How to use the datacompy.utils.columns_equal function in datacompy

|2017-01-01|False
||True"""
    df = pd.read_csv(six.StringIO(data), sep="|")
    # First compare just the strings
    actual_out = utils.columns_equal(df.a, df.b, rel_tol=0.2, ignore_spaces=True, ignore_case=True)
    expect_out = df["expected"]
    assert_series_equal(expect_out, actual_out, check_names=False)

    # Then compare converted to datetime objects
    df["a"] = pd.to_datetime(df["a"])
    df["b"] = pd.to_datetime(df["b"])
    actual_out = utils.columns_equal(df.a, df.b, rel_tol=0.2, ignore_spaces=True)
    expect_out = df["expected"]
    assert_series_equal(expect_out, actual_out, check_names=False)
    # and reverse
    actual_out_rev = utils.columns_equal(df.b, df.a, rel_tol=0.2, ignore_spaces=True)
    assert_series_equal(expect_out, actual_out_rev, check_names=False)

def test_decimal_columns_equal():
    df = pd.DataFrame(
        [
            {"a": Decimal("1"), "b": Decimal("1"), "expected": True},
            {"a": Decimal("1.3"), "b": Decimal("1.3"), "expected": True},
            {"a": Decimal("1.000003"), "b": Decimal("1.000003"), "expected": True},
            {"a": Decimal("1.000000004"), "b": Decimal("1.000000003"), "expected": False},
            {"a": Decimal("1.3"), "b": Decimal("1.2"), "expected": False},
            {"a": np.nan, "b": np.nan, "expected": True},
            {"a": np.nan, "b": Decimal("1"), "expected": False},
            {"a": Decimal("1"), "b": np.nan, "expected": False},
        ]
    )
    actual_out = utils.columns_equal(df.a, df.b)
    expect_out = df["expected"]
    assert_series_equal(expect_out, actual_out, check_names=False)

def test_mixed_column():
    df = pd.DataFrame(
        [
            {"a": "hi", "b": "hi", "expected": True},
            {"a": 1, "b": 1, "expected": True},
            {"a": np.inf, "b": np.inf, "expected": True},
            {"a": Decimal("1"), "b": Decimal("1"), "expected": True},
            {"a": 1, "b": "1", "expected": False},
            {"a": 1, "b": "yo", "expected": False},
        ]
    )
    actual_out = utils.columns_equal(df.a, df.b)
    expect_out = df["expected"]
    assert_series_equal(expect_out, actual_out, check_names=False)

def test_date_columns_unequal():
    """I want datetime fields to match with dates stored as strings
    """
    df = pd.DataFrame([{"a": "2017-01-01", "b": "2017-01-02"}, {"a": "2017-01-01"}])
    df["a_dt"] = pd.to_datetime(df["a"])
    df["b_dt"] = pd.to_datetime(df["b"])
    assert utils.columns_equal(df.a, df.a_dt).all()
    assert utils.columns_equal(df.b, df.b_dt).all()
    assert utils.columns_equal(df.a_dt, df.a).all()
    assert utils.columns_equal(df.b_dt, df.b).all()
    assert not utils.columns_equal(df.b_dt, df.a).any()
    assert not utils.columns_equal(df.a_dt, df.b).any()
    assert not utils.columns_equal(df.a, df.b_dt).any()
    assert not utils.columns_equal(df.b, df.a_dt).any()

def test_date_columns_unequal():
    """I want datetime fields to match with dates stored as strings
    """
    df = pd.DataFrame([{"a": "2017-01-01", "b": "2017-01-02"}, {"a": "2017-01-01"}])
    df["a_dt"] = pd.to_datetime(df["a"])
    df["b_dt"] = pd.to_datetime(df["b"])
    assert utils.columns_equal(df.a, df.a_dt).all()
    assert utils.columns_equal(df.b, df.b_dt).all()
    assert utils.columns_equal(df.a_dt, df.a).all()
    assert utils.columns_equal(df.b_dt, df.b).all()
    assert not utils.columns_equal(df.b_dt, df.a).any()
    assert not utils.columns_equal(df.a_dt, df.b).any()
    assert not utils.columns_equal(df.a, df.b_dt).any()
    assert not utils.columns_equal(df.b, df.a_dt).any()

def test_decimal_float_columns_equal():
    df = pd.DataFrame(
        [
            {"a": Decimal("1"), "b": 1, "expected": True},
            {"a": Decimal("1.3"), "b": 1.3, "expected": True},
            {"a": Decimal("1.000003"), "b": 1.000003, "expected": True},
            {"a": Decimal("1.000000004"), "b": 1.000000003, "expected": False},
            {"a": Decimal("1.3"), "b": 1.2, "expected": False},
            {"a": np.nan, "b": np.nan, "expected": True},
            {"a": np.nan, "b": 1, "expected": False},
            {"a": Decimal("1"), "b": np.nan, "expected": False},
        ]
    )
    actual_out = utils.columns_equal(df.a, df.b)
    expect_out = df["expected"]
    assert_series_equal(expect_out, actual_out, check_names=False)

def test_rounded_date_columns():
    """If strings can't be coerced into dates then it should be false for the
    whole column.
    """
    df = pd.DataFrame(
        [
            {"a": "2017-01-01", "b": "2017-01-01 00:00:00.000000", "exp": True},
            {"a": "2017-01-01", "b": "2017-01-01 00:00:00.123456", "exp": False},
            {"a": "2017-01-01", "b": "2017-01-01 00:00:01.000000", "exp": False},
            {"a": "2017-01-01", "b": "2017-01-01 00:00:00", "exp": True},
        ]
    )
    df["a_dt"] = pd.to_datetime(df["a"])
    actual = utils.columns_equal(df.a_dt, df.b)
    expected = df["exp"]
    assert_series_equal(actual, expected, check_names=False)

def test_mixed_column_with_ignore_spaces_and_case():
    df = pd.DataFrame(
        [
            {"a": "hi", "b": "hi ", "expected": True},
            {"a": 1, "b": 1, "expected": True},
            {"a": np.inf, "b": np.inf, "expected": True},
            {"a": Decimal("1"), "b": Decimal("1"), "expected": True},
            {"a": 1, "b": "1 ", "expected": False},
            {"a": 1, "b": "yo ", "expected": False},
            {"a": "Hi", "b": "hI ", "expected": True},
            {"a": "HI", "b": "HI ", "expected": True},
            {"a": "hi", "b": "hi ", "expected": True},
        ]
    )
    actual_out = utils.columns_equal(df.a, df.b, ignore_spaces=True, ignore_case=True)
    expect_out = df["expected"]
    assert_series_equal(expect_out, actual_out, check_names=False)

def test_date_columns_unequal():
    """I want datetime fields to match with dates stored as strings
    """
    df = pd.DataFrame([{"a": "2017-01-01", "b": "2017-01-02"}, {"a": "2017-01-01"}])
    df["a_dt"] = pd.to_datetime(df["a"])
    df["b_dt"] = pd.to_datetime(df["b"])
    assert utils.columns_equal(df.a, df.a_dt).all()
    assert utils.columns_equal(df.b, df.b_dt).all()
    assert utils.columns_equal(df.a_dt, df.a).all()
    assert utils.columns_equal(df.b_dt, df.b).all()
    assert not utils.columns_equal(df.b_dt, df.a).any()
    assert not utils.columns_equal(df.a_dt, df.b).any()
    assert not utils.columns_equal(df.a, df.b_dt).any()
    assert not utils.columns_equal(df.b, df.a_dt).any()