Merge pull request #13 from theislab/sergio_dev

sphinx_errors_corrected

Author: sergiomarco25

README.md

@@ -8,7 +8,7 @@
 
 Package for the analysis of transcripts outside segmented cells in python
 
-![Alt text][images/logo_fish.png]
+![alt text](images/logo_fish.png)
 
 ## Getting started
 

docs/api.md

@@ -9,9 +9,15 @@
 .. autosummary::
     :toctree: generated
 
+    pp.create_grid_squares
+    pp.aggregate_extracellular_transcripts
     pp.compute_extracellular_counts
     pp.define_extracellular
-    pp.compute_crosstab
+    pp.filter_xrna
+    pp.process_dataframe
+    pp.segmentation_free_sainsc
+    pp.xenium_converter
+    pp.cosmx_converter
     pp.format_adata
 ```
 
@@ -24,24 +30,27 @@
 .. autosummary::
     :toctree: generated
 
-    tl.compute_source_cells
-    tl.distance_to_source_cell
-    tl.compute_distant_cells_prop
-    tl.get_proportion_expressed_per_cell_type
-    tl.calculate_target_cells
-    tl.define_target_by_celltype
     tl.colocalization_proportion
+    tl.latent_factor
+    tl.apply_exrna_factors_to_cells
+    tl.image_intensities_per_transcript
+    tl.get_gene_interaction_strength
+    tl.compute_communication_strength
+    tl.gene_specific_interactions
     tl.spatial_variability
     tl.create_xrna_metadata
     tl.quantify_overexpression
     tl.extracellular_enrichment
     tl.spatial_colocalization
-    tl.get_number_of_communication_genes
-    tl.get_gene_interaction_strength
-    tl.apply_nmf_to_adata
-    tl.nmf
-    tl.apply_exrna_factors_to_cells
+    tl.in_out_correlation
+    tl.assess_diffussion
+    tl.cluster_distribution_from_source
+    tl.compute_js_divergence
+    tl.compare_intra_extra_distribution
     tl.segmentation_free_clustering
+    tl.get_proportion_expressed_per_cell_type
+    tl.compute_source_score
+    tl.compute_target_score
 ```
 
 ## Plotting
@@ -53,18 +62,35 @@
 .. autosummary::
     :toctree: generated
 
+    pl.pie
+    pl.crosstab
+    pl.histogram
+    pl.get_palette
+    pl.get_colormap
+    pl.celltype_communication
+    pl.gene_communication
+    pl.target_score_by_celltype
+    pl.rank_factor_genes_loadings
+    pl.rank_factor_genes_loadings_matrixplot
+    pl.factors_in_cells
+    pl.top_bottom_probes_of_metric
+    pl.metric_scatter
+    pl.logfoldratio_over_noise
+    pl.gene_metric_heatmap
     pl.sorted_heatmap
     pl.coupled_scatter
     pl.heatmap
-    pl.plot_crosstab
-    pl.pie_of_positive
     pl.genes_over_noise
     pl.moranI_histogram
-    pl.proportion_above_threshold
-    pl.nmf_factors_exrna_cells_W
-    pl.nmf_gene_contributions
-    pl.apply_exrnaH_to_cellular_to_create_cellularW
-    pl.paired_nmf_factors
     pl.spatial_interactions
     pl.interactions_with_arrows
+    pl.intra_extra_density
+    pl.spatial_inout_expression
+    pl.diffusion_results
+    pl.spatial_transcripts
+    pl.global_distribution_from_source
+    pl.distributions_by_cluster
+    pl.gene_distribution_from_source
+    pl.source_score_by_celltype
+
 ```

docs/conf.py

@@ -9,10 +9,11 @@
 from datetime import datetime
 from importlib.metadata import metadata
 from pathlib import Path
+import os
 
 HERE = Path(__file__).parent
 sys.path.insert(0, str(HERE / "extensions"))
-
+sys.path.insert(0, os.path.abspath("../src"))
 
 # -- Project information -----------------------------------------------------
 
@@ -91,13 +92,19 @@
     ".myst": "myst-nb",
 }
 
+autodoc_mock_imports = [
+    "mpl_chord_diagram",
+    # add others here if they’re missing
+]
+
 intersphinx_mapping = {
     "python": ("https://docs.python.org/3", None),
     "anndata": ("https://anndata.readthedocs.io/en/stable/", None),
     "scanpy": ("https://scanpy.readthedocs.io/en/stable/", None),
     "numpy": ("https://numpy.org/doc/stable/", None),
     "pandas": ("https://pandas.pydata.org/pandas-docs/stable/", None),
     "spatialdata": ("https://spatialdata.scverse.org/en/stable/", None),
+    "matplotlib": ("https://matplotlib.org/stable/", None),
 }
 
 # List of patterns, relative to source directory, that match files and

docs/images/logo_fish.png

@@ -105,33 +105,33 @@ def crosstab(
 
     Parameters
     ----------
-    sdata : sd.SpatialData
+    sdata : spatialdata.SpatialData
         The input spatial data object containing the categorical variables.
     xvar : str
         The categorical variable for the x-axis.
     yvar : str
         The categorical variable for the y-axis.
-    layer : str, optional
+    layer : str
         The layer in `sdata.points` to extract data from (default is "transcripts").
-    normalize : bool, optional
+    normalize : bool
         Whether to normalize proportions (default is True).
-    axis : int, optional
+    axis : int
         Axis to normalize across (1 = row, 0 = column).
-    kind : str, optional
+    kind : str
         Plot type: 'barh', 'bar', 'heatmap', 'clustermap'.
-    save : bool, optional
+    save : bool
         Whether to save the plot (default is True).
-    figures_path : str, optional
+    figures_path : str
         Path to save the plot.
-    stacked : bool, optional
+    stacked : bool
         Whether bar plots should be stacked (default is True).
-    figsize : tuple, optional
+    figsize : tuple
         Automatically computed based on the number of categories unless manually specified.
-    cmap : str, optional
+    cmap : str
         Custom color palette.
-    saving_format : str, optional
+    saving_format : str
         File format to save the plot (e.g., 'png', 'pdf').
-    sortby : str, optional
+    sortby : str
         Column/row to sort before plotting.
 
     Returns
@@ -216,29 +216,29 @@ def histogram(
 
     Parameters
     ----------
-    sdata : sd.SpatialData
+    sdata : spatialdata.SpatialData
         The input spatial data object.
     x : str
         The name of the numeric column to plot on the x-axis.
-    hue : str, optional
+    hue : str
         The column name used for color grouping (optional).
-    layer : str, optional
+    layer : str
         The layer in sdata.points to extract data from (default is "transcripts").
-    group_key : str, optional
+    group_key : str
         If provided, creates subplots by the unique values of this column.
-    figures_path : str, optional
+    figures_path : str
         Path to save the plot if `save` is True.
-    save : bool, optional
+    save : bool
         Whether to save the figure as a PDF.
-    title : str, optional
+    title : str
         Overall title for the plot.
-    custom_plot_filename : str, optional
+    custom_plot_filename : str
         Custom filename to use when saving the figure.
-    palette : str, optional
+    palette : str
         Color palette name for seaborn (default is "tab10").
-    bins : int, optional
+    bins : int
         Number of histogram bins (default is 30).
-    kde : bool, optional
+    kde : bool
         Whether to overlay a kernel density estimate (default is False).
 
     Returns

src/troutpy/pl/basic.py

@@ -9,12 +9,15 @@ def get_palette(name="default", n_colors=None):
 
     Parameters
     ----------
-    - name (str): Name of the palette ("default", "coolwarm", "viridis", etc.).
-    - n_colors (int, optional): Number of colors to return. If None, return all.
+    name: str
+        Name of the palette ("default", "coolwarm", "viridis", etc.).
+    n_colors: int
+        Number of colors to return. If None, return all.
 
     Returns
     -------
-    - list of hex color codes.
+    palette: str
+        list of hex color codes.
     """
     palettes = {
         "30colors": [
@@ -109,11 +112,13 @@ def get_colormap(name="default"):
 
     Parameters
     ----------
-    - name (str): Name of the colormap ("default", "coolwarm", "viridis", etc.).
+    name: str
+        Name of the colormap ("default", "coolwarm", "viridis", etc.).
 
     Returns
     -------
-    - matplotlib.colors.Colormap object.
+    list
+        matplotlib.colors.Colormap object.
     """
     colormaps = {
         "30colors": mcolors.LinearSegmentedColormap.from_list("custom_cmap", get_palette("30colors")),

src/troutpy/pl/colors.py

@@ -13,19 +13,19 @@ def celltype_communication(sdata, kind="heatmap", celltype_key="cell type", vmax
 
     Parameters
     ----------
-    sdata : SpatialData object
+    sdata : spatialdata.SpatialData
         The spatial data object containing interaction scores.
-    kind : str, optional
+    kind : str
         Type of plot, either 'heatmap' or 'chord'. Default is 'heatmap'.
-    celltype_key : str, optional
+    celltype_key : str
         Key for cell type colors in `sdata['table'].uns`. Default is 'cell type'.
-    vmax : float, optional
+    vmax : float
         Max value for colormap scaling. Default is None.
-    vmin : float, optional
+    vmin : float
         Min value for colormap scaling. Default is None.
-    cmap : str, optional
+    cmap : str
         Colormap for heatmap or chord diagram. Default is 'BuPu'.
-    **kwargs : dict
+    kwargs : dict
         Additional arguments passed to the plotting functions.
     """
     interaction_strength = sdata["source_score"].uns["interaction_strength"]
@@ -63,21 +63,21 @@ def gene_communication(
 
     Parameters
     ----------
-    sdata : SpatialData object
+    sdata : spatialdata.SpatialData
         The spatial data object containing interaction scores.
-    kind : str, optional
+    kind : str
         Type of plot, either 'heatmap' or 'chord'. Default is 'heatmap'.
-    celltype_key : str, optional
+    celltype_key : str
         Key for cell type colors in `sdata['table'].uns`. Default is 'cell type'.
-    gene
+    gene: str
         Name of the gene to be plotted
-    vmax : float, optional
+    vmax : float
         Max value for colormap scaling. Default is None.
-    vmin : float, optional
+    vmin : float
         Min value for colormap scaling. Default is None.
-    cmap : str, optional
+    cmap : str
         Colormap for heatmap or chord diagram. Default is 'BuPu'.
-    **kwargs : dict
+    kwargs : dict
         Additional arguments passed to the plotting functions.
     """
     gene_interaction_strength = sdata["source_score"].uns["gene_interaction_strength"]
@@ -124,34 +124,34 @@ def target_score_by_celltype(
     title: str | None = "Target Score by Cell Type",
     cluster_axis: str = "both",
     cmap: str = "coolwarm",
-    figsize: tuple = (10, 8),
+    figsize: tuple = None,
 ) -> None:
     """
     Plots a heatmap or clustered heatmap of target scores by cell type.
 
     Parameters
     ----------
-    sdata : sd.SpatialData
+    sdata : spatialdata.SpatialData
         A SpatialData object containing `target_score` data.
-    gene_key : str, default="feature_name"
+    gene_key : str
         The key in `obs` that contains gene names.
-    min_counts : int, default=100
+    min_counts : int
         Minimum count threshold for genes to be included.
-    min_value : float, optional
+    min_value : float
         Genes presenting the highest target score below this will be filtered out in visualization
-    max_value : float, optional
+    max_value : float
         Genes presenting the highest target score above this will be filtered out in visualization
-    title : str, optional
+    title : str
         Custom title for the plot.
-    cluster_axis : str, default="both"
+    cluster_axis : str
         Determines clustering:
         - "none" (no clustering)
         - "x" (cluster columns only)
         - "y" (cluster rows only)
         - "both" (cluster rows and columns)
-    cmap : str, default="coolwarm"
+    cmap : str
         Colormap for the heatmap.
-    figsize : tuple, default=(10, 8)
+    figsize : tuple
         Size of the figure.
 
     Returns
@@ -164,6 +164,8 @@ def target_score_by_celltype(
     target_score["gene"] = sdata["target_score"].obs[gene_key]
     gene_by_celltype_score = target_score.groupby("gene").mean()
 
+    if figsize is None:
+        figsize = (10, 8)
     # Filter genes based on count threshold
     genes = sdata["xrna_metadata"].var.index[sdata["xrna_metadata"].var["count"] > min_counts]
     filtered_gene_by_celltype_score = gene_by_celltype_score.loc[gene_by_celltype_score.index.isin(genes), :]