python - 在Matplotlib中为Boxplot提供自定义四分位数间距

Matplotlib或Seaborn箱形图给出了介于25％和75％之间的四分位数范围。有没有办法为Boxplot提供自定义四分位数间距？我需要获得箱形图，以使四分位数范围介于10％和90％之间。在Google和其他来源上查找后，就知道了如何在箱形图上获取自定义晶须，而不是自定义四分位间距。希望在这里可以获得一些有用的解决方案。

最佳答案

是的，可以在所需的任何百分位数处绘制带有框边的框线图。

惯例

对于箱形图和晶须图，通常绘制数据的第25和第75个百分位。因此，您应该意识到，背离该约定会使您面临误导读者的风险。您还应该仔细考虑改变框的百分位数对离群值分类和框图的晶须意味着什么。

快速解决方案

一种快速解决方案（忽略晶须位置的任何含义）是计算所需的箱线图统计信息，更改q1和q3的位置，然后使用ax.bxp进行绘制：

import matplotlib.cbook as cbook
import matplotlib.pyplot as plt
import numpy as np

# Generate some random data to visualise
np.random.seed(2019)
data = np.random.normal(size=100)

stats = {}
# Compute the boxplot stats (as in the default matplotlib implementation)
stats['A'] = cbook.boxplot_stats(data, labels='A')[0]
stats['B'] = cbook.boxplot_stats(data, labels='B')[0]
stats['C'] = cbook.boxplot_stats(data, labels='C')[0]

# For box A compute the 1st and 99th percentiles
stats['A']['q1'], stats['A']['q3'] = np.percentile(data, [1, 99])
# For box B compute the 10th and 90th percentiles
stats['B']['q1'], stats['B']['q3'] = np.percentile(data, [10, 90])
# For box C compute the 25th and 75th percentiles (matplotlib default)
stats['C']['q1'], stats['C']['q3'] = np.percentile(data, [25, 75])

fig, ax = plt.subplots(1, 1)
# Plot boxplots from our computed statistics
ax.bxp([stats['A'], stats['B'], stats['C']], positions=range(3))

但是，查看生成的图，我们发现在改变晶须的同时保持晶须不变的情况下，改变q1和q3可能不是一个明智的主意。您可以通过重新计算来解决这个问题。 stats['A']['iqr']以及晶须位置stats['A']['whishi']和stats['A']['whislo']。



更完整的解决方案

查看matplotlib的源代码，我们发现matplotlib使用matplotlib.cbook.boxplot_stats来计算箱线图中使用的统计信息。

在boxplot_stats中，我们找到代码q1, med, q3 = np.percentile(x, [25, 50, 75])。这是我们可以更改以更改绘制的百分位数的线。

因此，一种潜在的解决方案是复制matplotlib.cbook.boxplot_stats并根据需要更改它。在这里，我调用函数my_boxplot_stats并添加参数percents，以轻松更改q1和q3的位置。

import itertools
from matplotlib.cbook import _reshape_2D
import matplotlib.pyplot as plt
import numpy as np

# Function adapted from matplotlib.cbook
def my_boxplot_stats(X, whis=1.5, bootstrap=None, labels=None,
                  autorange=False, percents=[25, 75]):

    def _bootstrap_median(data, N=5000):
        # determine 95% confidence intervals of the median
        M = len(data)
        percentiles = [2.5, 97.5]

        bs_index = np.random.randint(M, size=(N, M))
        bsData = data[bs_index]
        estimate = np.median(bsData, axis=1, overwrite_input=True)

        CI = np.percentile(estimate, percentiles)
        return CI

    def _compute_conf_interval(data, med, iqr, bootstrap):
        if bootstrap is not None:
            # Do a bootstrap estimate of notch locations.
            # get conf. intervals around median
            CI = _bootstrap_median(data, N=bootstrap)
            notch_min = CI[0]
            notch_max = CI[1]
        else:

            N = len(data)
            notch_min = med - 1.57 * iqr / np.sqrt(N)
            notch_max = med + 1.57 * iqr / np.sqrt(N)

        return notch_min, notch_max

    # output is a list of dicts
    bxpstats = []

    # convert X to a list of lists
    X = _reshape_2D(X, "X")

    ncols = len(X)
    if labels is None:
        labels = itertools.repeat(None)
    elif len(labels) != ncols:
        raise ValueError("Dimensions of labels and X must be compatible")

    input_whis = whis
    for ii, (x, label) in enumerate(zip(X, labels)):

        # empty dict
        stats = {}
        if label is not None:
            stats['label'] = label

        # restore whis to the input values in case it got changed in the loop
        whis = input_whis

        # note tricksyness, append up here and then mutate below
        bxpstats.append(stats)

        # if empty, bail
        if len(x) == 0:
            stats['fliers'] = np.array([])
            stats['mean'] = np.nan
            stats['med'] = np.nan
            stats['q1'] = np.nan
            stats['q3'] = np.nan
            stats['cilo'] = np.nan
            stats['cihi'] = np.nan
            stats['whislo'] = np.nan
            stats['whishi'] = np.nan
            stats['med'] = np.nan
            continue

        # up-convert to an array, just to be safe
        x = np.asarray(x)

        # arithmetic mean
        stats['mean'] = np.mean(x)

        # median
        med = np.percentile(x, 50)
        ## Altered line
        q1, q3 = np.percentile(x, (percents[0], percents[1]))

        # interquartile range
        stats['iqr'] = q3 - q1
        if stats['iqr'] == 0 and autorange:
            whis = 'range'

        # conf. interval around median
        stats['cilo'], stats['cihi'] = _compute_conf_interval(
            x, med, stats['iqr'], bootstrap
        )

        # lowest/highest non-outliers
        if np.isscalar(whis):
            if np.isreal(whis):
                loval = q1 - whis * stats['iqr']
                hival = q3 + whis * stats['iqr']
            elif whis in ['range', 'limit', 'limits', 'min/max']:
                loval = np.min(x)
                hival = np.max(x)
            else:
                raise ValueError('whis must be a float, valid string, or list '
                                 'of percentiles')
        else:
            loval = np.percentile(x, whis[0])
            hival = np.percentile(x, whis[1])

        # get high extreme
        wiskhi = np.compress(x <= hival, x)
        if len(wiskhi) == 0 or np.max(wiskhi) < q3:
            stats['whishi'] = q3
        else:
            stats['whishi'] = np.max(wiskhi)

        # get low extreme
        wisklo = np.compress(x >= loval, x)
        if len(wisklo) == 0 or np.min(wisklo) > q1:
            stats['whislo'] = q1
        else:
            stats['whislo'] = np.min(wisklo)

        # compute a single array of outliers
        stats['fliers'] = np.hstack([
            np.compress(x < stats['whislo'], x),
            np.compress(x > stats['whishi'], x)
        ])

        # add in the remaining stats
        stats['q1'], stats['med'], stats['q3'] = q1, med, q3

    return bxpstats

有了这个，我们可以计算统计数据，然后使用plt.bxp进行绘制。

# Generate some random data to visualise
np.random.seed(2019)
data = np.random.normal(size=100)

stats = {}

# Compute the boxplot stats with our desired percentiles
stats['A'] = my_boxplot_stats(data, labels='A', percents=[1, 99])[0]
stats['B'] = my_boxplot_stats(data, labels='B', percents=[10, 90])[0]
stats['C'] = my_boxplot_stats(data, labels='C', percents=[25, 75])[0]

fig, ax = plt.subplots(1, 1)
# Plot boxplots from our computed statistics
ax.bxp([stats['A'], stats['B'], stats['C']], positions=range(3))

看到通过该解决方案，晶须会根据我们选择的百分位数在我们的功能中进行调整：

关于python - 在Matplotlib中为Boxplot提供自定义四分位数间距，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/54911424/