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
|
from vbench.api import Benchmark
from datetime import datetime
common_setup = """from pandas_vb_common import *
"""
setup = common_setup + """
N = 100000
ngroups = 100
def get_test_data(ngroups=100, n=N):
unique_groups = range(ngroups)
arr = np.asarray(np.tile(unique_groups, n / ngroups), dtype=object)
if len(arr) < n:
arr = np.asarray(list(arr) + unique_groups[:n - len(arr)],
dtype=object)
random.shuffle(arr)
return arr
# aggregate multiple columns
df = DataFrame({'key1' : get_test_data(ngroups=ngroups),
'key2' : get_test_data(ngroups=ngroups),
'data1' : np.random.randn(N),
'data2' : np.random.randn(N)})
def f():
df.groupby(['key1', 'key2']).agg(lambda x: x.values.sum())
simple_series = Series(np.random.randn(N))
key1 = df['key1']
"""
stmt1 = "df.groupby(['key1', 'key2'])['data1'].agg(lambda x: x.values.sum())"
groupby_multi_python = Benchmark(stmt1, setup,
start_date=datetime(2011, 7, 1))
stmt3 = "df.groupby(['key1', 'key2']).sum()"
groupby_multi_cython = Benchmark(stmt3, setup,
start_date=datetime(2011, 7, 1))
stmt = "df.groupby(['key1', 'key2'])['data1'].agg(np.std)"
groupby_multi_series_op = Benchmark(stmt, setup,
start_date=datetime(2011, 8, 1))
groupby_series_simple_cython = \
Benchmark('simple_series.groupby(key1).sum()', setup,
start_date=datetime(2011, 3, 1))
#----------------------------------------------------------------------
# 2d grouping, aggregate many columns
setup = common_setup + """
labels = np.random.randint(0, 100, size=1000)
df = DataFrame(randn(1000, 1000))
"""
groupby_frame_cython_many_columns = Benchmark('df.groupby(labels).sum()', setup,
start_date=datetime(2011, 8, 1),
logy=True)
#----------------------------------------------------------------------
# single key, long, integer key
setup = common_setup + """
data = np.random.randn(100000, 1)
labels = np.random.randint(0, 1000, size=100000)
df = DataFrame(data)
"""
groupby_frame_singlekey_integer = \
Benchmark('df.groupby(labels).sum()', setup,
start_date=datetime(2011, 8, 1), logy=True)
#----------------------------------------------------------------------
# group with different functions per column
setup = common_setup + """
fac1 = np.array(['A', 'B', 'C'], dtype='O')
fac2 = np.array(['one', 'two'], dtype='O')
df = DataFrame({'key1': fac1.take(np.random.randint(0, 3, size=100000)),
'key2': fac2.take(np.random.randint(0, 2, size=100000)),
'value1' : np.random.randn(100000),
'value2' : np.random.randn(100000),
'value3' : np.random.randn(100000)})
"""
groupby_multi_different_functions = \
Benchmark("""df.groupby(['key1', 'key2']).agg({'value1' : 'mean',
'value2' : 'var',
'value3' : 'sum'})""",
setup, start_date=datetime(2011, 9, 1))
groupby_multi_different_numpy_functions = \
Benchmark("""df.groupby(['key1', 'key2']).agg({'value1' : np.mean,
'value2' : np.var,
'value3' : np.sum})""",
setup, start_date=datetime(2011, 9, 1))
#----------------------------------------------------------------------
# size() speed
setup = common_setup + """
df = DataFrame({'key1': np.random.randint(0, 500, size=100000),
'key2': np.random.randint(0, 100, size=100000),
'value1' : np.random.randn(100000),
'value2' : np.random.randn(100000),
'value3' : np.random.randn(100000)})
"""
groupby_multi_size = Benchmark("df.groupby(['key1', 'key2']).size()",
setup, start_date=datetime(2011, 10, 1))
#----------------------------------------------------------------------
# Series.value_counts
setup = common_setup + """
s = Series(np.random.randint(0, 1000, size=100000))
"""
series_value_counts_int64 = Benchmark('s.value_counts()', setup,
start_date=datetime(2011, 10, 21))
#----------------------------------------------------------------------
# pivot_table
setup = common_setup + """
fac1 = np.array(['A', 'B', 'C'], dtype='O')
fac2 = np.array(['one', 'two'], dtype='O')
ind1 = np.random.randint(0, 3, size=100000)
ind2 = np.random.randint(0, 2, size=100000)
df = DataFrame({'key1': fac1.take(ind1),
'key2': fac2.take(ind2),
'key3': fac2.take(ind2),
'value1' : np.random.randn(100000),
'value2' : np.random.randn(100000),
'value3' : np.random.randn(100000)})
"""
stmt = "df.pivot_table(rows='key1', cols=['key2', 'key3'])"
groupby_pivot_table = Benchmark(stmt, setup, start_date=datetime(2011, 12, 15))
#----------------------------------------------------------------------
# dict return values
setup = common_setup + """
labels = np.arange(1000).repeat(10)
data = Series(randn(len(labels)))
f = lambda x: {'first': x.values[0], 'last': x.values[-1]}
"""
groupby_apply_dict_return = Benchmark('data.groupby(labels).apply(f)',
setup, start_date=datetime(2011, 12, 15))
#----------------------------------------------------------------------
# First / last functions
setup = common_setup + """
labels = np.arange(10000).repeat(10)
data = Series(randn(len(labels)))
data[::3] = np.nan
data[1::3] = np.nan
labels = labels.take(np.random.permutation(len(labels)))
"""
groupby_first = Benchmark('data.groupby(labels).first()', setup,
start_date=datetime(2012, 5, 1))
groupby_last = Benchmark('data.groupby(labels).last()', setup,
start_date=datetime(2012, 5, 1))
#----------------------------------------------------------------------
# groupby_indices replacement, chop up Series
setup = common_setup + """
try:
rng = date_range('1/1/2000', '12/31/2005', freq='H')
year, month, day = rng.year, rng.month, rng.day
except:
rng = date_range('1/1/2000', '12/31/2000', offset=datetools.Hour())
year = rng.map(lambda x: x.year)
month = rng.map(lambda x: x.month)
day = rng.map(lambda x: x.day)
ts = Series(np.random.randn(len(rng)), index=rng)
"""
groupby_indices = Benchmark('len(ts.groupby([year, month, day]))',
setup, start_date=datetime(2012, 1, 1))
|
