestGroupby(BaseDecimal, base.BaseGroupbyTests):
+    pass
+
+
+def test_series_constructor_coerce_data_to_extension_dtype_raises():
+    xpr = ("Cannot cast data to extension dtype 'decimal'. Pass the "
+           "extension array directly.")
+    with tm.assert_raises_regex(ValueError, xpr):
+        pd.Series([0, 1, 2], dtype=DecimalDtype())
+
+
+def test_series_constructor_with_same_dtype_ok():
+    arr = DecimalArray([decimal.Decimal('10.0')])
+    result = pd.Series(arr, dtype=DecimalDtype())
+    expected = pd.Series(arr)
+    tm.assert_series_equal(result, expected)
+
+
+def test_series_constructor_coerce_extension_array_to_dtype_raises():
+    arr = DecimalArray([decimal.Decimal('10.0')])
+    xpr = r"Cannot specify a dtype 'int64' .* \('decimal'\)."
+
+    with tm.assert_raises_regex(ValueError, xpr):
+        pd.Series(arr, dtype='int64')
+
+
+def test_dataframe_constructor_with_same_dtype_ok():
+    arr = DecimalArray([decimal.Decimal('10.0')])
+
+    result = pd.DataFrame({"A": arr}, dtype=DecimalDtype())
+    expected = pd.DataFrame({"A": arr})
+    tm.assert_frame_equal(result, expected)
+
+
+def test_dataframe_constructor_with_different_dtype_raises():
+    arr = DecimalArray([decimal.Decimal('10.0')])
+
+    xpr = "Cannot coerce extension array to dtype 'int64'. "
+    with tm.assert_raises_regex(ValueError, xpr):
+        pd.DataFrame({"A": arr}, dtype='int64')