mirror of
https://github.com/chanzuckerberg/cellxgene.git
synced 2026-09-18 18:38:11 +08:00
f3015cb9df
* Fix Makefile whitespace and .PHONY use
* Fix Makefile filename
* Modularize Makefile into client and server Makefiles
Part of the reason that the Makefile in the root directory is a bit
complicated is that it tries to handle tasks that can be handled
separately in the client and server modules.
This commit pushes some of the make logic specific to each module into
their own makefiles and calls out to those makefiles from that in the
project root.
* Add auto-formatting to client and server modules
One thing that can make linting faster is auto-formatting. This commit
adds the yapf auto-formatting tool to the server module and uses
eslint's "fix" functionality to speed up the linting/formatting process.
* Add yapf for automatic code formatting
* Add a root test target that calls sub-tests
* Apply yapf to python files
* Do not duplicate npm commands, simply pass through
* Update documentation
* Do not shadow reserved word len
* Add general test target
* Fix make call in dev-env
* Use black instead of yapf
* Run flake8 from the root directory
* Revert "Apply yapf to python files"
This reverts commit cdca128a01.
* Apply black to python code
* Resolve lint errors resulting from black format
* Add explanation of server unit tests in dev guidelines
114 lines
3.5 KiB
Python
114 lines
3.5 KiB
Python
from abc import ABCMeta, abstractmethod
|
|
|
|
"""
|
|
Sort order for methods
|
|
1. Initialize
|
|
2. Helper
|
|
3. Filter
|
|
4. Data & Metadata
|
|
5. Computation
|
|
"""
|
|
|
|
|
|
class CXGDriver(metaclass=ABCMeta):
|
|
def __init__(self, data_locator=None, args={}):
|
|
self.config = self._get_default_config()
|
|
self.config.update(args)
|
|
if data_locator:
|
|
self._load_data(data_locator)
|
|
self.data_locator = data_locator
|
|
else:
|
|
self.data = None
|
|
|
|
def update(self, data_locator=None, args={}):
|
|
self.config.update(args)
|
|
if data_locator:
|
|
self._load_data(data_locator)
|
|
self.data_locator = data_locator
|
|
|
|
@staticmethod
|
|
def _get_default_config():
|
|
return {
|
|
"layout": None,
|
|
"max_category_items": None,
|
|
"diffexp_lfc_cutoff": None,
|
|
"disable_diffexp": False,
|
|
"diffexp_may_be_slow": False,
|
|
}
|
|
|
|
@abstractmethod
|
|
def get_config_parameters(self, uid=None):
|
|
"""
|
|
return a dict of properties that will be used to set the engine-specific
|
|
"parameters" info for client-side configuration.
|
|
|
|
See rest.py /config route for use
|
|
"""
|
|
pass
|
|
|
|
@property
|
|
def features(self):
|
|
features = {
|
|
"cluster": {"available": False},
|
|
"layout": {"obs": {"available": False}, "var": {"available": False}},
|
|
"diffexp": {"available": True, "interactiveLimit": 50000},
|
|
}
|
|
# TODO - Interactive limit should be generated from the actual available methods see GH issue #94
|
|
if self.config["layout"]:
|
|
# TODO handle "var" when gene layout becomes available
|
|
features["layout"]["obs"] = {"available": True, "interactiveLimit": 50000}
|
|
return features
|
|
|
|
@abstractmethod
|
|
def get_schema(self):
|
|
"""
|
|
Return current schema
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def _load_data(self, data_locator):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def annotation_to_fbs_matrix(self, axis, field=None, uid=None):
|
|
"""
|
|
Gets annotation value for each observation
|
|
:param axis: string obs or var
|
|
:param fields: list of keys for annotation to return, returns all annotation values if not set.
|
|
:return: flatbuffer: in fbs/matrix.fbs encoding
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def annotation_put_fbs(self, axis, fbs, uid=None):
|
|
"""
|
|
Put/save FBS as user-defined labels
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def data_frame_to_fbs_matrix(self, filter, axis):
|
|
pass
|
|
|
|
@abstractmethod
|
|
def diffexp_topN(self, obsFilter1, obsFilter2, top_n=None, interactive_limit=None):
|
|
"""
|
|
Computes the top N differentially expressed variables between two observation sets. If mode
|
|
is "TOP_N", then stats for the top N
|
|
dataframes
|
|
contain a subset of variables, then statistics for all variables will be returned, otherwise
|
|
only the top N vars will be returned.
|
|
:param obsFilter1: filter: dictionary with filter params for first set of observations
|
|
:param obsFilter2: filter: dictionary with filter params for second set of observations
|
|
:param top_n: Limit results to top N (Top var mode only)
|
|
:param interactive_limit: -- don't compute if total # genes in dataframes are larger than this
|
|
:return: top N genes and corresponding stats
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def layout_to_fbs_matrix(self, filter):
|
|
""" same as layout, except returns a flatbuffer """
|
|
pass
|