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
|
import sys
import numpy as np
from pandas import (
DataFrame,
Index,
concat,
date_range,
json_normalize,
read_json,
timedelta_range,
)
from ..pandas_vb_common import BaseIO
class ReadJSON(BaseIO):
fname = "__test__.json"
params = (["split", "index", "records"], ["int", "datetime"])
param_names = ["orient", "index"]
def setup(self, orient, index):
N = 100000
indexes = {
"int": np.arange(N),
"datetime": date_range("20000101", periods=N, freq="h"),
}
df = DataFrame(
np.random.randn(N, 5),
columns=[f"float_{i}" for i in range(5)],
index=indexes[index],
)
df.to_json(self.fname, orient=orient)
def time_read_json(self, orient, index):
read_json(self.fname, orient=orient)
class ReadJSONLines(BaseIO):
fname = "__test_lines__.json"
params = ["int", "datetime"]
param_names = ["index"]
def setup(self, index):
N = 100000
indexes = {
"int": np.arange(N),
"datetime": date_range("20000101", periods=N, freq="h"),
}
df = DataFrame(
np.random.randn(N, 5),
columns=[f"float_{i}" for i in range(5)],
index=indexes[index],
)
df.to_json(self.fname, orient="records", lines=True)
def time_read_json_lines(self, index):
read_json(self.fname, orient="records", lines=True)
def time_read_json_lines_concat(self, index):
concat(read_json(self.fname, orient="records", lines=True, chunksize=25000))
def time_read_json_lines_nrows(self, index):
read_json(self.fname, orient="records", lines=True, nrows=25000)
def peakmem_read_json_lines(self, index):
read_json(self.fname, orient="records", lines=True)
def peakmem_read_json_lines_concat(self, index):
concat(read_json(self.fname, orient="records", lines=True, chunksize=25000))
def peakmem_read_json_lines_nrows(self, index):
read_json(self.fname, orient="records", lines=True, nrows=15000)
class NormalizeJSON(BaseIO):
fname = "__test__.json"
params = [
["split", "columns", "index", "values", "records"],
["df", "df_date_idx", "df_td_int_ts", "df_int_floats", "df_int_float_str"],
]
param_names = ["orient", "frame"]
def setup(self, orient, frame):
data = {
"hello": ["thisisatest", 999898, "mixed types"],
"nest1": {"nest2": {"nest3": "nest3_value", "nest3_int": 3445}},
"nest1_list": {"nest2": ["blah", 32423, 546456.876, 92030234]},
"hello2": "string",
}
self.data = [data for i in range(10000)]
def time_normalize_json(self, orient, frame):
json_normalize(self.data)
class ToJSON(BaseIO):
fname = "__test__.json"
params = [
["split", "columns", "index", "values", "records"],
["df", "df_date_idx", "df_td_int_ts", "df_int_floats", "df_int_float_str"],
]
param_names = ["orient", "frame"]
def setup(self, orient, frame):
N = 10**5
ncols = 5
index = date_range("20000101", periods=N, freq="h")
timedeltas = timedelta_range(start=1, periods=N, freq="s")
datetimes = date_range(start=1, periods=N, freq="s")
ints = np.random.randint(100000000, size=N)
longints = sys.maxsize * np.random.randint(100000000, size=N)
floats = np.random.randn(N)
strings = Index([f"i-{i}" for i in range(N)], dtype=object)
self.df = DataFrame(np.random.randn(N, ncols), index=np.arange(N))
self.df_date_idx = DataFrame(np.random.randn(N, ncols), index=index)
self.df_td_int_ts = DataFrame(
{
"td_1": timedeltas,
"td_2": timedeltas,
"int_1": ints,
"int_2": ints,
"ts_1": datetimes,
"ts_2": datetimes,
},
index=index,
)
self.df_int_floats = DataFrame(
{
"int_1": ints,
"int_2": ints,
"int_3": ints,
"float_1": floats,
"float_2": floats,
"float_3": floats,
},
index=index,
)
self.df_int_float_str = DataFrame(
{
"int_1": ints,
"int_2": ints,
"float_1": floats,
"float_2": floats,
"str_1": strings,
"str_2": strings,
},
index=index,
)
self.df_longint_float_str = DataFrame(
{
"longint_1": longints,
"longint_2": longints,
"float_1": floats,
"float_2": floats,
"str_1": strings,
"str_2": strings,
},
index=index,
)
def time_to_json(self, orient, frame):
getattr(self, frame).to_json(self.fname, orient=orient)
def peakmem_to_json(self, orient, frame):
getattr(self, frame).to_json(self.fname, orient=orient)
class ToJSONWide(ToJSON):
def setup(self, orient, frame):
super().setup(orient, frame)
base_df = getattr(self, frame).copy()
df_wide = concat([base_df.iloc[:100]] * 1000, ignore_index=True, axis=1)
self.df_wide = df_wide
def time_to_json_wide(self, orient, frame):
self.df_wide.to_json(self.fname, orient=orient)
def peakmem_to_json_wide(self, orient, frame):
self.df_wide.to_json(self.fname, orient=orient)
class ToJSONISO(BaseIO):
fname = "__test__.json"
params = [["split", "columns", "index", "values", "records"]]
param_names = ["orient"]
def setup(self, orient):
N = 10**5
index = date_range("20000101", periods=N, freq="h")
timedeltas = timedelta_range(start=1, periods=N, freq="s")
datetimes = date_range(start=1, periods=N, freq="s")
self.df = DataFrame(
{
"td_1": timedeltas,
"td_2": timedeltas,
"ts_1": datetimes,
"ts_2": datetimes,
},
index=index,
)
def time_iso_format(self, orient):
self.df.to_json(orient=orient, date_format="iso")
class ToJSONLines(BaseIO):
fname = "__test__.json"
def setup(self):
N = 10**5
ncols = 5
index = date_range("20000101", periods=N, freq="h")
timedeltas = timedelta_range(start=1, periods=N, freq="s")
datetimes = date_range(start=1, periods=N, freq="s")
ints = np.random.randint(100000000, size=N)
longints = sys.maxsize * np.random.randint(100000000, size=N)
floats = np.random.randn(N)
strings = Index([f"i-{i}" for i in range(N)], dtype=object)
self.df = DataFrame(np.random.randn(N, ncols), index=np.arange(N))
self.df_date_idx = DataFrame(np.random.randn(N, ncols), index=index)
self.df_td_int_ts = DataFrame(
{
"td_1": timedeltas,
"td_2": timedeltas,
"int_1": ints,
"int_2": ints,
"ts_1": datetimes,
"ts_2": datetimes,
},
index=index,
)
self.df_int_floats = DataFrame(
{
"int_1": ints,
"int_2": ints,
"int_3": ints,
"float_1": floats,
"float_2": floats,
"float_3": floats,
},
index=index,
)
self.df_int_float_str = DataFrame(
{
"int_1": ints,
"int_2": ints,
"float_1": floats,
"float_2": floats,
"str_1": strings,
"str_2": strings,
},
index=index,
)
self.df_longint_float_str = DataFrame(
{
"longint_1": longints,
"longint_2": longints,
"float_1": floats,
"float_2": floats,
"str_1": strings,
"str_2": strings,
},
index=index,
)
def time_floats_with_int_idex_lines(self):
self.df.to_json(self.fname, orient="records", lines=True)
def time_floats_with_dt_index_lines(self):
self.df_date_idx.to_json(self.fname, orient="records", lines=True)
def time_delta_int_tstamp_lines(self):
self.df_td_int_ts.to_json(self.fname, orient="records", lines=True)
def time_float_int_lines(self):
self.df_int_floats.to_json(self.fname, orient="records", lines=True)
def time_float_int_str_lines(self):
self.df_int_float_str.to_json(self.fname, orient="records", lines=True)
def time_float_longint_str_lines(self):
self.df_longint_float_str.to_json(self.fname, orient="records", lines=True)
class ToJSONMem:
def setup_cache(self):
df = DataFrame([[1]])
df2 = DataFrame(range(8), date_range("1/1/2000", periods=8, freq="min"))
frames = {"int": df, "float": df.astype(float), "datetime": df2}
return frames
def peakmem_int(self, frames):
df = frames["int"]
for _ in range(100_000):
df.to_json()
def peakmem_float(self, frames):
df = frames["float"]
for _ in range(100_000):
df.to_json()
def peakmem_time(self, frames):
df = frames["datetime"]
for _ in range(10_000):
df.to_json(orient="table")
from ..pandas_vb_common import setup # noqa: F401 isort:skip
|
