def test_string_join_non_key(str_data, num_cols, how, how_raise):
other_data = [1, 2, 3, 4, 5][:len(str_data)]
pdf = pd.DataFrame()
gdf = DataFrame()
for i in range(num_cols):
pdf[i] = pd.Series(str_data, dtype="str")
gdf[i] = Series(str_data, dtype="str")
pdf["a"] = other_data
gdf["a"] = other_data
pdf2 = pdf.copy()
gdf2 = gdf.copy()
expectation = raise_builder([how_raise], NotImplementedError)
with expectation:
expect = pdf.merge(pdf2, on=["a"], how=how)
got = gdf.merge(gdf2, on=["a"], how=how)
if len(expect) == 0 and len(got) == 0:
expect = expect.reset_index(drop=True)
got = got[expect.columns]
assert_eq(expect, got)
def test_onehot_get_dummies_simple():
df = DataFrame({'x': np.arange(10)})
original = df.copy()
encoded = get_dummies(df, prefix='test')
assert df == original # the original df should be unchanged
cols = list(encoded.columns)[1:]
actual = DataFrame(dict(zip(cols, np.eye(len(cols)))))
assert (encoded.loc[:, cols] == actual).all().all()
def test_dataframe_empty_concat():
gdf1 = DataFrame()
gdf1['a'] = []
gdf1['b'] = []
gdf2 = gdf1.copy()
gdf3 = gd.concat([gdf1, gdf2])
assert len(gdf3) == 0
assert len(gdf3.columns) == 2
def test_dataframe_copy_shallow():
# Test for copy dataframe using class method
df = DataFrame()
df['a'] = [1, 2, 3]
df2 = df.copy()
df2['b'] = [4, 2, 3]
got = df.to_string()
print(got)
expect = '''
a
0 1
1 2
2 3
'''
# values should match despite whitespace difference
assert got.split() == expect.split()
def test_onehot_get_dummies_multicol(n_cols):
from string import ascii_lowercase
n_categories = 5
df = DataFrame(
dict(
zip(ascii_lowercase,
(np.arange(n_categories) for _ in range(n_cols)))))
original = df.copy()
encoded = get_dummies(df, prefix='test')
assert df == original
cols = list(encoded.columns)[n_cols:]
actual = DataFrame(
dict(
zip(
cols,
np.concatenate(
list(np.eye(n_categories) for _ in range(n_cols))))))
assert (encoded.loc[:, cols] == actual).all().all()