Merge pull request aristoteleo#690 from chansigit/master

init a branch for fixing

.github/workflows/python-docker.yml

@@ -29,7 +29,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-lastest, windows-2016]
-        node-version: [12.x, 14.x]
+        node-version: [22.x, 24.x]
 
     steps:
       - uses: actions/checkout@v1

.github/workflows/python-package.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9]
+        python-version: [3.8, 3.9, 3.10.14, 3.11]
 
     steps:
     - uses: actions/checkout@v2
@@ -40,4 +40,4 @@ jobs:
         flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
 #    - name: Test with pytest
 #      run: |
-#        pytest
+#        pytest

.github/workflows/python-plain-run-test.yml

@@ -13,8 +13,9 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.8, 3.9]
+        python-version: [3.8, 3.9, 3.10.14, 3.11]
 
+    continue-on-error: true
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}

docs/source/_ext/pdfembed.py

@@ -3,6 +3,7 @@
 
 from docutils import nodes
 
+
 def pdfembed_html(pdfembed_specs):
     """
     Build the iframe code for the pdf file,
@@ -20,27 +21,31 @@ def pdfembed_html(pdfembed_specs):
                                 align="%s">
                         </iframe>
                      """
-    return ( html_base_code % (pdfembed_specs['src'   ],
-                               pdfembed_specs['height'],
-                               pdfembed_specs['width' ],
-                               pdfembed_specs['align' ]) )
+    return html_base_code % (
+        pdfembed_specs["src"],
+        pdfembed_specs["height"],
+        pdfembed_specs["width"],
+        pdfembed_specs["align"],
+    )
+
 
 def pdfembed_role(typ, rawtext, text, lineno, inliner, options={}, content=[]):
     """
     Get iframe specifications and generate the associate HTML code for the pdf iframe.
     """
     # parse and init variables
-    text           = text.replace(' ', '')
+    text = text.replace(" ", "")
     pdfembed_specs = {}
     # read specs
-    for component in text.split(','):
-         pdfembed_specs[component.split(':')[0]] = component.split(':')[1]
+    for component in text.split(","):
+        pdfembed_specs[component.split(":")[0]] = component.split(":")[1]
     # build node from pdf iframe html code
-    node = nodes.raw('', pdfembed_html(pdfembed_specs), format='html')
+    node = nodes.raw("", pdfembed_html(pdfembed_specs), format="html")
     return [node], []
 
+
 def setup(app):
     """
     Set up the app with the extension function
     """
-    app.add_role('pdfembed', pdfembed_role)
+    app.add_role("pdfembed", pdfembed_role)

docs/source/conf.py

@@ -114,7 +114,7 @@
     "sphinxcontrib.bibtex",
     "sphinx_gallery.load_style",
     # pdf embed
-    'pdfembed',
+    "pdfembed",
 ]
 
 # Mappings for sphinx.ext.intersphinx. Projects have to have Sphinx-generated doc! (.inv file)

dynamo/__init__.py

@@ -1,7 +1,7 @@
 """Mapping Vector Field of Single Cells
 """
 
-from .get_version import get_version, get_dynamo_version
+from .get_version import get_dynamo_version, get_version
 
 __version__ = get_version(__file__)
 del get_version
@@ -19,7 +19,6 @@
 from . import mv
 from . import shiny
 from . import sim
-from .data_io import *
 from . import sample_data
 from . import configuration
 from . import ext

dynamo/configuration.py

@@ -1,8 +1,9 @@
 import warnings
-from typing import Any, List, Generator, Optional, Tuple, Union
+from typing import Any, Generator, List, Optional, Tuple, Union
 
 import colorcet
 import matplotlib
+import matplotlib as mpl
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
@@ -15,6 +16,7 @@
 
 class DynamoAdataKeyManager:
     """A class to manage the keys used in anndata object for dynamo."""
+
     VAR_GENE_MEAN_KEY = "pp_gene_mean"
     VAR_GENE_VAR_KEY = "pp_gene_variance"
     VAR_GENE_HIGHLY_VARIABLE_KEY = "gene_highly_variable"
@@ -41,8 +43,8 @@ class DynamoAdataKeyManager:
     RAW = "raw"
 
     def _select_layer_cell_chunked_data(
-            mat: np.ndarray,
-            chunk_size: int,
+        mat: np.ndarray,
+        chunk_size: int,
     ) -> Generator:
         """Select layer data in cell chunks based on chunk_size."""
         start = 0
@@ -55,8 +57,8 @@ def _select_layer_cell_chunked_data(
             yield (mat[start:n, :], start, n)
 
     def _select_layer_gene_chunked_data(
-            mat: np.ndarray,
-            chunk_size: int,
+        mat: np.ndarray,
+        chunk_size: int,
     ) -> Generator:
         """Select layer data in gene chunks based on chunk_size."""
         start = 0
@@ -131,8 +133,11 @@ def select_layer_chunked_data(
             elif layer == DynamoAdataKeyManager.RAW:
                 return DynamoAdataKeyManager._select_layer_cell_chunked_data(adata.raw.X, chunk_size=chunk_size)
             elif layer == DynamoAdataKeyManager.PROTEIN_LAYER:
-                return DynamoAdataKeyManager._select_layer_cell_chunked_data(
-                    adata.obsm["protein"], chunk_size=chunk_size) if "protein" in adata.obsm_keys() else None
+                return (
+                    DynamoAdataKeyManager._select_layer_cell_chunked_data(adata.obsm["protein"], chunk_size=chunk_size)
+                    if "protein" in adata.obsm_keys()
+                    else None
+                )
             else:
                 return DynamoAdataKeyManager._select_layer_cell_chunked_data(adata.layers[layer], chunk_size=chunk_size)
         elif chunk_mode == "gene":
@@ -141,8 +146,11 @@ def select_layer_chunked_data(
             elif layer == DynamoAdataKeyManager.RAW:
                 return DynamoAdataKeyManager._select_layer_gene_chunked_data(adata.raw.X, chunk_size=chunk_size)
             elif layer == DynamoAdataKeyManager.PROTEIN_LAYER:
-                return DynamoAdataKeyManager._select_layer_gene_chunked_data(
-                    adata.obsm["protein"], chunk_size=chunk_size) if "protein" in adata.obsm_keys() else None
+                return (
+                    DynamoAdataKeyManager._select_layer_gene_chunked_data(adata.obsm["protein"], chunk_size=chunk_size)
+                    if "protein" in adata.obsm_keys()
+                    else None
+                )
             else:
                 return DynamoAdataKeyManager._select_layer_gene_chunked_data(adata.layers[layer], chunk_size=chunk_size)
         else:
@@ -172,7 +180,10 @@ def check_if_layer_exist(adata: AnnData, layer: str) -> bool:
         return layer in adata.layers
 
     def get_available_layer_keys(
-        adata: AnnData, layers: str = "all", remove_pp_layers: bool = True, include_protein: bool = True,
+        adata: AnnData,
+        layers: str = "all",
+        remove_pp_layers: bool = True,
+        include_protein: bool = True,
     ) -> List[str]:
         """Get the list of available layers' keys. If `layers` is set to all, return a list of all available layers; if
         `layers` is set to a list, then the intersetion of available layers and `layers` will be returned."""
@@ -278,6 +289,7 @@ def aggregate_layers_into_total(
 
 class DynamoVisConfig:
     """Dynamo visualization config class holding static variables to change behaviors of functions globally."""
+
     def set_default_mode(background="white"):
         """Set the default mode for dynamo visualization."""
         set_figure_params("dynamo", background=background)
@@ -340,7 +352,7 @@ def use_default_var_if_none(val: Any, key: str, replace_val: Optional[Any] = Non
         Returns:
             `val` or config value set in DynamoAdataConfig according to the method description above.
         """
-        if not key in DynamoAdataConfig.config_key_to_values:
+        if key not in DynamoAdataConfig.config_key_to_values:
             assert KeyError("Config %s not exist in DynamoAdataConfig." % (key))
         if val == replace_val:
             config_val = DynamoAdataConfig.config_key_to_values[key]
@@ -431,26 +443,26 @@ def update_data_store_mode(mode: str) -> None:
 # register cmap
 with warnings.catch_warnings():
     warnings.simplefilter("ignore")
-    if "zebrafish" not in matplotlib.colormaps():
-        plt.register_cmap("zebrafish", zebrafish_cmap)
-    if "fire" not in matplotlib.colormaps():
-        plt.register_cmap("fire", fire_cmap)
-    if "darkblue" not in matplotlib.colormaps():
-        plt.register_cmap("darkblue", darkblue_cmap)
-    if "darkgreen" not in matplotlib.colormaps():
-        plt.register_cmap("darkgreen", darkgreen_cmap)
-    if "darkred" not in matplotlib.colormaps():
-        plt.register_cmap("darkred", darkred_cmap)
-    if "darkpurple" not in matplotlib.colormaps():
-        plt.register_cmap("darkpurple", darkpurple_cmap)
-    if "div_blue_black_red" not in matplotlib.colormaps():
-        plt.register_cmap("div_blue_black_red", div_blue_black_red_cmap)
-    if "div_blue_red" not in matplotlib.colormaps():
-        plt.register_cmap("div_blue_red", div_blue_red_cmap)
-    if "glasbey_white" not in matplotlib.colormaps():
-        plt.register_cmap("glasbey_white", glasbey_white_cmap)
-    if "glasbey_dark" not in matplotlib.colormaps():
-        plt.register_cmap("glasbey_dark", glasbey_dark_cmap)
+    if "zebrafish" not in mpl.colormaps():
+        mpl.colormaps.register(name="zebrafish", cmap=zebrafish_cmap)
+    if "fire" not in mpl.colormaps():
+        mpl.colormaps.register(name="fire", cmap=fire_cmap)
+    if "darkblue" not in mpl.colormaps():
+        mpl.colormaps.register(name="darkblue", cmap=darkblue_cmap)
+    if "darkgreen" not in mpl.colormaps():
+        mpl.colormaps.register(name="darkgreen", cmap=darkgreen_cmap)
+    if "darkred" not in mpl.colormaps():
+        mpl.colormaps.register(name="darkred", cmap=darkred_cmap)
+    if "darkpurple" not in mpl.colormaps():
+        mpl.colormaps.register(name="darkpurple", cmap=darkpurple_cmap)
+    if "div_blue_black_red" not in mpl.colormaps():
+        mpl.colormaps.register(name="div_blue_black_red", cmap=div_blue_black_red_cmap)
+    if "div_blue_red" not in mpl.colormaps():
+        mpl.colormaps.register(name="div_blue_red", cmap=div_blue_red_cmap)
+    if "glasbey_white" not in mpl.colormaps():
+        mpl.colormaps.register(name="glasbey_white", cmap=glasbey_white_cmap)
+    if "glasbey_dark" not in mpl.colormaps():
+        mpl.colormaps.register(name="glasbey_dark", cmap=glasbey_dark_cmap)
 
 
 _themes = {

dynamo/data_io.py

@@ -78,7 +78,11 @@ def convert2float(adata: AnnData, columns: List, var: bool = False) -> None:
 
 
 def load_NASC_seq(
-    dir: str, type: str = "TPM", delimiter: str = "_", colnames: Optional[List] = None, dropna: bool = False,
+    dir: str,
+    type: str = "TPM",
+    delimiter: str = "_",
+    colnames: Optional[List] = None,
+    dropna: bool = False,
 ) -> AnnData:
     """Function to create an anndata object from NASC-seq pipeline.
 
@@ -134,7 +138,7 @@ def load_NASC_seq(
         tot_RNA = None
         cells_raw, cells = None, None
 
-        for f in tqdm(files, desc=f"reading rmse output files:"):
+        for f in tqdm(files, desc="reading rmse output files:"):
             tmp = pd.read_csv(f, index_col=0, sep="\t")
 
             if tot_RNA is None:
@@ -247,7 +251,7 @@ def aggregate_adata(file_list: list) -> AnnData:
 
     if len(valid_cells) == 0 or len(valid_genes) == 0:
         raise Exception(
-            f"we don't find any gene or cell names shared across different adata objects." f"Please check your data. "
+            "we don't find any gene or cell names shared across different adata objects."+"Please check your data. "
         )
 
     layer_dict = {}
@@ -323,7 +327,10 @@ def cleanup(adata: AnnData, del_prediction: bool = False, del_2nd_moments: bool
 
 
 def export_rank_xlsx(
-    adata: AnnData, path: str = "rank_info.xlsx", ext: str = "excel", rank_prefix: str = "rank",
+    adata: AnnData,
+    path: str = "rank_info.xlsx",
+    ext: str = "excel",
+    rank_prefix: str = "rank",
 ) -> None:
     import pandas as pd
 
@@ -373,15 +380,16 @@ def export_h5ad(adata: AnnData, path: str = "data/processed_data.h5ad") -> None:
     for i in fate_keys:
         if i is not None:
             if "prediction" in adata.uns[i].keys():
-                adata.uns[i]["prediction"] = {str(index): array for index, array in
-                                              enumerate(adata.uns[i]["prediction"])}
+                adata.uns[i]["prediction"] = {
+                    str(index): array for index, array in enumerate(adata.uns[i]["prediction"])
+                }
             if "t" in adata.uns[i].keys():
                 adata.uns[i]["t"] = {str(index): array for index, array in enumerate(adata.uns[i]["t"])}
 
     adata.write_h5ad(path)
 
 
-def import_h5ad(path: str ="data/processed_data.h5ad") -> AnnData:
+def import_h5ad(path: str = "data/processed_data.h5ad") -> AnnData:
     """Import a Dynamo h5ad object into anndata."""
 
     adata = read_h5ad(path)
@@ -397,4 +405,3 @@ def import_h5ad(path: str ="data/processed_data.h5ad") -> AnnData:
                 adata.uns[i]["t"] = [adata.uns[i]["t"][index] for index in adata.uns[i]["t"]]
 
     return adata
-

dynamo/dynamo_logger.py

@@ -1,10 +1,9 @@
-from typing import Iterable, Optional
-
 import functools
 import logging
 import sys
 import time
 from contextlib import contextmanager
+from typing import Iterable, Optional
 
 
 def silence_logger(name: str) -> None:
@@ -176,7 +175,13 @@ def error(self, message: str, indent_level: int = 1, *args, **kwargs) -> None:
         return self.logger.error(message, *args, **kwargs)
 
     def info_insert_adata(
-        self, key: str, adata_attr: str = "obsm", log_level: int = logging.NOTSET, indent_level: int = 1, *args, **kwargs
+        self,
+        key: str,
+        adata_attr: str = "obsm",
+        log_level: int = logging.NOTSET,
+        indent_level: int = 1,
+        *args,
+        **kwargs,
     ) -> None:
         """Log a message for inserting data into an AnnData object."""
         message = "<insert> %s to %s in AnnData Object." % (key, adata_attr)
@@ -314,7 +319,10 @@ def get_temp_timer_logger() -> Logger:
 
     @staticmethod
     def progress_logger(
-        generator: Iterable, logger: Optional[Logger] = None, progress_name: str = "", indent_level: int = 1,
+        generator: Iterable,
+        logger: Optional[Logger] = None,
+        progress_name: str = "",
+        indent_level: int = 1,
     ) -> Iterable:
         """A generator that logs the progress of another generator."""
         if logger is None:
@@ -362,7 +370,10 @@ def main_critical(message: str, indent_level: int = 1) -> None:
 
 
 def main_tqdm(
-    generator: Iterable, desc: str = "", indent_level: int = 1, logger: LoggerManager = LoggerManager().main_logger,
+    generator: Iterable,
+    desc: str = "",
+    indent_level: int = 1,
+    logger: LoggerManager = LoggerManager().main_logger,
 ) -> Iterable:
     """a TQDM style wrapper for logging something like a loop.
 

dynamo/estimation/csc/utils_velocity.py

@@ -302,7 +302,7 @@ def fit_linreg_robust(
                 f"estimation method {est_method} is not implemented. "
                 f"Currently supported linear regression methods include `rlm` and `ransac`."
             )
-    except:
+    except Exception as e:
         if intercept:
             ym = np.mean(yy)
             xm = np.mean(xx)