408/notes_estom
1
0
Fork 0
mirror of https://github.com/Estom/notes.git synced 2026-04-02 10:30:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

matplotlib & pandas

Browse Source
This commit is contained in:
estomm
2020-09-26 22:03:11 +08:00
parent 73cc328c81
commit d31be4f219
599 changed files with 99925 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

213
Python/matplotlab/gallery/statistics/barchart_demo.md Normal file
View File

@@ -0,0 +1,213 @@
# 条形图演示
使用Matplotlib的许多形状和大小的条形图。
条形图对于可视化计数或带有误差栏的汇总统计信息非常有用。这些示例显示了使用Matplotlib执行此操作的几种方法。
```python
# Credit: Josh Hemann
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.ticker import MaxNLocator
from collections import namedtuple
n_groups = 5
means_men = (20, 35, 30, 35, 27)
std_men = (2, 3, 4, 1, 2)
means_women = (25, 32, 34, 20, 25)
std_women = (3, 5, 2, 3, 3)
fig, ax = plt.subplots()
index = np.arange(n_groups)
bar_width = 0.35
opacity = 0.4
error_config = {'ecolor': '0.3'}
rects1 = ax.bar(index, means_men, bar_width,
alpha=opacity, color='b',
yerr=std_men, error_kw=error_config,
label='Men')
rects2 = ax.bar(index + bar_width, means_women, bar_width,
alpha=opacity, color='r',
yerr=std_women, error_kw=error_config,
label='Women')
ax.set_xlabel('Group')
ax.set_ylabel('Scores')
ax.set_title('Scores by group and gender')
ax.set_xticks(index + bar_width / 2)
ax.set_xticklabels(('A', 'B', 'C', 'D', 'E'))
ax.legend()
fig.tight_layout()
plt.show()
```
![条形图演示](https://matplotlib.org/_images/sphx_glr_barchart_demo_001.png)
这个例子来自一个应用程序，在这个应用程序中，小学体育教师希望能够向父母展示他们的孩子在一些健身测试中的表现，而且重要的是，相对于其他孩子的表现。 为了演示目的提取绘图代码，我们只为小Johnny Doe编制一些数据......
```python
Student = namedtuple('Student', ['name', 'grade', 'gender'])
Score = namedtuple('Score', ['score', 'percentile'])
# GLOBAL CONSTANTS
testNames = ['Pacer Test', 'Flexed Arm\n Hang', 'Mile Run', 'Agility',
'Push Ups']
testMeta = dict(zip(testNames, ['laps', 'sec', 'min:sec', 'sec', '']))
def attach_ordinal(num):
"""helper function to add ordinal string to integers
1 -> 1st
56 -> 56th
"""
suffixes = {str(i): v
for i, v in enumerate(['th', 'st', 'nd', 'rd', 'th',
'th', 'th', 'th', 'th', 'th'])}
v = str(num)
# special case early teens
if v in {'11', '12', '13'}:
return v + 'th'
return v + suffixes[v[-1]]
def format_score(scr, test):
"""
Build up the score labels for the right Y-axis by first
appending a carriage return to each string and then tacking on
the appropriate meta information (i.e., 'laps' vs 'seconds'). We
want the labels centered on the ticks, so if there is no meta
info (like for pushups) then don't add the carriage return to
the string
"""
md = testMeta[test]
if md:
return '{0}\n{1}'.format(scr, md)
else:
return scr
def format_ycursor(y):
y = int(y)
if y < 0 or y >= len(testNames):
return ''
else:
return testNames[y]
def plot_student_results(student, scores, cohort_size):
# create the figure
fig, ax1 = plt.subplots(figsize=(9, 7))
fig.subplots_adjust(left=0.115, right=0.88)
fig.canvas.set_window_title('Eldorado K-8 Fitness Chart')
pos = np.arange(len(testNames))
rects = ax1.barh(pos, [scores[k].percentile for k in testNames],
align='center',
height=0.5, color='m',
tick_label=testNames)
ax1.set_title(student.name)
ax1.set_xlim([0, 100])
ax1.xaxis.set_major_locator(MaxNLocator(11))
ax1.xaxis.grid(True, linestyle='--', which='major',
color='grey', alpha=.25)
# Plot a solid vertical gridline to highlight the median position
ax1.axvline(50, color='grey', alpha=0.25)
# set X-axis tick marks at the deciles
cohort_label = ax1.text(.5, -.07, 'Cohort Size: {0}'.format(cohort_size),
horizontalalignment='center', size='small',
transform=ax1.transAxes)
# Set the right-hand Y-axis ticks and labels
ax2 = ax1.twinx()
scoreLabels = [format_score(scores[k].score, k) for k in testNames]
# set the tick locations
ax2.set_yticks(pos)
# make sure that the limits are set equally on both yaxis so the
# ticks line up
ax2.set_ylim(ax1.get_ylim())
# set the tick labels
ax2.set_yticklabels(scoreLabels)
ax2.set_ylabel('Test Scores')
ax2.set_xlabel(('Percentile Ranking Across '
'{grade} Grade {gender}s').format(
grade=attach_ordinal(student.grade),
gender=student.gender.title()))
rect_labels = []
# Lastly, write in the ranking inside each bar to aid in interpretation
for rect in rects:
# Rectangle widths are already integer-valued but are floating
# type, so it helps to remove the trailing decimal point and 0 by
# converting width to int type
width = int(rect.get_width())
rankStr = attach_ordinal(width)
# The bars aren't wide enough to print the ranking inside
if width < 5:
# Shift the text to the right side of the right edge
xloc = width + 1
# Black against white background
clr = 'black'
align = 'left'
else:
# Shift the text to the left side of the right edge
xloc = 0.98*width
# White on magenta
clr = 'white'
align = 'right'
# Center the text vertically in the bar
yloc = rect.get_y() + rect.get_height()/2.0
label = ax1.text(xloc, yloc, rankStr, horizontalalignment=align,
verticalalignment='center', color=clr, weight='bold',
clip_on=True)
rect_labels.append(label)
# make the interactive mouse over give the bar title
ax2.fmt_ydata = format_ycursor
# return all of the artists created
return {'fig': fig,
'ax': ax1,
'ax_right': ax2,
'bars': rects,
'perc_labels': rect_labels,
'cohort_label': cohort_label}
student = Student('Johnny Doe', 2, 'boy')
scores = dict(zip(testNames,
(Score(v, p) for v, p in
zip(['7', '48', '12:52', '17', '14'],
np.round(np.random.uniform(0, 1,
len(testNames))*100, 0)))))
cohort_size = 62 # The number of other 2nd grade boys
arts = plot_student_results(student, scores, cohort_size)
plt.show()
```
![条形图演示2](https://matplotlib.org/_images/sphx_glr_barchart_demo_002.png)
## 下载这个示例
- [下载python源码: barchart_demo.py](https://matplotlib.org/_downloads/barchart_demo.py)
- [下载Jupyter notebook: barchart_demo.ipynb](https://matplotlib.org/_downloads/barchart_demo.ipynb)

97
Python/matplotlab/gallery/statistics/boxplot.md Normal file
View File

@@ -0,0 +1,97 @@
# 箱形图中的艺术
此示例演示如何使用各种kwargs完全自定义箱形图。第一个图演示了如何删除和添加单个组件（请注意，平均值是默认情况下未显示的唯一值）。第二个图展示了如何定制艺术家的风格。它还演示了如何将胡须的极限设置为特定的百分位数（右下轴）
关于箱形图及其历史的一般参考可以在这里找到：http://vita.had.co.nz/papers/boxplots.pdf
```python
import numpy as np
import matplotlib.pyplot as plt
# fake data
np.random.seed(19680801)
data = np.random.lognormal(size=(37, 4), mean=1.5, sigma=1.75)
labels = list('ABCD')
fs = 10 # fontsize
```
演示如何切换不同元素的显示：
```python
fig, axes = plt.subplots(nrows=2, ncols=3, figsize=(6, 6), sharey=True)
axes[0, 0].boxplot(data, labels=labels)
axes[0, 0].set_title('Default', fontsize=fs)
axes[0, 1].boxplot(data, labels=labels, showmeans=True)
axes[0, 1].set_title('showmeans=True', fontsize=fs)
axes[0, 2].boxplot(data, labels=labels, showmeans=True, meanline=True)
axes[0, 2].set_title('showmeans=True,\nmeanline=True', fontsize=fs)
axes[1, 0].boxplot(data, labels=labels, showbox=False, showcaps=False)
tufte_title = 'Tufte Style \n(showbox=False,\nshowcaps=False)'
axes[1, 0].set_title(tufte_title, fontsize=fs)
axes[1, 1].boxplot(data, labels=labels, notch=True, bootstrap=10000)
axes[1, 1].set_title('notch=True,\nbootstrap=10000', fontsize=fs)
axes[1, 2].boxplot(data, labels=labels, showfliers=False)
axes[1, 2].set_title('showfliers=False', fontsize=fs)
for ax in axes.flatten():
ax.set_yscale('log')
ax.set_yticklabels([])
fig.subplots_adjust(hspace=0.4)
plt.show()
```
![箱形图示例](https://matplotlib.org/_images/sphx_glr_boxplot_001.png)
演示如何自定义显示不同的元素：
```python
boxprops = dict(linestyle='--', linewidth=3, color='darkgoldenrod')
flierprops = dict(marker='o', markerfacecolor='green', markersize=12,
linestyle='none')
medianprops = dict(linestyle='-.', linewidth=2.5, color='firebrick')
meanpointprops = dict(marker='D', markeredgecolor='black',
markerfacecolor='firebrick')
meanlineprops = dict(linestyle='--', linewidth=2.5, color='purple')
fig, axes = plt.subplots(nrows=2, ncols=3, figsize=(6, 6), sharey=True)
axes[0, 0].boxplot(data, boxprops=boxprops)
axes[0, 0].set_title('Custom boxprops', fontsize=fs)
axes[0, 1].boxplot(data, flierprops=flierprops, medianprops=medianprops)
axes[0, 1].set_title('Custom medianprops\nand flierprops', fontsize=fs)
axes[0, 2].boxplot(data, whis='range')
axes[0, 2].set_title('whis="range"', fontsize=fs)
axes[1, 0].boxplot(data, meanprops=meanpointprops, meanline=False,
showmeans=True)
axes[1, 0].set_title('Custom mean\nas point', fontsize=fs)
axes[1, 1].boxplot(data, meanprops=meanlineprops, meanline=True,
showmeans=True)
axes[1, 1].set_title('Custom mean\nas line', fontsize=fs)
axes[1, 2].boxplot(data, whis=[15, 85])
axes[1, 2].set_title('whis=[15, 85]\n#percentiles', fontsize=fs)
for ax in axes.flatten():
ax.set_yscale('log')
ax.set_yticklabels([])
fig.suptitle("I never said they'd be pretty")
fig.subplots_adjust(hspace=0.4)
plt.show()
```
![箱型图示例2](https://matplotlib.org/_images/sphx_glr_boxplot_002.png)
## 下载这个示例
- [下载python源码: boxplot.py](https://matplotlib.org/_downloads/boxplot.py)
- [下载Jupyter notebook: boxplot.ipynb](https://matplotlib.org/_downloads/boxplot.ipynb)

53
Python/matplotlab/gallery/statistics/boxplot_color.md Normal file
View File

@@ -0,0 +1,53 @@
# 带有自定义填充颜色的箱形图
此图说明了如何创建两种类型的箱形图（矩形和缺口），以及如何通过访问框图的艺术家属性来使用自定义颜色填充它们。 此外，labels参数用于为每个样本提供x-tick标签。
关于箱形图及其历史的一般参考可以在这里找到：http://vita.had.co.nz/papers/boxplots.pdf
![自定义颜色箱形图示例](https://matplotlib.org/_images/sphx_glr_boxplot_color_001.png)
```python
import matplotlib.pyplot as plt
import numpy as np
# Random test data
np.random.seed(19680801)
all_data = [np.random.normal(0, std, size=100) for std in range(1, 4)]
labels = ['x1', 'x2', 'x3']
fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(9, 4))
# rectangular box plot
bplot1 = axes[0].boxplot(all_data,
vert=True, # vertical box alignment
patch_artist=True, # fill with color
labels=labels) # will be used to label x-ticks
axes[0].set_title('Rectangular box plot')
# notch shape box plot
bplot2 = axes[1].boxplot(all_data,
notch=True, # notch shape
vert=True, # vertical box alignment
patch_artist=True, # fill with color
labels=labels) # will be used to label x-ticks
axes[1].set_title('Notched box plot')
# fill with colors
colors = ['pink', 'lightblue', 'lightgreen']
for bplot in (bplot1, bplot2):
for patch, color in zip(bplot['boxes'], colors):
patch.set_facecolor(color)
# adding horizontal grid lines
for ax in axes:
ax.yaxis.grid(True)
ax.set_xlabel('Three separate samples')
ax.set_ylabel('Observed values')
plt.show()
```
## 下载这个示例
- [下载python源码: boxplot_color.py](https://matplotlib.org/_downloads/boxplot_color.py)
- [下载Jupyter notebook: boxplot_color.ipynb](https://matplotlib.org/_downloads/boxplot_color.ipynb)

238
Python/matplotlab/gallery/statistics/boxplot_demo.md Normal file
View File

@@ -0,0 +1,238 @@
# 箱形图
用matplotlib可视化箱形图。
以下示例展示了如何使用Matplotlib可视化箱图。有许多选项可以控制它们的外观以及用于汇总数据的统计信息。
```python
import matplotlib.pyplot as plt
import numpy as np
from matplotlib.patches import Polygon
# Fixing random state for reproducibility
np.random.seed(19680801)
# fake up some data
spread = np.random.rand(50) * 100
center = np.ones(25) * 50
flier_high = np.random.rand(10) * 100 + 100
flier_low = np.random.rand(10) * -100
data = np.concatenate((spread, center, flier_high, flier_low))
fig, axs = plt.subplots(2, 3)
# basic plot
axs[0, 0].boxplot(data)
axs[0, 0].set_title('basic plot')
# notched plot
axs[0, 1].boxplot(data, 1)
axs[0, 1].set_title('notched plot')
# change outlier point symbols
axs[0, 2].boxplot(data, 0, 'gD')
axs[0, 2].set_title('change outlier\npoint symbols')
# don't show outlier points
axs[1, 0].boxplot(data, 0, '')
axs[1, 0].set_title("don't show\noutlier points")
# horizontal boxes
axs[1, 1].boxplot(data, 0, 'rs', 0)
axs[1, 1].set_title('horizontal boxes')
# change whisker length
axs[1, 2].boxplot(data, 0, 'rs', 0, 0.75)
axs[1, 2].set_title('change whisker length')
fig.subplots_adjust(left=0.08, right=0.98, bottom=0.05, top=0.9,
hspace=0.4, wspace=0.3)
# fake up some more data
spread = np.random.rand(50) * 100
center = np.ones(25) * 40
flier_high = np.random.rand(10) * 100 + 100
flier_low = np.random.rand(10) * -100
d2 = np.concatenate((spread, center, flier_high, flier_low))
data.shape = (-1, 1)
d2.shape = (-1, 1)
# Making a 2-D array only works if all the columns are the
# same length. If they are not, then use a list instead.
# This is actually more efficient because boxplot converts
# a 2-D array into a list of vectors internally anyway.
data = [data, d2, d2[::2, 0]]
# Multiple box plots on one Axes
fig, ax = plt.subplots()
ax.boxplot(data)
plt.show()
```
下面我们将从五个不同的概率分布生成数据，每个概率分布具有不同的特征。 我们想要了解数据的IID引导程序重采样如何保留原始样本的分布属性，并且箱形图是进行此评估的一种可视化工具。
```python
numDists = 5
randomDists = ['Normal(1,1)', ' Lognormal(1,1)', 'Exp(1)', 'Gumbel(6,4)',
'Triangular(2,9,11)']
N = 500
norm = np.random.normal(1, 1, N)
logn = np.random.lognormal(1, 1, N)
expo = np.random.exponential(1, N)
gumb = np.random.gumbel(6, 4, N)
tria = np.random.triangular(2, 9, 11, N)
# Generate some random indices that we'll use to resample the original data
# arrays. For code brevity, just use the same random indices for each array
bootstrapIndices = np.random.random_integers(0, N - 1, N)
normBoot = norm[bootstrapIndices]
expoBoot = expo[bootstrapIndices]
gumbBoot = gumb[bootstrapIndices]
lognBoot = logn[bootstrapIndices]
triaBoot = tria[bootstrapIndices]
data = [norm, normBoot, logn, lognBoot, expo, expoBoot, gumb, gumbBoot,
tria, triaBoot]
fig, ax1 = plt.subplots(figsize=(10, 6))
fig.canvas.set_window_title('A Boxplot Example')
fig.subplots_adjust(left=0.075, right=0.95, top=0.9, bottom=0.25)
bp = ax1.boxplot(data, notch=0, sym='+', vert=1, whis=1.5)
plt.setp(bp['boxes'], color='black')
plt.setp(bp['whiskers'], color='black')
plt.setp(bp['fliers'], color='red', marker='+')
# Add a horizontal grid to the plot, but make it very light in color
# so we can use it for reading data values but not be distracting
ax1.yaxis.grid(True, linestyle='-', which='major', color='lightgrey',
alpha=0.5)
# Hide these grid behind plot objects
ax1.set_axisbelow(True)
ax1.set_title('Comparison of IID Bootstrap Resampling Across Five Distributions')
ax1.set_xlabel('Distribution')
ax1.set_ylabel('Value')
# Now fill the boxes with desired colors
boxColors = ['darkkhaki', 'royalblue']
numBoxes = numDists*2
medians = list(range(numBoxes))
for i in range(numBoxes):
box = bp['boxes'][i]
boxX = []
boxY = []
for j in range(5):
boxX.append(box.get_xdata()[j])
boxY.append(box.get_ydata()[j])
boxCoords = np.column_stack([boxX, boxY])
# Alternate between Dark Khaki and Royal Blue
k = i % 2
boxPolygon = Polygon(boxCoords, facecolor=boxColors[k])
ax1.add_patch(boxPolygon)
# Now draw the median lines back over what we just filled in
med = bp['medians'][i]
medianX = []
medianY = []
for j in range(2):
medianX.append(med.get_xdata()[j])
medianY.append(med.get_ydata()[j])
ax1.plot(medianX, medianY, 'k')
medians[i] = medianY[0]
# Finally, overplot the sample averages, with horizontal alignment
# in the center of each box
ax1.plot([np.average(med.get_xdata())], [np.average(data[i])],
color='w', marker='*', markeredgecolor='k')
# Set the axes ranges and axes labels
ax1.set_xlim(0.5, numBoxes + 0.5)
top = 40
bottom = -5
ax1.set_ylim(bottom, top)
ax1.set_xticklabels(np.repeat(randomDists, 2),
rotation=45, fontsize=8)
# Due to the Y-axis scale being different across samples, it can be
# hard to compare differences in medians across the samples. Add upper
# X-axis tick labels with the sample medians to aid in comparison
# (just use two decimal places of precision)
pos = np.arange(numBoxes) + 1
upperLabels = [str(np.round(s, 2)) for s in medians]
weights = ['bold', 'semibold']
for tick, label in zip(range(numBoxes), ax1.get_xticklabels()):
k = tick % 2
ax1.text(pos[tick], top - (top*0.05), upperLabels[tick],
horizontalalignment='center', size='x-small', weight=weights[k],
color=boxColors[k])
# Finally, add a basic legend
fig.text(0.80, 0.08, str(N) + ' Random Numbers',
backgroundcolor=boxColors[0], color='black', weight='roman',
size='x-small')
fig.text(0.80, 0.045, 'IID Bootstrap Resample',
backgroundcolor=boxColors[1],
color='white', weight='roman', size='x-small')
fig.text(0.80, 0.015, '*', color='white', backgroundcolor='silver',
weight='roman', size='medium')
fig.text(0.815, 0.013, ' Average Value', color='black', weight='roman',
size='x-small')
plt.show()
```
![箱形图](https://matplotlib.org/_images/sphx_glr_boxplot_demo_003.png)
在这里，我们编写一个自定义函数来引导置信区间。然后我们可以使用boxplot和此函数来显示这些间隔。
```python
def fakeBootStrapper(n):
'''
This is just a placeholder for the user's method of
bootstrapping the median and its confidence intervals.
Returns an arbitrary median and confidence intervals
packed into a tuple
'''
if n == 1:
med = 0.1
CI = (-0.25, 0.25)
else:
med = 0.2
CI = (-0.35, 0.50)
return med, CI
inc = 0.1
e1 = np.random.normal(0, 1, size=(500,))
e2 = np.random.normal(0, 1, size=(500,))
e3 = np.random.normal(0, 1 + inc, size=(500,))
e4 = np.random.normal(0, 1 + 2*inc, size=(500,))
treatments = [e1, e2, e3, e4]
med1, CI1 = fakeBootStrapper(1)
med2, CI2 = fakeBootStrapper(2)
medians = [None, None, med1, med2]
conf_intervals = [None, None, CI1, CI2]
fig, ax = plt.subplots()
pos = np.array(range(len(treatments))) + 1
bp = ax.boxplot(treatments, sym='k+', positions=pos,
notch=1, bootstrap=5000,
usermedians=medians,
conf_intervals=conf_intervals)
ax.set_xlabel('treatment')
ax.set_ylabel('response')
plt.setp(bp['whiskers'], color='k', linestyle='-')
plt.setp(bp['fliers'], markersize=3.0)
plt.show()
```
![箱形图2](https://matplotlib.org/_images/sphx_glr_boxplot_demo_004.png)
## 下载这个示例
- [下载python源码: boxplot_demo.py](https://matplotlib.org/_downloads/boxplot_demo.py)
- [下载Jupyter notebook: boxplot_demo.ipynb](https://matplotlib.org/_downloads/boxplot_demo.ipynb)

54
Python/matplotlab/gallery/statistics/boxplot_vs_violin.md Normal file
View File

@@ -0,0 +1,54 @@
# 箱形图与小提琴图对比
请注意，尽管小提琴图与Tukey（1977）的箱形图密切相关，但它们还添加了有用的信息，例如样本数据的分布（密度轨迹）。
默认情况下，箱形图显示1.5 *四分位数范围之外的数据点作为晶须上方或下方的异常值，而小提琴图则显示数据的整个范围。
关于箱形图及其历史的一般参考可以在这里找到：http://vita.had.co.nz/papers/boxplots.pdf
小提琴图需要 matplotlib >= 1.4。
有关小提琴绘制的更多信息，scikit-learn文档有一个很棒的部分：http://scikit-learn.org/stable/modules/density.html
![箱形图与小提琴图对比示例](https://matplotlib.org/_images/sphx_glr_boxplot_vs_violin_001.png)
```python
import matplotlib.pyplot as plt
import numpy as np
fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(9, 4))
# Fixing random state for reproducibility
np.random.seed(19680801)
# generate some random test data
all_data = [np.random.normal(0, std, 100) for std in range(6, 10)]
# plot violin plot
axes[0].violinplot(all_data,
showmeans=False,
showmedians=True)
axes[0].set_title('Violin plot')
# plot box plot
axes[1].boxplot(all_data)
axes[1].set_title('Box plot')
# adding horizontal grid lines
for ax in axes:
ax.yaxis.grid(True)
ax.set_xticks([y + 1 for y in range(len(all_data))])
ax.set_xlabel('Four separate samples')
ax.set_ylabel('Observed values')
# add x-tick labels
plt.setp(axes, xticks=[y + 1 for y in range(len(all_data))],
xticklabels=['x1', 'x2', 'x3', 'x4'])
plt.show()
```
## 下载这个示例
- [下载python源码: boxplot_vs_violin.py](https://matplotlib.org/_downloads/boxplot_vs_violin.py)
- [下载Jupyter notebook: boxplot_vs_violin.ipynb](https://matplotlib.org/_downloads/boxplot_vs_violin.ipynb)

112
Python/matplotlab/gallery/statistics/bxp.md Normal file
View File

@@ -0,0 +1,112 @@
# 箱形图抽屉功能
此示例演示如何将预先计算的箱形图统计信息传递到框图抽屉。第一个图演示了如何删除和添加单个组件（请注意，平均值是默认情况下未显示的唯一值）。第二个图展示了如何定制艺术风格。
关于箱形图及其历史的一个很好的一般参考可以在这里找到：http://vita.had.co.nz/papers/boxplots.pdf
```python
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cbook as cbook
# fake data
np.random.seed(19680801)
data = np.random.lognormal(size=(37, 4), mean=1.5, sigma=1.75)
labels = list('ABCD')
# compute the boxplot stats
stats = cbook.boxplot_stats(data, labels=labels, bootstrap=10000)
```
在我们计算了统计数据之后，我们可以通过并改变任何事情。 为了证明这一点，我将每组的中位数设置为所有数据的中位数，并将均值加倍
```python
for n in range(len(stats)):
stats[n]['med'] = np.median(data)
stats[n]['mean'] *= 2
print(list(stats[0]))
fs = 10 # fontsize
```
输出：
```python
['label', 'mean', 'iqr', 'cilo', 'cihi', 'whishi', 'whislo', 'fliers', 'q1', 'med', 'q3']
```
演示如何切换不同元素的显示：
```python
fig, axes = plt.subplots(nrows=2, ncols=3, figsize=(6, 6), sharey=True)
axes[0, 0].bxp(stats)
axes[0, 0].set_title('Default', fontsize=fs)
axes[0, 1].bxp(stats, showmeans=True)
axes[0, 1].set_title('showmeans=True', fontsize=fs)
axes[0, 2].bxp(stats, showmeans=True, meanline=True)
axes[0, 2].set_title('showmeans=True,\nmeanline=True', fontsize=fs)
axes[1, 0].bxp(stats, showbox=False, showcaps=False)
tufte_title = 'Tufte Style\n(showbox=False,\nshowcaps=False)'
axes[1, 0].set_title(tufte_title, fontsize=fs)
axes[1, 1].bxp(stats, shownotches=True)
axes[1, 1].set_title('notch=True', fontsize=fs)
axes[1, 2].bxp(stats, showfliers=False)
axes[1, 2].set_title('showfliers=False', fontsize=fs)
for ax in axes.flatten():
ax.set_yscale('log')
ax.set_yticklabels([])
fig.subplots_adjust(hspace=0.4)
plt.show()
```
![箱形图抽屉功能示例](https://matplotlib.org/_images/sphx_glr_bxp_001.png)
演示如何自定义显示不同的元素：
```python
boxprops = dict(linestyle='--', linewidth=3, color='darkgoldenrod')
flierprops = dict(marker='o', markerfacecolor='green', markersize=12,
linestyle='none')
medianprops = dict(linestyle='-.', linewidth=2.5, color='firebrick')
meanpointprops = dict(marker='D', markeredgecolor='black',
markerfacecolor='firebrick')
meanlineprops = dict(linestyle='--', linewidth=2.5, color='purple')
fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(6, 6), sharey=True)
axes[0, 0].bxp(stats, boxprops=boxprops)
axes[0, 0].set_title('Custom boxprops', fontsize=fs)
axes[0, 1].bxp(stats, flierprops=flierprops, medianprops=medianprops)
axes[0, 1].set_title('Custom medianprops\nand flierprops', fontsize=fs)
axes[1, 0].bxp(stats, meanprops=meanpointprops, meanline=False,
showmeans=True)
axes[1, 0].set_title('Custom mean\nas point', fontsize=fs)
axes[1, 1].bxp(stats, meanprops=meanlineprops, meanline=True,
showmeans=True)
axes[1, 1].set_title('Custom mean\nas line', fontsize=fs)
for ax in axes.flatten():
ax.set_yscale('log')
ax.set_yticklabels([])
fig.suptitle("I never said they'd be pretty")
fig.subplots_adjust(hspace=0.4)
plt.show()
```
![箱形图抽屉功能](https://matplotlib.org/_images/sphx_glr_bxp_002.png)
## 下载这个示例
- [下载python源码: bxp.py](https://matplotlib.org/_downloads/bxp.py)
- [下载Jupyter notebook: bxp.ipynb](https://matplotlib.org/_downloads/bxp.ipynb)

75
Python/matplotlab/gallery/statistics/customized_violin.md Normal file
View File

@@ -0,0 +1,75 @@
# 自定义小提琴图
此示例演示如何完全自定义小提琴图。 第一个图通过仅提供数据来显示默认样式。第二个图首先限制了matplotlib用额外的kwargs绘制的内容。然后在顶部绘制箱形图的简化表示。 最后，修改了小提琴图的风格。
有关小提琴图的更多信息，scikit-learn文档有一个很棒的部分：http://scikit-learn.org/stable/modules/density.html
![自定义小提琴图示例](https://matplotlib.org/_images/sphx_glr_customized_violin_001.png)
```python
import matplotlib.pyplot as plt
import numpy as np
def adjacent_values(vals, q1, q3):
upper_adjacent_value = q3 + (q3 - q1) * 1.5
upper_adjacent_value = np.clip(upper_adjacent_value, q3, vals[-1])
lower_adjacent_value = q1 - (q3 - q1) * 1.5
lower_adjacent_value = np.clip(lower_adjacent_value, vals[0], q1)
return lower_adjacent_value, upper_adjacent_value
def set_axis_style(ax, labels):
ax.get_xaxis().set_tick_params(direction='out')
ax.xaxis.set_ticks_position('bottom')
ax.set_xticks(np.arange(1, len(labels) + 1))
ax.set_xticklabels(labels)
ax.set_xlim(0.25, len(labels) + 0.75)
ax.set_xlabel('Sample name')
# create test data
np.random.seed(19680801)
data = [sorted(np.random.normal(0, std, 100)) for std in range(1, 5)]
fig, (ax1, ax2) = plt.subplots(nrows=1, ncols=2, figsize=(9, 4), sharey=True)
ax1.set_title('Default violin plot')
ax1.set_ylabel('Observed values')
ax1.violinplot(data)
ax2.set_title('Customized violin plot')
parts = ax2.violinplot(
data, showmeans=False, showmedians=False,
showextrema=False)
for pc in parts['bodies']:
pc.set_facecolor('#D43F3A')
pc.set_edgecolor('black')
pc.set_alpha(1)
quartile1, medians, quartile3 = np.percentile(data, [25, 50, 75], axis=1)
whiskers = np.array([
adjacent_values(sorted_array, q1, q3)
for sorted_array, q1, q3 in zip(data, quartile1, quartile3)])
whiskersMin, whiskersMax = whiskers[:, 0], whiskers[:, 1]
inds = np.arange(1, len(medians) + 1)
ax2.scatter(inds, medians, marker='o', color='white', s=30, zorder=3)
ax2.vlines(inds, quartile1, quartile3, color='k', linestyle='-', lw=5)
ax2.vlines(inds, whiskersMin, whiskersMax, color='k', linestyle='-', lw=1)
# set style for the axes
labels = ['A', 'B', 'C', 'D']
for ax in [ax1, ax2]:
set_axis_style(ax, labels)
plt.subplots_adjust(bottom=0.15, wspace=0.05)
plt.show()
```
## 下载这个示例
- [下载python源码: customized_violin.py](https://matplotlib.org/_downloads/customized_violin.py)
- [下载Jupyter notebook: customized_violin.ipynb](https://matplotlib.org/_downloads/customized_violin.ipynb)

23
Python/matplotlab/gallery/statistics/errorbar.md Normal file
View File

@@ -0,0 +1,23 @@
# 误差条形图功能
这展示了误差条形图功能的最基本用法。在这种情况下，为x方向和y方向的误差提供常数值。
![误差条形图示例](https://matplotlib.org/_images/sphx_glr_errorbar_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
# example data
x = np.arange(0.1, 4, 0.5)
y = np.exp(-x)
fig, ax = plt.subplots()
ax.errorbar(x, y, xerr=0.2, yerr=0.4)
plt.show()
```
## 下载这个示例
- [下载python源码: errorbar.py](https://matplotlib.org/_downloads/errorbar.py)
- [下载Jupyter notebook: errorbar.ipynb](https://matplotlib.org/_downloads/errorbar.ipynb)

47
Python/matplotlab/gallery/statistics/errorbar_features.md Normal file
View File

@@ -0,0 +1,47 @@
# 误差条形图的不同方法
可以将错误指定为常数值(如errorbar_demo.py中所示)。但是，此示例通过指定错误值数组来演示它们的不同之处。
如果原始x和y数据的长度为N，则有两个选项：
1. 数组形状为(N,):
每个点的误差都不同，但误差值是对称的(即，上下两个值相等)。
1. 数组形状为(2, N):
每个点的误差不同，并且下限和上限(按该顺序)不同(非对称情况)。
此外，此示例演示如何使用带有误差线的对数刻度。
![](https://matplotlib.org/_images/sphx_glr_errorbar_features_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
# example data
x = np.arange(0.1, 4, 0.5)
y = np.exp(-x)
# example error bar values that vary with x-position
error = 0.1 + 0.2 * x
fig, (ax0, ax1) = plt.subplots(nrows=2, sharex=True)
ax0.errorbar(x, y, yerr=error, fmt='-o')
ax0.set_title('variable, symmetric error')
# error bar values w/ different -/+ errors that
# also vary with the x-position
lower_error = 0.4 * error
upper_error = error
asymmetric_error = [lower_error, upper_error]
ax1.errorbar(x, y, xerr=asymmetric_error, fmt='o')
ax1.set_title('variable, asymmetric error')
ax1.set_yscale('log')
plt.show()
```
## 下载这个示例
- [下载python源码: errorbar_features.py](https://matplotlib.org/_downloads/errorbar_features.py)
- [下载Jupyter notebook: errorbar_features.ipynb](https://matplotlib.org/_downloads/errorbar_features.ipynb)

73
Python/matplotlab/gallery/statistics/errorbar_limits.md Normal file
View File

@@ -0,0 +1,73 @@
# 误差条形图中的上限和下限
在matplotlib中，误差条可以有“限制”。对误差线应用限制实质上使误差单向。因此，可以分别通过``uplims``，``lolims``，``xuplims``和``xlolims``参数在y方向和x方向上应用上限和下限。 这些参数可以是标量或布尔数组。
例如，如果``xlolims``为``True``，则``x-error``条形将仅从数据扩展到递增值。如果``uplims``是一个填充了``False``的数组，除了第4和第7个值之外，所有y误差条都是双向的，除了第4和第7个条形，它们将从数据延伸到减小的y值。
![条形图限制示例](https://matplotlib.org/_images/sphx_glr_errorbar_limits_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
# example data
x = np.array([0.5, 1.0, 1.5, 2.0, 2.5, 3.0, 3.5, 4.0, 4.5, 5.0])
y = np.exp(-x)
xerr = 0.1
yerr = 0.2
# lower & upper limits of the error
lolims = np.array([0, 0, 1, 0, 1, 0, 0, 0, 1, 0], dtype=bool)
uplims = np.array([0, 1, 0, 0, 0, 1, 0, 0, 0, 1], dtype=bool)
ls = 'dotted'
fig, ax = plt.subplots(figsize=(7, 4))
# standard error bars
ax.errorbar(x, y, xerr=xerr, yerr=yerr, linestyle=ls)
# including upper limits
ax.errorbar(x, y + 0.5, xerr=xerr, yerr=yerr, uplims=uplims,
linestyle=ls)
# including lower limits
ax.errorbar(x, y + 1.0, xerr=xerr, yerr=yerr, lolims=lolims,
linestyle=ls)
# including upper and lower limits
ax.errorbar(x, y + 1.5, xerr=xerr, yerr=yerr,
lolims=lolims, uplims=uplims,
marker='o', markersize=8,
linestyle=ls)
# Plot a series with lower and upper limits in both x & y
# constant x-error with varying y-error
xerr = 0.2
yerr = np.zeros_like(x) + 0.2
yerr[[3, 6]] = 0.3
# mock up some limits by modifying previous data
xlolims = lolims
xuplims = uplims
lolims = np.zeros(x.shape)
uplims = np.zeros(x.shape)
lolims[[6]] = True # only limited at this index
uplims[[3]] = True # only limited at this index
# do the plotting
ax.errorbar(x, y + 2.1, xerr=xerr, yerr=yerr,
xlolims=xlolims, xuplims=xuplims,
uplims=uplims, lolims=lolims,
marker='o', markersize=8,
linestyle='none')
# tidy up the figure
ax.set_xlim((0, 5.5))
ax.set_title('Errorbar upper and lower limits')
plt.show()
```
## 下载这个示例
- [下载python源码: errorbar_limits.py](https://matplotlib.org/_downloads/errorbar_limits.py)
- [下载Jupyter notebook: errorbar_limits.ipynb](https://matplotlib.org/_downloads/errorbar_limits.ipynb)

68
Python/matplotlab/gallery/statistics/errorbars_and_boxes.md Normal file
View File

@@ -0,0 +1,68 @@
# 使用PatchCollection在误差图中创建箱型图
在这个例子中，我们通过在x方向和y方向上添加由条形极限定义的矩形块来拼写一个非常标准的误差条形图。为此，我们必须编写自己的自定义函数 ``make_error_boxes``。仔细检查此函数将揭示matplotlib编写函数的首选模式：
1. an Axes object is passed directly to the function
1. the function operates on the Axes methods directly, not through the ``pyplot`` interface
1. plotting kwargs that could be abbreviated are spelled out for better code readability in the future (for example we use ``facecolor`` instead of fc)
1. the artists returned by the Axes plotting methods are then returned by the function so that, if desired, their styles can be modified later outside of the function (they are not modified in this example).
![创建箱型图示例](https://matplotlib.org/_images/sphx_glr_errorbars_and_boxes_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.collections import PatchCollection
from matplotlib.patches import Rectangle
# Number of data points
n = 5
# Dummy data
np.random.seed(19680801)
x = np.arange(0, n, 1)
y = np.random.rand(n) * 5.
# Dummy errors (above and below)
xerr = np.random.rand(2, n) + 0.1
yerr = np.random.rand(2, n) + 0.2
def make_error_boxes(ax, xdata, ydata, xerror, yerror, facecolor='r',
edgecolor='None', alpha=0.5):
# Create list for all the error patches
errorboxes = []
# Loop over data points; create box from errors at each point
for x, y, xe, ye in zip(xdata, ydata, xerror.T, yerror.T):
rect = Rectangle((x - xe[0], y - ye[0]), xe.sum(), ye.sum())
errorboxes.append(rect)
# Create patch collection with specified colour/alpha
pc = PatchCollection(errorboxes, facecolor=facecolor, alpha=alpha,
edgecolor=edgecolor)
# Add collection to axes
ax.add_collection(pc)
# Plot errorbars
artists = ax.errorbar(xdata, ydata, xerr=xerror, yerr=yerror,
fmt='None', ecolor='k')
return artists
# Create figure and axes
fig, ax = plt.subplots(1)
# Call function to create error boxes
_ = make_error_boxes(ax, x, y, xerr, yerr)
plt.show()
```
## 下载这个示例
- [下载python源码: errorbars_and_boxes.py](https://matplotlib.org/_downloads/errorbars_and_boxes.py)
- [下载Jupyter notebook: errorbars_and_boxes.ipynb](https://matplotlib.org/_downloads/errorbars_and_boxes.ipynb)

46
Python/matplotlab/gallery/statistics/hexbin_demo.md Normal file
View File

@@ -0,0 +1,46 @@
# Hexbin 演示
使用Matplotlib绘制hexbins。
Hexbin是一种轴方法或pyplot函数，它基本上是具有六边形单元的二维直方图的pcolor。 它可以比散点图更具信息性。 在下面的第一个图中，尝试用'scatter'代替'hexbin'。
![Hexbin演示](https://matplotlib.org/_images/sphx_glr_hexbin_demo_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
# Fixing random state for reproducibility
np.random.seed(19680801)
n = 100000
x = np.random.standard_normal(n)
y = 2.0 + 3.0 * x + 4.0 * np.random.standard_normal(n)
xmin = x.min()
xmax = x.max()
ymin = y.min()
ymax = y.max()
fig, axs = plt.subplots(ncols=2, sharey=True, figsize=(7, 4))
fig.subplots_adjust(hspace=0.5, left=0.07, right=0.93)
ax = axs[0]
hb = ax.hexbin(x, y, gridsize=50, cmap='inferno')
ax.axis([xmin, xmax, ymin, ymax])
ax.set_title("Hexagon binning")
cb = fig.colorbar(hb, ax=ax)
cb.set_label('counts')
ax = axs[1]
hb = ax.hexbin(x, y, gridsize=50, bins='log', cmap='inferno')
ax.axis([xmin, xmax, ymin, ymax])
ax.set_title("With a log color scale")
cb = fig.colorbar(hb, ax=ax)
cb.set_label('log10(N)')
plt.show()
```
## 下载这个示例
- [下载python源码: hexbin_demo.py](https://matplotlib.org/_downloads/hexbin_demo.py)
- [下载Jupyter notebook: hexbin_demo.ipynb](https://matplotlib.org/_downloads/hexbin_demo.ipynb)

102
Python/matplotlab/gallery/statistics/hist.md Normal file
View File

@@ -0,0 +1,102 @@
# 直方图
演示如何使用matplotlib绘制直方图。
```python
import matplotlib.pyplot as plt
import numpy as np
from matplotlib import colors
from matplotlib.ticker import PercentFormatter
# Fixing random state for reproducibility
np.random.seed(19680801)
```
## 生成数据并绘制简单的直方图
要生成一维直方图，我们只需要一个数字矢量。对于二维直方图，我们需要第二个矢量。我们将在下面生成两者，并显示每个向量的直方图。
```python
N_points = 100000
n_bins = 20
# Generate a normal distribution, center at x=0 and y=5
x = np.random.randn(N_points)
y = .4 * x + np.random.randn(100000) + 5
fig, axs = plt.subplots(1, 2, sharey=True, tight_layout=True)
# We can set the number of bins with the `bins` kwarg
axs[0].hist(x, bins=n_bins)
axs[1].hist(y, bins=n_bins)
```
![直方图示例](https://matplotlib.org/_images/sphx_glr_hist_001.png)
## 更新直方图颜色
直方图方法(除其他外)返回一个修补程序对象。这使我们可以访问所绘制对象的特性。使用这个，我们可以根据自己的喜好编辑直方图。让我们根据每个条的y值更改其颜色。
```python
fig, axs = plt.subplots(1, 2, tight_layout=True)
# N is the count in each bin, bins is the lower-limit of the bin
N, bins, patches = axs[0].hist(x, bins=n_bins)
# We'll color code by height, but you could use any scalar
fracs = N / N.max()
# we need to normalize the data to 0..1 for the full range of the colormap
norm = colors.Normalize(fracs.min(), fracs.max())
# Now, we'll loop through our objects and set the color of each accordingly
for thisfrac, thispatch in zip(fracs, patches):
color = plt.cm.viridis(norm(thisfrac))
thispatch.set_facecolor(color)
# We can also normalize our inputs by the total number of counts
axs[1].hist(x, bins=n_bins, density=True)
# Now we format the y-axis to display percentage
axs[1].yaxis.set_major_formatter(PercentFormatter(xmax=1))
```
![直方图示例2](https://matplotlib.org/_images/sphx_glr_hist_002.png)
## 绘制二维直方图
要绘制二维直方图，只需两个长度相同的向量，对应于直方图的每个轴。
```python
fig, ax = plt.subplots(tight_layout=True)
hist = ax.hist2d(x, y)
```
![直方图示例3](https://matplotlib.org/_images/sphx_glr_hist_003.png)
## 自定义直方图
自定义2D直方图类似于1D情况，您可以控制可视组件，如存储箱大小或颜色规格化。
```python
fig, axs = plt.subplots(3, 1, figsize=(5, 15), sharex=True, sharey=True,
tight_layout=True)
# We can increase the number of bins on each axis
axs[0].hist2d(x, y, bins=40)
# As well as define normalization of the colors
axs[1].hist2d(x, y, bins=40, norm=colors.LogNorm())
# We can also define custom numbers of bins for each axis
axs[2].hist2d(x, y, bins=(80, 10), norm=colors.LogNorm())
plt.show()
```
![直方图示例4](https://matplotlib.org/_images/sphx_glr_hist_004.png)
## 下载这个示例
- [下载python源码: hist.py](https://matplotlib.org/_downloads/hist.py)
- [下载Jupyter notebook: hist.ipynb](https://matplotlib.org/_downloads/hist.ipynb)

55
Python/matplotlab/gallery/statistics/histogram_cumulative.md Normal file
View File

@@ -0,0 +1,55 @@
# 使用直方图绘制累积分布
这展示了如何绘制一个累积的、归一化的直方图作为一个步骤函数，以便可视化一个样本的经验累积分布函数(CDF)。文中还给出了理论上的CDF值。
演示了 ``hist`` 函数的其他几个选项。也就是说，我们使用 ``normed`` 参数来标准化直方图以及 ``累积`` 参数的几个不同选项。normed参数采用布尔值。 如果为 ``True`` ，则会对箱高进行缩放，使得柱状图的总面积为1。``累积``的kwarg稍微有些细微差别。与normed一样，您可以将其传递为True或False，但您也可以将其传递-1以反转分布。
由于我们显示了归一化和累积直方图，因此这些曲线实际上是样本的累积分布函数（CDF）。 在工程学中，经验CDF有时被称为“非超越”曲线。 换句话说，您可以查看给定-x值的y值，以使样本的概率和观察值不超过该x值。 例如，x轴上的值225对应于y轴上的约0.85，因此样本中的观察值不超过225的可能性为85％。相反，设置累积为-1，如同已完成 在此示例的最后一个系列中，创建“超出”曲线。
选择不同的箱数和大小会显着影响直方图的形状。Astropy文档有关于如何选择这些参数的重要部分：http://docs.astropy.org/en/stable/visualization/histogram.html
![使用直方图绘制累积分布](https://matplotlib.org/_images/sphx_glr_histogram_cumulative_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
np.random.seed(19680801)
mu = 200
sigma = 25
n_bins = 50
x = np.random.normal(mu, sigma, size=100)
fig, ax = plt.subplots(figsize=(8, 4))
# plot the cumulative histogram
n, bins, patches = ax.hist(x, n_bins, density=True, histtype='step',
cumulative=True, label='Empirical')
# Add a line showing the expected distribution.
y = ((1 / (np.sqrt(2 * np.pi) * sigma)) *
np.exp(-0.5 * (1 / sigma * (bins - mu))**2))
y = y.cumsum()
y /= y[-1]
ax.plot(bins, y, 'k--', linewidth=1.5, label='Theoretical')
# Overlay a reversed cumulative histogram.
ax.hist(x, bins=bins, density=True, histtype='step', cumulative=-1,
label='Reversed emp.')
# tidy up the figure
ax.grid(True)
ax.legend(loc='right')
ax.set_title('Cumulative step histograms')
ax.set_xlabel('Annual rainfall (mm)')
ax.set_ylabel('Likelihood of occurrence')
plt.show()
```
## 下载这个示例
- [下载python源码: histogram_cumulative.py](https://matplotlib.org/_downloads/histogram_cumulative.py)
- [下载Jupyter notebook: histogram_cumulative.ipynb](https://matplotlib.org/_downloads/histogram_cumulative.ipynb)

60
Python/matplotlab/gallery/statistics/histogram_features.md Normal file
View File

@@ -0,0 +1,60 @@
# 直方图(hist)函数的几个特性演示
除基本直方图外，此演示还显示了一些可选功能：
- 设置数据箱的数量。
- ``标准化``标志，用于标准化箱高度，使直方图的积分为1.得到的直方图是概率密度函数的近似值。
- 设置条形的面部颜色。
- 设置不透明度（alpha值）。
选择不同的存储量和大小会显著影响直方图的形状。Astropy文档有很多关于如何选择这些参数的部分。
```python
import matplotlib
import numpy as np
import matplotlib.pyplot as plt
np.random.seed(19680801)
# example data
mu = 100 # mean of distribution
sigma = 15 # standard deviation of distribution
x = mu + sigma * np.random.randn(437)
num_bins = 50
fig, ax = plt.subplots()
# the histogram of the data
n, bins, patches = ax.hist(x, num_bins, density=1)
# add a 'best fit' line
y = ((1 / (np.sqrt(2 * np.pi) * sigma)) *
np.exp(-0.5 * (1 / sigma * (bins - mu))**2))
ax.plot(bins, y, '--')
ax.set_xlabel('Smarts')
ax.set_ylabel('Probability density')
ax.set_title(r'Histogram of IQ: $\mu=100$, $\sigma=15$')
# Tweak spacing to prevent clipping of ylabel
fig.tight_layout()
plt.show()
```
![直方图特性演示](https://matplotlib.org/_images/sphx_glr_histogram_features_001.png)
## 参考
此示例显示了以下函数和方法的使用：
```python
matplotlib.axes.Axes.hist
matplotlib.axes.Axes.set_title
matplotlib.axes.Axes.set_xlabel
matplotlib.axes.Axes.set_ylabel
```
## 下载这个示例
- [下载python源码: histogram_features.py](https://matplotlib.org/_downloads/histogram_features.py)
- [下载Jupyter notebook: histogram_features.ipynb](https://matplotlib.org/_downloads/histogram_features.ipynb)

37
Python/matplotlab/gallery/statistics/histogram_histtypes.md Normal file
View File

@@ -0,0 +1,37 @@
# 演示直方图函数的不同histtype设置
- 具有颜色填充的步进曲线的直方图。
- 具有自定义和不相等的箱宽度的直方图。
选择不同的存储量和大小会显著影响直方图的形状。Astropy文档有很多关于如何选择这些参数的部分: http://docs.astropy.org/en/stable/visualization/histogram.html
![不同histtype设置示例](https://matplotlib.org/_images/sphx_glr_histogram_histtypes_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
np.random.seed(19680801)
mu = 200
sigma = 25
x = np.random.normal(mu, sigma, size=100)
fig, (ax0, ax1) = plt.subplots(ncols=2, figsize=(8, 4))
ax0.hist(x, 20, density=True, histtype='stepfilled', facecolor='g', alpha=0.75)
ax0.set_title('stepfilled')
# Create a histogram by providing the bin edges (unequally spaced).
bins = [100, 150, 180, 195, 205, 220, 250, 300]
ax1.hist(x, bins, density=True, histtype='bar', rwidth=0.8)
ax1.set_title('unequal bins')
fig.tight_layout()
plt.show()
```
## 下载这个示例
- [下载python源码: histogram_histtypes.py](https://matplotlib.org/_downloads/histogram_histtypes.py)
- [下载Jupyter notebook: histogram_histtypes.ipynb](https://matplotlib.org/_downloads/histogram_histtypes.ipynb)

50
Python/matplotlab/gallery/statistics/histogram_multihist.md Normal file
View File

@@ -0,0 +1,50 @@
# 使用多个数据集演示直方图(hist)函数
绘制具有多个样本集的直方图并演示：
- 使用带有多个样本集的图例
- 堆积图
- 没有填充的步进曲线
- 不同样本量的数据集
选择不同的存储量和大小会显著影响直方图的形状。Astropy文档有很多关于如何选择这些参数的部分: http://docs.astropy.org/en/stable/visualization/histogram.html
![多个数据集演示直方图](https://matplotlib.org/_images/sphx_glr_histogram_multihist_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
np.random.seed(19680801)
n_bins = 10
x = np.random.randn(1000, 3)
fig, axes = plt.subplots(nrows=2, ncols=2)
ax0, ax1, ax2, ax3 = axes.flatten()
colors = ['red', 'tan', 'lime']
ax0.hist(x, n_bins, density=True, histtype='bar', color=colors, label=colors)
ax0.legend(prop={'size': 10})
ax0.set_title('bars with legend')
ax1.hist(x, n_bins, density=True, histtype='bar', stacked=True)
ax1.set_title('stacked bar')
ax2.hist(x, n_bins, histtype='step', stacked=True, fill=False)
ax2.set_title('stack step (unfilled)')
# Make a multiple-histogram of data-sets with different length.
x_multi = [np.random.randn(n) for n in [10000, 5000, 2000]]
ax3.hist(x_multi, n_bins, histtype='bar')
ax3.set_title('different sample sizes')
fig.tight_layout()
plt.show()
```
## 下载这个示例
- [下载python源码: histogram_multihist.py](https://matplotlib.org/_downloads/histogram_multihist.py)
- [下载Jupyter notebook: histogram_multihist.ipynb](https://matplotlib.org/_downloads/histogram_multihist.ipynb)

57
Python/matplotlab/gallery/statistics/multiple_histograms_side_by_side.md Normal file
View File

@@ -0,0 +1,57 @@
# 并排生成多个直方图
此示例沿范畴x轴绘制不同样本的水平直方图。此外，直方图被绘制成与它们的x位置对称，从而使它们与小提琴图非常相似。
为了使这个高度专门化的绘制，我们不能使用标准的 ``hist`` 方法。相反，我们使用 ``barh`` 直接绘制水平线。通过 ``np.histogram`` 函数计算棒材的垂直位置和长度。使用相同的范围(最小和最大值)和存储箱数量计算所有采样的直方图，以便每个采样的存储箱位于相同的垂直位置。
选择不同的存储量和大小会显著影响直方图的形状。Astropy文档有很多关于如何选择这些参数的部分: http://docs.astropy.org/en/stable/visualization/histogram.html
![并排生成多个直方图示例](https://matplotlib.org/_images/sphx_glr_multiple_histograms_side_by_side_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
np.random.seed(19680801)
number_of_bins = 20
# An example of three data sets to compare
number_of_data_points = 387
labels = ["A", "B", "C"]
data_sets = [np.random.normal(0, 1, number_of_data_points),
np.random.normal(6, 1, number_of_data_points),
np.random.normal(-3, 1, number_of_data_points)]
# Computed quantities to aid plotting
hist_range = (np.min(data_sets), np.max(data_sets))
binned_data_sets = [
np.histogram(d, range=hist_range, bins=number_of_bins)[0]
for d in data_sets
]
binned_maximums = np.max(binned_data_sets, axis=1)
x_locations = np.arange(0, sum(binned_maximums), np.max(binned_maximums))
# The bin_edges are the same for all of the histograms
bin_edges = np.linspace(hist_range[0], hist_range[1], number_of_bins + 1)
centers = 0.5 * (bin_edges + np.roll(bin_edges, 1))[:-1]
heights = np.diff(bin_edges)
# Cycle through and plot each histogram
fig, ax = plt.subplots()
for x_loc, binned_data in zip(x_locations, binned_data_sets):
lefts = x_loc - 0.5 * binned_data
ax.barh(centers, binned_data, height=heights, left=lefts)
ax.set_xticks(x_locations)
ax.set_xticklabels(labels)
ax.set_ylabel("Data values")
ax.set_xlabel("Data sets")
plt.show()
```
## 下载这个示例
- [下载python源码: multiple_histograms_side_by_side.py](https://matplotlib.org/_downloads/multiple_histograms_side_by_side.py)
- [下载Jupyter notebook: multiple_histograms_side_by_side.ipynb](https://matplotlib.org/_downloads/multiple_histograms_side_by_side.ipynb)

63
Python/matplotlab/gallery/statistics/violinplot.md Normal file
View File

@@ -0,0 +1,63 @@
# 小提琴图基础
小提琴图类似于直方图和箱形图，因为它们显示了样本概率分布的抽象表示。小提琴图使用核密度估计（KDE）来计算样本的经验分布，而不是显示属于分类或顺序统计的数据点的计数。该计算由几个参数控制。此示例演示如何修改评估KDE的点数 ``(points)`` 以及如何修改KDE ``（bw_method）`` 的带宽。
有关小提琴图和KDE的更多信息，请参阅scikit-learn文档
有一个很棒的部分：http://scikit-learn.org/stable/modules/density.html
![小提琴图基础示例](https://matplotlib.org/_images/sphx_glr_violinplot_001.png)
```python
import numpy as np
import matplotlib.pyplot as plt
# Fixing random state for reproducibility
np.random.seed(19680801)
# fake data
fs = 10 # fontsize
pos = [1, 2, 4, 5, 7, 8]
data = [np.random.normal(0, std, size=100) for std in pos]
fig, axes = plt.subplots(nrows=2, ncols=3, figsize=(6, 6))
axes[0, 0].violinplot(data, pos, points=20, widths=0.3,
showmeans=True, showextrema=True, showmedians=True)
axes[0, 0].set_title('Custom violinplot 1', fontsize=fs)
axes[0, 1].violinplot(data, pos, points=40, widths=0.5,
showmeans=True, showextrema=True, showmedians=True,
bw_method='silverman')
axes[0, 1].set_title('Custom violinplot 2', fontsize=fs)
axes[0, 2].violinplot(data, pos, points=60, widths=0.7, showmeans=True,
showextrema=True, showmedians=True, bw_method=0.5)
axes[0, 2].set_title('Custom violinplot 3', fontsize=fs)
axes[1, 0].violinplot(data, pos, points=80, vert=False, widths=0.7,
showmeans=True, showextrema=True, showmedians=True)
axes[1, 0].set_title('Custom violinplot 4', fontsize=fs)
axes[1, 1].violinplot(data, pos, points=100, vert=False, widths=0.9,
showmeans=True, showextrema=True, showmedians=True,
bw_method='silverman')
axes[1, 1].set_title('Custom violinplot 5', fontsize=fs)
axes[1, 2].violinplot(data, pos, points=200, vert=False, widths=1.1,
showmeans=True, showextrema=True, showmedians=True,
bw_method=0.5)
axes[1, 2].set_title('Custom violinplot 6', fontsize=fs)
for ax in axes.flatten():
ax.set_yticklabels([])
fig.suptitle("Violin Plotting Examples")
fig.subplots_adjust(hspace=0.4)
plt.show()
```
## 下载这个示例
- [下载python源码: violinplot.py](https://matplotlib.org/_downloads/violinplot.py)
- [下载Jupyter notebook: violinplot.ipynb](https://matplotlib.org/_downloads/violinplot.ipynb)