def test_categorical_value_counts(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_value_counts = gdf['a'].value_counts()
# pandas
pdf = pd.DataFrame()
pdf['a'] = pd_cat
pdf_value_counts = pdf['a'].value_counts()
# verify
pandas_dict = pdf_value_counts.to_dict()
gdf_dict = gdf_value_counts.to_pandas().to_dict()
assert pandas_dict == gdf_dict
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'].unique_count()
# 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())
# 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)
