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.

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

Multiprocessing and Performance Improvements #1117

Draft
wants to merge 2 commits into
base: dev
Choose a base branch
from
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
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 .pre-commit-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@ repos:
pyarrow>=1.0.1,
chardet>=3.0.4,
fastavro>=1.0.0.post1,
python-snappy>=0.5.4,
cramjam>=2.7.0,
charset-normalizer>=1.3.6,
psutil>=4.0.0,
scipy>=1.4.1,
Expand Down
16 changes: 0 additions & 16 deletions dataprofiler/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -20,22 +20,6 @@
from .validators.base_validators import Validator
from .version import __version__

try:
import snappy
except ImportError:
import warnings

warnings.warn(
"Snappy must be installed to use parquet/avro datasets."
"\n\n"
"For macOS use Homebrew:\n"
"\t`brew install snappy`"
"\n\n"
"For linux use apt-get:\n`"
"\tsudo apt-get -y install libsnappy-dev`\n",
ImportWarning,
)


def set_seed(seed=None):
# also check it's an integer
Expand Down
2 changes: 1 addition & 1 deletion dataprofiler/profilers/profile_builder.py
Original file line number Diff line number Diff line change
Expand Up @@ -3003,7 +3003,7 @@ def tqdm(level: set[int]) -> Generator[int, None, None]:
notification_str = "Calculating the statistics... "
pool = None
if auto_multiprocess_toggle:
pool, pool_size = profiler_utils.generate_pool(4, est_data_size)
pool, pool_size = profiler_utils.generate_pool(profiler_utils.suggest_pool_size(), est_data_size)
if pool:
notification_str += " (with " + str(pool_size) + " processes)"

Expand Down
40 changes: 0 additions & 40 deletions dataprofiler/tests/test_data_profiler.py
Original file line number Diff line number Diff line change
Expand Up @@ -56,46 +56,6 @@ def test_data_profiling(self):
self.assertIsNotNone(profile.profile)
self.assertIsNotNone(profile.report())

def test_no_snappy(self):
import importlib
import sys
import types

orig_import = __import__
# necessary for any wrapper around the library to test if snappy caught
# as an issue

def reload_data_profiler():
"""Recursively reload modules."""
sys_modules = sys.modules.copy()
for module_name, module in sys_modules.items():
# Only reload top level of the dataprofiler
if "dataprofiler" in module_name and len(module_name.split(".")) < 3:
if isinstance(module, types.ModuleType):
importlib.reload(module)

def import_mock(name, *args, **kwargs):
if name == "snappy":
raise ImportError("test")
return orig_import(name, *args, **kwargs)

with mock.patch("builtins.__import__", side_effect=import_mock):
with self.assertWarns(ImportWarning) as w:
import dataprofiler

reload_data_profiler()

self.assertEqual(
str(w.warning),
"Snappy must be installed to use parquet/avro datasets."
"\n\n"
"For macOS use Homebrew:\n"
"\t`brew install snappy`"
"\n\n"
"For linux use apt-get:\n`"
"\tsudo apt-get -y install libsnappy-dev`\n",
)

def test_no_tensorflow(self):
import sys

Expand Down
2 changes: 1 addition & 1 deletion requirements.txt
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ pytz>=2020.1
pyarrow>=1.0.1
chardet>=3.0.4
fastavro>=1.0.0.post1
python-snappy>=0.5.4
cramjam>=2.7.0
charset-normalizer>=1.3.6
psutil>=4.0.0
scipy>=1.10.0
Expand Down
Loading