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)

asv_bench/benchmarks/hdfstore_bench.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 import os
 
 
@@ -152,7 +152,7 @@ class read_store_table_panel(object):
 
     def setup(self):
         self.f = '__test__.h5'
-        self.p = Panel(randn(20, 1000, 25), items=[('Item%03d' % i) for i in xrange(20)], major_axis=date_range('1/1/2000', periods=1000), minor_axis=[('E%03d' % i) for i in xrange(25)])
+        self.p = Panel(randn(20, 1000, 25), items=[('Item%03d' % i) for i in range(20)], major_axis=date_range('1/1/2000', periods=1000), minor_axis=[('E%03d' % i) for i in range(25)])
         self.remove(self.f)
         self.store = HDFStore(self.f)
         self.store.append('p1', self.p)
@@ -267,7 +267,7 @@ class write_store_table_dc(object):
 
     def setup(self):
         self.f = '__test__.h5'
-        self.df = DataFrame(np.random.randn(10000, 10), columns=[('C%03d' % i) for i in xrange(10)])
+        self.df = DataFrame(np.random.randn(10000, 10), columns=[('C%03d' % i) for i in range(10)])
         self.remove(self.f)
         self.store = HDFStore(self.f)
 
@@ -312,7 +312,7 @@ class write_store_table_panel(object):
 
     def setup(self):
         self.f = '__test__.h5'
-        self.p = Panel(randn(20, 1000, 25), items=[('Item%03d' % i) for i in xrange(20)], major_axis=date_range('1/1/2000', periods=1000), minor_axis=[('E%03d' % i) for i in xrange(25)])
+        self.p = Panel(randn(20, 1000, 25), items=[('Item%03d' % i) for i in range(20)], major_axis=date_range('1/1/2000', periods=1000), minor_axis=[('E%03d' % i) for i in range(25)])
         self.remove(self.f)
         self.store = HDFStore(self.f)
 

asv_bench/benchmarks/index_object.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 
 
 class datetime_index_intersection(object):
@@ -248,7 +248,7 @@ class multiindex_from_product(object):
     goal_time = 0.2
 
     def setup(self):
-        self.iterables = [tm.makeStringIndex(10000), xrange(20)]
+        self.iterables = [tm.makeStringIndex(10000), range(20)]
 
     def time_multiindex_from_product(self):
         MultiIndex.from_product(self.iterables)

asv_bench/benchmarks/inference.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 import pandas as pd
 
 

asv_bench/benchmarks/io_bench.py

@@ -1,6 +1,9 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 from pandas import concat, Timestamp
-from StringIO import StringIO
+try:
+    from StringIO import StringIO
+except ImportError:
+    from io import StringIO
 
 
 class frame_to_csv(object):
@@ -53,7 +56,7 @@ def time_frame_to_csv_mixed(self):
         self.df.to_csv('__test__.csv')
 
     def create_cols(self, name):
-        return [('%s%03d' % (name, i)) for i in xrange(5)]
+        return [('%s%03d' % (name, i)) for i in range(5)]
 
 
 class read_csv_infer_datetime_format_custom(object):

asv_bench/benchmarks/io_sql.py

@@ -1,7 +1,7 @@
-from pandas_vb_common import *
-from sqlalchemy import create_engine
-import sqlite3
 import sqlalchemy
+from .pandas_vb_common import *
+import sqlite3
+from sqlalchemy import create_engine
 
 
 class sql_datetime_read_and_parse_sqlalchemy(object):

asv_bench/benchmarks/join_merge.py

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

asv_bench/benchmarks/miscellaneous.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 from pandas.util.decorators import cache_readonly
 
 

asv_bench/benchmarks/packers.py

@@ -1,9 +1,9 @@
+from .pandas_vb_common import *
 from numpy.random import randint
 import pandas as pd
 from collections import OrderedDict
 from pandas.compat import BytesIO
 import sqlite3
-from pandas_vb_common import *
 import os
 from sqlalchemy import create_engine
 import numpy as np

asv_bench/benchmarks/pandas_vb_common.py

@@ -0,0 +1,30 @@
+from pandas import *
+import pandas as pd
+from datetime import timedelta
+from numpy.random import randn
+from numpy.random import randint
+from numpy.random import permutation
+import pandas.util.testing as tm
+import random
+import numpy as np
+try:
+    from pandas.compat import range
+except ImportError:
+    pass
+
+np.random.seed(1234)
+try:
+    import pandas._tseries as lib
+except:
+    import pandas.lib as lib
+
+try:
+    Panel = WidePanel
+except Exception:
+    pass
+
+# didn't add to namespace until later
+try:
+    from pandas.core.index import MultiIndex
+except ImportError:
+    pass

asv_bench/benchmarks/pandas_vb_common.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 
 
 class panel_from_dict_all_different_indexes(object):
@@ -8,7 +8,7 @@ def setup(self):
         self.data_frames = {}
         self.start = datetime(1990, 1, 1)
         self.end = datetime(2012, 1, 1)
-        for x in xrange(100):
+        for x in range(100):
             self.end += timedelta(days=1)
             self.dr = np.asarray(date_range(self.start, self.end))
             self.df = DataFrame({'a': ([0] * len(self.dr)), 'b': ([1] * len(self.dr)), 'c': ([2] * len(self.dr)), }, index=self.dr)
@@ -23,7 +23,7 @@ class panel_from_dict_equiv_indexes(object):
 
     def setup(self):
         self.data_frames = {}
-        for x in xrange(100):
+        for x in range(100):
             self.dr = np.asarray(DatetimeIndex(start=datetime(1990, 1, 1), end=datetime(2012, 1, 1), freq=datetools.Day(1)))
             self.df = DataFrame({'a': ([0] * len(self.dr)), 'b': ([1] * len(self.dr)), 'c': ([2] * len(self.dr)), }, index=self.dr)
             self.data_frames[x] = self.df
@@ -38,7 +38,7 @@ class panel_from_dict_same_index(object):
     def setup(self):
         self.dr = np.asarray(DatetimeIndex(start=datetime(1990, 1, 1), end=datetime(2012, 1, 1), freq=datetools.Day(1)))
         self.data_frames = {}
-        for x in xrange(100):
+        for x in range(100):
             self.df = DataFrame({'a': ([0] * len(self.dr)), 'b': ([1] * len(self.dr)), 'c': ([2] * len(self.dr)), }, index=self.dr)
             self.data_frames[x] = self.df
 
@@ -53,7 +53,7 @@ def setup(self):
         self.data_frames = {}
         self.start = datetime(1990, 1, 1)
         self.end = datetime(2012, 1, 1)
-        for x in xrange(100):
+        for x in range(100):
             if (x == 50):
                 self.end += timedelta(days=1)
             self.dr = np.asarray(date_range(self.start, self.end))

asv_bench/benchmarks/panel_ctor.py

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

asv_bench/benchmarks/panel_methods.py

@@ -1,7 +1,10 @@
-from cStringIO import StringIO
-from pandas_vb_common import *
+from .pandas_vb_common import *
 import os
 from pandas import read_csv, read_table
+try:
+    from cStringIO import StringIO
+except ImportError:
+    from io import StringIO
 
 
 class read_csv_comment2(object):

asv_bench/benchmarks/parser_vb.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 try:
     from pandas import date_range
 except ImportError:

asv_bench/benchmarks/plotting.py

@@ -1,4 +1,4 @@
-from pandas_vb_common import *
+from .pandas_vb_common import *
 from random import shuffle