holgi
/
sensospot_parser
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Compare commits

base: holgi:master
Branches Tags
holgi:master
holgi:xmlparsing
..
compare: holgi:xmlparsing
Branches Tags
holgi:master
holgi:xmlparsing

No commits in common. 'master' and 'xmlparsing' have entirely different histories.
master ... xmlparsing

18 changed files with 167 additions and 259 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats
  1. 1
      .gitignore
  2. 27
      .pre-commit-config.yaml
  3. 15
      CHANGES.md
  4. 25
      Makefile
  5. 6
      README.md
  6. 8
      noxfile.py
  7. 79
      pyproject.toml
  8. 34
      src/sensospot_parser/__init__.py
  9. 30
      src/sensospot_parser/csv_parser.py
  10. 18
      src/sensospot_parser/parameters.py
  11. 27
      src/sensospot_parser/xml_parser.py
  12. 20
      tests/conftest.py
  13. 1
      tests/test_columns.py
  14. 29
      tests/test_csv_parser.py
  15. 4
      tests/test_parameters.py
  16. 17
      tests/test_sensospot_data.py
  17. 71
      tests/test_xml_parser.py
  18. 14
      tox.ini

1
.gitignore vendored
Unescape View File

@ -39,7 +39,6 @@ pip-delete-this-directory.txt
# Unit test / coverage reports # Unit test / coverage reports
htmlcov/ htmlcov/
.tox/ .tox/
.nox/
.coverage .coverage
.coverage.* .coverage.*
.cache .cache

27
.pre-commit-config.yaml
Unescape View File

@ -11,18 +11,33 @@ repos:
- id: detect-private-key - id: detect-private-key
- repo: local - repo: local
hooks: hooks:
- id: isort-project
name: isort project
entry: isort -rc src
language: system
pass_filenames: false
- id: isort-test
name: isort test
entry: isort -rc tests
language: system
pass_filenames: false
- id: black - id: black
name: Autoformatting code with "black" name: black
entry: black src tests entry: black src tests
language: system language: system
pass_filenames: false pass_filenames: false
- id: ruff - id: flake8
name: Linting code with "ruff" name: flake8 project
entry: ruff src tests entry: flake8 --ignore E231,W503 src
language: system
pass_filenames: false
- id: flake8
name: flake8 test
entry: flake8 --ignore S101,W503 tests
language: system language: system
pass_filenames: false pass_filenames: false
- id: pytest - id: pytest
name: Testing the project with "pytest" name: pytest
entry: pytest tests entry: pytest tests
language: system
pass_filenames: false pass_filenames: false
language: system

15
CHANGES.md
Unescape View File

@ -1,18 +1,3 @@
2.0.0 - xml parsing
-------------------
- The assay results xml file is now parsed first
- CSV parsing is still available as fallback if the XML could not be parsed
1.0.0 - cli cleanup
-------------------
- the cli interface was cleaned up a lot
- default output of cli is now stdout
- multiple sources can be specified instead of the clumsy '-r' option before
0.7.0 - simplifications 0.7.0 - simplifications
----------------------- -----------------------

25
Makefile
Unescape View File

@ -1,4 +1,4 @@
.PHONY: clean coverage coverall docs devenv install lint prepareenv repo serve-docs test testall testfunctional nox tox .PHONY: clean coverage coverall docs devenv install lint prepareenv repo serve-docs test testall testfunctional tox
.DEFAULT_GOAL := help .DEFAULT_GOAL := help
define BROWSER_PYSCRIPT define BROWSER_PYSCRIPT
@ -54,8 +54,11 @@ clean-test: ## remove test and coverage artifacts
rm -fr htmlcov/ rm -fr htmlcov/
lint: ## reformat with black and check style with flake8 lint: ## reformat with black and check style with flake8
isort src
isort tests
black src tests black src tests
ruff src tests flake8 --ignore E231,W503,E402 src
flake8 --ignore S101,W503 tests
test: lint ## run tests quickly, stop on first error test: lint ## run tests quickly, stop on first error
pytest tests -x -l --last-failed --disable-warnings -m "not functional" pytest tests -x -l --last-failed --disable-warnings -m "not functional"
@ -76,11 +79,8 @@ coverall: lint ## full test suite, check code coverage and open coverage report
coverage html coverage html
$(BROWSER) htmlcov/index.html $(BROWSER) htmlcov/index.html
nox: ## run fully isolated tests with nox tox: ## run fully isolated tests with tox
nox tox
tox: ## old habits die hard: typo-squatting to use nox
nox
docs: ## build the documentation using mkdocs docs: ## build the documentation using mkdocs
mkdocs build mkdocs build
@ -88,14 +88,14 @@ docs: ## build the documentation using mkdocs
serve-docs: docs ## build the documentation and serve them in a web server serve-docs: docs ## build the documentation and serve them in a web server
mkdocs serve mkdocs serve
install: ## install updated project.toml install: ## install updated project.toml with flint
.venv/bin/pip3 install -e ".[docs,dev,test]" flit install --pth-file
prepareenv: ## setup virtual environment and install packages prepareenv: ## setup virtual environment and install packages
rm -fr .venv/
python3 -m venv --prompt sensospot .venv python3 -m venv --prompt sensospot .venv
.venv/bin/pip3 install --upgrade pip wheel .venv/bin/pip3 install --upgrade pip
.venv/bin/pip3 install -e ".[docs,dev,test]" .venv/bin/pip3 install "flit>3.2"
.venv/bin/flit install --pth-file
devenv: prepareenv ## setup development environment including precommit hooks devenv: prepareenv ## setup development environment including precommit hooks
.venv/bin/pre-commit install --install-hooks .venv/bin/pre-commit install --install-hooks
@ -107,4 +107,5 @@ repo: prepareenv ## complete project setup with development environment and git
git branch -m main git branch -m main
git remote add origin https://git.cpi.imtek.uni-freiburg.de/holgi/sensospot_parser.git git remote add origin https://git.cpi.imtek.uni-freiburg.de/holgi/sensospot_parser.git
git push -u origin main --no-verify git push -u origin main --no-verify
.venv/bin/pre-commit install --install-hooks .venv/bin/pre-commit install --install-hooks

6
README.md
Unescape View File

@ -43,11 +43,6 @@ There is a `columns` module available, providing constans that define the column
## Avaliable public functions: ## Avaliable public functions:
All public functions return a [pandas DataFrame][pandas] object.
Be aware that some columns might contain no values. This is depending on the parsing
method (xml or csv) and if a parameters file could be found or not.
- **parse_folder(path_to_folder)** - **parse_folder(path_to_folder)**
Tries the `parse_xml_folder()` function first and if an error occurs, Tries the `parse_xml_folder()` function first and if an error occurs,
it falls back to the `parse_csv_folder()` it falls back to the `parse_csv_folder()`
@ -93,4 +88,3 @@ To generate the documentation pages use `make docs` or `make serve-docs` for
starting a webserver with the generated documentation starting a webserver with the generated documentation
[sensospot]: https://www.miltenyi-imaging.com/products/sensospot [sensospot]: https://www.miltenyi-imaging.com/products/sensospot
[pandas]: https://pandas.pydata.org/docs/reference/frame.html

8
noxfile.py
Unescape View File

@ -1,8 +0,0 @@
import nox
@nox.session(python=["3.9", "3.10", "3.11"])
def tests(session):
session.install(".[test]")
session.run("pytest", *session.posargs)

79
pyproject.toml
Unescape View File

@ -27,10 +27,10 @@ classifiers = [
] ]
dependencies = [ dependencies = [
"click",
"defusedxml >=0.6.0",
"pandas >=1.0.0", "pandas >=1.0.0",
"defusedxml >=0.6.0",
"tables >=3.6.1", "tables >=3.6.1",
"click",
] ]
[project.urls] [project.urls]
Source = "https://git.cpi.imtek.uni-freiburg.de/holgi/sensospot_parser.git" Source = "https://git.cpi.imtek.uni-freiburg.de/holgi/sensospot_parser.git"
@ -39,34 +39,26 @@ Source = "https://git.cpi.imtek.uni-freiburg.de/holgi/sensospot_parser.git"
sensospot_parse = "sensospot_parser:main" sensospot_parse = "sensospot_parser:main"
[project.optional-dependencies] [project.optional-dependencies]
test = [
"pytest >=4.0.0",
"pytest-cov",
"pytest-mock",
"pytest-randomly >=3.5.0",
"tox",
]
dev = [ dev = [
"black", "black",
"flit", "flake8",
"flake8-comprehensions",
"flake8-bandit",
"isort >= 5.0.0",
"keyring", "keyring",
"pre-commit", "pre-commit",
"ruff",
] ]
docs = [ docs = [
"mkdocs", "mkdocs",
"mkdocstrings[python]", "mkdocstrings[python]",
] ]
test = [
"pytest >=4.0.0",
"pytest-cov",
"pytest-mock",
"pytest-randomly >=3.5.0",
"nox",
]
[tool.pytest.ini_options]
markers = [
"functional: marks tests as functional (deselect with '-m \"not functional\"')",
]
addopts = [
"--strict-markers",
]
[tool.black] [tool.black]
line-length = 79 line-length = 79
@ -82,39 +74,16 @@ extend-exclude = '''
^/.dist ^/.dist
''' '''
[tool.ruff] [tool.isort]
# see https://github.com/charliermarsh/ruff line_length=79
select = ["ALL"] multi_line_output=3
ignore = [ length_sort="True"
# ignored for now, should be activated in the future include_trailing_comma="True"
# docstrings
"D",
# flake8-annotations
"ANN",
# flake8-type-checking
"TCH",
# ignored, "black" will handle this
# flake8-commas
"COM",
# ignored, due to Windows / WSL2 setup [tool.pytest.ini_options]
# flake8-executable markers = [
"EXE", "functional: marks tests as functional (deselect with '-m \"not functional\"')",
]
# project specific ignores addopts = [
# flake8-import-conventions "--strict-markers",
"ICN",
] ]
fixable = ["I"]
fix = true
line-length=79
target-version = "py38"
[tool.ruff.per-file-ignores]
# see https://github.com/charliermarsh/ruff
"src/*" = ["SLF001", "G004"]
"tests/*" = ["FBT003", "INP001", "PLR2004", "S101", "SLF001"]
[tool.ruff.pydocstyle]
convention = "pep257" # Accepts: "google", "numpy", or "pep257".

34
src/sensospot_parser/__init__.py
Unescape View File

@ -3,9 +3,9 @@
Parsing the numerical output from Sensovations Sensospot image analysis. Parsing the numerical output from Sensovations Sensospot image analysis.
""" """
__version__ = "2.0.2" __version__ = "2.0.0"
import logging
import pathlib import pathlib
from typing import Union from typing import Union
@ -16,15 +16,12 @@ from . import columns # noqa: F401
from .csv_parser import parse_csv_folder from .csv_parser import parse_csv_folder
from .xml_parser import parse_xml_folder from .xml_parser import parse_xml_folder
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger("sensospot_parser")
DEFAULT_OUTPUT_FILENAME = "collected_data.csv" DEFAULT_OUTPUT_FILENAME = "collected_data.csv"
PathLike = Union[str, pathlib.Path] PathLike = Union[str, pathlib.Path]
def parse_folder(source: PathLike, *, quiet: bool = False) -> pandas.DataFrame: def parse_folder(source: PathLike, quiet: bool = False) -> pandas.DataFrame:
"""parses an assay result folder """parses an assay result folder
The function will first try to use an assay results xml file, and will The function will first try to use an assay results xml file, and will
@ -41,10 +38,7 @@ def parse_folder(source: PathLike, *, quiet: bool = False) -> pandas.DataFrame:
return parse_xml_folder(source) return parse_xml_folder(source)
except ValueError: except ValueError:
pass pass
logger.info( return parse_csv_folder(source, quiet)
"Could not parse xml results file, using fall-back csv parsing"
)
return parse_csv_folder(source, quiet=quiet)
@click.command() @click.command()
@ -74,30 +68,16 @@ def parse_folder(source: PathLike, *, quiet: bool = False) -> pandas.DataFrame:
default=False, default=False,
help="Ignore sanity check for csv file parsing", help="Ignore sanity check for csv file parsing",
) )
@click.option( def main(sources, output, quiet=False):
"-v",
"--verbose",
help="Set verbosity of log, add multiple -vv for more verbose logging",
count=True,
)
def main(sources, output, verbose, quiet=False): # noqa: FBT002
"""Parses the measurement results of the Sensospot reader """Parses the measurement results of the Sensospot reader
The resulting output is either echoed to stdout or saved to a file. The resulting output is either echoed to stdout or saved to a file.
At first parsing the assay result xml file is tried. At first parsing the assay result xml file is tried.
If this doesn't work, the fallback is to parse the csv files. I this doesn't work, the fallback is to parse the csv files.
""" """
if verbose == 0:
logging.disable()
elif verbose == 1:
logging.disable(level=logging.DEBUG)
else:
logging.disable(level=logging.NOTSET)
paths = (pathlib.Path(source) for source in sources) paths = (pathlib.Path(source) for source in sources)
collection = (parse_folder(source, quiet=quiet) for source in paths) collection = (parse_folder(source, quiet) for source in paths)
result = ( result = (
pandas.concat(collection, ignore_index=True) pandas.concat(collection, ignore_index=True)
.reset_index() .reset_index()

30
src/sensospot_parser/csv_parser.py
Unescape View File

@ -3,19 +3,16 @@
Parsing the csv result files from Sensovations Sensospot image analysis. Parsing the csv result files from Sensovations Sensospot image analysis.
""" """
import logging
import pathlib
import re import re
import pathlib
from typing import Union, TextIO, Optional, Sequence
from collections import namedtuple from collections import namedtuple
from typing import Optional, Sequence, TextIO, Union
import pandas import pandas
from . import columns from . import columns
from .parameters import add_measurement_parameters from .parameters import add_measurement_parameters
logger = logging.getLogger("sensospot_parser")
PathLike = Union[str, pathlib.Path] PathLike = Union[str, pathlib.Path]
REGEX_WELL = re.compile( REGEX_WELL = re.compile(
@ -77,11 +74,10 @@ def _extract_measurement_info(data_file: PathLike) -> FileInfo:
named tuple FileInfo with parsed metadata named tuple FileInfo with parsed metadata
""" """
data_path = pathlib.Path(data_file) data_path = pathlib.Path(data_file)
*rest, well, exposure = data_path.stem.rsplit("_", 2) *rest, well, exposure = data_path.stem.rsplit("_", 2) # noqa: F841
matched = REGEX_WELL.match(well) matched = REGEX_WELL.match(well)
if matched is None: if matched is None:
msg = f"not a valid well: '{well}'" raise ValueError(f"not a valid well: '{well}'")
raise ValueError(msg)
row = matched["row"].upper() row = matched["row"].upper()
column = int(matched["column"]) column = int(matched["column"])
exposure = int(exposure) exposure = int(exposure)
@ -103,7 +99,6 @@ def parse_csv_file(data_file: PathLike) -> pandas.DataFrame:
ValueError: if metadata could not be extracted ValueError: if metadata could not be extracted
""" """
data_path = pathlib.Path(data_file).resolve() data_path = pathlib.Path(data_file).resolve()
logger.debug(f"Parsing csv file {data_path}")
measurement_info = _extract_measurement_info(data_path) measurement_info = _extract_measurement_info(data_path)
data_frame = _parse_csv(data_path) data_frame = _parse_csv(data_path)
# normalized well name # normalized well name
@ -148,8 +143,7 @@ def parse_multiple_csv_files(
pandas data frame with all parsed data combined pandas data frame with all parsed data combined
""" """
if not file_list: if not file_list:
msg = "Empty file list provided" raise ValueError("Empty file list provided")
raise ValueError(msg)
collection = (_parse_csv_file_silenced(path) for path in file_list) collection = (_parse_csv_file_silenced(path) for path in file_list)
filtered = (frame for frame in collection if frame is not None) filtered = (frame for frame in collection if frame is not None)
data_frame = pandas.concat(filtered, ignore_index=True).reset_index() data_frame = pandas.concat(filtered, ignore_index=True).reset_index()
@ -192,8 +186,9 @@ def _sanity_check(data_frame: pandas.DataFrame) -> pandas.DataFrame:
spot_positions = len(data_frame[columns.POS_ID].unique()) spot_positions = len(data_frame[columns.POS_ID].unique())
expected_rows = field_rows * field_cols * exposures * spot_positions expected_rows = field_rows * field_cols * exposures * spot_positions
if expected_rows != len(data_frame): if expected_rows != len(data_frame):
msg = f"Measurements are missing: {expected_rows} != {len(data_frame)}" raise ValueError(
raise ValueError(msg) f"Measurements are missing: {expected_rows} != {len(data_frame)}"
)
# set the right data type for measurement columns # set the right data type for measurement columns
for raw_column in columns.NUMERIC_COLUMNS: for raw_column in columns.NUMERIC_COLUMNS:
data_frame[raw_column] = pandas.to_numeric(data_frame[raw_column]) data_frame[raw_column] = pandas.to_numeric(data_frame[raw_column])
@ -201,7 +196,7 @@ def _sanity_check(data_frame: pandas.DataFrame) -> pandas.DataFrame:
def parse_csv_folder( def parse_csv_folder(
folder: PathLike, *, quiet: bool = False folder: PathLike, quiet: bool = False
) -> pandas.DataFrame: ) -> pandas.DataFrame:
"""parses all csv files in a folder to one large dataframe """parses all csv files in a folder to one large dataframe
@ -215,15 +210,12 @@ def parse_csv_folder(
Returns: Returns:
a pandas data frame with parsed data a pandas data frame with parsed data
""" """
logger.info(f"Parsing csv files in folder {folder}")
folder_path = pathlib.Path(folder) folder_path = pathlib.Path(folder)
file_list = find_csv_files(folder_path) file_list = find_csv_files(folder_path)
try: try:
data_frame = parse_multiple_csv_files(file_list) data_frame = parse_multiple_csv_files(file_list)
except ValueError as e: except ValueError:
msg = f"No sensospot data found in folder '{folder}'" raise ValueError(f"No sensospot data found in folder '{folder}'")
logger.warning(msg)
raise ValueError(msg) from e
data_frame = add_measurement_parameters(data_frame, folder_path) data_frame = add_measurement_parameters(data_frame, folder_path)

18
src/sensospot_parser/parameters.py
Unescape View File

@ -3,10 +3,9 @@
Parsing the numerical output from Sensovations Sensospot image analysis. Parsing the numerical output from Sensovations Sensospot image analysis.
""" """
import logging
import pathlib import pathlib
from typing import Any, Dict, Optional, Union from typing import Any, Dict, Union, Optional
from xml.etree.ElementTree import Element as ElementType from xml.etree.ElementTree import Element as ElementType # noqa: S405
import numpy import numpy
import pandas import pandas
@ -16,8 +15,6 @@ from . import columns
PathLike = Union[str, pathlib.Path] PathLike = Union[str, pathlib.Path]
logger = logging.getLogger("sensospot_parser")
def _search_params_file(folder: PathLike) -> Optional[pathlib.Path]: def _search_params_file(folder: PathLike) -> Optional[pathlib.Path]:
"""searches for a exposure settings file in a folder """searches for a exposure settings file in a folder
@ -33,7 +30,10 @@ def _search_params_file(folder: PathLike) -> Optional[pathlib.Path]:
if not params_folder.is_dir(): if not params_folder.is_dir():
return None return None
param_files = list(params_folder.glob("**/*.svexp")) param_files = list(params_folder.glob("**/*.svexp"))
return param_files[0] if len(param_files) == 1 else None if len(param_files) == 1:
return param_files[0]
else:
return None
def _get_channel_data(channel_node: ElementType) -> Dict[str, Any]: def _get_channel_data(channel_node: ElementType) -> Dict[str, Any]:
@ -45,9 +45,9 @@ def _get_channel_data(channel_node: ElementType) -> Dict[str, Any]:
Returns: Returns:
dict with the information dict with the information
""" """
# Example "ChannelConfig1" # child.tag == "ChannelConfig1"
exposure_id = int(channel_node.tag[-1]) exposure_id = int(channel_node.tag[-1])
# Example "Cy3 Green" # channel_description == "[Cy3|Cy5] Green"
description = channel_node.attrib["Description"] description = channel_node.attrib["Description"]
exposure_channel = description.rsplit(" ", 1)[-1] exposure_channel = description.rsplit(" ", 1)[-1]
# floats can be used for exposure times, not only ints # floats can be used for exposure times, not only ints
@ -68,7 +68,6 @@ def _parse_measurement_params(params_file: PathLike) -> pandas.DataFrame:
Returns: Returns:
pandas data frame with the parsed information pandas data frame with the parsed information
""" """
logger.debug(f"Parsing parameters file {params_file}")
file_path = pathlib.Path(params_file) file_path = pathlib.Path(params_file)
with file_path.open("r") as file_handle: with file_path.open("r") as file_handle:
tree = ElementTree.parse(file_handle) tree = ElementTree.parse(file_handle)
@ -88,7 +87,6 @@ def get_measurement_params(folder: PathLike) -> Optional[pandas.DataFrame]:
params_file = _search_params_file(folder) params_file = _search_params_file(folder)
if params_file is not None: if params_file is not None:
return _parse_measurement_params(params_file) return _parse_measurement_params(params_file)
logger.debug(f"Could not locate parameters file in folder {folder}")
return None return None

27
src/sensospot_parser/xml_parser.py
Unescape View File

@ -3,18 +3,15 @@
Parsing the csv result files from Sensovations Sensospot image analysis. Parsing the csv result files from Sensovations Sensospot image analysis.
""" """
import logging
import pathlib import pathlib
from typing import Union, Optional
from datetime import datetime from datetime import datetime
from typing import Optional, Union
import pandas import pandas
from defusedxml import ElementTree from defusedxml import ElementTree
from . import columns, parameters from . import columns, parameters
logger = logging.getLogger("sensospot_parser")
PathLike = Union[str, pathlib.Path] PathLike = Union[str, pathlib.Path]
RESULT_TAG_TYPES = { RESULT_TAG_TYPES = {
@ -79,9 +76,7 @@ class ParserTarget:
def _data_timestamp_parser(self, data: str) -> None: def _data_timestamp_parser(self, data: str) -> None:
"""parses the data section of a "Timestamp" tag""" """parses the data section of a "Timestamp" tag"""
timestamp = datetime.strptime( # noqa: DTZ007 timestamp = datetime.strptime(data.strip(), DATETIME_XML_FORMAT)
data.strip(), DATETIME_XML_FORMAT
)
self._current[columns.ANALYSIS_DATETIME] = timestamp self._current[columns.ANALYSIS_DATETIME] = timestamp
def _data_image_name_parser(self, data: str) -> None: def _data_image_name_parser(self, data: str) -> None:
@ -113,6 +108,7 @@ class ParserTarget:
def closed(self) -> None: def closed(self) -> None:
"""the end of the xml file is reached""" """the end of the xml file is reached"""
pass
def _find_result_xml_file(folder: PathLike) -> Optional[pathlib.Path]: def _find_result_xml_file(folder: PathLike) -> Optional[pathlib.Path]:
@ -156,12 +152,9 @@ def parse_xml_file(xml_file: PathLike) -> pandas.DataFrame:
Raises: Raises:
ValueError if the xml file could not be parsed ValueError if the xml file could not be parsed
""" """
logger.info(f"Parsing xml results file {xml_file}")
xml_file = pathlib.Path(xml_file) xml_file = pathlib.Path(xml_file)
if not xml_file.is_file(): if not xml_file.is_file():
msg = "Xml file does not exist" raise ValueError("Xml file does not exist")
logger.debug(f"{msg}: {xml_file}")
raise ValueError(msg)
target = ParserTarget() target = ParserTarget()
parser = ElementTree.DefusedXMLParser(target=target) parser = ElementTree.DefusedXMLParser(target=target)
@ -169,15 +162,11 @@ def parse_xml_file(xml_file: PathLike) -> pandas.DataFrame:
try: try:
parser.feed(xml_file.read_text()) parser.feed(xml_file.read_text())
except (IndexError, KeyError, ValueError, TypeError) as e: except (IndexError, KeyError, ValueError, TypeError) as e:
msg = "Malformed data in xml file" raise ValueError("Malformed data in xml file") from e
logger.warning(f"{msg} {xml_file}")
raise ValueError(msg) from e
data_frame = pandas.DataFrame(data=target.collected).reset_index() data_frame = pandas.DataFrame(data=target.collected).reset_index()
if data_frame.empty: if data_frame.empty:
msg = "Could not parse assay results xml file" raise ValueError("Could not parse assay results xml file")
logger.warning(f"{msg} {xml_file}")
raise ValueError(msg)
return columns._cleanup_data_columns(data_frame) return columns._cleanup_data_columns(data_frame)
@ -197,9 +186,7 @@ def parse_xml_folder(folder: PathLike) -> pandas.DataFrame:
folder = pathlib.Path(folder) folder = pathlib.Path(folder)
xml_file = _find_result_xml_file(folder) xml_file = _find_result_xml_file(folder)
if xml_file is None: if xml_file is None:
msg = "Could not find assay results xml file" raise ValueError("Could not find assay results xml file")
logger.debug(f"{msg} in folder {folder}")
raise ValueError(msg)
data_frame = parse_xml_file(xml_file) data_frame = parse_xml_file(xml_file)
data_frame = parameters.add_measurement_parameters(data_frame, folder) data_frame = parameters.add_measurement_parameters(data_frame, folder)
return columns._cleanup_data_columns(data_frame) return columns._cleanup_data_columns(data_frame)

20
tests/conftest.py
Unescape View File

@ -14,23 +14,23 @@ EXAMPLE_DIR_XML_WITH_PARAMS = "xml_with_parameters"
@pytest.fixture(scope="session") @pytest.fixture(scope="session")
def example_dir(request): def example_dir(request):
root_dir = Path(request.config.rootdir) root_dir = Path(request.config.rootdir)
return root_dir / "example_data" yield root_dir / "example_data"
@pytest.fixture() @pytest.fixture
def example_file(example_dir): def example_file(example_dir):
data_dir = example_dir / EXAMPLE_DIR_CSV_WO_PARAMS data_dir = example_dir / EXAMPLE_DIR_CSV_WO_PARAMS
return data_dir / "160218_SG2-013-001_Regen1_Cy3-100_1_A1_1.csv" yield data_dir / "160218_SG2-013-001_Regen1_Cy3-100_1_A1_1.csv"
@pytest.fixture() @pytest.fixture
def exposure_df(): def exposure_df():
from pandas import DataFrame from pandas import DataFrame
return DataFrame(data={"Exposure.Id": [1, 2, 3]}) yield DataFrame(data={"Exposure.Id": [1, 2, 3]})
@pytest.fixture() @pytest.fixture
def normalization_data_frame(): def normalization_data_frame():
from sensospot_parser.columns import RAW_DATA_NORMALIZATION_MAP from sensospot_parser.columns import RAW_DATA_NORMALIZATION_MAP
@ -86,10 +86,10 @@ def normalization_data_frame():
data_frame = pandas.DataFrame(overflow_test_data) data_frame = pandas.DataFrame(overflow_test_data)
data_frame["Exposure.Channel"] = "Cy5" data_frame["Exposure.Channel"] = "Cy5"
for value_column in RAW_DATA_NORMALIZATION_MAP: for value_column in RAW_DATA_NORMALIZATION_MAP.keys():
data_frame[value_column] = data_frame["Value"] data_frame[value_column] = data_frame["Value"]
return data_frame yield data_frame
@pytest.fixture(scope="session") @pytest.fixture(scope="session")
@ -106,11 +106,11 @@ def parsed_data_frame_without_params(example_dir):
return parse_csv_folder(example_dir / EXAMPLE_DIR_CSV_WO_PARAMS) return parse_csv_folder(example_dir / EXAMPLE_DIR_CSV_WO_PARAMS)
@pytest.fixture() @pytest.fixture
def data_frame_with_params(parsed_data_frame_with_params): def data_frame_with_params(parsed_data_frame_with_params):
return parsed_data_frame_with_params.copy() return parsed_data_frame_with_params.copy()
@pytest.fixture() @pytest.fixture
def data_frame_without_params(parsed_data_frame_without_params): def data_frame_without_params(parsed_data_frame_without_params):
return parsed_data_frame_without_params.copy() return parsed_data_frame_without_params.copy()

1
tests/test_columns.py
Unescape View File

@ -1,5 +1,6 @@
def test_cleanup_data_columns(): def test_cleanup_data_columns():
from pandas import DataFrame from pandas import DataFrame
from sensospot_parser.columns import _cleanup_data_columns from sensospot_parser.columns import _cleanup_data_columns
columns = ["Rect.", "Contour", " ID ", "Found", "Dia."] columns = ["Rect.", "Contour", " ID ", "Found", "Dia."]

29
tests/test_csv_parser.py
Unescape View File

@ -4,11 +4,11 @@
import numpy import numpy
import pytest import pytest
from .conftest import EXAMPLE_DIR_CSV_WITH_PARAMS, EXAMPLE_DIR_CSV_WO_PARAMS from .conftest import EXAMPLE_DIR_CSV_WO_PARAMS, EXAMPLE_DIR_CSV_WITH_PARAMS
@pytest.mark.parametrize( @pytest.mark.parametrize(
("sub_dir", "file_name"), "sub_dir, file_name",
[ [
( (
EXAMPLE_DIR_CSV_WO_PARAMS, EXAMPLE_DIR_CSV_WO_PARAMS,
@ -65,15 +65,14 @@ def test_parse_csv_no_array(example_dir):
@pytest.mark.parametrize( @pytest.mark.parametrize(
("provided", "expected"), "input, expected", [("", "."), ("..,", "."), (".,,", ","), ("..,,", ".")]
[("", "."), ("..,", "."), (".,,", ","), ("..,,", ".")],
) )
def test_guess_decimal_separator_returns_correct_separator(provided, expected): def test_guess_decimal_separator_returns_correct_separator(input, expected):
from io import StringIO from io import StringIO
from sensospot_parser.csv_parser import _guess_decimal_separator from sensospot_parser.csv_parser import _guess_decimal_separator
handle = StringIO(f"header\n{provided}\n") handle = StringIO(f"header\n{input}\n")
result = _guess_decimal_separator(handle) result = _guess_decimal_separator(handle)
assert result == expected assert result == expected
@ -99,17 +98,17 @@ def test_well_regex_ok():
assert result["column"] == "123" assert result["column"] == "123"
@pytest.mark.parametrize("provided", ["", "A", "1", "1A", "-1", "A-"]) @pytest.mark.parametrize("input", ["", "A", "1", "1A", "-1", "A-"])
def test_well_regex_no_match(provided): def test_well_regex_no_match(input):
from sensospot_parser.csv_parser import REGEX_WELL from sensospot_parser.csv_parser import REGEX_WELL
result = REGEX_WELL.match(provided) result = REGEX_WELL.match(input)
assert result is None assert result is None
@pytest.mark.parametrize( @pytest.mark.parametrize(
("filename", "expected"), "filename, expected",
[("A1_1.csv", ("A", 1, 1)), ("test/measurement_1_H12_2", ("H", 12, 2))], [("A1_1.csv", ("A", 1, 1)), ("test/measurement_1_H12_2", ("H", 12, 2))],
) )
def test_extract_measurement_info_ok(filename, expected): def test_extract_measurement_info_ok(filename, expected):
@ -124,7 +123,7 @@ def test_extract_measurement_info_ok(filename, expected):
def test_extract_measurement_info_raises_error(filename): def test_extract_measurement_info_raises_error(filename):
from sensospot_parser.csv_parser import _extract_measurement_info from sensospot_parser.csv_parser import _extract_measurement_info
with pytest.raises(ValueError): # noqa: PT011 with pytest.raises(ValueError):
_extract_measurement_info(filename) _extract_measurement_info(filename)
@ -179,7 +178,7 @@ def test_parse_file_raises_error(example_dir):
/ "should_raise_value_error.csv" / "should_raise_value_error.csv"
) )
with pytest.raises(ValueError): # noqa: PT011 with pytest.raises(ValueError):
parse_csv_file(csv_file) parse_csv_file(csv_file)
@ -224,6 +223,7 @@ def testparse_multiple_files_ok(example_dir, file_list):
files = [sub_dir / file for file in file_list] files = [sub_dir / file for file in file_list]
data_frame = parse_multiple_csv_files(files) data_frame = parse_multiple_csv_files(files)
print(data_frame["Exposure.Id"].unique())
assert len(data_frame) == 100 * len(files) assert len(data_frame) == 100 * len(files)
assert len(data_frame["Exposure.Id"].unique()) == len(files) assert len(data_frame["Exposure.Id"].unique()) == len(files)
@ -232,7 +232,7 @@ def testparse_multiple_files_ok(example_dir, file_list):
def testparse_multiple_files_empty_file_list(): def testparse_multiple_files_empty_file_list():
from sensospot_parser.csv_parser import parse_multiple_csv_files from sensospot_parser.csv_parser import parse_multiple_csv_files
with pytest.raises(ValueError): # noqa: PT011 with pytest.raises(ValueError):
parse_multiple_csv_files([]) parse_multiple_csv_files([])
@ -242,6 +242,7 @@ def testparse_multiple_files_empty_array(example_dir):
files = [example_dir / "no_array_A1_1.csv"] files = [example_dir / "no_array_A1_1.csv"]
data_frame = parse_multiple_csv_files(files) data_frame = parse_multiple_csv_files(files)
print(data_frame["Exposure.Id"].unique())
assert len(data_frame) == 1 assert len(data_frame) == 1
@ -305,5 +306,5 @@ def test_sanity_check_raises_value_error(example_dir):
data_frame = parse_multiple_csv_files(files) data_frame = parse_multiple_csv_files(files)
data_frame = data_frame.drop(data_frame.index[1]) data_frame = data_frame.drop(data_frame.index[1])
with pytest.raises(ValueError): # noqa: PT011 with pytest.raises(ValueError):
_sanity_check(data_frame) _sanity_check(data_frame)

4
tests/test_parameters.py
Unescape View File

@ -1,6 +1,6 @@
import pandas import pandas
from .conftest import EXAMPLE_DIR_CSV_WITH_PARAMS, EXAMPLE_DIR_CSV_WO_PARAMS from .conftest import EXAMPLE_DIR_CSV_WO_PARAMS, EXAMPLE_DIR_CSV_WITH_PARAMS
def test_search_params_file_ok(example_dir): def test_search_params_file_ok(example_dir):
@ -32,8 +32,8 @@ def test_ssearch_measurement_params_file_parameters_file(tmpdir):
def test_parse_channel_info(example_dir): def test_parse_channel_info(example_dir):
from sensospot_parser.parameters import ( from sensospot_parser.parameters import (
_parse_measurement_params,
_search_params_file, _search_params_file,
_parse_measurement_params,
) )
params = _search_params_file(example_dir / EXAMPLE_DIR_CSV_WITH_PARAMS) params = _search_params_file(example_dir / EXAMPLE_DIR_CSV_WITH_PARAMS)

17
tests/test_sensospot_data.py
Unescape View File

@ -5,17 +5,16 @@ from .conftest import EXAMPLE_DIR_CSV_WO_PARAMS, EXAMPLE_DIR_XML_WO_PARAMS
def test_import_api(): def test_import_api():
from sensospot_parser import ( from sensospot_parser import main # noqa: F401
columns, # noqa: F401 from sensospot_parser import columns # noqa: F401
main, # noqa: F401 from sensospot_parser import parse_folder # noqa: F401
parse_csv_folder, # noqa: F401 from sensospot_parser import parse_csv_folder # noqa: F401
parse_folder, # noqa: F401 from sensospot_parser import parse_xml_folder # noqa: F401
parse_xml_folder, # noqa: F401
)
def test_compare_xml_to_csv(example_dir): def test_compare_xml_to_csv(example_dir):
import pandas import pandas
from sensospot_parser import parse_csv_folder, parse_xml_folder from sensospot_parser import parse_csv_folder, parse_xml_folder
folder = example_dir / EXAMPLE_DIR_XML_WO_PARAMS folder = example_dir / EXAMPLE_DIR_XML_WO_PARAMS
@ -27,14 +26,13 @@ def test_compare_xml_to_csv(example_dir):
assert isinstance(xml_df, pandas.DataFrame) assert isinstance(xml_df, pandas.DataFrame)
assert len(csv_df) == len(xml_df) assert len(csv_df) == len(xml_df)
assert set(csv_df.columns) == set(xml_df.columns)
assert set(csv_df["Well.Name"]) == set(xml_df["Well.Name"]) assert set(csv_df["Well.Name"]) == set(xml_df["Well.Name"])
assert set(csv_df["Exposure.Id"]) == set(xml_df["Exposure.Id"]) assert set(csv_df["Exposure.Id"]) == set(xml_df["Exposure.Id"])
assert set(csv_df["Spot.Diameter"]) == set(xml_df["Spot.Diameter"]) assert set(csv_df["Spot.Diameter"]) == set(xml_df["Spot.Diameter"])
@pytest.mark.parametrize( @pytest.mark.parametrize(
("folder", "length", "hasnans"), "folder, length, hasnans",
[ [
(EXAMPLE_DIR_XML_WO_PARAMS, 6400, False), (EXAMPLE_DIR_XML_WO_PARAMS, 6400, False),
(EXAMPLE_DIR_CSV_WO_PARAMS, 28800, True), (EXAMPLE_DIR_CSV_WO_PARAMS, 28800, True),
@ -42,6 +40,7 @@ def test_compare_xml_to_csv(example_dir):
) )
def test_parse_folder_switches_parser(example_dir, folder, length, hasnans): def test_parse_folder_switches_parser(example_dir, folder, length, hasnans):
import pandas import pandas
from sensospot_parser import parse_folder from sensospot_parser import parse_folder
result = parse_folder(example_dir / folder) result = parse_folder(example_dir / folder)

71
tests/test_xml_parser.py
Unescape View File

@ -2,7 +2,7 @@ from datetime import datetime
import pytest import pytest
from .conftest import EXAMPLE_DIR_XML_WITH_PARAMS, EXAMPLE_DIR_XML_WO_PARAMS from .conftest import EXAMPLE_DIR_XML_WO_PARAMS, EXAMPLE_DIR_XML_WITH_PARAMS
class DummyDataFunc: class DummyDataFunc:
@ -28,7 +28,7 @@ def test_parser_target_init():
@pytest.mark.parametrize( @pytest.mark.parametrize(
("tag", "attributes", "expected"), "tag, attributes, expected",
[ [
("UnknownTag", {"ID": "something"}, {}), ("UnknownTag", {"ID": "something"}, {}),
( (
@ -84,7 +84,7 @@ def test_parser_target_start_image_file_name():
@pytest.mark.parametrize( @pytest.mark.parametrize(
("data_type", "value", "expected"), "data_type, value, expected",
[ [
("unknown type", 1, "1"), ("unknown type", 1, "1"),
("System.Int32", "12", 12), ("System.Int32", "12", 12),
@ -108,40 +108,16 @@ def test_parser_target_result_attributes_parser(data_type, value, expected):
@pytest.mark.parametrize( @pytest.mark.parametrize(
("value", "expected"), "value, expected",
[ [
( ("3/7/2022 5:31:47 PM", datetime(2022, 3, 7, 17, 31, 47)),
"3/7/2022 5:31:47 PM", ("03/7/2022 5:31:47 PM", datetime(2022, 3, 7, 17, 31, 47)),
datetime(2022, 3, 7, 17, 31, 47), # noqa: DTZ001 ("3/07/2022 5:31:47 PM", datetime(2022, 3, 7, 17, 31, 47)),
), ("03/07/2022 5:31:47 PM", datetime(2022, 3, 7, 17, 31, 47)),
( ("3/7/2022 5:3:47 PM", datetime(2022, 3, 7, 17, 3, 47)),
"03/7/2022 5:31:47 PM", ("3/7/2022 5:31:4 PM", datetime(2022, 3, 7, 17, 31, 4)),
datetime(2022, 3, 7, 17, 31, 47), # noqa: DTZ001 ("3/7/2022 5:31:47 pm", datetime(2022, 3, 7, 17, 31, 47)),
), ("3/7/2022 5:31:47 AM", datetime(2022, 3, 7, 5, 31, 47)),
(
"3/07/2022 5:31:47 PM",
datetime(2022, 3, 7, 17, 31, 47), # noqa: DTZ001
),
(
"03/07/2022 5:31:47 PM",
datetime(2022, 3, 7, 17, 31, 47), # noqa: DTZ001
),
(
"3/7/2022 5:3:47 PM",
datetime(2022, 3, 7, 17, 3, 47), # noqa: DTZ001
),
(
"3/7/2022 5:31:4 PM",
datetime(2022, 3, 7, 17, 31, 4), # noqa: DTZ001
),
(
"3/7/2022 5:31:47 pm",
datetime(2022, 3, 7, 17, 31, 47), # noqa: DTZ001
),
(
"3/7/2022 5:31:47 AM",
datetime(2022, 3, 7, 5, 31, 47), # noqa: DTZ001
),
], ],
) )
def test_parser_target_data_timestamp_parser(value, expected): def test_parser_target_data_timestamp_parser(value, expected):
@ -227,6 +203,8 @@ def test_find_result_xml_file_ok(tmp_path):
xml_file = tmp_path / "result.xml" xml_file = tmp_path / "result.xml"
xml_file.touch() xml_file.touch()
print(list(tmp_path.iterdir()))
result = _find_result_xml_file(tmp_path) result = _find_result_xml_file(tmp_path)
assert result == xml_file assert result == xml_file
@ -279,6 +257,8 @@ def test_find_result_hidden_xsl_file(tmp_path):
xml_file = tmp_path / ".result.xml" xml_file = tmp_path / ".result.xml"
xml_file.touch() xml_file.touch()
print(list(tmp_path.iterdir()))
result = _find_result_xml_file(tmp_path) result = _find_result_xml_file(tmp_path)
assert result is None assert result is None
@ -286,9 +266,10 @@ def test_find_result_hidden_xsl_file(tmp_path):
def test_parse_xml_file_ok(example_dir): def test_parse_xml_file_ok(example_dir):
import pandas import pandas
from sensospot_parser.xml_parser import ( from sensospot_parser.xml_parser import (
_find_result_xml_file,
parse_xml_file, parse_xml_file,
_find_result_xml_file,
) )
folder = example_dir / EXAMPLE_DIR_XML_WO_PARAMS folder = example_dir / EXAMPLE_DIR_XML_WO_PARAMS
@ -307,10 +288,10 @@ def test_parse_xml_file_ok(example_dir):
@pytest.mark.parametrize( @pytest.mark.parametrize(
("file_name", "message"), "file_name, message",
[ [
("not_existing.xml", "Xml file does not exist"), ("not_existing.xml", "Xml file does not exist"),
("defect.xml", "Could not parse assay results xml file"), ("incomplete.xml", "Could not parse assay results xml file"),
("malformed_data.xml", "Malformed data in xml file"), ("malformed_data.xml", "Malformed data in xml file"),
], ],
) )
@ -319,14 +300,14 @@ def test_parse_xml_file_raies_error(file_name, message, example_dir):
xml_file = example_dir / file_name xml_file = example_dir / file_name
with pytest.raises(ValueError) as e: # noqa: PT011 with pytest.raises(ValueError) as e:
parse_xml_file(xml_file) parse_xml_file(xml_file)
assert message in str(e)
assert message in str(e)
def test_parse_xml_folder_with_params(example_dir): def test_parse_xml_folder_with_params(example_dir):
import pandas import pandas
from sensospot_parser.xml_parser import parse_xml_folder from sensospot_parser.xml_parser import parse_xml_folder
folder = example_dir / EXAMPLE_DIR_XML_WITH_PARAMS folder = example_dir / EXAMPLE_DIR_XML_WITH_PARAMS
@ -340,6 +321,7 @@ def test_parse_xml_folder_with_params(example_dir):
def test_parse_xml_folder_without_params(example_dir): def test_parse_xml_folder_without_params(example_dir):
import pandas import pandas
from sensospot_parser.xml_parser import parse_xml_folder from sensospot_parser.xml_parser import parse_xml_folder
folder = example_dir / EXAMPLE_DIR_XML_WO_PARAMS folder = example_dir / EXAMPLE_DIR_XML_WO_PARAMS
@ -354,7 +336,6 @@ def test_parse_xml_folder_without_params(example_dir):
def test_parse_xml_folder_non_existing_xml_file(tmp_path): def test_parse_xml_folder_non_existing_xml_file(tmp_path):
from sensospot_parser.xml_parser import parse_xml_folder from sensospot_parser.xml_parser import parse_xml_folder
with pytest.raises(ValueError) as e: # noqa: PT011 with pytest.raises(ValueError) as e:
parse_xml_folder(tmp_path) parse_xml_folder(tmp_path)
assert "Could not find assay results xml file" in str(e)
assert "Could not find assay results xml file" in str(e)

14
tox.ini
Unescape View File

@ -0,0 +1,14 @@
[tox]
envlist = py39, py310
isolated_build = True
[testenv]
deps =
pytest
pytest-cov
pytest-mock
setuptools>=41.2.0
pip>=20.0.2
changedir = {toxinidir}/tests
commands = pytest --cov=sensovation_parser
Write Preview
Loading…
Cancel
Save