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
|
import numpy as np
import pandas as pd
from pandas import (
NA,
Categorical,
DataFrame,
Float64Dtype,
MultiIndex,
Series,
Timestamp,
date_range,
)
try:
from pandas.tseries.offsets import (
Hour,
Nano,
)
except ImportError:
# For compatibility with older versions
from pandas.core.datetools import (
Hour,
Nano,
)
class FromDicts:
def setup(self):
N, K = 5000, 50
self.index = pd.Index([f"i-{i}" for i in range(N)], dtype=object)
self.columns = pd.Index([f"i-{i}" for i in range(K)], dtype=object)
frame = DataFrame(np.random.randn(N, K), index=self.index, columns=self.columns)
self.data = frame.to_dict()
self.dict_list = frame.to_dict(orient="records")
self.data2 = {i: {j: float(j) for j in range(100)} for i in range(2000)}
# arrays which we won't consolidate
self.dict_of_categoricals = {i: Categorical(np.arange(N)) for i in range(K)}
def time_list_of_dict(self):
DataFrame(self.dict_list)
def time_nested_dict(self):
DataFrame(self.data)
def time_nested_dict_index(self):
DataFrame(self.data, index=self.index)
def time_nested_dict_columns(self):
DataFrame(self.data, columns=self.columns)
def time_nested_dict_index_columns(self):
DataFrame(self.data, index=self.index, columns=self.columns)
def time_nested_dict_int64(self):
# nested dict, integer indexes, regression described in #621
DataFrame(self.data2)
def time_dict_of_categoricals(self):
# dict of arrays that we won't consolidate
DataFrame(self.dict_of_categoricals)
class FromSeries:
def setup(self):
mi = MultiIndex.from_product([range(100), range(100)])
self.s = Series(np.random.randn(10000), index=mi)
def time_mi_series(self):
DataFrame(self.s)
class FromDictwithTimestamp:
params = [Nano(1), Hour(1)]
param_names = ["offset"]
def setup(self, offset):
N = 10**3
idx = date_range(Timestamp("1/1/1900"), freq=offset, periods=N)
df = DataFrame(np.random.randn(N, 10), index=idx)
self.d = df.to_dict()
def time_dict_with_timestamp_offsets(self, offset):
DataFrame(self.d)
class FromRecords:
params = [None, 1000]
param_names = ["nrows"]
# Generators get exhausted on use, so run setup before every call
number = 1
repeat = (3, 250, 10)
def setup(self, nrows):
N = 100000
self.gen = ((x, (x * 20), (x * 100)) for x in range(N))
def time_frame_from_records_generator(self, nrows):
# issue-6700
self.df = DataFrame.from_records(self.gen, nrows=nrows)
class FromNDArray:
def setup(self):
N = 100000
self.data = np.random.randn(N)
def time_frame_from_ndarray(self):
self.df = DataFrame(self.data)
class FromLists:
goal_time = 0.2
def setup(self):
N = 1000
M = 100
self.data = [list(range(M)) for i in range(N)]
def time_frame_from_lists(self):
self.df = DataFrame(self.data)
class FromRange:
goal_time = 0.2
def setup(self):
N = 1_000_000
self.data = range(N)
def time_frame_from_range(self):
self.df = DataFrame(self.data)
class FromScalar:
def setup(self):
self.nrows = 100_000
def time_frame_from_scalar_ea_float64(self):
DataFrame(
1.0,
index=range(self.nrows),
columns=list("abc"),
dtype=Float64Dtype(),
)
def time_frame_from_scalar_ea_float64_na(self):
DataFrame(
NA,
index=range(self.nrows),
columns=list("abc"),
dtype=Float64Dtype(),
)
class FromArrays:
goal_time = 0.2
def setup(self):
N_rows = 1000
N_cols = 1000
self.float_arrays = [np.random.randn(N_rows) for _ in range(N_cols)]
self.sparse_arrays = [
pd.arrays.SparseArray(np.random.randint(0, 2, N_rows), dtype="float64")
for _ in range(N_cols)
]
self.int_arrays = [
pd.array(np.random.randint(1000, size=N_rows), dtype="Int64")
for _ in range(N_cols)
]
self.index = pd.Index(range(N_rows))
self.columns = pd.Index(range(N_cols))
def time_frame_from_arrays_float(self):
self.df = DataFrame._from_arrays(
self.float_arrays,
index=self.index,
columns=self.columns,
verify_integrity=False,
)
def time_frame_from_arrays_int(self):
self.df = DataFrame._from_arrays(
self.int_arrays,
index=self.index,
columns=self.columns,
verify_integrity=False,
)
def time_frame_from_arrays_sparse(self):
self.df = DataFrame._from_arrays(
self.sparse_arrays,
index=self.index,
columns=self.columns,
verify_integrity=False,
)
from .pandas_vb_common import setup # noqa: F401 isort:skip
|
