各projectの被リンク数histogram

https://gyazo.com/b566d14014f35d98cf27386ca519f20d

横軸のメモリ幅を統一したほうが比較しやすい

使用したscript

code:plot.py

from __future__ import print_function

from __future__ import unicode_literals

import requests

import matplotlib.pyplot as plt

import matplotlib as mpl

import collections

import argparse

mpl.use("Agg")

# matplotlibで日本語を使えるようにする

def main(project):

pages = []

response = requests.get(

followingId = response.headers.get('X-Following-Id')

pages += response.json()

while followingId == None:

response = requests.get(

followingId = response.headers.get('X-Following-Id')

pages += response.json()

pass

print('Finish loading all data')

# 取得結果の確認

for page in pages:

print('Calculating the number of back links...')

temp = []

for page in pages:

linkNum = collections.Counter(temp);

print(linkNum)

print('finished.')

print('Plotting a histogram...')

n, bins, patches = plt.hist(linkNum.values(), bins=max(linkNum.values())-min(linkNum.values()), log=True)

for i in range(len(bins)-1)]

ax=plt.gca()

ax.set_title(project)

ax.set_xlabel('被リンク数')

ax.set_ylabel('ページ数')

plt.savefig(f'{project}.png')

print('finished.')

if __name__ == "__main__":

# Command line argumentsの設定

parser = argparse.ArgumentParser(

description="指定したscrapbox projectの被リンク数のhistogramを作成するscript")

parser.add_argument('project',help='分析したいscrapbox project name')

# argumentsを解析する

args = parser.parse_args()

project = args.project

# main loop

main(project)