Merge pull request pandas-dev#1 from pandas-dev/master

...

Author: P-Tillmann

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,4 +1,4 @@
  - [ ] closes #xxxx
  - [ ] tests added / passed
- - [ ] passes ``git diff upstream/master --name-only -- '*.py' | flake8 --diff`` (On Windows, ``git diff upstream/master -u -- "*.py" | flake8 --diff`` might work as an alternative.)
+ - [ ] passes ``git diff upstream/master -u -- "*.py" | flake8 --diff``
  - [ ] whatsnew entry

.pep8speaks.yml

@@ -0,0 +1,10 @@
+# File : .pep8speaks.yml
+
+scanner:
+    diff_only: True  # If True, errors caused by only the patch are shown
+
+pycodestyle:
+    max-line-length: 79
+    ignore:  # Errors and warnings to ignore
+        - E731
+        - E402

asv_bench/benchmarks/rolling.py

@@ -0,0 +1,185 @@
+from .pandas_vb_common import *
+import pandas as pd
+import numpy as np
+
+
+class DataframeRolling(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.N = 100000
+        self.Ns = 10000
+        self.df = pd.DataFrame({'a': np.random.random(self.N)})
+        self.dfs = pd.DataFrame({'a': np.random.random(self.Ns)})
+        self.wins = 10
+        self.winl = 1000
+
+    def time_rolling_quantile_0(self):
+        (self.df.rolling(self.wins).quantile(0.0))
+
+    def time_rolling_quantile_1(self):
+        (self.df.rolling(self.wins).quantile(1.0))
+
+    def time_rolling_quantile_median(self):
+        (self.df.rolling(self.wins).quantile(0.5))
+
+    def time_rolling_median(self):
+        (self.df.rolling(self.wins).median())
+
+    def time_rolling_mean(self):
+        (self.df.rolling(self.wins).mean())
+
+    def time_rolling_max(self):
+        (self.df.rolling(self.wins).max())
+
+    def time_rolling_min(self):
+        (self.df.rolling(self.wins).min())
+
+    def time_rolling_std(self):
+        (self.df.rolling(self.wins).std())
+
+    def time_rolling_count(self):
+        (self.df.rolling(self.wins).count())
+
+    def time_rolling_skew(self):
+        (self.df.rolling(self.wins).skew())
+
+    def time_rolling_kurt(self):
+        (self.df.rolling(self.wins).kurt())
+
+    def time_rolling_sum(self):
+        (self.df.rolling(self.wins).sum())
+
+    def time_rolling_corr(self):
+        (self.dfs.rolling(self.wins).corr())
+
+    def time_rolling_cov(self):
+        (self.dfs.rolling(self.wins).cov())
+        
+    def time_rolling_quantile_0_l(self):
+        (self.df.rolling(self.winl).quantile(0.0))
+
+    def time_rolling_quantile_1_l(self):
+        (self.df.rolling(self.winl).quantile(1.0))
+
+    def time_rolling_quantile_median_l(self):
+        (self.df.rolling(self.winl).quantile(0.5))
+
+    def time_rolling_median_l(self):
+        (self.df.rolling(self.winl).median())
+
+    def time_rolling_mean_l(self):
+        (self.df.rolling(self.winl).mean())
+
+    def time_rolling_max_l(self):
+        (self.df.rolling(self.winl).max())
+
+    def time_rolling_min_l(self):
+        (self.df.rolling(self.winl).min())
+
+    def time_rolling_std_l(self):
+        (self.df.rolling(self.wins).std())
+
+    def time_rolling_count_l(self):
+        (self.df.rolling(self.wins).count())
+
+    def time_rolling_skew_l(self):
+        (self.df.rolling(self.wins).skew())
+
+    def time_rolling_kurt_l(self):
+        (self.df.rolling(self.wins).kurt())
+
+    def time_rolling_sum_l(self):
+        (self.df.rolling(self.wins).sum())
+
+
+class SeriesRolling(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.N = 100000
+        self.Ns = 10000
+        self.df = pd.DataFrame({'a': np.random.random(self.N)})
+        self.dfs = pd.DataFrame({'a': np.random.random(self.Ns)})
+        self.sr = self.df.a
+        self.srs = self.dfs.a
+        self.wins = 10
+        self.winl = 1000
+
+    def time_rolling_quantile_0(self):
+        (self.sr.rolling(self.wins).quantile(0.0))
+
+    def time_rolling_quantile_1(self):
+        (self.sr.rolling(self.wins).quantile(1.0))
+
+    def time_rolling_quantile_median(self):
+        (self.sr.rolling(self.wins).quantile(0.5))
+
+    def time_rolling_median(self):
+        (self.sr.rolling(self.wins).median())
+
+    def time_rolling_mean(self):
+        (self.sr.rolling(self.wins).mean())
+
+    def time_rolling_max(self):
+        (self.sr.rolling(self.wins).max())
+
+    def time_rolling_min(self):
+        (self.sr.rolling(self.wins).min())
+
+    def time_rolling_std(self):
+        (self.sr.rolling(self.wins).std())
+
+    def time_rolling_count(self):
+        (self.sr.rolling(self.wins).count())
+
+    def time_rolling_skew(self):
+        (self.sr.rolling(self.wins).skew())
+
+    def time_rolling_kurt(self):
+        (self.sr.rolling(self.wins).kurt())
+
+    def time_rolling_sum(self):
+        (self.sr.rolling(self.wins).sum())
+
+    def time_rolling_corr(self):
+        (self.srs.rolling(self.wins).corr())
+
+    def time_rolling_cov(self):
+        (self.srs.rolling(self.wins).cov())
+        
+    def time_rolling_quantile_0_l(self):
+        (self.sr.rolling(self.winl).quantile(0.0))
+
+    def time_rolling_quantile_1_l(self):
+        (self.sr.rolling(self.winl).quantile(1.0))
+
+    def time_rolling_quantile_median_l(self):
+        (self.sr.rolling(self.winl).quantile(0.5))
+
+    def time_rolling_median_l(self):
+        (self.sr.rolling(self.winl).median())
+
+    def time_rolling_mean_l(self):
+        (self.sr.rolling(self.winl).mean())
+
+    def time_rolling_max_l(self):
+        (self.sr.rolling(self.winl).max())
+
+    def time_rolling_min_l(self):
+        (self.sr.rolling(self.winl).min())
+
+    def time_rolling_std_l(self):
+        (self.sr.rolling(self.wins).std())
+
+    def time_rolling_count_l(self):
+        (self.sr.rolling(self.wins).count())
+
+    def time_rolling_skew_l(self):
+        (self.sr.rolling(self.wins).skew())
+
+    def time_rolling_kurt_l(self):
+        (self.sr.rolling(self.wins).kurt())
+
+    def time_rolling_sum_l(self):
+        (self.sr.rolling(self.wins).sum())

asv_bench/benchmarks/sparse.py

@@ -1,3 +1,5 @@
+from itertools import repeat
+
 from .pandas_vb_common import *
 import scipy.sparse
 from pandas import SparseSeries, SparseDataFrame
@@ -27,6 +29,12 @@ class sparse_frame_constructor(object):
     def time_sparse_frame_constructor(self):
         SparseDataFrame(columns=np.arange(100), index=np.arange(1000))
 
+    def time_sparse_from_scipy(self):
+        SparseDataFrame(scipy.sparse.rand(1000, 1000, 0.005))
+
+    def time_sparse_from_dict(self):
+        SparseDataFrame(dict(zip(range(1000), repeat([0]))))
+
 
 class sparse_series_from_coo(object):
     goal_time = 0.2

asv_bench/benchmarks/timeseries.py

@@ -53,7 +53,11 @@ def setup(self):
         self.rng6 = date_range(start='1/1/1', periods=self.N, freq='B')
 
         self.rng7 = date_range(start='1/1/1700', freq='D', periods=100000)
-        self.a = self.rng7[:50000].append(self.rng7[50002:])
+        self.no_freq = self.rng7[:50000].append(self.rng7[50002:])
+        self.d_freq = self.rng7[:50000].append(self.rng7[50000:])
+
+        self.rng8 = date_range(start='1/1/1700', freq='B', periods=100000)
+        self.b_freq = self.rng8[:50000].append(self.rng8[50000:])
 
     def time_add_timedelta(self):
         (self.rng + dt.timedelta(minutes=2))
@@ -94,8 +98,14 @@ def time_infer_dst(self):
     def time_timeseries_is_month_start(self):
         self.rng6.is_month_start
 
-    def time_infer_freq(self):
-        infer_freq(self.a)
+    def time_infer_freq_none(self):
+        infer_freq(self.no_freq)
+
+    def time_infer_freq_daily(self):
+        infer_freq(self.d_freq)
+
+    def time_infer_freq_business(self):
+        infer_freq(self.b_freq)
 
 
 class TimeDatetimeConverter(object):

asv_bench/vbench_to_asv.py

@@ -114,7 +114,7 @@ def translate_module(target_module):
     l_vars = {}
     exec('import ' + target_module) in g_vars
 
-    print target_module
+    print(target_module)
     module = eval(target_module, g_vars)
 
     benchmarks = []
@@ -157,7 +157,7 @@ def translate_module(target_module):
         mod = os.path.basename(module)
         if mod in ['make.py', 'measure_memory_consumption.py', 'perf_HEAD.py', 'run_suite.py', 'test_perf.py', 'generate_rst_files.py', 'test.py', 'suite.py']:
             continue
-        print
-        print mod
+        print('')
+        print(mod)
 
         translate_module(mod.replace('.py', ''))