aselimov/neovim
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Initial configuration commit

Browse source
This commit is contained in:
Alex Selimov 2023-10-24 22:54:55 -04:00
commit 31c8abea59
266 changed files with 780274 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

557
typings/seaborn/matrix.pyi Normal file
View file

@ -0,0 +1,557 @@
"""
This type stub file was generated by pyright.
"""
from .axisgrid import Grid
from ._decorators import _deprecate_positional_args
"""Functions to visualize matrices of data."""
__all__ = ["heatmap", "clustermap"]
class _HeatMapper:
"""Draw a heatmap plot of a matrix with nice labels and colormaps."""
def __init__(self, data, vmin, vmax, cmap, center, robust, annot, fmt, annot_kws, cbar, cbar_kws, xticklabels=..., yticklabels=..., mask=...) -> None:
"""Initialize the plotting object."""
...
def plot(self, ax, cax, kws): # -> None:
"""Draw the heatmap on the provided Axes."""
...
@_deprecate_positional_args
def heatmap(data, *, vmin=..., vmax=..., cmap=..., center=..., robust=..., annot=..., fmt=..., annot_kws=..., linewidths=..., linecolor=..., cbar=..., cbar_kws=..., cbar_ax=..., square=..., xticklabels=..., yticklabels=..., mask=..., ax=..., **kwargs): # -> Axes:
"""Plot rectangular data as a color-encoded matrix.
This is an Axes-level function and will draw the heatmap into the
currently-active Axes if none is provided to the ``ax`` argument. Part of
this Axes space will be taken and used to plot a colormap, unless ``cbar``
is False or a separate Axes is provided to ``cbar_ax``.
Parameters
----------
data : rectangular dataset
2D dataset that can be coerced into an ndarray. If a Pandas DataFrame
is provided, the index/column information will be used to label the
columns and rows.
vmin, vmax : floats, optional
Values to anchor the colormap, otherwise they are inferred from the
data and other keyword arguments.
cmap : matplotlib colormap name or object, or list of colors, optional
The mapping from data values to color space. If not provided, the
default will depend on whether ``center`` is set.
center : float, optional
The value at which to center the colormap when plotting divergant data.
Using this parameter will change the default ``cmap`` if none is
specified.
robust : bool, optional
If True and ``vmin`` or ``vmax`` are absent, the colormap range is
computed with robust quantiles instead of the extreme values.
annot : bool or rectangular dataset, optional
If True, write the data value in each cell. If an array-like with the
same shape as ``data``, then use this to annotate the heatmap instead
of the data. Note that DataFrames will match on position, not index.
fmt : str, optional
String formatting code to use when adding annotations.
annot_kws : dict of key, value mappings, optional
Keyword arguments for :meth:`matplotlib.axes.Axes.text` when ``annot``
is True.
linewidths : float, optional
Width of the lines that will divide each cell.
linecolor : color, optional
Color of the lines that will divide each cell.
cbar : bool, optional
Whether to draw a colorbar.
cbar_kws : dict of key, value mappings, optional
Keyword arguments for :meth:`matplotlib.figure.Figure.colorbar`.
cbar_ax : matplotlib Axes, optional
Axes in which to draw the colorbar, otherwise take space from the
main Axes.
square : bool, optional
If True, set the Axes aspect to "equal" so each cell will be
square-shaped.
xticklabels, yticklabels : "auto", bool, list-like, or int, optional
If True, plot the column names of the dataframe. If False, don't plot
the column names. If list-like, plot these alternate labels as the
xticklabels. If an integer, use the column names but plot only every
n label. If "auto", try to densely plot non-overlapping labels.
mask : bool array or DataFrame, optional
If passed, data will not be shown in cells where ``mask`` is True.
Cells with missing values are automatically masked.
ax : matplotlib Axes, optional
Axes in which to draw the plot, otherwise use the currently-active
Axes.
kwargs : other keyword arguments
All other keyword arguments are passed to
:meth:`matplotlib.axes.Axes.pcolormesh`.
Returns
-------
ax : matplotlib Axes
Axes object with the heatmap.
See Also
--------
clustermap : Plot a matrix using hierachical clustering to arrange the
rows and columns.
Examples
--------
Plot a heatmap for a numpy array:
.. plot::
:context: close-figs
>>> import numpy as np; np.random.seed(0)
>>> import seaborn as sns; sns.set_theme()
>>> uniform_data = np.random.rand(10, 12)
>>> ax = sns.heatmap(uniform_data)
Change the limits of the colormap:
.. plot::
:context: close-figs
>>> ax = sns.heatmap(uniform_data, vmin=0, vmax=1)
Plot a heatmap for data centered on 0 with a diverging colormap:
.. plot::
:context: close-figs
>>> normal_data = np.random.randn(10, 12)
>>> ax = sns.heatmap(normal_data, center=0)
Plot a dataframe with meaningful row and column labels:
.. plot::
:context: close-figs
>>> flights = sns.load_dataset("flights")
>>> flights = flights.pivot("month", "year", "passengers")
>>> ax = sns.heatmap(flights)
Annotate each cell with the numeric value using integer formatting:
.. plot::
:context: close-figs
>>> ax = sns.heatmap(flights, annot=True, fmt="d")
Add lines between each cell:
.. plot::
:context: close-figs
>>> ax = sns.heatmap(flights, linewidths=.5)
Use a different colormap:
.. plot::
:context: close-figs
>>> ax = sns.heatmap(flights, cmap="YlGnBu")
Center the colormap at a specific value:
.. plot::
:context: close-figs
>>> ax = sns.heatmap(flights, center=flights.loc["Jan", 1955])
Plot every other column label and don't plot row labels:
.. plot::
:context: close-figs
>>> data = np.random.randn(50, 20)
>>> ax = sns.heatmap(data, xticklabels=2, yticklabels=False)
Don't draw a colorbar:
.. plot::
:context: close-figs
>>> ax = sns.heatmap(flights, cbar=False)
Use different axes for the colorbar:
.. plot::
:context: close-figs
>>> grid_kws = {"height_ratios": (.9, .05), "hspace": .3}
>>> f, (ax, cbar_ax) = plt.subplots(2, gridspec_kw=grid_kws)
>>> ax = sns.heatmap(flights, ax=ax,
... cbar_ax=cbar_ax,
... cbar_kws={"orientation": "horizontal"})
Use a mask to plot only part of a matrix
.. plot::
:context: close-figs
>>> corr = np.corrcoef(np.random.randn(10, 200))
>>> mask = np.zeros_like(corr)
>>> mask[np.triu_indices_from(mask)] = True
>>> with sns.axes_style("white"):
... f, ax = plt.subplots(figsize=(7, 5))
... ax = sns.heatmap(corr, mask=mask, vmax=.3, square=True)
"""
...
class _DendrogramPlotter:
"""Object for drawing tree of similarities between data rows/columns"""
def __init__(self, data, linkage, metric, method, axis, label, rotate) -> None:
"""Plot a dendrogram of the relationships between the columns of data
Parameters
----------
data : pandas.DataFrame
Rectangular data
"""
...
@property
def calculated_linkage(self):
...
def calculate_dendrogram(self): # -> dict[str, Unknown]:
"""Calculates a dendrogram based on the linkage matrix
Made a separate function, not a property because don't want to
recalculate the dendrogram every time it is accessed.
Returns
-------
dendrogram : dict
Dendrogram dictionary as returned by scipy.cluster.hierarchy
.dendrogram. The important key-value pairing is
"reordered_ind" which indicates the re-ordering of the matrix
"""
...
@property
def reordered_ind(self):
"""Indices of the matrix, reordered by the dendrogram"""
...
def plot(self, ax, tree_kws): # -> Self@_DendrogramPlotter:
"""Plots a dendrogram of the similarities between data on the axes
Parameters
----------
ax : matplotlib.axes.Axes
Axes object upon which the dendrogram is plotted
"""
...
@_deprecate_positional_args
def dendrogram(data, *, linkage=..., axis=..., label=..., metric=..., method=..., rotate=..., tree_kws=..., ax=...): # -> _DendrogramPlotter:
"""Draw a tree diagram of relationships within a matrix
Parameters
----------
data : pandas.DataFrame
Rectangular data
linkage : numpy.array, optional
Linkage matrix
axis : int, optional
Which axis to use to calculate linkage. 0 is rows, 1 is columns.
label : bool, optional
If True, label the dendrogram at leaves with column or row names
metric : str, optional
Distance metric. Anything valid for scipy.spatial.distance.pdist
method : str, optional
Linkage method to use. Anything valid for
scipy.cluster.hierarchy.linkage
rotate : bool, optional
When plotting the matrix, whether to rotate it 90 degrees
counter-clockwise, so the leaves face right
tree_kws : dict, optional
Keyword arguments for the ``matplotlib.collections.LineCollection``
that is used for plotting the lines of the dendrogram tree.
ax : matplotlib axis, optional
Axis to plot on, otherwise uses current axis
Returns
-------
dendrogramplotter : _DendrogramPlotter
A Dendrogram plotter object.
Notes
-----
Access the reordered dendrogram indices with
dendrogramplotter.reordered_ind
"""
...
class ClusterGrid(Grid):
def __init__(self, data, pivot_kws=..., z_score=..., standard_scale=..., figsize=..., row_colors=..., col_colors=..., mask=..., dendrogram_ratio=..., colors_ratio=..., cbar_pos=...) -> None:
"""Grid object for organizing clustered heatmap input on to axes"""
...
def format_data(self, data, pivot_kws, z_score=..., standard_scale=...):
"""Extract variables from data or use directly."""
...
@staticmethod
def z_score(data2d, axis=...):
"""Standarize the mean and variance of the data axis
Parameters
----------
data2d : pandas.DataFrame
Data to normalize
axis : int
Which axis to normalize across. If 0, normalize across rows, if 1,
normalize across columns.
Returns
-------
normalized : pandas.DataFrame
Noramlized data with a mean of 0 and variance of 1 across the
specified axis.
"""
...
@staticmethod
def standard_scale(data2d, axis=...):
"""Divide the data by the difference between the max and min
Parameters
----------
data2d : pandas.DataFrame
Data to normalize
axis : int
Which axis to normalize across. If 0, normalize across rows, if 1,
normalize across columns.
vmin : int
If 0, then subtract the minimum of the data before dividing by
the range.
Returns
-------
standardized : pandas.DataFrame
Noramlized data with a mean of 0 and variance of 1 across the
specified axis.
"""
...
def dim_ratios(self, colors, dendrogram_ratio, colors_ratio): # -> list[Unknown]:
"""Get the proportions of the figure taken up by each axes."""
...
@staticmethod
def color_list_to_matrix_and_cmap(colors, ind, axis=...): # -> tuple[ndarray[Any, dtype[Any]], Unknown]:
"""Turns a list of colors into a numpy matrix and matplotlib colormap
These arguments can now be plotted using heatmap(matrix, cmap)
and the provided colors will be plotted.
Parameters
----------
colors : list of matplotlib colors
Colors to label the rows or columns of a dataframe.
ind : list of ints
Ordering of the rows or columns, to reorder the original colors
by the clustered dendrogram order
axis : int
Which axis this is labeling
Returns
-------
matrix : numpy.array
A numpy array of integer values, where each corresponds to a color
from the originally provided list of colors
cmap : matplotlib.colors.ListedColormap
"""
...
def savefig(self, *args, **kwargs): # -> None:
...
def plot_dendrograms(self, row_cluster, col_cluster, metric, method, row_linkage, col_linkage, tree_kws): # -> None:
...
def plot_colors(self, xind, yind, **kws): # -> None:
"""Plots color labels between the dendrogram and the heatmap
Parameters
----------
heatmap_kws : dict
Keyword arguments heatmap
"""
...
def plot_matrix(self, colorbar_kws, xind, yind, **kws): # -> None:
...
def plot(self, metric, method, colorbar_kws, row_cluster, col_cluster, row_linkage, col_linkage, tree_kws, **kws): # -> Self@ClusterGrid:
...
@_deprecate_positional_args
def clustermap(data, *, pivot_kws=..., method=..., metric=..., z_score=..., standard_scale=..., figsize=..., cbar_kws=..., row_cluster=..., col_cluster=..., row_linkage=..., col_linkage=..., row_colors=..., col_colors=..., mask=..., dendrogram_ratio=..., colors_ratio=..., cbar_pos=..., tree_kws=..., **kwargs): # -> ClusterGrid:
"""
Plot a matrix dataset as a hierarchically-clustered heatmap.
Parameters
----------
data : 2D array-like
Rectangular data for clustering. Cannot contain NAs.
pivot_kws : dict, optional
If `data` is a tidy dataframe, can provide keyword arguments for
pivot to create a rectangular dataframe.
method : str, optional
Linkage method to use for calculating clusters. See
:func:`scipy.cluster.hierarchy.linkage` documentation for more
information.
metric : str, optional
Distance metric to use for the data. See
:func:`scipy.spatial.distance.pdist` documentation for more options.
To use different metrics (or methods) for rows and columns, you may
construct each linkage matrix yourself and provide them as
`{row,col}_linkage`.
z_score : int or None, optional
Either 0 (rows) or 1 (columns). Whether or not to calculate z-scores
for the rows or the columns. Z scores are: z = (x - mean)/std, so
values in each row (column) will get the mean of the row (column)
subtracted, then divided by the standard deviation of the row (column).
This ensures that each row (column) has mean of 0 and variance of 1.
standard_scale : int or None, optional
Either 0 (rows) or 1 (columns). Whether or not to standardize that
dimension, meaning for each row or column, subtract the minimum and
divide each by its maximum.
figsize : tuple of (width, height), optional
Overall size of the figure.
cbar_kws : dict, optional
Keyword arguments to pass to `cbar_kws` in :func:`heatmap`, e.g. to
add a label to the colorbar.
{row,col}_cluster : bool, optional
If ``True``, cluster the {rows, columns}.
{row,col}_linkage : :class:`numpy.ndarray`, optional
Precomputed linkage matrix for the rows or columns. See
:func:`scipy.cluster.hierarchy.linkage` for specific formats.
{row,col}_colors : list-like or pandas DataFrame/Series, optional
List of colors to label for either the rows or columns. Useful to evaluate
whether samples within a group are clustered together. Can use nested lists or
DataFrame for multiple color levels of labeling. If given as a
:class:`pandas.DataFrame` or :class:`pandas.Series`, labels for the colors are
extracted from the DataFrames column names or from the name of the Series.
DataFrame/Series colors are also matched to the data by their index, ensuring
colors are drawn in the correct order.
mask : bool array or DataFrame, optional
If passed, data will not be shown in cells where `mask` is True.
Cells with missing values are automatically masked. Only used for
visualizing, not for calculating.
{dendrogram,colors}_ratio : float, or pair of floats, optional
Proportion of the figure size devoted to the two marginal elements. If
a pair is given, they correspond to (row, col) ratios.
cbar_pos : tuple of (left, bottom, width, height), optional
Position of the colorbar axes in the figure. Setting to ``None`` will
disable the colorbar.
tree_kws : dict, optional
Parameters for the :class:`matplotlib.collections.LineCollection`
that is used to plot the lines of the dendrogram tree.
kwargs : other keyword arguments
All other keyword arguments are passed to :func:`heatmap`.
Returns
-------
:class:`ClusterGrid`
A :class:`ClusterGrid` instance.
See Also
--------
heatmap : Plot rectangular data as a color-encoded matrix.
Notes
-----
The returned object has a ``savefig`` method that should be used if you
want to save the figure object without clipping the dendrograms.
To access the reordered row indices, use:
``clustergrid.dendrogram_row.reordered_ind``
Column indices, use:
``clustergrid.dendrogram_col.reordered_ind``
Examples
--------
Plot a clustered heatmap:
.. plot::
:context: close-figs
>>> import seaborn as sns; sns.set_theme(color_codes=True)
>>> iris = sns.load_dataset("iris")
>>> species = iris.pop("species")
>>> g = sns.clustermap(iris)
Change the size and layout of the figure:
.. plot::
:context: close-figs
>>> g = sns.clustermap(iris,
... figsize=(7, 5),
... row_cluster=False,
... dendrogram_ratio=(.1, .2),
... cbar_pos=(0, .2, .03, .4))
Add colored labels to identify observations:
.. plot::
:context: close-figs
>>> lut = dict(zip(species.unique(), "rbg"))
>>> row_colors = species.map(lut)
>>> g = sns.clustermap(iris, row_colors=row_colors)
Use a different colormap and adjust the limits of the color range:
.. plot::
:context: close-figs
>>> g = sns.clustermap(iris, cmap="mako", vmin=0, vmax=10)
Use a different similarity metric:
.. plot::
:context: close-figs
>>> g = sns.clustermap(iris, metric="correlation")
Use a different clustering method:
.. plot::
:context: close-figs
>>> g = sns.clustermap(iris, method="single")
Standardize the data within the columns:
.. plot::
:context: close-figs
>>> g = sns.clustermap(iris, standard_scale=1)
Normalize the data within the rows:
.. plot::
:context: close-figs
>>> g = sns.clustermap(iris, z_score=0, cmap="vlag")
"""
...