integrate prepare cli (#401)

* move prepare into main CLI as subcommand

* naming and formatting tweaks to better match launch subcommand

server/cli/cli.py

@@ -1,6 +1,7 @@
 import click
 
 from .launch import launch
+from .prepare import prepare
 
 
 @click.group(name='cellxgene', context_settings=dict(max_content_width=85))
@@ -10,3 +11,4 @@ def cli():
 
 
 cli.add_command(launch)
+cli.add_command(prepare)

server/cli/prepare.py

@@ -4,28 +4,33 @@ from numpy import unique, ndarray
 from scipy.sparse.csc import csc_matrix
 from os.path import isfile, isdir, splitext, expanduser, sep
 
-settings = dict(help_option_names=['-h', '--help'])
-
 
 @click.command()
-@click.argument('dataset', nargs=1, metavar='<dataset: file or path to data>', required=True)
+@click.argument('data', nargs=1, metavar='<dataset: file or path to data>', required=True)
 @click.option('--layout', '-l', default=['umap', 'tsne'], multiple=True, type=click.Choice(['umap', 'tsne']),
-              help='layout algorithm', show_default=True)
+              help='Layout algorithm', show_default=True)
 @click.option('--recipe', '-r', default='none', type=click.Choice(['none', 'seurat', 'zheng17']),
-              help='preprocessing to run', show_default=True)
-@click.option('--output', '-o', default='', help='save a new file to filename', metavar='<filename>')
-@click.option('--set-obs-names', default='', help='named field to set as index for obs', metavar='<name>')
-@click.option('--set-var-names', default='', help='named field to set as index for var', metavar='<name>')
-@click.option('--make-obs-names-unique', default=True, is_flag=True, help='ensure obs index is unique', show_default=True)
-@click.option('--make-var-names-unique', default=True, is_flag=True, help='ensure var index is unique', show_default=True)
-@click.option('--sparse', default=False, is_flag=True, help='whether to force sparsity', show_default=True)
-@click.option('--overwriting', default=False, is_flag=True, help='whether to allow file overwriting', show_default=True)
-@click.option('--plotting', '-p', default=False, is_flag=True, help='whether to generate plots', show_default=True)
-def cli(dataset, layout, recipe, output, set_obs_names, set_var_names,
-        make_obs_names_unique, make_var_names_unique, sparse, overwriting, plotting):
-    """
-    preprocesses data for use with cellxgene
-    """
+              help='Preprocessing to run.', show_default=True)
+@click.option('--output', '-o', default='', help='Save a new file to filename.', metavar='<filename>')
+@click.option('--plotting', '-p', default=False, is_flag=True, help='Whether to generate plots.', show_default=True)
+@click.option('--sparse', default=False, is_flag=True, help='Whether to force sparsity.', show_default=True)
+@click.option('--overwrite', default=False, is_flag=True, help='Allow file overwriting.', show_default=True)
+@click.option('--set-obs-names', default='', help='Named field to set as index for obs.', metavar='<name>')
+@click.option('--set-var-names', default='', help='Named field to set as index for var.', metavar='<name>')
+@click.option('--make-obs-names-unique', default=True, is_flag=True,
+              help='Ensure obs index is unique.', show_default=True)
+@click.option('--make-var-names-unique', default=True, is_flag=True,
+              help='Ensure var index is unique.', show_default=True)
+def prepare(data, layout, recipe, output, plotting, sparse, overwrite,
+            set_obs_names, set_var_names, make_obs_names_unique, make_var_names_unique):
+    """Preprocesses data for use with cellxgene.
+
+    This tool runs a series of scanpy routines for preparing a dataset
+    for use with cellxgene. It loads data from different formats
+    (h5ad, loom, or a 10x directory), runs dimensionality reduction,
+    computes nearest neighbors, computes a layout, performs clustering,
+    and saves the results. Includes additional options for naming
+    annotations, ensuring sparsity, and plotting results."""
 
     # collect slow imports here to make CLI startup more responsive
     click.echo('[cellxgene] Starting CLI...')
@@ -43,31 +48,31 @@ def cli(dataset, layout, recipe, output, set_obs_names, set_var_names,
 
     output = expanduser(output)
     if isfile(output) and not overwrite:
-        raise click.UsageError('Cannot overwrite existing file %s, try using the flag --overwrite' % output)
+        raise click.UsageError(f'Cannot overwrite existing file {output}, try using the flag --overwrite')
 
-    def load_data(dataset):
-        if isfile(dataset):
-            name, extension = splitext(dataset)
+    def load_data(data):
+        if isfile(data):
+            name, extension = splitext(data)
             if extension == '.h5ad':
-                adata = sc.read_h5ad(dataset)
+                adata = sc.read_h5ad(data)
             elif extension == '.loom':
-                adata = sc.read_loom(dataset)
+                adata = sc.read_loom(data)
             else:
-                raise click.FileError(dataset, hint='does not have a valid extension [.h5ad | .loom]')
-        elif isdir(dataset):
-            if not dataset.endswith(sep):
-                dataset += sep
-            adata = sc.read_10x_mtx(dataset)
+                raise click.FileError(data, hint='does not have a valid extension [.h5ad | .loom]')
+        elif isdir(data):
+            if not data.endswith(sep):
+                data += sep
+            adata = sc.read_10x_mtx(data)
         else:
-            raise click.FileError(dataset, hint='not a valid file or path')
+            raise click.FileError(data, hint='not a valid file or path')
 
         if not set_obs_names == '':
             if set_obs_names not in adata.obs_keys():
-                raise click.UsageError('obs %s not found, options are: %s' % (set_obs_names, adata.obs_keys()))
+                raise click.UsageError(f'obs {set_obs_names} not found, options are: {adata.obs_keys()}')
             adata.obs_names = adata.obs[set_obs_names]
         if not set_var_names == '':
             if set_var_names not in adata.var_keys():
-                raise click.UsageError('var %s not found, options are: %s' % (set_var_names, adata.var_keys()))
+                raise click.UsageError(f'var {set_var_names} not found, options are: {adata.var_keys()}')
             adata.var_names = adata.var[set_var_names]
         if make_obs_names_unique:
             adata.obs_names_make_unique()
@@ -115,12 +120,12 @@ def cli(dataset, layout, recipe, output, set_obs_names, set_var_names,
         else:
             palette = 'tab20'
 
-        if layout == 'umap' or layout == 'umap+tsne':
+        if 'umap' in layout:
             sc.tl.umap(adata)
             if plotting:
                 sc.pl.umap(adata, color='louvain', palette=palette, save='_louvain')
 
-        if layout == 'tsne' or layout == 'umap+tsne':
+        if 'tsne' in layout:
             sc.tl.tsne(adata)
             if plotting:
                 sc.pl.tsne(adata, color='louvain', palette=palette, save='_louvain')
@@ -139,8 +144,8 @@ def cli(dataset, layout, recipe, output, set_obs_names, set_var_names,
 
     steps = [make_sparse, run_recipe, run_pca, run_neighbors, run_louvain, run_layout]
 
-    click.echo('[cellxgene] Loading data from %s, please wait...' % dataset)
-    adata = load_data(dataset)
+    click.echo(f'[cellxgene] Loading data from {data}, please wait...')
+    adata = load_data(data)
 
     click.echo('[cellxgene] Beginning preprocessing...')
     with click.progressbar(steps, label='[cellxgene] Progress', show_eta=False, item_show_func=show_step) as bar:
@@ -149,11 +154,7 @@ def cli(dataset, layout, recipe, output, set_obs_names, set_var_names,
 
     # saving
     if not output == '':
-        click.echo('[cellxgene] Saving results to %s...' % output)
+        click.echo(f'[cellxgene] Saving results to {output}...')
         adata.write(output)
 
-    click.echo('[cellxgene] ' + click.style('Success!', fg='green'))
-
-
-if __name__ == '__main__':
-    cli()
+    click.echo('[cellxgene] Success!')