用python绘制剖面图

Question

我正在尝试为熊猫.DataFrame. 我不希望这种情况直接出现在熊猫身上，但在matplotlib中似乎也没有任何内容。我到处找遍了，除了rootpy，没有在任何包里找到它。在我自己花时间写这篇文章之前，我想我应该问一下是否有一个小的包，里面包含了剖面直方图，也许它们的名字不同。在

如果您不知道我所说的“profile histogram”是什么意思，请看一下根实现。http://root.cern.ch/root/html/TProfile.html

Answer 1

使用seaborn。来自@MaxNoe的数据

import numpy as np
import seaborn as sns

# just some random numbers to get startet
x = np.random.uniform(-2, 2, 10000)
y = np.random.normal(x**2, np.abs(x) + 1)

sns.regplot(x=x, y=y, x_bins=10, fit_reg=None)

你可以做得更多（误差带来自bootstrap，你可以改变y轴上的估计器，添加回归…）

Answer 2

您可以使用^{}轻松完成。在

import scipy.stats
import numpy
import matplotlib.pyplot as plt

x = numpy.random.rand(10000)
y = x + scipy.stats.norm(0, 0.2).rvs(10000)

means_result = scipy.stats.binned_statistic(x, [y, y**2], bins=50, range=(0,1), statistic='mean')
means, means2 = means_result.statistic
standard_deviations = numpy.sqrt(means2 - means**2)
bin_edges = means_result.bin_edges
bin_centers = (bin_edges[:-1] + bin_edges[1:])/2.

plt.errorbar(x=bin_centers, y=means, yerr=standard_deviations, linestyle='none', marker='.')

Answer 3

我自己为这个功能做了一个模块。在

import pandas as pd
from pandas import Series, DataFrame
import numpy as np
import matplotlib.pyplot as plt

def Profile(x,y,nbins,xmin,xmax,ax):
    df = DataFrame({'x' : x , 'y' : y})

    binedges = xmin + ((xmax-xmin)/nbins) * np.arange(nbins+1)
    df['bin'] = np.digitize(df['x'],binedges)

    bincenters = xmin + ((xmax-xmin)/nbins)*np.arange(nbins) + ((xmax-xmin)/(2*nbins))
    ProfileFrame = DataFrame({'bincenters' : bincenters, 'N' : df['bin'].value_counts(sort=False)},index=range(1,nbins+1))

    bins = ProfileFrame.index.values
    for bin in bins:
        ProfileFrame.ix[bin,'ymean'] = df.ix[df['bin']==bin,'y'].mean()
        ProfileFrame.ix[bin,'yStandDev'] = df.ix[df['bin']==bin,'y'].std()
        ProfileFrame.ix[bin,'yMeanError'] = ProfileFrame.ix[bin,'yStandDev'] / np.sqrt(ProfileFrame.ix[bin,'N'])

    ax.errorbar(ProfileFrame['bincenters'], ProfileFrame['ymean'], yerr=ProfileFrame['yMeanError'], xerr=(xmax-xmin)/(2*nbins), fmt=None) 
    return ax


def Profile_Matrix(frame):
  #Much of this is stolen from https://github.com/pydata/pandas/blob/master/pandas/tools/plotting.py


    import pandas.core.common as com
    import pandas.tools.plotting as plots
    from pandas.compat import lrange
    from matplotlib.artist import setp

    range_padding=0.05

    df = frame._get_numeric_data()
    n = df.columns.size

    fig, axes = plots._subplots(nrows=n, ncols=n, squeeze=False)

    # no gaps between subplots
    fig.subplots_adjust(wspace=0, hspace=0)

    mask = com.notnull(df)

    boundaries_list = []
    for a in df.columns:
        values = df[a].values[mask[a].values]
        rmin_, rmax_ = np.min(values), np.max(values)
        rdelta_ext = (rmax_ - rmin_) * range_padding / 2.
        boundaries_list.append((rmin_ - rdelta_ext, rmax_+ rdelta_ext))

    for i, a in zip(lrange(n), df.columns):
        for j, b in zip(lrange(n), df.columns):

            common = (mask[a] & mask[b]).values
            nbins = 100
            (xmin,xmax) = boundaries_list[i]

            ax = axes[i, j]
            Profile(df[a][common],df[b][common],nbins,xmin,xmax,ax)

            ax.set_xlabel('')
            ax.set_ylabel('')

            plots._label_axis(ax, kind='x', label=b, position='bottom', rotate=True)
            plots._label_axis(ax, kind='y', label=a, position='left')

            if j!= 0:
                ax.yaxis.set_visible(False)
            if i != n-1:
                ax.xaxis.set_visible(False)

    for ax in axes.flat:
        setp(ax.get_xticklabels(), fontsize=8)
        setp(ax.get_yticklabels(), fontsize=8)

    return axes