codecov changes to workflow

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

@@ -1,4 +1,4 @@
-# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# This workflow will install Python dependencies, run tests, collect coverage and lint with a variety of Python versions
 # For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
 
 name: dynamo test
@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9]
+        python-version: [3.8, 3.9]
 
     steps:
     - uses: actions/checkout@v2
@@ -39,7 +39,13 @@ jobs:
 #    - name: Test with pytest
 #      run: |
 #        pytest
-    - name: Test with plain runs
+    - name: Run tests and collect coverage
       run: |
-        # pytest -v
-        # bash ./tests/run_plain_tests.sh
+        pip install pytest-cov
+        pip install mygene igraph leidenalg
+        pytest --cov=./ --cov-report=xml
+    - name: Upload coverage to Codecov
+      uses: codecov/codecov-action@v3
+      with:
+        fail_ci_if_error: true
+        verbose: true

README.md

@@ -4,13 +4,14 @@
 
 ##
 
-[![package](https://github.com/aristoteleo/dynamo-release/workflows/Python%20package/badge.svg)](https://github.com/aristoteleo/dynamo-release/runs/950435412) 
-[![upload](https://github.com/aristoteleo/dynamo-release/workflows/Upload%20Python%20Package/badge.svg)](https://pypi.org/project/dynamo-release/) 
+[![package](https://github.com/aristoteleo/dynamo-release/workflows/Python%20package/badge.svg)](https://github.com/aristoteleo/dynamo-release)
 [![documentation](https://readthedocs.org/projects/dynamo-release/badge/?version=latest)](https://dynamo-release.readthedocs.io/en/latest/)
+[![upload](https://img.shields.io/pypi/v/dynamo-release?logo=PyPI)](https://pypi.org/project/dynamo-release/) 
+[![download](https://static.pepy.tech/badge/dynamo-release)](https://pepy.tech/project/dynamo-release)
+[![star](https://img.shields.io/github/stars/aristoteleo/dynamo-release?logo=GitHub&color=red)](https://github.com/aristoteleo/dynamo-release/stargazers)
 ![build](https://github.com/aristoteleo/dynamo-release/actions/workflows/python-package.yml/badge.svg)
 ![test](https://github.com/aristoteleo/dynamo-release/actions/workflows/python-plain-run-test.yml/badge.svg)
 
-
 ## **Dynamo**: Mapping Transcriptomic Vector Fields of Single Cells
 
 Inclusive model of expression dynamics with metabolic labeling based scRNA-seq / multiomics, vector field reconstruction, potential landscape mapping, differential geometry analyses, and most probably paths / *in silico* perturbation predictions.

dynamo/configuration.py

@@ -36,6 +36,7 @@ class DynamoAdataKeyManager:
     # special key names frequently used in dynamo
     X_LAYER = "X"
     PROTEIN_LAYER = "protein"
+    X_PCA = "X_pca"
 
     def gen_new_layer_key(layer_name, key, sep="_") -> str:
         """utility function for returning a new key name for a specific layer. By convention layer_name should not have the separator as the last character."""
@@ -106,7 +107,7 @@ def check_if_layer_exist(adata: AnnData, layer: str) -> bool:
     def get_available_layer_keys(adata, layers="all", remove_pp_layers=True, include_protein=True):
         """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."""
         layer_keys = list(adata.layers.keys())
-        if layers is None: # layers=adata.uns["pp"]["experiment_layers"], in calc_sz_factor
+        if layers is None:  # layers=adata.uns["pp"]["experiment_layers"], in calc_sz_factor
             layers = "X"
         if remove_pp_layers:
             layer_keys = [i for i in layer_keys if not i.startswith("X_")]
@@ -143,10 +144,7 @@ def allowed_X_layer_names():
     def init_uns_pp_namespace(adata: AnnData):
         adata.uns[DynamoAdataKeyManager.UNS_PP_KEY] = {}
 
-    def get_excluded_layers(
-        X_total_layers: bool = False,
-        splicing_total_layers: bool = False
-    ) -> List:
+    def get_excluded_layers(X_total_layers: bool = False, splicing_total_layers: bool = False) -> List:
         """Get a list of excluded layers based on the provided arguments.
 
         When splicing_total_layers is False, the function normalize spliced and unspliced RNA separately using each
@@ -199,6 +197,7 @@ def aggregate_layers_into_total(
                 layers.extend(["_total_"])
         return total_layers, layers
 
+
 # TODO discuss alias naming convention
 DKM = DynamoAdataKeyManager
 

dynamo/dynamo_logger.py

@@ -152,19 +152,35 @@ def error(self, message, indent_level=1, *args, **kwargs):
         message = format_logging_message(message, logging.ERROR, indent_level=indent_level)
         return self.logger.error(message, *args, **kwargs)
 
-    def info_insert_adata(self, key, adata_attr="obsm", indent_level=1, *args, **kwargs):
+    def info_insert_adata(self, key, adata_attr="obsm", log_level=logging.NOTSET, indent_level=1, *args, **kwargs):
         message = "<insert> %s to %s in AnnData Object." % (key, adata_attr)
-        message = format_logging_message(message, logging.DEBUG, indent_level=indent_level)
-        return self.logger.debug(message, *args, **kwargs)
+        if log_level == logging.NOTSET or log_level == logging.DEBUG:
+            self.debug(message, indent_level=indent_level, *args, **kwargs)
+        elif log_level == logging.INFO:
+            self.info(message, indent_level=indent_level, *args, **kwargs)
+        elif log_level == logging.WARN:
+            self.warning(message, indent_level=indent_level, *args, **kwargs)
+        elif log_level == logging.ERROR:
+            self.error(message, indent_level=indent_level, *args, **kwargs)
+        elif log_level == logging.CRITICAL:
+            self.critical(message, indent_level=indent_level, *args, **kwargs)
+        else:
+            raise NotImplementedError
 
-    def info_insert_adata_var(self, key, indent_level=1, *args, **kwargs):
-        return self.info_insert_adata(self, key, adata_attr="var", indent_level=1, *args, **kwargs)
+    def info_insert_adata_var(self, key, log_level, indent_level, *args, **kwargs):
+        return self.info_insert_adata(
+            self, key, adata_attr="var", log_level=log_level, indent_level=indent_level, *args, **kwargs
+        )
 
-    def info_insert_adata_obsm(self, key, indent_level=1, *args, **kwargs):
-        return self.info_insert_adata(self, key, adata_attr="obsm", indent_level=1, *args, **kwargs)
+    def info_insert_adata_obsm(self, key, log_level, indent_level, *args, **kwargs):
+        return self.info_insert_adata(
+            self, key, adata_attr="obsm", log_level=log_level, indent_level=indent_level, *args, **kwargs
+        )
 
-    def info_insert_adata_uns(self, key, indent_level=1, *args, **kwargs):
-        return self.info_insert_adata(self, key, adata_attr="uns", indent_level=1, *args, **kwargs)
+    def info_insert_adata_uns(self, key, log_level, indent_level, *args, **kwargs):
+        return self.info_insert_adata(
+            self, key, adata_attr="uns", log_level=log_level, indent_level=indent_level, *args, **kwargs
+        )
 
     def log_time(self):
         now = time.time()

dynamo/external/gseapy.py

@@ -70,7 +70,6 @@ def enrichr(
         gene_sets=gene_sets,  # GO_Biological_Process_2018
         organism=organism,  # don't forget to set organism to the one you desired! e.g. Yeast
         background=background,
-        description=description,
         outdir=outdir,
         no_plot=no_plot,
         cutoff=cutoff,  # test dataset, use lower value from range(0,1)

dynamo/external/scifate.py

@@ -169,7 +169,7 @@ def adata_processing_TF_link(
     total = adata.layers[nt_layers[1]]
 
     # recalculate size factor
-    from ..preprocessing import calc_sz_factor_legacy
+    from ..preprocessing.deprecated import calc_sz_factor_legacy
 
     adata = calc_sz_factor_legacy(
         adata,

dynamo/external/scribe.py

@@ -151,7 +151,7 @@ def scribe(
 
     if normalize:
         # recalculate size factor
-        from ..preprocessing import calc_sz_factor_legacy
+        from ..preprocessing.deprecated import calc_sz_factor_legacy
 
         adata = calc_sz_factor_legacy(
             adata,

dynamo/plot/connectivity.py

@@ -331,8 +331,6 @@ def connectivity_base(
         plt.show()
     if save_show_or_return in ["return", "all"]:
         return ax
-    else:
-        raise NotImplementedError("Unsupported save_show_or_return")
 
 
 docstrings.delete_params("con_base.parameters", "edge_df", "save_show_or_return", "save_kwargs")

dynamo/plot/dynamics.py

@@ -1089,8 +1089,6 @@ def phase_portraits(
         plt.show()
     if save_show_or_return in ["return", "all"]:
         return g
-    else:
-        raise NotImplementedError("Unsupported save_show_or_return")
 
 
 def dynamics(

dynamo/plot/networks.py

@@ -367,6 +367,7 @@ def circosPlot(
     """
     try:
         import nxviz as nv
+        from nxviz import annotate
     except ImportError:
         raise ImportError("install nxviz via `pip install nxviz`.")
 
@@ -382,9 +383,9 @@ def circosPlot(
         },
     )
 
-    nv.annotate.circos_labels(network, group_by=node_label_key, layout=circos_label_layout)
+    annotate.circos_labels(network, group_by=node_label_key, layout=circos_label_layout)
     if node_color_key and show_colorbar:
-        nv.annotate.node_colormapping(
+        annotate.node_colormapping(
             network,
             color_by=node_color_key,
             legend_kwargs={"loc": "upper right", "bbox_to_anchor": (0.0, 1.0)},

dynamo/plot/preprocess.py

@@ -16,7 +16,7 @@
 
 from ..configuration import DynamoAdataKeyManager
 from ..dynamo_logger import main_warning
-from ..preprocessing import preprocess as pp
+from ..preprocessing import gene_selection
 from ..preprocessing.gene_selection import get_prediction_by_svr
 from ..preprocessing.utils import detect_experiment_datatype
 from ..tools.utils import get_mapper, update_dict
@@ -49,8 +49,10 @@ def basic_stats(
         (seaborn.FacetGrid) would be returned.
     """
 
+    import matplotlib.pyplot as plt
+
     if len(adata.obs.columns.intersection(["nGenes", "nCounts", "pMito"])) != 3:
-        from ..preprocessing.utils import basic_stats
+        from ..preprocessing.QC import basic_stats
 
         basic_stats(adata)
 
@@ -118,7 +120,6 @@ def basic_stats(
             s_kwargs["close"] = False
         save_fig(**s_kwargs)
     if save_show_or_return in ["show", "both", "all"]:
-        import matplotlib.pyplot as plt
         plt.tight_layout()
         plt.show()
     if save_show_or_return in ["return", "all"]:
@@ -435,7 +436,6 @@ def biplot(
     figsize: Tuple[float, float] = (6, 4),
     scale_pca_embedding: bool = False,
     draw_pca_embedding: bool = False,
-
     save_show_or_return: Literal["save", "show", "return"] = "show",
     save_kwargs: Dict[str, Any] = {},
     ax: Optional[Axes] = None,
@@ -992,7 +992,7 @@ def highest_frac_genes(
     if log:
         ax.set_xscale("log")
 
-    adata = pp.highest_frac_genes(
+    adata = gene_selection.highest_frac_genes(
         adata,
         store_key=store_key,
         n_top=n_top,

dynamo/prediction/fate.py

@@ -9,6 +9,7 @@
 from sklearn.neighbors import NearestNeighbors
 from tqdm import tqdm
 
+from ..configuration import DKM
 from ..dynamo_logger import (
     LoggerManager,
     main_info,
@@ -173,7 +174,7 @@ def fate(
         ndim = adata.uns["umap_fit"]["fit"]._raw_data.shape[1]
 
         if "X" in adata.obsm_keys():
-            if ndim == adata.obsm["X"].shape[1]:  # lift the dimension up again
+            if ndim == adata.obsm[DKM.X_PCA].shape[1]:  # lift the dimension up again
                 exprs = adata.uns["pca_fit"].inverse_transform(prediction)
 
         if adata.var.use_for_dynamics.sum() == exprs.shape[1]:
@@ -211,7 +212,7 @@ def _fate(
     interpolation_num: int = 250,
     average: bool = True,
     sampling: str = "arc_length",
-    cores:int = 1,
+    cores: int = 1,
 ) -> Tuple[np.ndarray, np.ndarray]:
     """Predict the historical and future cell transcriptomic states over arbitrary time scales by integrating vector
     field functions from one or a set of initial cell state(s).

dynamo/preprocessing/Preprocessor.py

@@ -16,30 +16,26 @@
     main_info_insert_adata,
     main_warning,
 )
+from ..tools.connectivity import neighbors as default_neighbors
+from ..tools.utils import update_dict
+from .cell_cycle import cell_cycle_scores
 from .external import (
     normalize_layers_pearson_residuals,
     sctransform,
     select_genes_by_pearson_residuals,
 )
-from ..tools.connectivity import neighbors as default_neighbors
-from ..tools.utils import update_dict
-from .cell_cycle import cell_cycle_scores
 from .gene_selection import select_genes_by_seurat_recipe, select_genes_monocle
-from .preprocess import normalize_cell_expr_by_size_factors_legacy, pca
-from .preprocessor_utils import (
-    Freeman_Tukey,
-    _infer_labeling_experiment_type,
-    calc_sz_factor,
-)
-from .preprocessor_utils import (
+from .normalization import calc_sz_factor, normalize
+from .pca import pca
+from .QC import (
+    basic_stats,
     filter_cells_by_outliers as monocle_filter_cells_by_outliers,
-)
-from .preprocessor_utils import (
     filter_genes_by_outliers as monocle_filter_genes_by_outliers,
+    regress_out_parallel,
 )
-from .preprocessor_utils import log, log1p, log2, normalize, regress_out_parallel
+from .transform import Freeman_Tukey, log, log1p, log2
 from .utils import (
-    basic_stats,
+    _infer_labeling_experiment_type,
     collapse_species_adata,
     convert2symbol,
     convert_layers2csr,
@@ -128,7 +124,6 @@ def __init__(
         self.regress_out = regress_out_parallel
         self.pca = pca_function
         self.pca_kwargs = pca_kwargs
-        self.cell_cycle_score = cell_cycle_scores
 
         # self.n_top_genes = n_top_genes
         self.convert_gene_name = convert_gene_name_function
@@ -493,6 +488,7 @@ def config_monocle_recipe(self, adata: AnnData, n_top_genes: int = 2000) -> None
         self.pca = pca
         self.pca_kwargs = {"pca_key": "X_pca"}
 
+        self.cell_cycle_score = None  # optional: cell_cycle_scores
         self.cell_cycle_score_kwargs = {
             "layer": None,
             "gene_list": None,