def test_value_counts(normalize, bins, dropna):
# We sort indices for Modin and pandas result because of issue #1650
values = np.array([3, 1, 2, 3, 4, np.nan])
modin_result = sort_index_for_equal_values(
pd.value_counts(values, normalize=normalize, ascending=False), False
)
pandas_result = sort_index_for_equal_values(
pandas.value_counts(values, normalize=normalize, ascending=False), False
)
df_equals(modin_result, pandas_result)
modin_result = sort_index_for_equal_values(
pd.value_counts(values, bins=bins, ascending=False), False
)
pandas_result = sort_index_for_equal_values(
pandas.value_counts(values, bins=bins, ascending=False), False
)
df_equals(modin_result, pandas_result)
modin_result = sort_index_for_equal_values(
pd.value_counts(values, dropna=dropna, ascending=True), True
)
pandas_result = sort_index_for_equal_values(
pandas.value_counts(values, dropna=dropna, ascending=True), True
)
df_equals(modin_result, pandas_result)
def test_value_counts(normalize, bins, dropna):
def sort_index_for_equal_values(result, ascending):
is_range = False
is_end = False
i = 0
new_index = np.empty(len(result), dtype=type(result.index))
while i < len(result):
j = i
if i < len(result) - 1:
while result[result.index[i]] == result[result.index[i + 1]]:
i += 1
if is_range is False:
is_range = True
if i == len(result) - 1:
is_end = True
break
if is_range:
k = j
for val in sorted(result.index[j:i + 1],
reverse=not ascending):
new_index[k] = val
k += 1
if is_end:
break
is_range = False
else:
new_index[j] = result.index[j]
i += 1
return type(result)(result, index=new_index)
# We sort indices for Modin and pandas result because of issue #1650
values = np.array([3, 1, 2, 3, 4, np.nan])
modin_result = sort_index_for_equal_values(
pd.value_counts(values, normalize=normalize, ascending=False), False)
pandas_result = sort_index_for_equal_values(
pandas.value_counts(values, normalize=normalize, ascending=False),
False)
df_equals(modin_result, pandas_result)
modin_result = sort_index_for_equal_values(
pd.value_counts(values, bins=bins, ascending=False), False)
pandas_result = sort_index_for_equal_values(
pandas.value_counts(values, bins=bins, ascending=False), False)
df_equals(modin_result, pandas_result)
modin_result = sort_index_for_equal_values(
pd.value_counts(values, dropna=dropna, ascending=True), True)
pandas_result = sort_index_for_equal_values(
pandas.value_counts(values, dropna=dropna, ascending=True), True)
df_equals(modin_result, pandas_result)
