forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcsv.py
322 lines (234 loc) · 10.2 KB
/
csv.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
import random
import string
import numpy as np
import pandas.util.testing as tm
from pandas import DataFrame, Categorical, date_range, read_csv
from pandas.io.parsers import _parser_defaults
from io import StringIO
from ..pandas_vb_common import BaseIO
class ToCSV(BaseIO):
fname = '__test__.csv'
params = ['wide', 'long', 'mixed']
param_names = ['kind']
def setup(self, kind):
wide_frame = DataFrame(np.random.randn(3000, 30))
long_frame = DataFrame({'A': np.arange(50000),
'B': np.arange(50000) + 1.,
'C': np.arange(50000) + 2.,
'D': np.arange(50000) + 3.})
mixed_frame = DataFrame({'float': np.random.randn(5000),
'int': np.random.randn(5000).astype(int),
'bool': (np.arange(5000) % 2) == 0,
'datetime': date_range('2001',
freq='s',
periods=5000),
'object': ['foo'] * 5000})
mixed_frame.loc[30:500, 'float'] = np.nan
data = {'wide': wide_frame,
'long': long_frame,
'mixed': mixed_frame}
self.df = data[kind]
def time_frame(self, kind):
self.df.to_csv(self.fname)
class ToCSVDatetime(BaseIO):
fname = '__test__.csv'
def setup(self):
rng = date_range('1/1/2000', periods=1000)
self.data = DataFrame(rng, index=rng)
def time_frame_date_formatting(self):
self.data.to_csv(self.fname, date_format='%Y%m%d')
class ToCSVDatetimeBig(BaseIO):
fname = '__test__.csv'
timeout = 1500
params = [1000, 10000, 100000]
param_names = ['obs']
def setup(self, obs):
d = '2018-11-29'
dt = '2018-11-26 11:18:27.0'
self.data = DataFrame({'dt': [np.datetime64(dt)] * obs,
'd': [np.datetime64(d)] * obs,
'r': [np.random.uniform()] * obs})
def time_frame(self, obs):
self.data.to_csv(self.fname)
class StringIORewind:
def data(self, stringio_object):
stringio_object.seek(0)
return stringio_object
class ReadCSVDInferDatetimeFormat(StringIORewind):
params = ([True, False], ['custom', 'iso8601', 'ymd'])
param_names = ['infer_datetime_format', 'format']
def setup(self, infer_datetime_format, format):
rng = date_range('1/1/2000', periods=1000)
formats = {'custom': '%m/%d/%Y %H:%M:%S.%f',
'iso8601': '%Y-%m-%d %H:%M:%S',
'ymd': '%Y%m%d'}
dt_format = formats[format]
self.StringIO_input = StringIO('\n'.join(
rng.strftime(dt_format).tolist()))
def time_read_csv(self, infer_datetime_format, format):
read_csv(self.data(self.StringIO_input),
header=None, names=['foo'], parse_dates=['foo'],
infer_datetime_format=infer_datetime_format)
class ReadCSVConcatDatetime(StringIORewind):
iso8601 = '%Y-%m-%d %H:%M:%S'
def setup(self):
rng = date_range('1/1/2000', periods=50000, freq='S')
self.StringIO_input = StringIO('\n'.join(
rng.strftime(self.iso8601).tolist()))
def time_read_csv(self):
read_csv(self.data(self.StringIO_input),
header=None, names=['foo'], parse_dates=['foo'],
infer_datetime_format=False)
class ReadCSVConcatDatetimeBadDateValue(StringIORewind):
params = (['nan', '0', ''],)
param_names = ['bad_date_value']
def setup(self, bad_date_value):
self.StringIO_input = StringIO(('%s,\n' % bad_date_value) * 50000)
def time_read_csv(self, bad_date_value):
read_csv(self.data(self.StringIO_input),
header=None, names=['foo', 'bar'], parse_dates=['foo'],
infer_datetime_format=False)
class ReadCSVSkipRows(BaseIO):
fname = '__test__.csv'
params = [None, 10000]
param_names = ['skiprows']
def setup(self, skiprows):
N = 20000
index = tm.makeStringIndex(N)
df = DataFrame({'float1': np.random.randn(N),
'float2': np.random.randn(N),
'string1': ['foo'] * N,
'bool1': [True] * N,
'int1': np.random.randint(0, N, size=N)},
index=index)
df.to_csv(self.fname)
def time_skipprows(self, skiprows):
read_csv(self.fname, skiprows=skiprows)
class ReadUint64Integers(StringIORewind):
def setup(self):
self.na_values = [2**63 + 500]
arr = np.arange(10000).astype('uint64') + 2**63
self.data1 = StringIO('\n'.join(arr.astype(str).tolist()))
arr = arr.astype(object)
arr[500] = -1
self.data2 = StringIO('\n'.join(arr.astype(str).tolist()))
def time_read_uint64(self):
read_csv(self.data(self.data1), header=None, names=['foo'])
def time_read_uint64_neg_values(self):
read_csv(self.data(self.data2), header=None, names=['foo'])
def time_read_uint64_na_values(self):
read_csv(self.data(self.data1), header=None, names=['foo'],
na_values=self.na_values)
class ReadCSVThousands(BaseIO):
fname = '__test__.csv'
params = ([',', '|'], [None, ','])
param_names = ['sep', 'thousands']
def setup(self, sep, thousands):
N = 10000
K = 8
data = np.random.randn(N, K) * np.random.randint(100, 10000, (N, K))
df = DataFrame(data)
if thousands is not None:
fmt = ':{}'.format(thousands)
fmt = '{' + fmt + '}'
df = df.applymap(lambda x: fmt.format(x))
df.to_csv(self.fname, sep=sep)
def time_thousands(self, sep, thousands):
read_csv(self.fname, sep=sep, thousands=thousands)
class ReadCSVComment(StringIORewind):
def setup(self):
data = ['A,B,C'] + (['1,2,3 # comment'] * 100000)
self.StringIO_input = StringIO('\n'.join(data))
def time_comment(self):
read_csv(self.data(self.StringIO_input), comment='#',
header=None, names=list('abc'))
class ReadCSVFloatPrecision(StringIORewind):
params = ([',', ';'], ['.', '_'], [None, 'high', 'round_trip'])
param_names = ['sep', 'decimal', 'float_precision']
def setup(self, sep, decimal, float_precision):
floats = [''.join(random.choice(string.digits) for _ in range(28))
for _ in range(15)]
rows = sep.join(['0{}'.format(decimal) + '{}'] * 3) + '\n'
data = rows * 5
data = data.format(*floats) * 200 # 1000 x 3 strings csv
self.StringIO_input = StringIO(data)
def time_read_csv(self, sep, decimal, float_precision):
read_csv(self.data(self.StringIO_input), sep=sep, header=None,
names=list('abc'), float_precision=float_precision)
def time_read_csv_python_engine(self, sep, decimal, float_precision):
read_csv(self.data(self.StringIO_input), sep=sep, header=None,
engine='python', float_precision=None, names=list('abc'))
class ReadCSVCategorical(BaseIO):
fname = '__test__.csv'
def setup(self):
N = 100000
group1 = ['aaaaaaaa', 'bbbbbbb', 'cccccccc', 'dddddddd', 'eeeeeeee']
df = DataFrame(np.random.choice(group1, (N, 3)), columns=list('abc'))
df.to_csv(self.fname, index=False)
def time_convert_post(self):
read_csv(self.fname).apply(Categorical)
def time_convert_direct(self):
read_csv(self.fname, dtype='category')
class ReadCSVParseDates(StringIORewind):
def setup(self):
data = """{},19:00:00,18:56:00,0.8100,2.8100,7.2000,0.0000,280.0000\n
{},20:00:00,19:56:00,0.0100,2.2100,7.2000,0.0000,260.0000\n
{},21:00:00,20:56:00,-0.5900,2.2100,5.7000,0.0000,280.0000\n
{},21:00:00,21:18:00,-0.9900,2.0100,3.6000,0.0000,270.0000\n
{},22:00:00,21:56:00,-0.5900,1.7100,5.1000,0.0000,290.0000\n
"""
two_cols = ['KORD,19990127'] * 5
data = data.format(*two_cols)
self.StringIO_input = StringIO(data)
def time_multiple_date(self):
read_csv(self.data(self.StringIO_input), sep=',', header=None,
names=list(string.digits[:9]),
parse_dates=[[1, 2], [1, 3]])
def time_baseline(self):
read_csv(self.data(self.StringIO_input), sep=',', header=None,
parse_dates=[1],
names=list(string.digits[:9]))
class ReadCSVCachedParseDates(StringIORewind):
params = ([True, False],)
param_names = ['do_cache']
def setup(self, do_cache):
data = ('\n'.join('10/{}'.format(year)
for year in range(2000, 2100)) + '\n') * 10
self.StringIO_input = StringIO(data)
def time_read_csv_cached(self, do_cache):
# kwds setting here is used to avoid breaking tests in
# previous version of pandas, because this is api changes
kwds = {}
if 'cache_dates' in _parser_defaults:
kwds['cache_dates'] = do_cache
read_csv(self.data(self.StringIO_input), header=None,
parse_dates=[0], **kwds)
class ReadCSVMemoryGrowth(BaseIO):
chunksize = 20
num_rows = 1000
fname = "__test__.csv"
def setup(self):
with open(self.fname, "w") as f:
for i in range(self.num_rows):
f.write("{i}\n".format(i=i))
def mem_parser_chunks(self):
# see gh-24805.
result = read_csv(self.fname, chunksize=self.chunksize)
for _ in result:
pass
class ReadCSVParseSpecialDate(StringIORewind):
params = (['mY', 'mdY', 'hm'],)
params_name = ['value']
objects = {
'mY': '01-2019\n10-2019\n02/2000\n',
'mdY': '12/02/2010\n',
'hm': '21:34\n'
}
def setup(self, value):
count_elem = 10000
data = self.objects[value] * count_elem
self.StringIO_input = StringIO(data)
def time_read_special_date(self, value):
read_csv(self.data(self.StringIO_input), sep=',', header=None,
names=['Date'], parse_dates=['Date'])
from ..pandas_vb_common import setup # noqa: F401