docs cleanup

docs/api.md

@@ -16,6 +16,7 @@ import pytometry as pt
     :toctree: generated
 
     io.read_fcs
+    io.read_and_merge
 ```
 
 ## Preprocessing (`pp`)
@@ -44,7 +45,7 @@ import pytometry as pt
 
    tl.normalize_arcsinh
    tl.normalize_logicle
-   tl.normalize_biExp
+   tl.normalize_biexp
    tl.normalize_autologicle
 ```
 

docs/notebooks/preprocessing.ipynb

@@ -214,7 +214,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "adata_biex = pm.tl.normalize_biExp(adata, inplace=False)"
+    "adata_biex = pm.tl.normalize_biexp(adata, inplace=False)"
    ]
   }
  ],

docs/notebooks/quickstart.ipynb

@@ -144,7 +144,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "adata_biexp = pm.tl.normalize_biExp(adata, inplace=False)"
+    "adata_biexp = pm.tl.normalize_biexp(adata, inplace=False)"
    ]
   },
   {

src/pytometry/io/__init__.py

@@ -1 +1 @@
-from ._readfcs import read_fcs
+from ._readfcs import read_and_merge, read_fcs

src/pytometry/io/_readfcs.py

@@ -1,5 +1,3 @@
-from __future__ import annotations
-
 from pathlib import Path
 from typing import Any
 
@@ -11,16 +9,16 @@
 def read_fcs(path: str, reindex: bool = True) -> AnnData:
     """Read FCS file and convert into AnnData format.
 
-    Args:
-        path: str or Path
-            location of fcs file to parse
-        reindex: boolean
-            use the marker info to reindex variable names
-            defaults to True
+    Parameters
+    ----------
+    path
+        location of fcs file to parse
+    reindex
+        use the marker info to reindex variable names
 
     Returns
     -------
-        an AnnData object of the fcs file
+    An AnnData object of the fcs file
     """
     return readfcs.read(path, reindex=reindex)
 
@@ -34,26 +32,27 @@ def read_and_merge(
 ) -> AnnData:
     """Read and merge multiple FCS files into a single AnnData object.
 
-    Args:
-        files (str | list[str]): either a list of file paths or a directory path
-        sample_ids (list[Any] | None): list of sample ids to use as a column in
-        the AnnData object
-        sample_id_from_filename (bool): whether to use the filename to extract the
-        sample id
-        sample_id_index (int): which index of the filename to use as the sample id,
-        defaults to 0
-        sample_id_sep (str): separator to use when splitting the filename, defaults
-        to "_"
+    Parameters
+    ----------
+    files
+        either a list of file paths or a directory path
+    sample_ids
+        list of sample ids to use as a column in the AnnData object
+    sample_id_from_filename
+        whether to use the filename to extract the sample id
+    sample_id_index
+        which index of the filename to use as the sample id
+    sample_id_sep
+        separator to use when splitting the filename
 
     Returns
     -------
-        AnnData: merged AnnData object
+    Merged AnnData object
     """
     if isinstance(files, str):
-        if Path(files).is_dir():
-            files = [str(f) for f in Path(files).glob("*.fcs")]
-        else:
+        if not Path(files).is_dir():
             raise ValueError("files must be a list of files or a directory path")
+        files = [str(f) for f in Path(files).glob("*.fcs")]
     elif isinstance(files, list):
         files = [str(Path(f)) for f in files if Path(f).suffix == ".fcs"]
 

src/pytometry/pl/_histogram.py

@@ -1,19 +1,25 @@
+from typing import Literal
+
 import numpy as np
 import seaborn as sns
 from anndata import AnnData
 from matplotlib import pyplot as plt
 from matplotlib import rcParams
 
 from pytometry.pp._process_data import find_indexes
-from pytometry.tl._normalization import normalize_arcsinh, normalize_biExp, normalize_logicle
+from pytometry.tl._normalization import (
+    normalize_arcsinh,
+    normalize_biexp,
+    normalize_logicle,
+)
 
 
 # Plot data. Choose between Area, Height both(default)
 def plotdata(
     adata: AnnData,
     key: str = "signal_type",
     option: str = "area",
-    normalize: str | None = None,
+    normalize: Literal["arcsinh", "biexp", "logicle"] | None = None,
     cofactor: float | None = 10,
     figsize: tuple[float, float] = (15, 6),
     bins: int = 400,
@@ -28,19 +34,18 @@ def plotdata(
     adata
         Anndata object containing data.
     key
-        Key in adata.var to plot. Default is 'signal_type' which is generated
+        Key in adata.var to plot. Default is 'signal_type', which is generated
         when calling the preprocessing function :func:`~pytometry.pp.split_signal`.
     normalize
-        Normalization type. Default is None but can be set to "arcsinh", "biExp"
-        or "logicle"
+        Normalization type.
     cofactor
-        Cofactor for arcsinh normalization. Default is 10.
+        Cofactor for arcsinh normalization.
     figsize
-        Figure size (width, height). Default is (15, 6).
+        Figure size (width, height).
     option
-        Switch to choose directly between area and height data. Default is "area".
+        Switch to choose directly between area and height data.
     bins
-        Number of bins for the histogram. Default is 400.
+        Number of bins for the histogram.
     save
         Path to save the figure.
     **kwargs
@@ -62,7 +67,7 @@ def plotdata(
         if normalize.lower().count("arcsinh") > 0:
             normalize_arcsinh(adata_, cofactor)
         elif normalize.lower().count("biexp") > 0:
-            normalize_biExp(adata_)
+            normalize_biexp(adata_)
         elif normalize.lower().count("logicle") > 0:
             normalize_logicle(adata_)
         else:

src/pytometry/pl/_scatter_density.py

@@ -1,6 +1,4 @@
-from typing import (
-    Literal,
-)
+from typing import Literal
 
 import matplotlib.colors as mcolors
 import matplotlib.pyplot as plt
@@ -30,48 +28,44 @@ def scatter_density(
     vmax: float | None = None,
     *,
     layer: str | None = None,
-):
+) -> None:
     """Plots the cell density across two adata.obs.
 
     Parameters
     ----------
     adata
         AnnData object containing data.
     x
-        adata.obs to plot on x axis. Defaults to 'FSC-A'.
+        adata.obs to plot on x axis.
     y
-        adata.obs to plot on x axis. Defaults to 'SSC-A'.
+        adata.obs to plot on x axis.
     x_label
         x axis label.
     y_label
         y axis label.
     x_scale
-        x axis scale type to apply. Defaults to 'linear'.
+        x axis scale type to apply.
     y_scale
-        y axis scale type to apply. Defaults to 'linear'.
+        y axis scale type to apply.
     x_lim
         upper and lower limit of the x axis.
     y_lim
         upper and lower limit of the y axis.
     ax
         Axes to draw into. If None, create a new figure or use fignum to draw into an existing figure.
     figsize
-        Figure size (width, height) if ax not provided. Defaults to (10, 10).
+        Figure size (width, height) if ax not provided.
     bins
         Number of bins for the np.histogram2d function.
     cmap
         For scalar aggregates, a matplotlib colormap name or instance. Alternatively, an iterable
-        of colors can be passed and will be converted to a colormap. Defaults to 'jet'.
+        of colors can be passed and will be converted to a colormap.
     vmin, vmax
         For scalar aggregates, the data range that the colormap covers. If vmin or vmax is None (default),
         the colormap autoscales to the range of data in the area displayed, unless the corresponding
         value is already set in the norm.
     layer
         The layer in adata to use. If None, use adata.X.
-
-    Returns
-    -------
-    Scatter plot that displays cell density
     """
     ax = plt.subplots(figsize=figsize)[1] if ax is None else ax
 

src/pytometry/pp/_process_data.py

@@ -1,4 +1,5 @@
 import re
+from typing import Literal
 
 import numpy as np
 import pandas as pd
@@ -16,7 +17,7 @@ def create_comp_mat(spillmat: pd.DataFrame, relevant_data: str = "") -> pd.DataF
     spillmat
         Spillover matrix as pandas dataframe.
     relevant_data:
-        A list of channels for customized selection. Defaults to ''.
+        A list of channels for customized selection.
 
     Returns
     -------
@@ -36,7 +37,7 @@ def find_indexes(
     adata: AnnData,
     var_key: str = None,
     key_added: str = "signal_type",
-    data_type: str = "facs",
+    data_type: Literal["facs", "cytof"] = "facs",
     inplace: bool = True,
 ) -> AnnData | None:
     """Find channels of interest for computing compensation.
@@ -48,15 +49,14 @@ def find_indexes(
     var_key
         Key where to check if a feature is an area, height etc. type of value. Use `var_names` if None.
     key_added
-        Key where result vector is added to the adata.var. Defaults to 'signal_type'.
+        Key where result vector is added to the adata.var.
     data_type
-        Either 'facs' or 'cytof'. Defaults to 'facs'.
+        Type of cytometry data
     inplace
 
     Returns
     -------
-        Depending on `inplace`, returns or updates `adata` with the following
-        updated field adata.var[f'{key_added}']
+    Depending on `inplace`, returns or updates `adata` with the following updated field `adata.var[f'{key_added}']`
     """
     adata = adata if inplace else adata.copy()
 
@@ -108,15 +108,15 @@ def compensate(
     adata
         AnnData object.
     key
-        Key where result vector is added to the adata.var. Defaults to 'signal_type'.
+        Key where result vector is added to the adata.var.
     comp_matrix
         A custom compensation matrix. Please note that by default we use the spillover matrix directly for numeric stability.
     matrix_type
         Whether to use a spillover matrix (default) or a compensation matrix. Only considered for custom compensation
         matrices. Usually, custom compensation matrices are the inverse of the spillover matrix. If you want to use
         a compensation matrix, not the spillover matrix, set `matrix_type` to `compensation`.
     inplace
-        Return a copy instead of writing to adata. Defaults to True.
+        Return a copy instead of writing to adata.
 
     Returns
     -------
@@ -193,7 +193,7 @@ def split_signal(
     var_key: str | None = None,
     key: str = "signal_type",
     option: str = "area",
-    data_type: str = "facs",
+    data_type: Literal["facs", "cytof"] = "facs",
     inplace: bool = True,
 ) -> AnnData | None:
     """Method to filter out height or area data.
@@ -205,13 +205,13 @@ def split_signal(
     var_key
         Key where to check if a feature is an area, height etc. type of value. Use `var_names` if None.
     key
-        Key for adata.var where the variable type is stored. Defaults to 'signal_type'.
+        Key for adata.var where the variable type is stored.
     option
-        For choosing 'area' or 'height' in case of FACS data and 'element' for cyTOF data. Defaults to 'area'.
+        For choosing 'area' or 'height' in case of FACS data and 'element' for cyTOF data.
     data_type
-        Either 'facs' or 'cytof'/'cyTOF'. Defaults to 'facs'.
+        Type of cytometry data
     inplace
-        Return a copy instead of writing to adata. Defaults to True.
+        Return a copy instead of writing to adata.
 
     Returns
     -------
@@ -253,15 +253,15 @@ def split_signal(
 
 
 # create test compensation matrix
-def _dummy_spillover(n_rows=10, row_names=None) -> pd.DataFrame:
+def _dummy_spillover(n_rows: int = 10, row_names: pd.Index | list[str] | None = None) -> pd.DataFrame:
     """Create dummy spillover matrix for testing.
 
     Parameters
     ----------
     n_rows
-        number of rows and columns. Defaults to 10.
+        number of rows and columns.
     row_names
-        Index to use for the resulting dataframe. Also used as column names. Defaults to None.
+        Index to use for the resulting dataframe. Also used as column names.
 
     Returns
     -------

src/pytometry/tl/__init__.py

@@ -2,6 +2,7 @@
     normalize_arcsinh,
     normalize_autologicle,
     normalize_biExp,
+    normalize_biexp,
     normalize_logicle,
 )
 from .clustering._flowsom import flowsom_clustering, meta_clustering, som_clustering