Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix: value counts on added/concatenated strings #908

Merged
merged 2 commits into from
Sep 24, 2020
Merged

Fix: value counts on added/concatenated strings #908

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4236db7
fix(core): value counts failed on virtual column of strings.
JovanVeljanoski Jul 17, 2020
933f94b
chore(ci): change cache key for compiled
maartenbreddels Sep 22, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/pythonpackage.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ jobs:
uses: actions/cache@v2
with:
path: packages/vaex-core/build
key: ${{ runner.OS }}-${{ matrix.python-version }}-${{ hashFiles('packages/vaex-core/src/*') }}-v1
key: ${{ runner.OS }}-${{ matrix.python-version }}-${{ hashFiles('packages/vaex-core/src/*') }}-v2
- name: Fix cache timestamp
if: steps.cache-compiled-binaries.outputs.cache-hit == 'true' && matrix.os != 'windows-latest'
shell: bash
Expand Down
6 changes: 3 additions & 3 deletions packages/vaex-core/vaex/expression.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -599,7 +599,7 @@ def value_counts(self, dropna=False, dropnan=False, dropmissing=False, ascending
:returns: Pandas series containing the counts
"""
from pandas import Series
dtype = self.dtype
data_type = self.data_type()

transient = self.transient or self.ds.filtered or self.ds.is_masked(self.expression)
if self.is_string() and not transient:
Expand All @@ -608,12 +608,12 @@ def value_counts(self, dropna=False, dropnan=False, dropmissing=False, ascending
if not isinstance(ar, ColumnString):
transient = True

counter_type = counter_type_from_dtype(self.dtype, transient)
counter_type = counter_type_from_dtype(data_type, transient)
counters = [None] * self.ds.executor.thread_pool.nthreads
def map(thread_index, i1, i2, ar):
if counters[thread_index] is None:
counters[thread_index] = counter_type()
if vaex.array_types.is_string_type(dtype):
if vaex.array_types.is_string_type(data_type):
previous_ar = ar
ar = _to_string_sequence(ar)
if not transient:
Expand Down
2 changes: 2 additions & 0 deletions packages/vaex-core/vaex/hash.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@ def counter_type_from_dtype(dtype, transient=True):
postfix = str(dtype)
if postfix == '>f8':
postfix = 'float64'
if postfix == 'double': # arrow
postfix = 'float64'
name = 'counter_' + postfix
return globals()[name]

Expand Down
11 changes: 11 additions & 0 deletions tests/value_counts_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,3 +102,14 @@ def test_value_counts_masked_str():
assert value_counts['A'] == 2
assert value_counts['B'] == 1
assert value_counts[''] == 2


def test_value_counts_add_strings():
x = ['car', 'car', 'boat']
y = ['red', 'red', 'blue']
df = vaex.from_arrays(x=x, y=y)
df['z'] = df.x + '-' + df.y

value_counts = df.z.value_counts()
assert list(value_counts.index) == ['car-red', 'boat-blue']
assert value_counts.values.tolist() == [2, 1]