pyxllib 0.3.197__py3-none-any.whl → 3.201.1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- pyxllib/__init__.py +14 -21
- pyxllib/algo/__init__.py +8 -8
- pyxllib/algo/disjoint.py +54 -54
- pyxllib/algo/geo.py +537 -541
- pyxllib/algo/intervals.py +964 -964
- pyxllib/algo/matcher.py +389 -389
- pyxllib/algo/newbie.py +166 -166
- pyxllib/algo/pupil.py +629 -629
- pyxllib/algo/shapelylib.py +67 -67
- pyxllib/algo/specialist.py +241 -241
- pyxllib/algo/stat.py +494 -494
- pyxllib/algo/treelib.py +145 -149
- pyxllib/algo/unitlib.py +62 -66
- pyxllib/autogui/__init__.py +5 -5
- pyxllib/autogui/activewin.py +246 -246
- pyxllib/autogui/all.py +9 -9
- pyxllib/autogui/autogui.py +846 -852
- pyxllib/autogui/uiautolib.py +362 -362
- pyxllib/autogui/virtualkey.py +102 -102
- pyxllib/autogui/wechat.py +827 -827
- pyxllib/autogui/wechat_msg.py +421 -421
- pyxllib/autogui/wxautolib.py +84 -84
- pyxllib/cv/__init__.py +5 -5
- pyxllib/cv/expert.py +267 -267
- pyxllib/cv/imfile.py +159 -159
- pyxllib/cv/imhash.py +39 -39
- pyxllib/cv/pupil.py +9 -9
- pyxllib/cv/rgbfmt.py +1525 -1525
- pyxllib/cv/slidercaptcha.py +137 -137
- pyxllib/cv/trackbartools.py +251 -251
- pyxllib/cv/xlcvlib.py +1040 -1040
- pyxllib/cv/xlpillib.py +423 -423
- pyxllib/data/echarts.py +236 -240
- pyxllib/data/jsonlib.py +85 -89
- pyxllib/data/oss.py +72 -72
- pyxllib/data/pglib.py +1111 -1127
- pyxllib/data/sqlite.py +568 -568
- pyxllib/data/sqllib.py +297 -297
- pyxllib/ext/JLineViewer.py +505 -505
- pyxllib/ext/__init__.py +6 -6
- pyxllib/ext/demolib.py +251 -246
- pyxllib/ext/drissionlib.py +277 -277
- pyxllib/ext/kq5034lib.py +12 -12
- pyxllib/ext/qt.py +449 -449
- pyxllib/ext/robustprocfile.py +493 -497
- pyxllib/ext/seleniumlib.py +76 -76
- pyxllib/ext/tk.py +173 -173
- pyxllib/ext/unixlib.py +821 -827
- pyxllib/ext/utools.py +345 -351
- pyxllib/ext/webhook.py +124 -119
- pyxllib/ext/win32lib.py +40 -40
- pyxllib/ext/wjxlib.py +91 -88
- pyxllib/ext/wpsapi.py +124 -124
- pyxllib/ext/xlwork.py +9 -9
- pyxllib/ext/yuquelib.py +1110 -1105
- pyxllib/file/__init__.py +17 -17
- pyxllib/file/docxlib.py +757 -761
- pyxllib/file/gitlib.py +309 -309
- pyxllib/file/libreoffice.py +165 -165
- pyxllib/file/movielib.py +144 -148
- pyxllib/file/newbie.py +10 -10
- pyxllib/file/onenotelib.py +1469 -1469
- pyxllib/file/packlib/__init__.py +330 -330
- pyxllib/file/packlib/zipfile.py +2441 -2441
- pyxllib/file/pdflib.py +422 -426
- pyxllib/file/pupil.py +185 -185
- pyxllib/file/specialist/__init__.py +681 -685
- pyxllib/file/specialist/dirlib.py +799 -799
- pyxllib/file/specialist/download.py +193 -193
- pyxllib/file/specialist/filelib.py +2825 -2829
- pyxllib/file/xlsxlib.py +3122 -3131
- pyxllib/file/xlsyncfile.py +341 -341
- pyxllib/prog/__init__.py +5 -5
- pyxllib/prog/cachetools.py +58 -64
- pyxllib/prog/deprecatedlib.py +233 -233
- pyxllib/prog/filelock.py +42 -42
- pyxllib/prog/ipyexec.py +253 -253
- pyxllib/prog/multiprogs.py +940 -940
- pyxllib/prog/newbie.py +451 -451
- pyxllib/prog/pupil.py +1208 -1197
- pyxllib/prog/sitepackages.py +33 -33
- pyxllib/prog/specialist/__init__.py +348 -391
- pyxllib/prog/specialist/bc.py +203 -203
- pyxllib/prog/specialist/browser.py +497 -497
- pyxllib/prog/specialist/common.py +347 -347
- pyxllib/prog/specialist/datetime.py +198 -198
- pyxllib/prog/specialist/tictoc.py +240 -240
- pyxllib/prog/specialist/xllog.py +180 -180
- pyxllib/prog/xlosenv.py +110 -108
- pyxllib/stdlib/__init__.py +17 -17
- pyxllib/stdlib/tablepyxl/__init__.py +10 -10
- pyxllib/stdlib/tablepyxl/style.py +303 -303
- pyxllib/stdlib/tablepyxl/tablepyxl.py +130 -130
- pyxllib/text/__init__.py +8 -8
- pyxllib/text/ahocorasick.py +36 -39
- pyxllib/text/airscript.js +754 -744
- pyxllib/text/charclasslib.py +121 -121
- pyxllib/text/jiebalib.py +267 -267
- pyxllib/text/jinjalib.py +27 -32
- pyxllib/text/jsa_ai_prompt.md +271 -271
- pyxllib/text/jscode.py +922 -922
- pyxllib/text/latex/__init__.py +158 -158
- pyxllib/text/levenshtein.py +303 -303
- pyxllib/text/nestenv.py +1215 -1215
- pyxllib/text/newbie.py +300 -300
- pyxllib/text/pupil/__init__.py +8 -8
- pyxllib/text/pupil/common.py +1121 -1121
- pyxllib/text/pupil/xlalign.py +326 -326
- pyxllib/text/pycode.py +47 -47
- pyxllib/text/specialist/__init__.py +8 -8
- pyxllib/text/specialist/common.py +112 -112
- pyxllib/text/specialist/ptag.py +186 -186
- pyxllib/text/spellchecker.py +172 -172
- pyxllib/text/templates/echart_base.html +10 -10
- pyxllib/text/templates/highlight_code.html +16 -16
- pyxllib/text/templates/latex_editor.html +102 -102
- pyxllib/text/vbacode.py +17 -17
- pyxllib/text/xmllib.py +741 -747
- pyxllib/xl.py +42 -39
- pyxllib/xlcv.py +17 -17
- pyxllib-3.201.1.dist-info/METADATA +296 -0
- pyxllib-3.201.1.dist-info/RECORD +125 -0
- {pyxllib-0.3.197.dist-info → pyxllib-3.201.1.dist-info}/licenses/LICENSE +190 -190
- pyxllib/ext/old.py +0 -663
- pyxllib-0.3.197.dist-info/METADATA +0 -48
- pyxllib-0.3.197.dist-info/RECORD +0 -126
- {pyxllib-0.3.197.dist-info → pyxllib-3.201.1.dist-info}/WHEEL +0 -0
@@ -1,347 +1,347 @@
|
|
1
|
-
#!/usr/bin/env python3
|
2
|
-
# -*- coding: utf-8 -*-
|
3
|
-
# @Author : 陈坤泽
|
4
|
-
# @Email : 877362867@qq.com
|
5
|
-
# @Date : 2020/06/02 11:09
|
6
|
-
|
7
|
-
from collections import defaultdict, Counter
|
8
|
-
import copy
|
9
|
-
import re
|
10
|
-
import sys
|
11
|
-
|
12
|
-
import pandas as pd
|
13
|
-
from more_itertools import unique_everseen
|
14
|
-
|
15
|
-
from pyxllib.prog.newbie import typename
|
16
|
-
from pyxllib.algo.pupil import natural_sort_key
|
17
|
-
from pyxllib.text.pupil import shorten, east_asian_shorten
|
18
|
-
|
19
|
-
|
20
|
-
def dataframe_str(df, *args, ambiguous_as_wide=None, shorten=True):
|
21
|
-
"""输出DataFrame
|
22
|
-
DataFrame可以直接输出的,这里是增加了对中文字符的对齐效果支持
|
23
|
-
|
24
|
-
:param df: DataFrame数据结构
|
25
|
-
:param args: option_context格式控制
|
26
|
-
:param ambiguous_as_wide: 是否对①②③这种域宽有歧义的设为宽字符
|
27
|
-
win32平台上和linux上①域宽不同,默认win32是域宽2,linux是域宽1
|
28
|
-
:param shorten: 是否对每个元素提前进行字符串化并控制长度在display.max_colwidth以内
|
29
|
-
因为pandas的字符串截取遇到中文是有问题的,可以用我自定义的函数先做截取
|
30
|
-
默认开启,不过这步比较消耗时间
|
31
|
-
|
32
|
-
>> df = pd.DataFrame({'哈哈': ['a'*100, '哈\n①'*10, 'a哈'*100]})
|
33
|
-
哈哈
|
34
|
-
0 aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa...
|
35
|
-
1 哈 ①哈 ①哈 ①哈 ①哈 ①哈 ①哈 ①哈 ①哈 ①...
|
36
|
-
2 a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a...
|
37
|
-
"""
|
38
|
-
import pandas as pd
|
39
|
-
|
40
|
-
if ambiguous_as_wide is None:
|
41
|
-
ambiguous_as_wide = sys.platform == 'win32'
|
42
|
-
with pd.option_context('display.unicode.east_asian_width', True, # 中文输出必备选项,用来控制正确的域宽
|
43
|
-
'display.unicode.ambiguous_as_wide', ambiguous_as_wide,
|
44
|
-
'max_columns', 20, # 最大列数设置到20列
|
45
|
-
'display.width', 200, # 最大宽度设置到200
|
46
|
-
*args):
|
47
|
-
if shorten: # applymap可以对所有的元素进行映射处理,并返回一个新的df
|
48
|
-
df = df.applymap(lambda x: east_asian_shorten(str(x), pd.options.display.max_colwidth))
|
49
|
-
s = str(df)
|
50
|
-
return s
|
51
|
-
|
52
|
-
|
53
|
-
class TypeConvert:
|
54
|
-
@classmethod
|
55
|
-
def dict2list(cls, d: dict, *, nsort=False):
|
56
|
-
""" 字典转n*2的list
|
57
|
-
|
58
|
-
:param d: 字典
|
59
|
-
:param nsort:
|
60
|
-
True: 对key使用自然排序
|
61
|
-
False: 使用d默认的遍历顺序
|
62
|
-
:return:
|
63
|
-
"""
|
64
|
-
ls = list(d.items())
|
65
|
-
if nsort:
|
66
|
-
ls = sorted(ls, key=lambda x: natural_sort_key(str(x[0])))
|
67
|
-
return ls
|
68
|
-
|
69
|
-
@classmethod
|
70
|
-
def dict2df(cls, d):
|
71
|
-
"""dict类型转DataFrame类型"""
|
72
|
-
name = typename(d)
|
73
|
-
if isinstance(d, Counter):
|
74
|
-
li = d.most_common()
|
75
|
-
else:
|
76
|
-
li = cls.dict2list(d, nsort=True)
|
77
|
-
return pd.DataFrame.from_records(li, columns=(f'{name}-key', f'{name}-value'))
|
78
|
-
|
79
|
-
@classmethod
|
80
|
-
def list2df(cls, li):
|
81
|
-
if li and isinstance(li[0], (list, tuple)): # 有两维时按表格显示
|
82
|
-
df = pd.DataFrame.from_records(li)
|
83
|
-
else: # 只有一维时按一列显示
|
84
|
-
df = pd.DataFrame(pd.Series(li), columns=(typename(li),))
|
85
|
-
return df
|
86
|
-
|
87
|
-
@classmethod
|
88
|
-
def try2df(cls, arg):
|
89
|
-
"""尝试将各种不同的类型转成dataframe"""
|
90
|
-
if isinstance(arg, dict):
|
91
|
-
df = cls.dict2df(arg)
|
92
|
-
elif isinstance(arg, (list, tuple)):
|
93
|
-
df = cls.list2df(arg)
|
94
|
-
elif isinstance(arg, pd.Series):
|
95
|
-
df = pd.DataFrame(arg)
|
96
|
-
else:
|
97
|
-
df = arg
|
98
|
-
return df
|
99
|
-
|
100
|
-
|
101
|
-
class NestedDict:
|
102
|
-
""" 字典嵌套结构相关功能
|
103
|
-
|
104
|
-
TODO 感觉跟 pprint 的嵌套识别美化输出相关,可能有些代码是可以结合简化的~~
|
105
|
-
"""
|
106
|
-
|
107
|
-
@classmethod
|
108
|
-
def has_subdict(cls, data, include_self=True):
|
109
|
-
"""是否含有dict子结构
|
110
|
-
:param include_self: 是否包含自身,即data本身是一个dict的话,也认为has_subdict是True
|
111
|
-
"""
|
112
|
-
if include_self and isinstance(data, dict):
|
113
|
-
return True
|
114
|
-
elif isinstance(data, (list, tuple, set)):
|
115
|
-
for v in data:
|
116
|
-
if cls.has_subdict(v):
|
117
|
-
return True
|
118
|
-
return False
|
119
|
-
|
120
|
-
@classmethod
|
121
|
-
def to_html_table(cls, data, max_items=10):
|
122
|
-
""" 以html表格套表格的形式,展示一个嵌套结构数据
|
123
|
-
|
124
|
-
:param data: 数据
|
125
|
-
:param max_items: 项目显示上限,有些数据项目太多了,要精简下
|
126
|
-
设为假值则不设上限
|
127
|
-
:return:
|
128
|
-
|
129
|
-
TODO 这个速度有点慢,怎么加速?
|
130
|
-
"""
|
131
|
-
|
132
|
-
def tohtml(d):
|
133
|
-
if max_items:
|
134
|
-
df = TypeConvert.try2df(d)
|
135
|
-
if len(df) > max_items:
|
136
|
-
n = len(df)
|
137
|
-
return df[:max_items].to_html(escape=False) + f'... {n - 1}'
|
138
|
-
else:
|
139
|
-
return df.to_html(escape=False)
|
140
|
-
else:
|
141
|
-
return TypeConvert.try2df(d).to_html(escape=False)
|
142
|
-
|
143
|
-
if not cls.has_subdict(data):
|
144
|
-
res = str(data)
|
145
|
-
elif isinstance(data, dict):
|
146
|
-
if isinstance(data, Counter):
|
147
|
-
d = data
|
148
|
-
else:
|
149
|
-
d = dict()
|
150
|
-
for k, v in data.items():
|
151
|
-
if cls.has_subdict(v):
|
152
|
-
v = cls.to_html_table(v, max_items=max_items)
|
153
|
-
d[k] = v
|
154
|
-
res = tohtml(d)
|
155
|
-
else:
|
156
|
-
li = [cls.to_html_table(x, max_items=max_items) for x in data]
|
157
|
-
res = tohtml(li)
|
158
|
-
|
159
|
-
return res.replace('\n', ' ')
|
160
|
-
|
161
|
-
|
162
|
-
class KeyValuesCounter:
|
163
|
-
""" 各种键值对出现次数的统计
|
164
|
-
会递归找子字典结构,但不存储结构信息,只记录纯粹的键值对信息
|
165
|
-
|
166
|
-
应用场景:对未知的json结构,批量读取后,显示所有键值对的出现情况
|
167
|
-
"""
|
168
|
-
|
169
|
-
def __init__(self):
|
170
|
-
self.kvs = defaultdict(Counter)
|
171
|
-
|
172
|
-
def add(self, data, max_value_length=100):
|
173
|
-
"""
|
174
|
-
:param max_value_length: 添加的值,进行截断,防止有些值太长
|
175
|
-
"""
|
176
|
-
if not NestedDict.has_subdict(data):
|
177
|
-
return
|
178
|
-
elif isinstance(data, dict):
|
179
|
-
for k, v in data.items():
|
180
|
-
if NestedDict.has_subdict(v):
|
181
|
-
self.add(v)
|
182
|
-
else:
|
183
|
-
self.kvs[k][shorten(str(v), max_value_length)] += 1
|
184
|
-
else: # 否则 data 应该是个可迭代对象,才可能含有dict
|
185
|
-
for x in data:
|
186
|
-
self.add(x)
|
187
|
-
|
188
|
-
def to_html_table(self, max_items=10):
|
189
|
-
return NestedDict.to_html_table(self.kvs, max_items=max_items)
|
190
|
-
|
191
|
-
|
192
|
-
class JsonStructParser:
|
193
|
-
""" 类json数据格式的结构解析
|
194
|
-
|
195
|
-
【名称定义】
|
196
|
-
item: 一条类json的数据条目
|
197
|
-
path: 用类路径的格式,表达item中某个数值的索引。例如
|
198
|
-
/a/b/3/c: 相当于 item['a']['b'][3]['c']
|
199
|
-
有一些特殊的path,例如容器类会以/结尾: /a/
|
200
|
-
以及一般会带上数值的类型标记,区分度更精确:/a/=dict
|
201
|
-
pathx: 泛指下述中某种格式
|
202
|
-
pathlist: list, 一条item对应的扁平化的路径
|
203
|
-
pathstr/struct: paths拼接成一个str
|
204
|
-
pathdict: paths重新组装成一个dict字典(未实装,太难写,性价比也低)
|
205
|
-
"""
|
206
|
-
|
207
|
-
default_cfg = {'include_container': True, # 包含容器(dict、list)的路径
|
208
|
-
'value_type': True, # 是否带上后缀:数值的类型
|
209
|
-
# 可以输入一个自定义的路径合并函数 path,type=merge_path(path,type)。
|
210
|
-
# 一般是字典中出现不断变化的数值id,格式不统一,使用一定的规则,可以将path几种相近的冗余形式合并。
|
211
|
-
# 也可以设True,默认会将数值类统一为0。
|
212
|
-
'merge_path': False,
|
213
|
-
}
|
214
|
-
|
215
|
-
@classmethod
|
216
|
-
def _get_item_path_types(cls, item, prefix=''):
|
217
|
-
"""
|
218
|
-
:param item: 类json结构的数据,可以含有类型: dict, list(tuple), int, str, bool, None
|
219
|
-
结点类型
|
220
|
-
其中 dict、list称为 container 容器类型
|
221
|
-
其他int、str称为数值类型
|
222
|
-
结构
|
223
|
-
item 可以看成一个树形结构
|
224
|
-
其中数值类型可以视为叶子结点,其他容器类是非叶子结点
|
225
|
-
|
226
|
-
瑕疵
|
227
|
-
1、如果key本身带有"/",会导致混乱
|
228
|
-
2、list的下标转为0123,和字符串类型的key会混淆,和普通的字典key也会混淆
|
229
|
-
"""
|
230
|
-
path_types = []
|
231
|
-
if isinstance(item, dict):
|
232
|
-
path_types.append([prefix + '/', 'dict'])
|
233
|
-
for k in sorted(item.keys()): # 实验表明,在这里对字典的键进行排序就行,最后总的paths不要排序,不然结构会乱
|
234
|
-
v = item[k]
|
235
|
-
path_types.extend(cls._get_item_path_types(v, f'{prefix}/{k}'))
|
236
|
-
elif isinstance(item, (list, tuple)):
|
237
|
-
path_types.append([prefix + '/', type(item).__name__])
|
238
|
-
for k, v in enumerate(item):
|
239
|
-
path_types.extend(cls._get_item_path_types(v, f'{prefix}/{k}'))
|
240
|
-
else:
|
241
|
-
path_types.append([prefix, type(item).__name__])
|
242
|
-
return path_types
|
243
|
-
|
244
|
-
@classmethod
|
245
|
-
def get_item_pathlist(cls, item, prefix='', **kwargs):
|
246
|
-
""" 获得字典的结构标识
|
247
|
-
"""
|
248
|
-
# 1 底层数据
|
249
|
-
cfg = copy.copy(cls.default_cfg)
|
250
|
-
cfg.update(kwargs)
|
251
|
-
paths = cls._get_item_path_types(item, prefix)
|
252
|
-
|
253
|
-
# 2 配置参数
|
254
|
-
if cfg['merge_path']:
|
255
|
-
if callable(cfg['merge_path']):
|
256
|
-
func = cfg['merge_path']
|
257
|
-
else:
|
258
|
-
def func(p, t):
|
259
|
-
return re.sub(r'\d+', '0', p), t
|
260
|
-
|
261
|
-
# 保序去重
|
262
|
-
paths = list(unique_everseen(map(lambda x: func(x[0], x[1]), paths)))
|
263
|
-
|
264
|
-
if not cfg['include_container']:
|
265
|
-
paths = [pt for pt in paths if (pt[0][-1] != '/')]
|
266
|
-
|
267
|
-
if cfg['value_type']:
|
268
|
-
paths = ['='.join(pt) for pt in paths]
|
269
|
-
else:
|
270
|
-
paths = [pt[0] for pt in paths]
|
271
|
-
|
272
|
-
return paths
|
273
|
-
|
274
|
-
@classmethod
|
275
|
-
def get_item_pathstr(cls, item, prefix='', **kwargs):
|
276
|
-
paths = cls.get_item_pathlist(item, prefix, **kwargs)
|
277
|
-
return '\n'.join(paths)
|
278
|
-
|
279
|
-
@classmethod
|
280
|
-
def get_items_struct2cnt(cls, items, **kwargs):
|
281
|
-
# 1 统计每种结构出现的次数
|
282
|
-
struct2cnt = Counter()
|
283
|
-
for item in items:
|
284
|
-
pathstr = cls.get_item_pathstr(item, **kwargs)
|
285
|
-
struct2cnt[pathstr] += 1
|
286
|
-
# 2 按照从多到少排序
|
287
|
-
struct2cnt = Counter(dict(sorted(struct2cnt.items(), key=lambda item: -item[1])))
|
288
|
-
return struct2cnt
|
289
|
-
|
290
|
-
@classmethod
|
291
|
-
def get_items_structdf(cls, items, **kwargs):
|
292
|
-
""" 分析一组题目里,出现了多少种不同的json结构 """
|
293
|
-
# 1 获取原始数据,初始化
|
294
|
-
struct2cnt = cls.get_items_struct2cnt(items, **kwargs)
|
295
|
-
m = len(struct2cnt)
|
296
|
-
|
297
|
-
# 2 path2cnt
|
298
|
-
path2cnt = Counter()
|
299
|
-
for struct in struct2cnt.keys():
|
300
|
-
path2cnt.update({path: struct2cnt[struct] for path in struct.splitlines()})
|
301
|
-
paths = sorted(path2cnt.keys(), key=lambda path: re.split(r'/=', path))
|
302
|
-
path2cnt = {path: path2cnt[path] for path in paths}
|
303
|
-
|
304
|
-
# 3 生成统计表
|
305
|
-
ls = []
|
306
|
-
columns = ['path', 'total'] + [f'struct{i}' for i in range(1, m + 1)]
|
307
|
-
for path, cnt in path2cnt.items():
|
308
|
-
row = [path, cnt]
|
309
|
-
for struct, cnt in struct2cnt.items():
|
310
|
-
t = cnt if path in struct else 0
|
311
|
-
row.append(t)
|
312
|
-
ls.append(row)
|
313
|
-
|
314
|
-
df = pd.DataFrame.from_records(ls, columns=columns)
|
315
|
-
return df
|
316
|
-
|
317
|
-
@classmethod
|
318
|
-
def get_itemgroups_structdf(cls, itemgroups, **kwargs):
|
319
|
-
""" 分析不同套数据间的json结构区别
|
320
|
-
|
321
|
-
这里为了减少冗余开发,直接复用get_items_structdf
|
322
|
-
虽然会造成一些冗余功能,
|
323
|
-
"""
|
324
|
-
# 1 统计所有paths出现情况
|
325
|
-
n = len(itemgroups)
|
326
|
-
d = dict()
|
327
|
-
for i, gs in enumerate(itemgroups):
|
328
|
-
for x in gs:
|
329
|
-
paths = cls.get_item_pathlist(x, **kwargs)
|
330
|
-
for p in paths:
|
331
|
-
if p not in d:
|
332
|
-
d[p] = [0] * n
|
333
|
-
d[p][i] += 1
|
334
|
-
|
335
|
-
# 排序
|
336
|
-
paths = sorted(d.keys(), key=lambda path: re.split(r'/=', path))
|
337
|
-
|
338
|
-
# 2 统计表
|
339
|
-
ls = []
|
340
|
-
columns = ['path', 'total'] + [f'group{i}' for i in range(1, n + 1)]
|
341
|
-
for path in paths:
|
342
|
-
vals = d[path]
|
343
|
-
row = [path, sum(vals)] + vals
|
344
|
-
ls.append(row)
|
345
|
-
|
346
|
-
df = pd.DataFrame.from_records(ls, columns=columns)
|
347
|
-
return df
|
1
|
+
#!/usr/bin/env python3
|
2
|
+
# -*- coding: utf-8 -*-
|
3
|
+
# @Author : 陈坤泽
|
4
|
+
# @Email : 877362867@qq.com
|
5
|
+
# @Date : 2020/06/02 11:09
|
6
|
+
|
7
|
+
from collections import defaultdict, Counter
|
8
|
+
import copy
|
9
|
+
import re
|
10
|
+
import sys
|
11
|
+
|
12
|
+
import pandas as pd
|
13
|
+
from more_itertools import unique_everseen
|
14
|
+
|
15
|
+
from pyxllib.prog.newbie import typename
|
16
|
+
from pyxllib.algo.pupil import natural_sort_key
|
17
|
+
from pyxllib.text.pupil import shorten, east_asian_shorten
|
18
|
+
|
19
|
+
|
20
|
+
def dataframe_str(df, *args, ambiguous_as_wide=None, shorten=True):
|
21
|
+
"""输出DataFrame
|
22
|
+
DataFrame可以直接输出的,这里是增加了对中文字符的对齐效果支持
|
23
|
+
|
24
|
+
:param df: DataFrame数据结构
|
25
|
+
:param args: option_context格式控制
|
26
|
+
:param ambiguous_as_wide: 是否对①②③这种域宽有歧义的设为宽字符
|
27
|
+
win32平台上和linux上①域宽不同,默认win32是域宽2,linux是域宽1
|
28
|
+
:param shorten: 是否对每个元素提前进行字符串化并控制长度在display.max_colwidth以内
|
29
|
+
因为pandas的字符串截取遇到中文是有问题的,可以用我自定义的函数先做截取
|
30
|
+
默认开启,不过这步比较消耗时间
|
31
|
+
|
32
|
+
>> df = pd.DataFrame({'哈哈': ['a'*100, '哈\n①'*10, 'a哈'*100]})
|
33
|
+
哈哈
|
34
|
+
0 aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa...
|
35
|
+
1 哈 ①哈 ①哈 ①哈 ①哈 ①哈 ①哈 ①哈 ①哈 ①...
|
36
|
+
2 a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a哈a...
|
37
|
+
"""
|
38
|
+
import pandas as pd
|
39
|
+
|
40
|
+
if ambiguous_as_wide is None:
|
41
|
+
ambiguous_as_wide = sys.platform == 'win32'
|
42
|
+
with pd.option_context('display.unicode.east_asian_width', True, # 中文输出必备选项,用来控制正确的域宽
|
43
|
+
'display.unicode.ambiguous_as_wide', ambiguous_as_wide,
|
44
|
+
'max_columns', 20, # 最大列数设置到20列
|
45
|
+
'display.width', 200, # 最大宽度设置到200
|
46
|
+
*args):
|
47
|
+
if shorten: # applymap可以对所有的元素进行映射处理,并返回一个新的df
|
48
|
+
df = df.applymap(lambda x: east_asian_shorten(str(x), pd.options.display.max_colwidth))
|
49
|
+
s = str(df)
|
50
|
+
return s
|
51
|
+
|
52
|
+
|
53
|
+
class TypeConvert:
|
54
|
+
@classmethod
|
55
|
+
def dict2list(cls, d: dict, *, nsort=False):
|
56
|
+
""" 字典转n*2的list
|
57
|
+
|
58
|
+
:param d: 字典
|
59
|
+
:param nsort:
|
60
|
+
True: 对key使用自然排序
|
61
|
+
False: 使用d默认的遍历顺序
|
62
|
+
:return:
|
63
|
+
"""
|
64
|
+
ls = list(d.items())
|
65
|
+
if nsort:
|
66
|
+
ls = sorted(ls, key=lambda x: natural_sort_key(str(x[0])))
|
67
|
+
return ls
|
68
|
+
|
69
|
+
@classmethod
|
70
|
+
def dict2df(cls, d):
|
71
|
+
"""dict类型转DataFrame类型"""
|
72
|
+
name = typename(d)
|
73
|
+
if isinstance(d, Counter):
|
74
|
+
li = d.most_common()
|
75
|
+
else:
|
76
|
+
li = cls.dict2list(d, nsort=True)
|
77
|
+
return pd.DataFrame.from_records(li, columns=(f'{name}-key', f'{name}-value'))
|
78
|
+
|
79
|
+
@classmethod
|
80
|
+
def list2df(cls, li):
|
81
|
+
if li and isinstance(li[0], (list, tuple)): # 有两维时按表格显示
|
82
|
+
df = pd.DataFrame.from_records(li)
|
83
|
+
else: # 只有一维时按一列显示
|
84
|
+
df = pd.DataFrame(pd.Series(li), columns=(typename(li),))
|
85
|
+
return df
|
86
|
+
|
87
|
+
@classmethod
|
88
|
+
def try2df(cls, arg):
|
89
|
+
"""尝试将各种不同的类型转成dataframe"""
|
90
|
+
if isinstance(arg, dict):
|
91
|
+
df = cls.dict2df(arg)
|
92
|
+
elif isinstance(arg, (list, tuple)):
|
93
|
+
df = cls.list2df(arg)
|
94
|
+
elif isinstance(arg, pd.Series):
|
95
|
+
df = pd.DataFrame(arg)
|
96
|
+
else:
|
97
|
+
df = arg
|
98
|
+
return df
|
99
|
+
|
100
|
+
|
101
|
+
class NestedDict:
|
102
|
+
""" 字典嵌套结构相关功能
|
103
|
+
|
104
|
+
TODO 感觉跟 pprint 的嵌套识别美化输出相关,可能有些代码是可以结合简化的~~
|
105
|
+
"""
|
106
|
+
|
107
|
+
@classmethod
|
108
|
+
def has_subdict(cls, data, include_self=True):
|
109
|
+
"""是否含有dict子结构
|
110
|
+
:param include_self: 是否包含自身,即data本身是一个dict的话,也认为has_subdict是True
|
111
|
+
"""
|
112
|
+
if include_self and isinstance(data, dict):
|
113
|
+
return True
|
114
|
+
elif isinstance(data, (list, tuple, set)):
|
115
|
+
for v in data:
|
116
|
+
if cls.has_subdict(v):
|
117
|
+
return True
|
118
|
+
return False
|
119
|
+
|
120
|
+
@classmethod
|
121
|
+
def to_html_table(cls, data, max_items=10):
|
122
|
+
""" 以html表格套表格的形式,展示一个嵌套结构数据
|
123
|
+
|
124
|
+
:param data: 数据
|
125
|
+
:param max_items: 项目显示上限,有些数据项目太多了,要精简下
|
126
|
+
设为假值则不设上限
|
127
|
+
:return:
|
128
|
+
|
129
|
+
TODO 这个速度有点慢,怎么加速?
|
130
|
+
"""
|
131
|
+
|
132
|
+
def tohtml(d):
|
133
|
+
if max_items:
|
134
|
+
df = TypeConvert.try2df(d)
|
135
|
+
if len(df) > max_items:
|
136
|
+
n = len(df)
|
137
|
+
return df[:max_items].to_html(escape=False) + f'... {n - 1}'
|
138
|
+
else:
|
139
|
+
return df.to_html(escape=False)
|
140
|
+
else:
|
141
|
+
return TypeConvert.try2df(d).to_html(escape=False)
|
142
|
+
|
143
|
+
if not cls.has_subdict(data):
|
144
|
+
res = str(data)
|
145
|
+
elif isinstance(data, dict):
|
146
|
+
if isinstance(data, Counter):
|
147
|
+
d = data
|
148
|
+
else:
|
149
|
+
d = dict()
|
150
|
+
for k, v in data.items():
|
151
|
+
if cls.has_subdict(v):
|
152
|
+
v = cls.to_html_table(v, max_items=max_items)
|
153
|
+
d[k] = v
|
154
|
+
res = tohtml(d)
|
155
|
+
else:
|
156
|
+
li = [cls.to_html_table(x, max_items=max_items) for x in data]
|
157
|
+
res = tohtml(li)
|
158
|
+
|
159
|
+
return res.replace('\n', ' ')
|
160
|
+
|
161
|
+
|
162
|
+
class KeyValuesCounter:
|
163
|
+
""" 各种键值对出现次数的统计
|
164
|
+
会递归找子字典结构,但不存储结构信息,只记录纯粹的键值对信息
|
165
|
+
|
166
|
+
应用场景:对未知的json结构,批量读取后,显示所有键值对的出现情况
|
167
|
+
"""
|
168
|
+
|
169
|
+
def __init__(self):
|
170
|
+
self.kvs = defaultdict(Counter)
|
171
|
+
|
172
|
+
def add(self, data, max_value_length=100):
|
173
|
+
"""
|
174
|
+
:param max_value_length: 添加的值,进行截断,防止有些值太长
|
175
|
+
"""
|
176
|
+
if not NestedDict.has_subdict(data):
|
177
|
+
return
|
178
|
+
elif isinstance(data, dict):
|
179
|
+
for k, v in data.items():
|
180
|
+
if NestedDict.has_subdict(v):
|
181
|
+
self.add(v)
|
182
|
+
else:
|
183
|
+
self.kvs[k][shorten(str(v), max_value_length)] += 1
|
184
|
+
else: # 否则 data 应该是个可迭代对象,才可能含有dict
|
185
|
+
for x in data:
|
186
|
+
self.add(x)
|
187
|
+
|
188
|
+
def to_html_table(self, max_items=10):
|
189
|
+
return NestedDict.to_html_table(self.kvs, max_items=max_items)
|
190
|
+
|
191
|
+
|
192
|
+
class JsonStructParser:
|
193
|
+
""" 类json数据格式的结构解析
|
194
|
+
|
195
|
+
【名称定义】
|
196
|
+
item: 一条类json的数据条目
|
197
|
+
path: 用类路径的格式,表达item中某个数值的索引。例如
|
198
|
+
/a/b/3/c: 相当于 item['a']['b'][3]['c']
|
199
|
+
有一些特殊的path,例如容器类会以/结尾: /a/
|
200
|
+
以及一般会带上数值的类型标记,区分度更精确:/a/=dict
|
201
|
+
pathx: 泛指下述中某种格式
|
202
|
+
pathlist: list, 一条item对应的扁平化的路径
|
203
|
+
pathstr/struct: paths拼接成一个str
|
204
|
+
pathdict: paths重新组装成一个dict字典(未实装,太难写,性价比也低)
|
205
|
+
"""
|
206
|
+
|
207
|
+
default_cfg = {'include_container': True, # 包含容器(dict、list)的路径
|
208
|
+
'value_type': True, # 是否带上后缀:数值的类型
|
209
|
+
# 可以输入一个自定义的路径合并函数 path,type=merge_path(path,type)。
|
210
|
+
# 一般是字典中出现不断变化的数值id,格式不统一,使用一定的规则,可以将path几种相近的冗余形式合并。
|
211
|
+
# 也可以设True,默认会将数值类统一为0。
|
212
|
+
'merge_path': False,
|
213
|
+
}
|
214
|
+
|
215
|
+
@classmethod
|
216
|
+
def _get_item_path_types(cls, item, prefix=''):
|
217
|
+
"""
|
218
|
+
:param item: 类json结构的数据,可以含有类型: dict, list(tuple), int, str, bool, None
|
219
|
+
结点类型
|
220
|
+
其中 dict、list称为 container 容器类型
|
221
|
+
其他int、str称为数值类型
|
222
|
+
结构
|
223
|
+
item 可以看成一个树形结构
|
224
|
+
其中数值类型可以视为叶子结点,其他容器类是非叶子结点
|
225
|
+
|
226
|
+
瑕疵
|
227
|
+
1、如果key本身带有"/",会导致混乱
|
228
|
+
2、list的下标转为0123,和字符串类型的key会混淆,和普通的字典key也会混淆
|
229
|
+
"""
|
230
|
+
path_types = []
|
231
|
+
if isinstance(item, dict):
|
232
|
+
path_types.append([prefix + '/', 'dict'])
|
233
|
+
for k in sorted(item.keys()): # 实验表明,在这里对字典的键进行排序就行,最后总的paths不要排序,不然结构会乱
|
234
|
+
v = item[k]
|
235
|
+
path_types.extend(cls._get_item_path_types(v, f'{prefix}/{k}'))
|
236
|
+
elif isinstance(item, (list, tuple)):
|
237
|
+
path_types.append([prefix + '/', type(item).__name__])
|
238
|
+
for k, v in enumerate(item):
|
239
|
+
path_types.extend(cls._get_item_path_types(v, f'{prefix}/{k}'))
|
240
|
+
else:
|
241
|
+
path_types.append([prefix, type(item).__name__])
|
242
|
+
return path_types
|
243
|
+
|
244
|
+
@classmethod
|
245
|
+
def get_item_pathlist(cls, item, prefix='', **kwargs):
|
246
|
+
""" 获得字典的结构标识
|
247
|
+
"""
|
248
|
+
# 1 底层数据
|
249
|
+
cfg = copy.copy(cls.default_cfg)
|
250
|
+
cfg.update(kwargs)
|
251
|
+
paths = cls._get_item_path_types(item, prefix)
|
252
|
+
|
253
|
+
# 2 配置参数
|
254
|
+
if cfg['merge_path']:
|
255
|
+
if callable(cfg['merge_path']):
|
256
|
+
func = cfg['merge_path']
|
257
|
+
else:
|
258
|
+
def func(p, t):
|
259
|
+
return re.sub(r'\d+', '0', p), t
|
260
|
+
|
261
|
+
# 保序去重
|
262
|
+
paths = list(unique_everseen(map(lambda x: func(x[0], x[1]), paths)))
|
263
|
+
|
264
|
+
if not cfg['include_container']:
|
265
|
+
paths = [pt for pt in paths if (pt[0][-1] != '/')]
|
266
|
+
|
267
|
+
if cfg['value_type']:
|
268
|
+
paths = ['='.join(pt) for pt in paths]
|
269
|
+
else:
|
270
|
+
paths = [pt[0] for pt in paths]
|
271
|
+
|
272
|
+
return paths
|
273
|
+
|
274
|
+
@classmethod
|
275
|
+
def get_item_pathstr(cls, item, prefix='', **kwargs):
|
276
|
+
paths = cls.get_item_pathlist(item, prefix, **kwargs)
|
277
|
+
return '\n'.join(paths)
|
278
|
+
|
279
|
+
@classmethod
|
280
|
+
def get_items_struct2cnt(cls, items, **kwargs):
|
281
|
+
# 1 统计每种结构出现的次数
|
282
|
+
struct2cnt = Counter()
|
283
|
+
for item in items:
|
284
|
+
pathstr = cls.get_item_pathstr(item, **kwargs)
|
285
|
+
struct2cnt[pathstr] += 1
|
286
|
+
# 2 按照从多到少排序
|
287
|
+
struct2cnt = Counter(dict(sorted(struct2cnt.items(), key=lambda item: -item[1])))
|
288
|
+
return struct2cnt
|
289
|
+
|
290
|
+
@classmethod
|
291
|
+
def get_items_structdf(cls, items, **kwargs):
|
292
|
+
""" 分析一组题目里,出现了多少种不同的json结构 """
|
293
|
+
# 1 获取原始数据,初始化
|
294
|
+
struct2cnt = cls.get_items_struct2cnt(items, **kwargs)
|
295
|
+
m = len(struct2cnt)
|
296
|
+
|
297
|
+
# 2 path2cnt
|
298
|
+
path2cnt = Counter()
|
299
|
+
for struct in struct2cnt.keys():
|
300
|
+
path2cnt.update({path: struct2cnt[struct] for path in struct.splitlines()})
|
301
|
+
paths = sorted(path2cnt.keys(), key=lambda path: re.split(r'/=', path))
|
302
|
+
path2cnt = {path: path2cnt[path] for path in paths}
|
303
|
+
|
304
|
+
# 3 生成统计表
|
305
|
+
ls = []
|
306
|
+
columns = ['path', 'total'] + [f'struct{i}' for i in range(1, m + 1)]
|
307
|
+
for path, cnt in path2cnt.items():
|
308
|
+
row = [path, cnt]
|
309
|
+
for struct, cnt in struct2cnt.items():
|
310
|
+
t = cnt if path in struct else 0
|
311
|
+
row.append(t)
|
312
|
+
ls.append(row)
|
313
|
+
|
314
|
+
df = pd.DataFrame.from_records(ls, columns=columns)
|
315
|
+
return df
|
316
|
+
|
317
|
+
@classmethod
|
318
|
+
def get_itemgroups_structdf(cls, itemgroups, **kwargs):
|
319
|
+
""" 分析不同套数据间的json结构区别
|
320
|
+
|
321
|
+
这里为了减少冗余开发,直接复用get_items_structdf
|
322
|
+
虽然会造成一些冗余功能,
|
323
|
+
"""
|
324
|
+
# 1 统计所有paths出现情况
|
325
|
+
n = len(itemgroups)
|
326
|
+
d = dict()
|
327
|
+
for i, gs in enumerate(itemgroups):
|
328
|
+
for x in gs:
|
329
|
+
paths = cls.get_item_pathlist(x, **kwargs)
|
330
|
+
for p in paths:
|
331
|
+
if p not in d:
|
332
|
+
d[p] = [0] * n
|
333
|
+
d[p][i] += 1
|
334
|
+
|
335
|
+
# 排序
|
336
|
+
paths = sorted(d.keys(), key=lambda path: re.split(r'/=', path))
|
337
|
+
|
338
|
+
# 2 统计表
|
339
|
+
ls = []
|
340
|
+
columns = ['path', 'total'] + [f'group{i}' for i in range(1, n + 1)]
|
341
|
+
for path in paths:
|
342
|
+
vals = d[path]
|
343
|
+
row = [path, sum(vals)] + vals
|
344
|
+
ls.append(row)
|
345
|
+
|
346
|
+
df = pd.DataFrame.from_records(ls, columns=columns)
|
347
|
+
return df
|