Python pandas.array方法代码示例

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def test_array_interface_tz(self):
        tz = "US/Central"
        data = DatetimeArray(pd.date_range('2017', periods=2, tz=tz))
        result = np.asarray(data)

        expected = np.array([pd.Timestamp('2017-01-01T00:00:00', tz=tz),
                             pd.Timestamp('2017-01-02T00:00:00', tz=tz)],
                            dtype=object)
        tm.assert_numpy_array_equal(result, expected)

        result = np.asarray(data, dtype=object)
        tm.assert_numpy_array_equal(result, expected)

        result = np.asarray(data, dtype='M8[ns]')

        expected = np.array(['2017-01-01T06:00:00',
                             '2017-01-02T06:00:00'], dtype="M8[ns]")
        tm.assert_numpy_array_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def test_sanitize_string_dtype():
    df = pd.DataFrame(
        {
            "string_object": ["a", "b", "c", "d"],
            "string_string": pd.array(["a", "b", "c", "d"], dtype="string"),
            "string_object_null": ["a", "b", None, "d"],
            "string_string_null": pd.array(["a", "b", None, "d"], dtype="string"),
        }
    )

    df_clean = sanitize_dataframe(df)
    assert {col.dtype.name for _, col in df_clean.iteritems()} == {"object"}

    result_python = {col_name: list(col) for col_name, col in df_clean.iteritems()}
    assert result_python == {
        "string_object": ["a", "b", "c", "d"],
        "string_string": ["a", "b", "c", "d"],
        "string_object_null": ["a", "b", None, "d"],
        "string_string_null": ["a", "b", None, "d"],
    } 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def test_sanitize_boolean_dtype():
    df = pd.DataFrame(
        {
            "bool_none": pd.array([True, False, None], dtype="boolean"),
            "none": pd.array([None, None, None], dtype="boolean"),
            "bool": pd.array([True, False, True], dtype="boolean"),
        }
    )

    df_clean = sanitize_dataframe(df)
    assert {col.dtype.name for _, col in df_clean.iteritems()} == {"object"}

    result_python = {col_name: list(col) for col_name, col in df_clean.iteritems()}
    assert result_python == {
        "bool_none": [True, False, None],
        "none": [None, None, None],
        "bool": [True, False, True],
    } 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def add_facility_id_unit_id_epa(df):
    """
    Harmonize columns that are added later.

    The datapackage validation checks for consistent column names, and these
    two columns aren't present before August 2008, so this adds them in.

    Args:
        df (pandas.DataFrame): A CEMS dataframe

    Returns:
        pandas.Dataframe: The same DataFrame guaranteed to have int facility_id
        and unit_id_epa cols.

    """
    if ("facility_id" not in df.columns) or ("unit_id_epa" not in df.columns):
        # Can't just assign np.NaN and get an integer NaN, so make a new array
        # with the right shape:
        na_col = pd.array(np.full(df.shape[0], np.NaN), dtype="Int64")
        if "facility_id" not in df.columns:
            df["facility_id"] = na_col
        if "unit_id_epa" not in df.columns:
            df["unit_id_epa"] = na_col
    return df 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def kind(self) -> str:
        """Return a character code (one of 'biufcmMOSUV'), default 'O'.

        This should match the NumPy dtype used when the array is
        converted to an ndarray, which is probably 'O' for object if
        the extension type cannot be represented as a built-in NumPy
        type.

        See Also
        --------
        numpy.dtype.kind
        """
        if pa.types.is_date(self.arrow_dtype):
            return "O"
        else:
            return np.dtype(self.arrow_dtype.to_pandas_dtype()).kind 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def test_pandas_array(self, data):
        # pd.array(extension_array) should be idempotent...
        result = pd.array(data)
        self.assert_extension_array_equal(result, data) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
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) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def data_missing(allow_in_pandas):
    return PandasArray(np.array([np.nan, (1,)])) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def data_for_sorting(allow_in_pandas):
    """Length-3 array with a known sort order.

    This should be three items [B, C, A] with
    A < B < C
    """
    # Use an empty tuple for first element, then remove,
    # to disable np.array's shape inference.
    return PandasArray(
        np.array([(), (2,), (3,), (1,)])[1:]
    ) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def data_missing_for_sorting(allow_in_pandas):
    """Length-3 array with a known sort order.

    This should be three items [B, NA, A] with
    A < B and NA missing.
    """
    return PandasArray(
        np.array([(1,), np.nan, (0,)])
    ) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def test_array_interface(self, data):
        # NumPy array shape inference
        pass 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def test_shift_fill_value(self, data):
        # np.array shape inference. Shift implementation fails.
        super().test_shift_fill_value(data) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def test_fillna_copy_frame(self, data_missing):
        # The "scalar" for this array isn't a scalar.
        pass 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def test_fillna_copy_series(self, data_missing):
        # The "scalar" for this array isn't a scalar.
        pass 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import array [as 别名]
def test_array(data, dtype, expected):
    result = pd.array(data, dtype=dtype)
    tm.assert_equal(result, expected)