matplotlib - 百分位分布图

Question

有谁知道如何更改 X 轴刻度和刻度以显示如下图所示的百分位数分布？该图像来自 MATLAB，但我想使用 Python(通过 Matplotlib 或 Seaborn)生成。

从@paulh 的指针来看，我现在更接近了。这段代码

import matplotlib
matplotlib.use('Agg')

import numpy as np
import matplotlib.pyplot as plt
import probscale
import seaborn as sns

clear_bkgd = {'axes.facecolor':'none', 'figure.facecolor':'none'}
sns.set(style='ticks', context='notebook', palette="muted", rc=clear_bkgd)

fig, ax = plt.subplots(figsize=(8, 4))

x = [30, 60, 80, 90, 95, 97, 98, 98.5, 98.9, 99.1, 99.2, 99.3, 99.4]
y = np.arange(0, 12.1, 1)

ax.set_xlim(40, 99.5)
ax.set_xscale('prob')

ax.plot(x, y)
sns.despine(fig=fig)

生成以下图(注意重新分布的 X 轴)

我发现它比标准量表有用得多:

我联系了原始图表的作者，他们给了我一些指导。它实际上是一个对数刻度图，x 轴反转，值为 [100-val]，并手动标记 x 轴刻度。下面的代码使用与此处其他图表相同的示例数据重新创建原始图像。

import matplotlib
matplotlib.use('Agg')

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

clear_bkgd = {'axes.facecolor':'none', 'figure.facecolor':'none'}
sns.set(style='ticks', context='notebook', palette="muted", rc=clear_bkgd)

x = [30, 60, 80, 90, 95, 97, 98, 98.5, 98.9, 99.1, 99.2, 99.3, 99.4]
y = np.arange(0, 12.1, 1)

# Number of intervals to display.
# Later calculations add 2 to this number to pad it to align with the reversed axis
num_intervals = 3
x_values = 1.0 - 1.0/10**np.arange(0,num_intervals+2)

# Start with hard-coded lengths for 0,90,99
# Rest of array generated to display correct number of decimal places as precision increases
lengths = [1,2,2] + [int(v)+1 for v in list(np.arange(3,num_intervals+2))]

# Build the label string by trimming on the calculated lengths and appending %
labels = [str(100*v)[0:l] + "%" for v,l in zip(x_values, lengths)]


fig, ax = plt.subplots(figsize=(8, 4))

ax.set_xscale('log')
plt.gca().invert_xaxis()
# Labels have to be reversed because axis is reversed
ax.xaxis.set_ticklabels( labels[::-1] )

ax.plot([100.0 - v for v in x], y)

ax.grid(True, linewidth=0.5, zorder=5)
ax.grid(True, which='minor', linewidth=0.5, linestyle=':')

sns.despine(fig=fig)

plt.savefig("test.png", dpi=300, format='png')

这是结果图:

Answer 1

以下 Python 代码使用 Pandas读取包含记录延迟值(以毫秒为单位)列表的 csv 文件，然后将这些延迟值(以微秒为单位)记录在 HdrHistogram 中，并将 HdrHistogram 保存到 hgrm文件，然后将由 Seaborn 使用至plot延迟分布图。

import pandas as pd
from hdrh.histogram import HdrHistogram
from hdrh.dump import dump
import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns
import sys
import argparse

# Parse the command line arguments.

parser = argparse.ArgumentParser()
parser.add_argument('csv_file')
parser.add_argument('hgrm_file')
parser.add_argument('png_file')
args = parser.parse_args()

csv_file = args.csv_file
hgrm_file = args.hgrm_file
png_file = args.png_file

# Read the csv file into a Pandas data frame and generate an hgrm file.

csv_df = pd.read_csv(csv_file, index_col=False)

USECS_PER_SEC=1000000
MIN_LATENCY_USECS = 1
MAX_LATENCY_USECS = 24 * 60 * 60 * USECS_PER_SEC # 24 hours
# MAX_LATENCY_USECS = int(csv_df['response-time'].max()) * USECS_PER_SEC # 1 hour
LATENCY_SIGNIFICANT_DIGITS = 5
histogram = HdrHistogram(MIN_LATENCY_USECS, MAX_LATENCY_USECS, LATENCY_SIGNIFICANT_DIGITS)
for latency_sec in csv_df['response-time'].tolist():
    histogram.record_value(latency_sec*USECS_PER_SEC)
    # histogram.record_corrected_value(latency_sec*USECS_PER_SEC, 10)
TICKS_PER_HALF_DISTANCE=5
histogram.output_percentile_distribution(open(hgrm_file, 'wb'), USECS_PER_SEC, TICKS_PER_HALF_DISTANCE)

# Read the generated hgrm file into a Pandas data frame.

hgrm_df = pd.read_csv(hgrm_file, comment='#', skip_blank_lines=True, sep=r"\s+", engine='python', header=0, names=['Latency', 'Percentile'], usecols=[0, 3])

# Plot the latency distribution using Seaborn and save it as a png file.

sns.set_theme()
sns.set_style("dark")
sns.set_context("paper")
sns.set_color_codes("pastel")

fig, ax = plt.subplots(1,1,figsize=(20,15))
fig.suptitle('Latency Results')

sns.lineplot(x='Percentile', y='Latency', data=hgrm_df, ax=ax)
ax.set_title('Latency Distribution')
ax.set_xlabel('Percentile (%)')
ax.set_ylabel('Latency (seconds)')
ax.set_xscale('log')
ax.set_xticks([1, 10, 100, 1000, 10000, 100000, 1000000, 10000000])
ax.set_xticklabels(['0', '90', '99', '99.9', '99.99', '99.999', '99.9999', '99.99999'])

fig.tight_layout()
fig.savefig(png_file)