PERF: Fix performance benchmark suite so it runs on Python 3

Author: qwhelan

asv_bench/asv.conf.json

@@ -26,7 +26,7 @@
     // The Pythons you'd like to test against.  If not provided, defaults
     // to the current version of Python used to run `asv`.
     // "pythons": ["2.7", "3.4"],
-    "pythons": ["2.7"],
+    "pythons": ["2.7", "3.4"],
 
     // The matrix of dependencies to test.  Each key is the name of a
     // package (in PyPI) and the values are version numbers.  An empty

asv_bench/benchmarks/attrs_caching.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 
 
 class getattr_dataframe_index(object):

asv_bench/benchmarks/binary_ops.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 import pandas.computation.expressions as expr
 
 

asv_bench/benchmarks/categoricals.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 
 
 class concat_categorical(object):

asv_bench/benchmarks/ctors.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 
 
 class frame_constructor_ndarray(object):

asv_bench/benchmarks/eval.py

@@ -1,6 +1,6 @@
-from pandas_vb_common import *
-import pandas.computation.expressions as expr
+from .pandas_vb_common import *
 import pandas as pd
+import pandas.computation.expressions as expr
 
 
 class eval_frame_add_all_threads(object):

asv_bench/benchmarks/frame_ctor.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 try:
     from pandas.tseries.offsets import *
 except:
@@ -1657,7 +1657,7 @@ class frame_ctor_nested_dict_int64(object):
     goal_time = 0.2
 
     def setup(self):
-        self.data = dict(((i, dict(((j, float(j)) for j in xrange(100)))) for i in xrange(2000)))
+        self.data = dict(((i, dict(((j, float(j)) for j in range(100)))) for i in xrange(2000)))
 
     def time_frame_ctor_nested_dict_int64(self):
         DataFrame(self.data)

asv_bench/benchmarks/frame_methods.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 
 
 class frame_apply_axis_1(object):
@@ -398,7 +398,7 @@ def time_frame_from_records_generator(self):
         self.df = DataFrame.from_records(self.get_data())
 
     def get_data(self, n=100000):
-        return ((x, (x * 20), (x * 100)) for x in xrange(n))
+        return ((x, (x * 20), (x * 100)) for x in range(n))
 
 
 class frame_from_records_generator_nrows(object):
@@ -408,7 +408,7 @@ def time_frame_from_records_generator_nrows(self):
         self.df = DataFrame.from_records(self.get_data(), nrows=1000)
 
     def get_data(self, n=100000):
-        return ((x, (x * 20), (x * 100)) for x in xrange(n))
+        return ((x, (x * 20), (x * 100)) for x in range(n))
 
 
 class frame_get_dtype_counts(object):
@@ -443,11 +443,11 @@ def g(self):
             pass
 
     def h(self):
-        for i in xrange(10000):
+        for i in range(10000):
             self.df2['A']
 
     def j(self):
-        for i in xrange(10000):
+        for i in range(10000):
             self.df3[0]
 
 
@@ -473,11 +473,11 @@ def g(self):
             pass
 
     def h(self):
-        for i in xrange(10000):
+        for i in range(10000):
             self.df2['A']
 
     def j(self):
-        for i in xrange(10000):
+        for i in range(10000):
             self.df3[0]
 
 
@@ -607,11 +607,11 @@ def g(self):
             pass
 
     def h(self):
-        for i in xrange(10000):
+        for i in range(10000):
             self.df2['A']
 
     def j(self):
-        for i in xrange(10000):
+        for i in range(10000):
             self.df3[0]
 
 
@@ -637,11 +637,11 @@ def g(self):
             pass
 
     def h(self):
-        for i in xrange(10000):
+        for i in range(10000):
             self.df2['A']
 
     def j(self):
-        for i in xrange(10000):
+        for i in range(10000):
             self.df3[0]
 
 

asv_bench/benchmarks/gil.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 from pandas.core import common as com
 try:
     from pandas.util.testing import test_parallel

asv_bench/benchmarks/groupby.py

@@ -1,6 +1,6 @@
-from pandas_vb_common import *
-from itertools import product
+from .pandas_vb_common import *
 from string import ascii_letters, digits
+from itertools import product
 
 
 class groupby_agg_builtins1(object):
@@ -1535,12 +1535,12 @@ def setup(self):
         self.secid_max = int('F0000000', 16)
         self.step = ((self.secid_max - self.secid_min) // (self.n_securities - 1))
         self.security_ids = map((lambda x: hex(x)[2:10].upper()), range(self.secid_min, (self.secid_max + 1), self.step))
-        self.data_index = MultiIndex(levels=[self.dates.values, self.security_ids], labels=[[i for i in xrange(self.n_dates) for _ in xrange(self.n_securities)], (range(self.n_securities) * self.n_dates)], names=['date', 'security_id'])
+        self.data_index = MultiIndex(levels=[self.dates.values, self.security_ids], labels=[[i for i in range(self.n_dates) for _ in xrange(self.n_securities)], (range(self.n_securities) * self.n_dates)], names=['date', 'security_id'])
         self.n_data = len(self.data_index)
-        self.columns = Index(['factor{}'.format(i) for i in xrange(1, (self.n_columns + 1))])
+        self.columns = Index(['factor{}'.format(i) for i in range(1, (self.n_columns + 1))])
         self.data = DataFrame(np.random.randn(self.n_data, self.n_columns), index=self.data_index, columns=self.columns)
         self.step = int((self.n_data * self.share_na))
-        for column_index in xrange(self.n_columns):
+        for column_index in range(self.n_columns):
             self.index = column_index
             while (self.index < self.n_data):
                 self.data.set_value(self.data_index[self.index], self.columns[column_index], np.nan)
@@ -1644,12 +1644,12 @@ def setup(self):
         self.secid_max = int('F0000000', 16)
         self.step = ((self.secid_max - self.secid_min) // (self.n_securities - 1))
         self.security_ids = map((lambda x: hex(x)[2:10].upper()), range(self.secid_min, (self.secid_max + 1), self.step))
-        self.data_index = MultiIndex(levels=[self.dates.values, self.security_ids], labels=[[i for i in xrange(self.n_dates) for _ in xrange(self.n_securities)], (range(self.n_securities) * self.n_dates)], names=['date', 'security_id'])
+        self.data_index = MultiIndex(levels=[self.dates.values, self.security_ids], labels=[[i for i in range(self.n_dates) for _ in xrange(self.n_securities)], (range(self.n_securities) * self.n_dates)], names=['date', 'security_id'])
         self.n_data = len(self.data_index)
-        self.columns = Index(['factor{}'.format(i) for i in xrange(1, (self.n_columns + 1))])
+        self.columns = Index(['factor{}'.format(i) for i in range(1, (self.n_columns + 1))])
         self.data = DataFrame(np.random.randn(self.n_data, self.n_columns), index=self.data_index, columns=self.columns)
         self.step = int((self.n_data * self.share_na))
-        for column_index in xrange(self.n_columns):
+        for column_index in range(self.n_columns):
             self.index = column_index
             while (self.index < self.n_data):
                 self.data.set_value(self.data_index[self.index], self.columns[column_index], np.nan)