extract prepare from main install (#887)

* extract prepare from main install

* add requirements-prepare to manifest

MANIFEST.in

@@ -1,4 +1,5 @@
 recursive-include server/app/web/templates *
 recursive-include server/app/web/static *
 
-include server/requirements.txt
+include server/requirements.txt
+include server/requirements-prepare.txt

server/cli/launch.py

@@ -185,11 +185,6 @@ def launch(
     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/cli/prepare.py

@@ -41,18 +41,18 @@ from scipy.sparse.csc import csc_matrix
     "--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,
-    run_qc,
-    make_obs_names_unique,
-    make_var_names_unique,
+        data,
+        layout,
+        recipe,
+        output,
+        plotting,
+        sparse,
+        overwrite,
+        set_obs_names,
+        set_var_names,
+        run_qc,
+        make_obs_names_unique,
+        make_var_names_unique,
 ):
     """Preprocesses data for use with cellxgene.
 
@@ -65,10 +65,16 @@ def prepare(
 
     # collect slow imports here to make CLI startup more responsive
     click.echo("[cellxgene] Starting CLI...")
-    import matplotlib
+    try:
+        import matplotlib
 
-    matplotlib.use("Agg")
-    import scanpy as sc
+        matplotlib.use("Agg")
+        import scanpy as sc
+    except ImportError:
+        raise click.ClickException(
+            "[cellxgene] cellxgene prepare has not been installed. Please run `pip install cellxgene[prepare]` "
+            "to install the necessary requirements."
+        )
 
     # scanpy settings
     sc.settings.verbosity = 0

server/requirements-prepare.txt

@@ -0,0 +1 @@
+scanpy>=1.3.7

server/requirements.txt

@@ -6,11 +6,7 @@ Flask-Compress>=1.4.0
 Flask-Cors>=3.0.6
 Flask-RESTful>=0.3.6
 flatbuffers>=1.10.0
-# TODO revert after scanpy updates their dependency on this
-matplotlib<3.1
 numpy>=1.15.2
 pandas>=0.23.1
-scanpy>=1.3.7
 scipy>=1.1.0
-scikit-learn>=0.19.1,!=0.20.0
 tables==3.5.1

setup.py

@@ -6,6 +6,9 @@ with open("README.md", "rb") as fh:
 with open("server/requirements.txt") as fh:
     requirements = fh.read().splitlines()
 
+with open("server/requirements-prepare.txt") as fh:
+    requirements_prepare = fh.read().splitlines()
+
 setup(
     name="cellxgene",
     version="0.11.0",
@@ -36,5 +39,5 @@ setup(
         "Topic :: Scientific/Engineering :: Bio-Informatics",
     ],
     entry_points={"console_scripts": ["cellxgene = server.cli.cli:cli"]},
-    extras_require=dict(louvain=["python-igraph", "louvain>=0.6"], gui=["PySide2>=5.12.3", "cefpython3>=66", "requests"]),
+    extras_require=dict(prepare=requirements_prepare, louvain=["python-igraph", "louvain>=0.6"], gui=["PySide2>=5.12.3", "cefpython3>=66", "requests"]),
 )