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

Use click to allow command line arguments #79

Merged
merged 6 commits into from
Mar 8, 2024
Merged
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
31 changes: 30 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -65,4 +65,33 @@ $ cupid-build config.yml # Will build HTML from Jupyter Book
```

After the last step is finished, you can use Jupyter to view generated notebooks in `${CUPID_ROOT}/examples/coupled-model/computed_notebooks/quick-run`
or you can view `${CUPID_ROOT}/examples/coupled-model/computed_notebooks/quick-run/_build/html/index.html` in a web browser.
or you can view `${CUPID_ROOT}/examples/coupled-model/computed_notebooks/quick-run/_build/html/index.html` in a web browser.

### CUPiD Options

Most of CUPiD's configuration is done via the `config.yml` file, but there are a few command line options as well:

```bash
(cupid-dev) $ cupid-run -h
Usage: cupid-run [OPTIONS] CONFIG_PATH

Main engine to set up running all the notebooks.

Options:
-s, --serial Do not use LocalCluster objects
-ts, --time-series Run time series generation scripts prior to diagnostics
-h, --help Show this message and exit.
```

By default, several of the example notebooks provided use a dask `LocalCluster` object to run in parallel.
However, the `--serial` option will pass a logical flag to each notebook that can be used to skip starting the cluster.

```py3
# Spin up cluster (if running in parallel)
client=None
if not serial:
cluster = LocalCluster(**lc_kwargs)
client = Client(cluster)

client
```
26 changes: 16 additions & 10 deletions cupid/run.py
Original file line number Diff line number Diff line change
@@ -1,29 +1,34 @@
#!/usr/bin/env python

import click
import os
import sys
from glob import glob
import papermill as pm
import intake
import cupid.util
import sys
from dask.distributed import Client
import dask
import time
import ploomber

def run():
CONTEXT_SETTINGS = dict(help_option_names=['-h', '--help'])
@click.command(context_settings=CONTEXT_SETTINGS)
@click.option("--serial", "-s", is_flag=True, help="Do not use LocalCluster objects")
@click.option("--time-series", "-ts", is_flag=True,
help="Run time series generation scripts prior to diagnostics")
@click.argument("config_path")
def run(config_path, serial=False, time_series=False):
"""
Main engine to set up running all the notebooks. Called by `cupid-run`.

Args:
none
Returns:
None

Main engine to set up running all the notebooks.
"""

# Abort if run with --time-series (until feature is added)
if time_series:
sys.tracebacklimit = 0
raise NotImplementedError("--time-series option not implemented yet")

# Get control structure
config_path = str(sys.argv[1])
control = cupid.util.get_control_dict(config_path)
cupid.util.setup_book(config_path)

Expand Down Expand Up @@ -87,6 +92,7 @@ def run():

for nb, info in all_nbs.items():

global_params['serial'] = serial
if "dependency" in info:
cupid.util.create_ploomber_nb_task(nb, info, cat_path, nb_path_root, output_dir, global_params, dag, dependency = info["dependency"])

Expand Down
1 change: 1 addition & 0 deletions environments/dev-environment.yml
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@ name: cupid-dev
dependencies:
- python=3.11.4
- black
- click
- dask
- dask-jobqueue
- intake
Expand Down
9 changes: 6 additions & 3 deletions examples/nblibrary/ocean_surface.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,7 @@
"outputs": [],
"source": [
"CESM_output_dir = \"/glade/campaign/cesm/development/cross-wg/diagnostic_framework/CESM_output_for_testing\"\n",
"serial = False # use dask LocalCluster\n",
"Case = \"b.e23_alpha16b.BLT1850.ne30_t232.054\"\n",
"savefigs = False\n",
"mom6_tools_config = {}\n",
Expand Down Expand Up @@ -130,9 +131,11 @@
"metadata": {},
"outputs": [],
"source": [
"# Spin up cluster\n",
"cluster = LocalCluster(**lc_kwargs)\n",
"client = Client(cluster)\n",
"# Spin up cluster (if running in parallel)\n",
"client=None\n",
"if not serial:\n",
" cluster = LocalCluster(**lc_kwargs)\n",
" client = Client(cluster)\n",
"\n",
"client"
]
Expand Down
9 changes: 6 additions & 3 deletions examples/nblibrary/seaice.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@
"outputs": [],
"source": [
"CESM_output_dir = \"/glade/campaign/cesm/development/cross-wg/diagnostic_framework/CESM_output_for_testing\"\n",
"serial = False # use dask LocalCluster\n",
"cases = [\"g.e23_a16g.GJRAv4.TL319_t232_zstar_N65.2024.004\",\"g.e23_a16g.GJRAv4.TL319_t232_hycom1_N75.2024.005\"]\n",
"\n",
"lc_kwargs = {}\n",
Expand All @@ -63,9 +64,11 @@
"metadata": {},
"outputs": [],
"source": [
"# Spin up cluster\n",
"cluster = LocalCluster(**lc_kwargs)\n",
"client = Client(cluster)\n",
"# Spin up cluster (if running in parallel)\n",
"client=None\n",
"if not serial:\n",
" cluster = LocalCluster(**lc_kwargs)\n",
" client = Client(cluster)\n",
"\n",
"client"
]
Expand Down
1 change: 1 addition & 0 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@ classifiers = [
]
dependencies = [
"black",
"click",
"dask",
"dask-jobqueue",
"intake",
Expand Down