pertpy 0.7.0__py3-none-any.whl → 0.9.1__py3-none-any.whl

pertpy/tools/_coda/_base_coda.py

@@ -15,6 +15,7 @@ import seaborn as sns
 from adjustText import adjust_text
 from anndata import AnnData
 from jax import config, random
+from lamin_utils import logger
 from matplotlib import cm, rcParams
 from matplotlib import image as mpimg
 from matplotlib.colors import ListedColormap
@@ -110,9 +111,9 @@ class CompositionalModel2(ABC):
                 Categorical covariates are handled automatically, with the covariate value of the first sample being used as the reference category.
                 To set a different level as the base category for a categorical covariate, use "C(<CovariateName>, Treatment('<ReferenceLevelName>'))"
             reference_cell_type: Column name that sets the reference cell type.
-                Reference the name of a column. If "automatic", the cell type with the lowest dispersion in relative abundance that is present in at least 90% of samlpes will be chosen. Defaults to "automatic".
+                Reference the name of a column. If "automatic", the cell type with the lowest dispersion in relative abundance that is present in at least 90% of samlpes will be chosen.
             automatic_reference_absence_threshold: If using reference_cell_type = "automatic", determine the maximum fraction of zero entries for a cell type
-                to be considered as a possible reference cell type. Defaults to 0.05.
+                to be considered as a possible reference cell type.
 
         Returns:
             AnnData object that is ready for CODA models.
@@ -148,7 +149,7 @@ class CompositionalModel2(ABC):
             ref_index = np.where(cell_type_disp == min_var)[0][0]
 
             ref_cell_type = cell_types[ref_index]
-            print(f"[bold blue]Automatic reference selection! Reference cell type set to {ref_cell_type}")
+            logger.info(f"Automatic reference selection! Reference cell type set to {ref_cell_type}")
 
         # Column name as reference cell type
         elif reference_cell_type in cell_types:
@@ -160,7 +161,7 @@ class CompositionalModel2(ABC):
 
         # Add pseudocount if zeroes are present.
         if np.count_nonzero(sample_adata.X) != np.size(sample_adata.X):
-            print("Zero counts encountered in data! Added a pseudocount of 0.5.")
+            logger.info("Zero counts encountered in data! Added a pseudocount of 0.5.")
             sample_adata.X[sample_adata.X == 0] = 0.5
 
         sample_adata.obsm["sample_counts"] = np.sum(sample_adata.X, axis=1)
@@ -201,7 +202,7 @@ class CompositionalModel2(ABC):
             sample_adata: anndata object with cell counts as sample_adata.X and covariates saved in sample_adata.obs.
             kernel: A `numpyro.infer.mcmc.MCMCKernel` object
             rng_key: The rng state used. If None, a random state will be selected
-            copy: Return a copy instead of writing to adata. Defaults to False.
+            copy: Return a copy instead of writing to adata.
             args: Passed to `numpyro.infer.mcmc.MCMC`
             kwargs: Passed to `numpyro.infer.mcmc.MCMC`
 
@@ -237,13 +238,13 @@ class CompositionalModel2(ABC):
 
         acc_rate = np.array(self.mcmc.last_state.mean_accept_prob)
         if acc_rate < 0.6:
-            print(
-                f"[bold red]Acceptance rate unusually low ({acc_rate} < 0.5)! Results might be incorrect! "
+            logger.warning(
+                f"Acceptance rate unusually low ({acc_rate} < 0.5)! Results might be incorrect! "
                 f"Please check feasibility of results and re-run the sampling step with a different rng_key if necessary."
             )
         if acc_rate > 0.95:
-            print(
-                f"[bold red]Acceptance rate unusually high ({acc_rate} > 0.95)! Results might be incorrect! "
+            logger.warning(
+                f"Acceptance rate unusually high ({acc_rate} > 0.95)! Results might be incorrect! "
                 f"Please check feasibility of results and re-run the sampling step with a different rng_key if necessary."
             )
 
@@ -286,11 +287,11 @@ class CompositionalModel2(ABC):
 
         Args:
             data: AnnData object or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
-            num_samples: Number of sampled values after burn-in. Defaults to 10000.
-            num_warmup: Number of burn-in (warmup) samples. Defaults to 1000.
-            rng_key: The rng state used. Defaults to 0.
-            copy: Return a copy instead of writing to adata. Defaults to False.
+            modality_key: If data is a MuData object, specify which modality to use.
+            num_samples: Number of sampled values after burn-in.
+            num_warmup: Number of burn-in (warmup) samples.
+            rng_key: The rng state used.
+            copy: Return a copy instead of writing to adata.
 
         Returns:
             Calls `self.__run_mcmc`
@@ -299,7 +300,7 @@ class CompositionalModel2(ABC):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data
@@ -339,11 +340,11 @@ class CompositionalModel2(ABC):
 
         Args:
             data: AnnData object or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
-            num_samples: Number of sampled values after burn-in. Defaults to 20000.
-            num_warmup: Number of burn-in (warmup) samples. Defaults to 5000.
-            rng_key: The rng state used. If None, a random state will be selected. Defaults to None.
-            copy: Return a copy instead of writing to adata. Defaults to False.
+            modality_key: If data is a MuData object, specify which modality to use.
+            num_samples: Number of sampled values after burn-in.
+            num_warmup: Number of burn-in (warmup) samples.
+            rng_key: The rng state used. If None, a random state will be selected.
+            copy: Return a copy instead of writing to adata.
 
         Examples:
             >>> import pertpy as pt
@@ -358,7 +359,7 @@ class CompositionalModel2(ABC):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data
@@ -397,7 +398,7 @@ class CompositionalModel2(ABC):
 
         Args:
             sample_adata: Anndata object with cell counts as sample_adata.X and covariates saved in sample_adata.obs.
-            est_fdr: Desired FDR value. Defaults to 0.05.
+            est_fdr: Desired FDR value.
             args: Passed to ``az.summary``
             kwargs: Passed to ``az.summary``
 
@@ -637,8 +638,8 @@ class CompositionalModel2(ABC):
             effect_df: Effect summary, see ``summary_prepare``
             model_type: String indicating the model type ("classic" or "tree_agg")
             select_type:  String indicating the type of spike_and_slab selection ("spikeslab" or "sslasso")
-            target_fdr: Desired FDR value. Defaults to 0.05.
-            node_df: If using tree aggregation, the node-level effect DataFrame must be passed. Defaults to None.
+            target_fdr: Desired FDR value.
+            node_df: If using tree aggregation, the node-level effect DataFrame must be passed.
 
         Returns:
             pd.DataFrame:  effect DataFrame with inclusion probability, final parameters, expected sample.
@@ -790,8 +791,8 @@ class CompositionalModel2(ABC):
 
         Args:
             data: AnnData object or MuData object.
-            extended: If True, return the extended summary with additional statistics. Defaults to False.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
+            extended: If True, return the extended summary with additional statistics.
+            modality_key: If data is a MuData object, specify which modality to use.
             args: Passed to az.summary
             kwargs: Passed to az.summary
 
@@ -809,7 +810,7 @@ class CompositionalModel2(ABC):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("[bold red]When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data
@@ -848,10 +849,10 @@ class CompositionalModel2(ABC):
         table.add_column("Name", justify="left", style="cyan")
         table.add_column("Value", justify="left")
         table.add_row("Data", "Data: %d samples, %d cell types" % data_dims)
-        table.add_row("Reference cell type", "%s" % str(sample_adata.uns["scCODA_params"]["reference_cell_type"]))
-        table.add_row("Formula", "%s" % sample_adata.uns["scCODA_params"]["formula"])
+        table.add_row("Reference cell type", "{}".format(str(sample_adata.uns["scCODA_params"]["reference_cell_type"])))
+        table.add_row("Formula", "{}".format(sample_adata.uns["scCODA_params"]["formula"]))
         if extended:
-            table.add_row("Reference index", "%s" % str(sample_adata.uns["scCODA_params"]["reference_index"]))
+            table.add_row("Reference index", "{}".format(str(sample_adata.uns["scCODA_params"]["reference_index"])))
             if select_type == "spikeslab":
                 table.add_row(
                     "Spike-and-slab threshold",
@@ -934,7 +935,7 @@ class CompositionalModel2(ABC):
 
         Args:
             data: AnnData object or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
+            modality_key: If data is a MuData object, specify which modality to use.
 
         Returns:
             pd.DataFrame: Intercept data frame.
@@ -953,7 +954,7 @@ class CompositionalModel2(ABC):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data
@@ -965,7 +966,7 @@ class CompositionalModel2(ABC):
 
         Args:
             data: AnnData object or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
+            modality_key: If data is a MuData object, specify which modality to use.
 
         Returns:
             pd.DataFrame: Effect data frame.
@@ -984,7 +985,7 @@ class CompositionalModel2(ABC):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data
@@ -1007,7 +1008,7 @@ class CompositionalModel2(ABC):
 
         Args:
             data: AnnData object or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
+            modality_key: If data is a MuData object, specify which modality to use.
 
         Returns:
             pd.DataFrame: Node effect data frame.
@@ -1032,7 +1033,7 @@ class CompositionalModel2(ABC):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data
@@ -1046,7 +1047,7 @@ class CompositionalModel2(ABC):
         Args:
             data: AnnData object or MuData object.
             est_fdr: Desired FDR value.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
+            modality_key: If data is a MuData object, specify which modality to use.
             args: passed to self.summary_prepare
             kwargs: passed to self.summary_prepare
 
@@ -1057,7 +1058,7 @@ class CompositionalModel2(ABC):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data
@@ -1080,8 +1081,8 @@ class CompositionalModel2(ABC):
 
         Args:
             data: AnnData object or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
-            est_fdr: Estimated false discovery rate. Must be between 0 and 1. Defaults to None.
+            modality_key: If data is a MuData object, specify which modality to use.
+            est_fdr: Estimated false discovery rate. Must be between 0 and 1.
 
         Returns:
             pd.Series: Credible effect decision series which includes boolean values indicate whether effects are credible under inc_prob_threshold.
@@ -1090,7 +1091,7 @@ class CompositionalModel2(ABC):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data
@@ -1143,10 +1144,10 @@ class CompositionalModel2(ABC):
             type_names: The names of all cell types
             title: Plot title, usually the covariate's name
             level_names: Names of the covariate's levels
-            figsize: Figure size. Defaults to None.
-            dpi: Dpi setting. Defaults to 100.
-            palette: The color map for the barplot. Defaults to cm.tab20.
-            show_legend: If True, adds a legend. Defaults to True.
+            figsize: Figure size (matplotlib).
+            dpi: Resolution in DPI (matplotlib).
+            palette: The color map for the barplot.
+            show_legend: If True, adds a legend.
 
         Returns:
             A :class:`~matplotlib.axes.Axes` object
@@ -1205,12 +1206,12 @@ class CompositionalModel2(ABC):
         Args:
             data: AnnData object or MuData object.
             feature_name: The name of the covariate to plot. If feature_name=="samples", one bar for every sample will be plotted
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
-            figsize: Figure size. Defaults to None.
-            dpi: Dpi setting. Defaults to 100.
-            palette: The matplotlib color map for the barplot. Defaults to cm.tab20.
-            show_legend: If True, adds a legend. Defaults to True.
-            level_order: Custom ordering of bars on the x-axis. Defaults to None.
+            modality_key: If data is a MuData object, specify which modality to use.
+            figsize: Figure size.
+            dpi: Dpi setting.
+            palette: The matplotlib color map for the barplot.
+            show_legend: If True, adds a legend.
+            level_order: Custom ordering of bars on the x-axis.
 
         Returns:
             A :class:`~matplotlib.axes.Axes` object
@@ -1311,20 +1312,17 @@ class CompositionalModel2(ABC):
 
         Args:
             data: AnnData object or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
-            covariates: The name of the covariates in data.obs to plot. Defaults to None.
-            parameter: The parameter in effect summary to plot. Defaults to "log2-fold change".
+            modality_key: If data is a MuData object, specify which modality to use.
+            covariates: The name of the covariates in data.obs to plot.
+            parameter: The parameter in effect summary to plot.
             plot_facets: If False, plot cell types on the x-axis. If True, plot as facets.
-                         Defaults to True.
             plot_zero_covariate: If True, plot covariate that have all zero effects. If False, do not plot.
-                                 Defaults to True.
             plot_zero_cell_type: If True, plot cell type that have zero effect. If False, do not plot.
-                                 Defaults to False.
-            figsize: Figure size. Defaults to None.
-            dpi: Figure size. Defaults to 100.
-            palette: The seaborn color map for the barplot. Defaults to cm.tab20.
-            level_order: Custom ordering of bars on the x-axis. Defaults to None.
-            args_barplot: Arguments passed to sns.barplot. Defaults to None.
+            figsize: Figure size.
+            dpi: Figure size.
+            palette: The seaborn color map for the barplot.
+            level_order: Custom ordering of bars on the x-axis.
+            args_barplot: Arguments passed to sns.barplot.
 
         Returns:
             Depending on `plot_facets`, returns a :class:`~matplotlib.axes.Axes` (`plot_facets = False`)
@@ -1519,20 +1517,19 @@ class CompositionalModel2(ABC):
         Args:
             data: AnnData object or MuData object
             feature_name: The name of the feature in data.obs to plot
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
+            modality_key: If data is a MuData object, specify which modality to use.
             y_scale: Transformation to of cell counts. Options: "relative" - Relative abundance, "log" - log(count),
                      "log10" - log10(count), "count" - absolute abundance (cell counts).
-                     Defaults to "relative".
-            plot_facets: If False, plot cell types on the x-axis. If True, plot as facets. Defaults to False.
-            add_dots: If True, overlay a scatterplot with one dot for each data point. Defaults to False.
-            cell_types: Subset of cell types that should be plotted. Defaults to None.
-            args_boxplot: Arguments passed to sns.boxplot. Defaults to {}.
-            args_swarmplot: Arguments passed to sns.swarmplot. Defaults to {}.
-            figsize: Figure size. Defaults to None.
-            dpi: Dpi setting. Defaults to 100.
-            palette: The seaborn color map for the barplot. Defaults to "Blues".
-            show_legend: If True, adds a legend. Defaults to True.
-            level_order: Custom ordering of bars on the x-axis. Defaults to None.
+            plot_facets: If False, plot cell types on the x-axis. If True, plot as facets.
+            add_dots: If True, overlay a scatterplot with one dot for each data point.
+            cell_types: Subset of cell types that should be plotted.
+            args_boxplot: Arguments passed to sns.boxplot.
+            args_swarmplot: Arguments passed to sns.swarmplot.
+            figsize: Figure size.
+            dpi: Dpi setting.
+            palette: The seaborn color map for the barplot.
+            show_legend: If True, adds a legend.
+            level_order: Custom ordering of bars on the x-axis.
 
         Returns:
             Depending on `plot_facets`, returns a :class:`~matplotlib.axes.Axes` (`plot_facets = False`)
@@ -1758,16 +1755,14 @@ class CompositionalModel2(ABC):
 
         Args:
             data: AnnData or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
-                          Defaults to "coda".
-            abundant_threshold: Presence threshold for abundant cell types. Defaults to 0.9.
-            default_color: Bar color for all non-minimal cell types. Defaults to "Grey".
+            modality_key: If data is a MuData object, specify which modality to use.
+            abundant_threshold: Presence threshold for abundant cell types.
+            default_color: Bar color for all non-minimal cell types.
             abundant_color: Bar color for cell types with abundant percentage larger than abundant_threshold.
-                            Defaults to "Red".
-            label_cell_types: Label dots with cell type names. Defaults to True.
-            figsize: Figure size. Defaults to None.
-            dpi: Dpi setting. Defaults to 100.
-            ax: A matplotlib axes object. Only works if plotting a single component. Defaults to None.
+            label_cell_types: Label dots with cell type names.
+            figsize: Figure size.
+            dpi: Dpi setting.
+            ax: A matplotlib axes object. Only works if plotting a single component.
 
         Returns:
             A :class:`~matplotlib.axes.Axes` object
@@ -1882,22 +1877,16 @@ class CompositionalModel2(ABC):
         Args:
             data: AnnData object or MuData object.
             modality_key: If data is a MuData object, specify which modality to use.
-                          Defaults to "coda".
             tree: A ete3 tree object or a str to indicate the tree stored in `.uns`.
-                  Defaults to "tree".
             tight_text: When False, boundaries of the text are approximated according to general font metrics,
                         producing slightly worse aligned text faces but improving the performance of tree visualization in scenes with a lot of text faces.
-                        Default to False.
             show_scale: Include the scale legend in the tree image or not.
-                        Defaults to False.
             show: If True, plot the tree inline. If false, return tree and tree_style objects.
-                  Defaults to True.
             file_name: Path to the output image file. Valid extensions are .SVG, .PDF, .PNG.
                        Output image can be saved whether show is True or not.
-                       Defaults to None.
-            units: Unit of image sizes. “px”: pixels, “mm”: millimeters, “in”: inches. Defaults to "px".
-            figsize: Figure size. Defaults to None.
-            dpi: Dots per inches. Defaults to 100.
+            units: Unit of image sizes. “px”: pixels, “mm”: millimeters, “in”: inches.
+            figsize: Figure size.
+            dpi: Dots per inches.
 
         Returns:
             Depending on `show`, returns :class:`ete3.TreeNode` and :class:`ete3.TreeStyle` (`show = False`) or plot the tree inline (`show = False`)
@@ -1972,23 +1961,18 @@ class CompositionalModel2(ABC):
             data: AnnData object or MuData object.
             covariate: The covariate, whose effects should be plotted.
             modality_key: If data is a MuData object, specify which modality to use.
-                          Defaults to "coda".
             tree: A ete3 tree object or a str to indicate the tree stored in `.uns`.
-                  Defaults to "tree".
             show_legend: If show legend of nodes significant effects or not.
                          Defaults to False if show_leaf_effects is True.
             show_leaf_effects: If True, plot bar plots which indicate leave-level significant effects.
-                               Defaults to False.
             tight_text: When False, boundaries of the text are approximated according to general font metrics,
                         producing slightly worse aligned text faces but improving the performance of tree visualization in scenes with a lot of text faces.
-                        Defaults to False.
-            show_scale: Include the scale legend in the tree image or not. Defaults to False.
-            show: If True, plot the tree inline. If false, return tree and tree_style objects. Defaults to True.
+            show_scale: Include the scale legend in the tree image or not.
+            show: If True, plot the tree inline. If false, return tree and tree_style objects.
             file_name: Path to the output image file. valid extensions are .SVG, .PDF, .PNG. Output image can be saved whether show is True or not.
-                       Defaults to None.
-            units: Unit of image sizes. “px”: pixels, “mm”: millimeters, “in”: inches. Defaults to "px".
-            figsize: Figure size. Defaults to None.
-            dpi: Dots per inches. Defaults to 100.
+            units: Unit of image sizes. “px”: pixels, “mm”: millimeters, “in”: inches.
+            figsize: Figure size.
+            dpi: Dots per inches.
 
         Returns:
             Depending on `show`, returns :class:`ete3.TreeNode` and :class:`ete3.TreeStyle` (`show = False`)
@@ -2026,7 +2010,7 @@ class CompositionalModel2(ABC):
         if show_legend is None:
             show_legend = not show_leaf_effects
         elif show_legend:
-            print("Tree leaves and leaf effect bars won't be aligned when legend is shown!")
+            logger.info("Tree leaves and leaf effect bars won't be aligned when legend is shown!")
 
         if isinstance(tree, str):
             tree = data.uns[tree]
@@ -2171,12 +2155,10 @@ class CompositionalModel2(ABC):
             effect_name: The name of the effect results in .varm of aggregated sample-level AnnData to plot
             cluster_key: The cluster information in .obs of cell-level AnnData (default is data['rna']).
                          To assign cell types' effects to original cells.
-            modality_key_1: Key to the cell-level AnnData in the MuData object. Defaults to "rna".
+            modality_key_1: Key to the cell-level AnnData in the MuData object.
             modality_key_2: Key to the aggregated sample-level AnnData object in the MuData object.
-                            Defaults to "coda".
-            show: Whether to display the figure or return axis. Defaults to None.
+            show: Whether to display the figure or return axis.
             ax: A matplotlib axes object. Only works if plotting a single component.
-                Defaults to None.
             **kwargs: All other keyword arguments are passed to `scanpy.plot.umap()`
 
         Returns:
@@ -2254,7 +2236,7 @@ class CompositionalModel2(ABC):
 
 
 def get_a(
-    tree: tt.tree,
+    tree: tt.core.ToyTree,
 ) -> tuple[np.ndarray, int]:
     """Calculate ancestor matrix from a toytree tree
 
@@ -2293,7 +2275,7 @@ def get_a(
     return A, n_nodes - 1
 
 
-def collapse_singularities(tree: tt.tree) -> tt.tree:
+def collapse_singularities(tree: tt.core.ToyTree) -> tt.core.ToyTree:
     """Collapses (deletes) nodes in a toytree tree that are singularities (have only one child).
 
     Args:
@@ -2509,15 +2491,14 @@ def import_tree(
 
     Args:
         data: A tascCODA-compatible data object.
-        modality_1: If `data` is MuData, specify the modality name to the original cell level anndata object. Defaults to None.
-        modality_2: If `data` is MuData, specify the modality name to the aggregated level anndata object. Defaults to None.
-        dendrogram_key: Key to the scanpy.tl.dendrogram result in `.uns` of original cell level anndata object. Defaults to None.
-        levels_orig: List that indicates which columns in `.obs` of the original data correspond to tree levels. The list must begin with the root level, and end with the leaf level. Defaults to None.
-        levels_agg: List that indicates which columns in `.var` of the aggregated data correspond to tree levels. The list must begin with the root level, and end with the leaf level. Defaults to None.
+        modality_1: If `data` is MuData, specify the modality name to the original cell level anndata object.
+        modality_2: If `data` is MuData, specify the modality name to the aggregated level anndata object.
+        dendrogram_key: Key to the scanpy.tl.dendrogram result in `.uns` of original cell level anndata object.
+        levels_orig: List that indicates which columns in `.obs` of the original data correspond to tree levels. The list must begin with the root level, and end with the leaf level.
+        levels_agg: List that indicates which columns in `.var` of the aggregated data correspond to tree levels. The list must begin with the root level, and end with the leaf level.
         add_level_name: If True, internal nodes in the tree will be named as "{level_name}_{node_name}" instead of just {level_name}.
-                        Defaults to True.
         key_added: If not specified, the tree is stored in .uns[‘tree’]. If `data` is AnnData, save tree in `data`.
-                   If `data` is MuData, save tree in data[modality_2]. Defaults to "tree".
+                   If `data` is MuData, save tree in data[modality_2].
 
     Returns:
         Updates data with the following:
@@ -2538,10 +2519,10 @@ def import_tree(
             data_1 = data[modality_1]
             data_2 = data[modality_2]
         except KeyError as name:
-            print(f"No {name} slot in MuData")
+            logger.error(f"No {name} slot in MuData")
             raise
         except IndexError:
-            print("Please specify modality_1 and modality_2 to indicate modalities in MuData")
+            logger.error("Please specify modality_1 and modality_2 to indicate modalities in MuData")
             raise
     else:
         data_1 = data
@@ -2613,43 +2594,38 @@ def from_scanpy(
     Returns:
         AnnData: A data set with cells aggregated to the (sample x cell type) level
     """
-    if isinstance(sample_identifier, str):
-        sample_identifier = [sample_identifier]
+    sample_identifier = [sample_identifier] if isinstance(sample_identifier, str) else sample_identifier
+    covariate_obs = list(set(covariate_obs or []) | set(sample_identifier))
 
-    if len(sample_identifier) > 1:
+    if isinstance(sample_identifier, list):
         adata.obs["scCODA_sample_id"] = adata.obs[sample_identifier].agg("-".join, axis=1)
         sample_identifier = "scCODA_sample_id"
-    else:
-        sample_identifier = sample_identifier[0]
 
-    # get cell type counts
-    ct_count_data = pd.crosstab(adata.obs[sample_identifier], adata.obs[cell_type_identifier])
-    ct_count_data = ct_count_data.fillna(0)
-
-    # get covariates from different sources
+    groups = adata.obs.value_counts([sample_identifier, cell_type_identifier])
+    ct_count_data = groups.unstack(level=cell_type_identifier).fillna(0)
     covariate_df_ = pd.DataFrame(index=ct_count_data.index)
 
     if covariate_uns is not None:
         covariate_df_uns = pd.DataFrame(adata.uns[covariate_uns], index=ct_count_data.index)
-        covariate_df_ = covariate_df_.join(covariate_df_uns, how="left")
+        covariate_df_ = pd.concat([covariate_df_, covariate_df_uns], axis=1)
 
     if covariate_obs:
-        is_unique = adata.obs.groupby(sample_identifier, observed=True).transform(lambda x: x.nunique() == 1)
-        unique_covariates = is_unique.columns[is_unique.all()].tolist()
-
-        if len(unique_covariates) < len(covariate_obs):
-            skipped = set(covariate_obs) - set(unique_covariates)
-            print(f"[bold yellow]Covariates {skipped} have non-unique values! Skipping...")
-        if unique_covariates:
-            covariate_df_obs = adata.obs.groupby(sample_identifier, observed=True).first()[unique_covariates]
-            covariate_df_ = covariate_df_.join(covariate_df_obs, how="left")
+        unique_check = adata.obs.groupby(sample_identifier).nunique()
+        for c in covariate_obs.copy():
+            if unique_check[c].max() != 1:
+                logger.warning(f"Covariate {c} has non-unique values for batch! Skipping...")
+                covariate_obs.remove(c)
+        if covariate_obs:
+            covariate_df_obs = adata.obs.groupby(sample_identifier).first()[covariate_obs]
+            covariate_df_ = pd.concat([covariate_df_, covariate_df_obs], axis=1)
 
     if covariate_df is not None:
-        if not covariate_df.index.equals(ct_count_data.index):
-            raise ValueError("AnnData sample names and covariate_df index do not have the same elements!")
-        covariate_df_ = covariate_df_.join(covariate_df, how="left")
+        if set(covariate_df.index) != set(ct_count_data.index):
+            raise ValueError("Mismatch between sample names in anndata and covariate_df!")
+        covariate_df_ = pd.concat([covariate_df_, covariate_df.reindex(ct_count_data.index)], axis=1)
 
-    var_dat = ct_count_data.sum(axis=0).rename("n_cells").to_frame()
+    var_dat = ct_count_data.sum().rename("n_cells").to_frame()
     var_dat.index = var_dat.index.astype(str)
+    covariate_df_.index = covariate_df_.index.astype(str)
 
     return AnnData(X=ct_count_data.values, var=var_dat, obs=covariate_df_)

pertpy/tools/_coda/_sccoda.py

@@ -9,6 +9,7 @@ import numpyro as npy
 import numpyro.distributions as npd
 from anndata import AnnData
 from jax import config, random
+from lamin_utils import logger
 from mudata import MuData
 from numpyro.infer import Predictive
 from rich import print
@@ -73,13 +74,13 @@ class Sccoda(CompositionalModel2):
             adata: AnnData object.
             type : Specify the input adata type, which could be either a cell-level AnnData or an aggregated sample-level AnnData.
             generate_sample_level: Whether to generate an AnnData object on the sample level or create an empty AnnData object.
-            cell_type_identifier: If type is "cell_level", specify column name in adata.obs that specifies the cell types. Defaults to None.
-            sample_identifier: If type is "cell_level", specify column name in adata.obs that specifies the sample. Defaults to None.
-            covariate_uns: If type is "cell_level", specify key for adata.uns, where covariate values are stored. Defaults to None.
-            covariate_obs: If type is "cell_level", specify list of keys for adata.obs, where covariate values are stored. Defaults to None.
-            covariate_df: If type is "cell_level", specify dataFrame with covariates. Defaults to None.
-            modality_key_1: Key to the cell-level AnnData in the MuData object. Defaults to "rna".
-            modality_key_2: Key to the aggregated sample-level AnnData object in the MuData object. Defaults to "coda".
+            cell_type_identifier: If type is "cell_level", specify column name in adata.obs that specifies the cell types.
+            sample_identifier: If type is "cell_level", specify column name in adata.obs that specifies the sample.
+            covariate_uns: If type is "cell_level", specify key for adata.uns, where covariate values are stored.
+            covariate_obs: If type is "cell_level", specify list of keys for adata.obs, where covariate values are stored.
+            covariate_df: If type is "cell_level", specify dataFrame with covariates.
+            modality_key_1: Key to the cell-level AnnData in the MuData object.
+            modality_key_2: Key to the aggregated sample-level AnnData object in the MuData object.
 
         Returns:
             MuData: MuData object with cell-level AnnData (`mudata[modality_key_1]`) and aggregated sample-level AnnData (`mudata[modality_key_2]`).
@@ -127,10 +128,10 @@ class Sccoda(CompositionalModel2):
                 Categorical covariates are handled automatically, with the covariate value of the first sample being used as the reference category.
                 To set a different level as the base category for a categorical covariate, use "C(<CovariateName>, Treatment('<ReferenceLevelName>'))"
             reference_cell_type: Column name that sets the reference cell type.
-                Reference the name of a column. If "automatic", the cell type with the lowest dispersion in relative abundance that is present in at least 90% of samlpes will be chosen. Defaults to "automatic".
+                Reference the name of a column. If "automatic", the cell type with the lowest dispersion in relative abundance that is present in at least 90% of samlpes will be chosen.
             automatic_reference_absence_threshold: If using reference_cell_type = "automatic", determine the maximum fraction of zero entries for a cell type
-                to be considered as a possible reference cell type. Defaults to 0.05.
-            modality_key: If data is a MuData object, specify key to the aggregated sample-level AnnData object in the MuData object. Defaults to "coda".
+                to be considered as a possible reference cell type.
+            modality_key: If data is a MuData object, specify key to the aggregated sample-level AnnData object in the MuData object.
 
         Returns:
             Return an AnnData (if input data is an AnnData object) or return a MuData (if input data is a MuData object)
@@ -309,10 +310,10 @@ class Sccoda(CompositionalModel2):
 
         Args:
             data: AnnData object or MuData object.
-            modality_key: If data is a MuData object, specify which modality to use. Defaults to "coda".
-            rng_key: The rng state used for the prior simulation. If None, a random state will be selected. Defaults to None.
-            num_prior_samples: Number of prior samples calculated. Defaults to 500.
-            use_posterior_predictive: If True, the posterior predictive will be calculated. Defaults to True.
+            modality_key: If data is a MuData object, specify which modality to use.
+            rng_key: The rng state used for the prior simulation. If None, a random state will be selected.
+            num_prior_samples: Number of prior samples calculated.
+            use_posterior_predictive: If True, the posterior predictive will be calculated.
 
         Returns:
             az.InferenceData: arviz_data with all MCMC information
@@ -335,7 +336,7 @@ class Sccoda(CompositionalModel2):
             try:
                 sample_adata = data[modality_key]
             except IndexError:
-                print("When data is a MuData object, modality_key must be specified!")
+                logger.error("When data is a MuData object, modality_key must be specified!")
                 raise
         if isinstance(data, AnnData):
             sample_adata = data