python 用于数据分析的Python - 第2章 - 示例

Posted 2021-05-10

import json
from pandas import DataFrame, Series
import pandas as pd
path = 'usagov_bitly_data2012-03-16-1331923249.txt'
records = [json.loads(line) for line in open(path)]

time_zones = [rec['tz'] for rec in records if 'tz' in rec]
frame = DataFrame(records)
clean_tz = frame['tz'].fillna('Missing')
clean_tz[clean_tz == ''] = 'Unknown'
tz_counts = clean_tz.value_counts()
tz_counts[:10]
tz_counts[:10].plot(kind='barh', rot = 0)
plt.show()
results = Series([x.split()[0] for x in frame.a.dropna()])
results.value_counts()[:8]
cframe = frame[frame.a.notnull()]
oper_system = np.where(cframe['a'].str.contains('Windows'), 'Windows', 'Not Windows')
oper_system[:10]
by_tz_os = cframe.groupby(['tz', oper_system])
agg_counts = by_tz_os.size().unstack().fillna(0)
agg_counts[:10]
indexer = agg_counts.sum(1).argsort()
indexer[:10]
count_subset = agg_counts.take(indexer)[-10:]
count_subset
normed_subset = count_subset.div(count_subset.sum(1), axis=0)
normed_subset.plot(kind='barh', stacked = True)