|
| 1 | +import pandas as pd |
| 2 | + |
| 3 | +# 加载数据 |
| 4 | +tag_df = pd.read_csv('D:/my/crawler_html2pdf/juejin/tag.csv') |
| 5 | + |
| 6 | +# 排序 |
| 7 | +sorted_tags = tag_df.sort_values(by=['viewsCount'], ascending=False) |
| 8 | +languages = ['Android', 'iOS', 'Java', 'Python', 'Ruby', 'Swift', 'Go', 'Dart', 'Objective-C', 'C', 'C++', 'C#', 'PHP', |
| 9 | + 'JavaScript', 'Perl', 'VB', 'R', 'MATLAB', 'Groovy', "Scala"] |
| 10 | + |
| 11 | +lang_tags = sorted_tags[sorted_tags["title"].isin(languages)] |
| 12 | + |
| 13 | +lang_tags = lang_tags[['title', 'viewsCount']] |
| 14 | +lang_tags.drop(177, axis=0, inplace=True) |
| 15 | + |
| 16 | +rules = {'前端': 'JavaScript'} |
| 17 | +lang_tags['title'].replace(rules, inplace=True) |
| 18 | + |
| 19 | +titles = lang_tags.ix[:, 0].values |
| 20 | + |
| 21 | +lang_tags.set_index(titles, inplace=True) |
| 22 | +lang_tags.drop('title', inplace=True, axis=1) |
| 23 | +print(lang_tags) |
| 24 | +lang_tags.to_csv("xx.csv") |
| 25 | +lang_tags.plot.pie(subplots=True, figsize=(8, 4)) |
| 26 | + |
| 27 | +# |
| 28 | +# import cufflinks as cf |
| 29 | +# |
| 30 | +# cf.set_config_file(world_readable=True,offline=False) |
| 31 | +# |
| 32 | +# pie = cf.datagen.pie() |
| 33 | +# pie.head() |
| 34 | + |
| 35 | + |
| 36 | +jd = ["前端", "后端", "Android", "iOS", "设计", "产品", "测试", "运营"] |
0 commit comments