def test_autocast_mixed_types_to_str(self):
# This is important in particular for Excel data, which is often a mix
# of int and str.
table = pd.DataFrame({"A": ["1A", 2]})
scrapetable.autocast_dtypes_in_place(table)
expected = pd.DataFrame({"A": ["1A", "2"]})
assert_frame_equal(table, expected)
def test_autocast_cast_crazy_types(self):
class Obj:
def __init__(self, s):
self.s = s
def __str__(self):
return self.s
obj1 = Obj("o1")
obj2 = Obj("o2")
table = pd.DataFrame({"A": [obj1, obj2]})
scrapetable.autocast_dtypes_in_place(table)
expected = pd.DataFrame({"A": ["o1", "o2"]})
assert_frame_equal(table, expected)
def test_autocast_int_from_str_categories_with_empty_str(self):
table = pd.DataFrame({"A": ["", "", "1"]}, dtype="category")
scrapetable.autocast_dtypes_in_place(table)
expected = pd.DataFrame({"A": [np.nan, np.nan, 1.0]}, dtype=np.float64)
assert_frame_equal(table, expected)
def test_autocast_str_categories_from_str_categories(self):
table = pd.DataFrame({"A": ["1", "2.1", "Yay"]}, dtype="category")
scrapetable.autocast_dtypes_in_place(table) # should be no-op
expected = pd.DataFrame({"A": ["1", "2.1", "Yay"]}, dtype="category")
assert_frame_equal(table, expected)
def test_autocast_float_from_str_categories_with_empty_str(self):
# example: used read_csv(dtype='category'), now want floats
table = pd.DataFrame({"A": ["1", "2.1", ""]}, dtype="category")
scrapetable.autocast_dtypes_in_place(table)
expected = pd.DataFrame({"A": [1.0, 2.1, np.nan]}, dtype=np.float64)
assert_frame_equal(table, expected)
def test_autocast_float_from_str_categories_with_dup_floats(self):
table = pd.DataFrame({"A": ["1", "1.0"]}, dtype="category")
scrapetable.autocast_dtypes_in_place(table)
expected = pd.DataFrame({"A": [1.0, 1.0]}, dtype=np.float64)
assert_frame_equal(table, expected)
def test_autocast_int_from_str_categories(self):
# example: used read_csv(dtype='category'), now want ints
table = pd.DataFrame({"A": ["1", "2"]}, dtype="category")
scrapetable.autocast_dtypes_in_place(table)
expected = pd.DataFrame({"A": [1, 2]})
assert_frame_equal(table, expected)
def test_autocast_int_from_str(self):
table = pd.DataFrame({"A": ["1", "2"]})
scrapetable.autocast_dtypes_in_place(table)
expected = pd.DataFrame({"A": [1, 2]})
assert_frame_equal(table, expected)
def test_autocast_all_empty_or_null_categories_is_text(self):
table = pd.DataFrame({"A": ["", np.nan, ""]}, dtype="category")
scrapetable.autocast_dtypes_in_place(table)
expected = pd.DataFrame({"A": ["", np.nan, ""]}, dtype="category")
assert_frame_equal(table, expected)
def test_autocast_all_empty_str_is_text(self):
table = pd.DataFrame({"A": ["", ""]})
scrapetable.autocast_dtypes_in_place(table)
assert_frame_equal(table, pd.DataFrame({"A": ["", ""]}))
def test_autocast_all_null_is_text(self):
table = pd.DataFrame({"A": [np.nan, np.nan]}, dtype=object)
scrapetable.autocast_dtypes_in_place(table)
expected = pd.DataFrame({"A": [np.nan, np.nan]}, dtype=object)
assert_frame_equal(table, expected)