def setUp(self):
args = {
"layout": ["umap"],
"max_category_items": 100,
"obs_names": None,
"var_names": None,
"diffexp_lfc_cutoff": 0.01,
}
self.data = ScanpyEngine("example-dataset/pbmc3k.h5ad", args)
def setUp(self):
args = {
"layout": ["umap"],
"max_category_items": 100,
"obs_names": None,
"var_names": None,
"diffexp_lfc_cutoff": 0.01,
"layout_file": None
}
self.data = ScanpyEngine(DataLocator(self.data_locator), args)
def setUp(self):
self.args = {
"layout": ["umap"],
"max_category_items": 100,
"obs_names": None,
"var_names": None,
"diffexp_lfc_cutoff": 0.01,
}
with warnings.catch_warnings():
warnings.simplefilter("ignore", category=UserWarning)
self.data = ScanpyEngine(DataLocator("server/test/test_datasets/nan.h5ad"), self.args)
self.data._create_schema()
def setUp(self):
self.tmpDir = tempfile.mkdtemp()
self.label_file = path.join(self.tmpDir, "labels.csv")
args = {
"layout": ["umap"],
"max_category_items": 100,
"obs_names": None,
"var_names": None,
"diffexp_lfc_cutoff": 0.01,
"label_file": self.label_file
}
self.data = ScanpyEngine(DataLocator("example-dataset/pbmc3k.h5ad"),
args)
def setUp(self):
args = {
"layout": "umap",
"diffexp": "ttest",
"max_category_items": 100,
"obs_names": None,
"var_names": None,
"diffexp_lfc_cutoff": 0.01,
"nan_to_num": True,
}
self.data = ScanpyEngine("example-dataset/pbmc3k.h5ad", args)
self.data._create_schema()
def run(self):
super(Worker, self).run()
if not self.data_file:
self.emit("finished")
return
from server.app.app import Server
from server.app.scanpy_engine.scanpy_engine import ScanpyEngine
# create server
try:
server = Server()
server.create_app()
except Exception as e:
self.emit("server_error", str(e))
self.emit("finished")
return
# load data
try:
args = {
"max_category_items": 100,
"diffexp_lfc_cutoff": 0.01,
"obs_names": None,
"var_names": None,
}
args.update(self.engine_options)
data = ScanpyEngine(self.data_file, args)
server.attach_data(data, self.title)
self.emit("ready")
except Exception as e:
self.emit("engine_error", str(e))
self.emit("finished")
return
# launch server
try:
server.app.run(host=self.host,
debug=False,
port=self.port,
threaded=True)
except Exception as e:
self.emit("server_error", str(e))
finally:
self.emit("finished")
def setUp(self):
self.data = ScanpyEngine("example-dataset/", schema="data_schema.json")
def launch(data, verbose, debug, open_browser, port, host, embedding,
obs_names, var_names, max_category_items, diffexp_lfc_cutoff, title,
scripts, about, experimental_label_file, backed, disable_diffexp):
"""Launch the cellxgene data viewer.
This web app lets you explore single-cell expression data.
Data must be in a format that cellxgene expects, read the
"getting started" guide.
Examples:
> cellxgene launch example_dataset/pbmc3k.h5ad --title pbmc3k
> cellxgene launch <your data file> --title <your title>
> cellxgene launch <url>"""
e_args = parse_engine_args(embedding, obs_names, var_names,
max_category_items, diffexp_lfc_cutoff,
experimental_label_file, backed,
disable_diffexp)
try:
data_locator = DataLocator(data)
except RuntimeError as re:
raise click.ClickException(
f"Unable to access data at {data}. {str(re)}")
# Startup message
click.echo("[cellxgene] Starting the CLI...")
# Argument checking
if data_locator.islocal():
# if data locator is local, apply file system conventions and other "cheap"
# validation checks. If a URI, defer until we actually fetch the data and
# try to read it. Many of these tests don't make sense for URIs (eg, extension-
# based typing).
if not data_locator.exists():
raise click.FileError(data, hint="file does not exist")
if not data_locator.isfile():
raise click.FileError(data, hint="data is not a file")
name, extension = splitext(data)
if extension != ".h5ad":
raise click.FileError(basename(data),
hint="file type must be .h5ad")
if debug:
verbose = True
open_browser = False
else:
warnings.formatwarning = custom_format_warning
if not verbose:
sys.tracebacklimit = 0
if scripts:
click.echo(r"""
/ / /\ \ \__ _ _ __ _ __ (_)_ __ __ _
\ \/ \/ / _` | '__| '_ \| | '_ \ / _` |
\ /\ / (_| | | | | | | | | | | (_| |
\/ \/ \__,_|_| |_| |_|_|_| |_|\__, |
|___/
The --scripts flag is intended for developers to include google analytics etc. You could be opening yourself to a
security risk by including the --scripts flag. Make sure you trust the scripts that you are including.
""")
scripts_pretty = ", ".join(scripts)
click.confirm(
f"Are you sure you want to inject these scripts: {scripts_pretty}?",
abort=True)
if not title:
file_parts = splitext(basename(data))
title = file_parts[0]
if port:
if debug:
raise click.ClickException(
"--port and --debug may not be used together (try --verbose for error logging)."
)
if not is_port_available(host, int(port)):
raise click.ClickException(
f"The port selected {port} is in use, please specify an open port using the --port flag."
)
else:
port = find_available_port(host)
if experimental_label_file:
lf_name, lf_ext = splitext(experimental_label_file)
if lf_ext and lf_ext != ".csv":
raise click.FileError(basename(experimental_label_file),
hint="label file type must be .csv")
if about:
def url_check(url):
try:
result = urlparse(url)
if all([result.scheme, result.netloc]):
return True
else:
return False
except ValueError:
return False
if not url_check(about):
raise click.ClickException(
"Must provide an absolute URL for --about. (Example format: http://example.com)"
)
# Setup app
cellxgene_url = f"http://{host}:{port}"
# Import Flask app
server = Server()
server.create_app()
server.app.config.update(SCRIPTS=scripts)
if not verbose:
log = logging.getLogger("werkzeug")
log.setLevel(logging.ERROR)
file_size = data_locator.size() if data_locator.islocal() else 0
# if a big file, let the user know it may take a while to load.
if file_size > BIG_FILE_SIZE_THRESHOLD:
click.echo(
f"[cellxgene] Loading data from {basename(data)}, this may take a while..."
)
else:
click.echo(f"[cellxgene] Loading data from {basename(data)}.")
from server.app.scanpy_engine.scanpy_engine import ScanpyEngine
try:
server.attach_data(ScanpyEngine(data_locator, e_args),
title=title,
about=about)
except ScanpyFileError as e:
raise click.ClickException(f"{e}")
if not disable_diffexp and server.app.data.config['diffexp_may_be_slow']:
click.echo(f"[cellxgene] CAUTION: due to the size of your dataset, "
f"running differential expression may take longer or fail.")
if open_browser:
click.echo(
f"[cellxgene] Launching! Opening your browser to {cellxgene_url} now."
)
webbrowser.open(cellxgene_url)
else:
click.echo(
f"[cellxgene] Launching! Please go to {cellxgene_url} in your browser."
)
click.echo("[cellxgene] Type CTRL-C at any time to exit.")
if not verbose:
f = open(devnull, "w")
sys.stdout = f
try:
server.app.run(host=host,
debug=debug,
port=port,
threaded=False if debug else True,
use_debugger=False)
except OSError as e:
if e.errno == errno.EADDRINUSE:
raise click.ClickException(
"Port is in use, please specify an open port using the --port flag."
) from e
raise
def test_url_http(self):
url = "http://raw.githubusercontent.com/chanzuckerberg/cellxgene/master/example-dataset/pbmc3k.h5ad"
locator = DataLocator(url)
data = ScanpyEngine(locator, self.args)
self.stdAsserts(data)
def test_posix_file(self):
locator = DataLocator("example-dataset/pbmc3k.h5ad")
data = ScanpyEngine(locator, self.args)
self.stdAsserts(data)
def setUp(self):
self.data_file = DataLocator("example-dataset/pbmc3k.h5ad")
self.data = ScanpyEngine()
def test_load(self):
with self.assertWarns(UserWarning):
ScanpyEngine("server/test/test_datasets/nan.h5ad", self.args)
def launch(data, verbose, debug, open_browser, port, host, layout, obs_names,
var_names, max_category_items, diffexp_lfc_cutoff, title, scripts):
"""Launch the cellxgene data viewer.
This web app lets you explore single-cell expression data.
Data must be in a format that cellxgene expects, read the
"getting started" guide.
Examples:
> cellxgene launch example_dataset/pbmc3k.h5ad --title pbmc3k
> cellxgene launch <your data file> --title <your title>"""
e_args = parse_engine_args(layout, obs_names, var_names,
max_category_items, diffexp_lfc_cutoff)
# Startup message
click.echo("[cellxgene] Starting the CLI...")
# Argument checking
name, extension = splitext(data)
if extension != ".h5ad":
raise click.FileError(basename(data), hint="file type must be .h5ad")
if debug:
verbose = True
open_browser = False
else:
warnings.formatwarning = custom_format_warning
if not verbose:
sys.tracebacklimit = 0
if scripts:
click.echo(r"""
/ / /\ \ \__ _ _ __ _ __ (_)_ __ __ _
\ \/ \/ / _` | '__| '_ \| | '_ \ / _` |
\ /\ / (_| | | | | | | | | | | (_| |
\/ \/ \__,_|_| |_| |_|_|_| |_|\__, |
|___/
The --scripts flag is intended for developers to include google analytics etc. You could be opening yourself to a
security risk by including the --scripts flag. Make sure you trust the scripts that you are including.
""")
scripts_pretty = ", ".join(scripts)
click.confirm(
f"Are you sure you want to inject these scripts: {scripts_pretty}?",
abort=True)
if not title:
file_parts = splitext(basename(data))
title = file_parts[0]
if port:
if debug:
raise click.ClickException(
"--port and --debug may not be used together (try --verbose for error logging)."
)
if not is_port_available(host, int(port)):
raise click.ClickException(
f"The port selected {port} is in use, please specify an open port using the --port flag."
)
else:
port = find_available_port(host)
# Setup app
cellxgene_url = f"http://{host}:{port}"
# Import Flask app
server = Server()
server.create_app()
server.app.config.update(SCRIPTS=scripts)
if not verbose:
log = logging.getLogger("werkzeug")
log.setLevel(logging.ERROR)
file_size = getsize(data)
# if a big file, let the user know it may take a while to load.
if file_size > BIG_FILE_SIZE_THRESHOLD:
click.echo(
f"[cellxgene] Loading data from {basename(data)}, this may take awhile..."
)
else:
click.echo(f"[cellxgene] Loading data from {basename(data)}.")
# Fix for anaconda python. matplotlib typically expects python to be installed as a framework TKAgg is usually
# available and fixes this issue. See https://matplotlib.org/faq/virtualenv_faq.html
import matplotlib as mpl
mpl.use("TkAgg")
from server.app.scanpy_engine.scanpy_engine import ScanpyEngine
try:
server.attach_data(ScanpyEngine(data, e_args), title=title)
except ScanpyFileError as e:
raise click.ClickException(f"{e}")
if open_browser:
click.echo(
f"[cellxgene] Launching! Opening your browser to {cellxgene_url} now."
)
webbrowser.open(cellxgene_url)
else:
click.echo(
f"[cellxgene] Launching! Please go to {cellxgene_url} in your browser."
)
click.echo("[cellxgene] Type CTRL-C at any time to exit.")
if not verbose:
f = open(devnull, "w")
sys.stdout = f
try:
server.app.run(host=host,
debug=debug,
port=port,
threaded=True,
use_debugger=False)
except OSError as e:
if e.errno == errno.EADDRINUSE:
raise click.ClickException(
"Port is in use, please specify an open port using the --port flag."
) from e
raise
def launch(
data,
layout,
diffexp,
title,
verbose,
debug,
obs_names,
var_names,
open_browser,
port,
host,
max_category_items,
diffexp_lfc_cutoff,
):
"""Launch the cellxgene data viewer.
This web app lets you explore single-cell expression data.
Data must be in a format that cellxgene expects, read the
"getting started" guide.
Examples:
> cellxgene launch example_dataset/pbmc3k.h5ad --title pbmc3k
> cellxgene launch <your data file> --title <your title>"""
# Startup message
click.echo("[cellxgene] Starting the CLI...")
# Argument checking
name, extension = splitext(data)
if extension != ".h5ad":
raise click.FileError(basename(data), hint="file type must be .h5ad")
if debug:
verbose = True
open_browser = False
else:
warnings.formatwarning = custom_format_warning
if not verbose:
sys.tracebacklimit = 0
if not title:
file_parts = splitext(basename(data))
title = file_parts[0]
# Setup app
cellxgene_url = f"http://{host}:{port}"
# Import Flask app
from server.app.app import app
app.config.update(DATASET_TITLE=title)
if not verbose:
log = logging.getLogger("werkzeug")
log.setLevel(logging.ERROR)
click.echo(
f"[cellxgene] Loading data from {basename(data)}, this may take awhile..."
)
# Fix for anaconda python. matplotlib typically expects python to be installed as a framework TKAgg is usually
# available and fixes this issue. See https://matplotlib.org/faq/virtualenv_faq.html
import matplotlib as mpl
mpl.use("TkAgg")
from server.app.scanpy_engine.scanpy_engine import ScanpyEngine
args = {
"layout": layout,
"diffexp": diffexp,
"max_category_items": max_category_items,
"diffexp_lfc_cutoff": diffexp_lfc_cutoff,
"obs_names": obs_names,
"var_names": var_names,
}
try:
app.data = ScanpyEngine(data, args)
except ScanpyFileError as e:
raise click.ClickException(f"{e}")
if open_browser:
click.echo(
f"[cellxgene] Launching! Opening your browser to {cellxgene_url} now."
)
webbrowser.open(cellxgene_url)
else:
click.echo(
f"[cellxgene] Launching! Please go to {cellxgene_url} in your browser."
)
click.echo("[cellxgene] Type CTRL-C at any time to exit.")
if not verbose:
f = open(devnull, "w")
sys.stdout = f
app.run(host=host, debug=debug, port=port, threaded=True)
def setUp(self):
self.data_file = "example-dataset/pbmc3k.h5ad"
self.data = ScanpyEngine()