def test_categorical_set_categories():
cat = pd.Categorical(["a", "a", "b", "c", "a"], categories=["a", "b", "c"])
psr = pd.Series(cat)
sr = Series.from_categorical(cat)
# adding category
expect = psr.cat.set_categories(["a", "b", "c", "d"])
got = sr.cat.set_categories(["a", "b", "c", "d"])
assert_eq(expect, got)
# removing category
expect = psr.cat.set_categories(["a", "b"])
got = sr.cat.set_categories(["a", "b"])
assert_eq(expect, got)
def test_categorical_unique_count(nelem):
from string import ascii_letters, digits
# create categorical series
np.random.seed(12)
pd_cat = pd.Categorical(
pd.Series(
np.random.choice(list(ascii_letters + digits), nelem),
dtype="category",
))
# gdf
gdf = DataFrame()
gdf["a"] = Series.from_categorical(pd_cat)
gdf_unique_count = gdf["a"].nunique()
# pandas
pdf = pd.DataFrame()
pdf["a"] = pd_cat
pdf_unique = pdf["a"].unique()
# verify
assert gdf_unique_count == len(pdf_unique)
def test_categorical_unique(num_elements):
from string import ascii_letters, digits
# create categorical series
np.random.seed(12)
pd_cat = pd.Categorical(
pd.Series(
np.random.choice(list(ascii_letters + digits), num_elements),
dtype="category",
))
# gdf
gdf = DataFrame()
gdf["a"] = Series.from_categorical(pd_cat)
gdf_unique_sorted = np.sort(gdf["a"].unique().to_pandas())
# pandas
pdf = pd.DataFrame()
pdf["a"] = pd_cat
pdf_unique_sorted = np.sort(pdf["a"].unique())
# verify
np.testing.assert_array_equal(pdf_unique_sorted, gdf_unique_sorted)
