Skip to content

CLN: ASV long and broken benchmarks #19113

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 10, 2018
Merged

CLN: ASV long and broken benchmarks #19113

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions asv_bench/benchmarks/frame_methods.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
from pandas import (DataFrame, Series, MultiIndex, date_range, period_range,
isnull, NaT)

from .pandas_vb_common import setup # noqa
from .pandas_vb_common import setup # noqa


class GetNumericData(object):
Expand Down Expand Up @@ -127,7 +127,7 @@ class ToHTML(object):
def setup(self):
nrows = 500
self.df2 = DataFrame(np.random.randn(nrows, 10))
self.df2[0] = period_range('2000', '2010', nrows)
self.df2[0] = period_range('2000', periods=nrows)
self.df2[1] = range(nrows)

def time_to_html_mixed(self):
Expand Down
131 changes: 19 additions & 112 deletions asv_bench/benchmarks/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
from string import ascii_letters, digits
from string import ascii_letters
from itertools import product
from functools import partial

Expand Down Expand Up @@ -275,18 +275,12 @@ class GroupStrings(object):

def setup(self):
n = 2 * 10**5
alpha = list(map(''.join, product((ascii_letters + digits), repeat=4)))
self.df = DataFrame({'a': np.repeat(np.random.choice(alpha,
(n // 11)), 11),
'b': np.repeat(np.random.choice(alpha,
(n // 7)), 7),
'c': np.repeat(np.random.choice(alpha,
(n // 5)), 5),
'd': np.repeat(np.random.choice(alpha,
(n // 1)), 1)})
alpha = list(map(''.join, product(ascii_letters, repeat=4)))
data = np.random.choice(alpha, (n // 5, 4), replace=False)
data = np.repeat(data, 5, axis=0)
self.df = DataFrame(data, columns=list('abcd'))
self.df['joe'] = (np.random.randn(len(self.df)) * 10).round(3)
i = np.random.permutation(len(self.df))
self.df = self.df.iloc[i].reset_index(drop=True)
self.df = self.df.sample(frac=1).reset_index(drop=True)

def time_multi_columns(self):
self.df.groupby(list('abcd')).max()
Expand Down Expand Up @@ -356,10 +350,16 @@ class GroupByMethods(object):

goal_time = 0.2

param_names = ['dtype', 'ngroups']
params = [['int', 'float'], [100, 10000]]
param_names = ['dtype', 'method']
params = [['int', 'float'],
['all', 'any', 'count', 'cumcount', 'cummax', 'cummin',
'cumprod', 'cumsum', 'describe', 'first', 'head', 'last', 'mad',
'max', 'min', 'median', 'mean', 'nunique', 'pct_change', 'prod',
'rank', 'sem', 'shift', 'size', 'skew', 'std', 'sum', 'tail',
'unique', 'value_counts', 'var']]

def setup(self, dtype, ngroups):
def setup(self, dtype, method):
ngroups = 1000
size = ngroups * 2
rng = np.arange(ngroups)
values = rng.take(np.random.randint(0, ngroups, size=size))
Expand All @@ -369,104 +369,11 @@ def setup(self, dtype, ngroups):
key = np.concatenate([np.random.random(ngroups) * 0.1,
np.random.random(ngroups) * 10.0])

self.df = DataFrame({'values': values,
'key': key})
df = DataFrame({'values': values, 'key': key})
self.df_groupby_method = getattr(df.groupby('key')['values'], method)

def time_all(self, dtype, ngroups):
self.df.groupby('key')['values'].all()

def time_any(self, dtype, ngroups):
self.df.groupby('key')['values'].any()

def time_count(self, dtype, ngroups):
self.df.groupby('key')['values'].count()

def time_cumcount(self, dtype, ngroups):
self.df.groupby('key')['values'].cumcount()

def time_cummax(self, dtype, ngroups):
self.df.groupby('key')['values'].cummax()

def time_cummin(self, dtype, ngroups):
self.df.groupby('key')['values'].cummin()

def time_cumprod(self, dtype, ngroups):
self.df.groupby('key')['values'].cumprod()

def time_cumsum(self, dtype, ngroups):
self.df.groupby('key')['values'].cumsum()

def time_describe(self, dtype, ngroups):
self.df.groupby('key')['values'].describe()

def time_diff(self, dtype, ngroups):
self.df.groupby('key')['values'].diff()

def time_first(self, dtype, ngroups):
self.df.groupby('key')['values'].first()

def time_head(self, dtype, ngroups):
self.df.groupby('key')['values'].head()

def time_last(self, dtype, ngroups):
self.df.groupby('key')['values'].last()

def time_mad(self, dtype, ngroups):
self.df.groupby('key')['values'].mad()

def time_max(self, dtype, ngroups):
self.df.groupby('key')['values'].max()

def time_mean(self, dtype, ngroups):
self.df.groupby('key')['values'].mean()

def time_median(self, dtype, ngroups):
self.df.groupby('key')['values'].median()

def time_min(self, dtype, ngroups):
self.df.groupby('key')['values'].min()

def time_nunique(self, dtype, ngroups):
self.df.groupby('key')['values'].nunique()

def time_pct_change(self, dtype, ngroups):
self.df.groupby('key')['values'].pct_change()

def time_prod(self, dtype, ngroups):
self.df.groupby('key')['values'].prod()

def time_rank(self, dtype, ngroups):
self.df.groupby('key')['values'].rank()

def time_sem(self, dtype, ngroups):
self.df.groupby('key')['values'].sem()

def time_shift(self, dtype, ngroups):
self.df.groupby('key')['values'].shift()

def time_size(self, dtype, ngroups):
self.df.groupby('key')['values'].size()

def time_skew(self, dtype, ngroups):
self.df.groupby('key')['values'].skew()

def time_std(self, dtype, ngroups):
self.df.groupby('key')['values'].std()

def time_sum(self, dtype, ngroups):
self.df.groupby('key')['values'].sum()

def time_tail(self, dtype, ngroups):
self.df.groupby('key')['values'].tail()

def time_unique(self, dtype, ngroups):
self.df.groupby('key')['values'].unique()

def time_value_counts(self, dtype, ngroups):
self.df.groupby('key')['values'].value_counts()

def time_var(self, dtype, ngroups):
self.df.groupby('key')['values'].var()
def time_method(self, dtype, method):
self.df_groupby_method()


class Float32(object):
Expand Down