Merge branch 'master' of https://github.com/pandas-dev/pandas into error-on-non-naive-datetime-strings

Author: 1kastner

asv_bench/benchmarks/attrs_caching.py

@@ -1,4 +1,5 @@
-from .pandas_vb_common import *
+import numpy as np
+from pandas import DataFrame
 
 try:
     from pandas.util import cache_readonly
@@ -7,9 +8,11 @@
 
 
 class DataFrameAttributes(object):
+
     goal_time = 0.2
 
     def setup(self):
+        np.random.seed(1234)
         self.df = DataFrame(np.random.randn(10, 6))
         self.cur_index = self.df.index
 
@@ -21,6 +24,7 @@ def time_set_index(self):
 
 
 class CacheReadonly(object):
+
     goal_time = 0.2
 
     def setup(self):

asv_bench/benchmarks/frame_ctor.py

@@ -132,7 +132,7 @@ def setup(self, offset, n_steps):
         offset = getattr(offsets, offset)
         self.idx = get_index_for_offset(offset(n_steps, **kwargs))
         self.df = DataFrame(np.random.randn(len(self.idx), 10), index=self.idx)
-        self.d = dict([(col, self.df[col]) for col in self.df.columns])
+        self.d = dict(self.df.items())
 
     def time_frame_ctor(self, offset, n_steps):
         DataFrame(self.d)

asv_bench/benchmarks/hdfstore_bench.py

@@ -40,10 +40,11 @@ def setup(self):
 
     def teardown(self):
         self.store.close()
+        self.remove(self.f)
 
     def remove(self, f):
         try:
-            os.remove(self.f)
+            os.remove(f)
         except:
             pass
 
@@ -115,10 +116,11 @@ def setup(self):
 
     def teardown(self):
         self.store.close()
+        self.remove(self.f)
 
     def remove(self, f):
         try:
-            os.remove(self.f)
+            os.remove(f)
         except:
             pass
 

asv_bench/benchmarks/io_bench.py

@@ -8,18 +8,36 @@
 import timeit
 
 
-class frame_to_csv(object):
+class _BenchTeardown(object):
+    """
+    base class for teardown method implementation
+    """
+    fname = None
+
+    def remove(self, f):
+        try:
+            os.remove(f)
+        except:
+            pass
+
+    def teardown(self):
+        self.remove(self.fname)
+
+
+class frame_to_csv(_BenchTeardown):
     goal_time = 0.2
+    fname = '__test__.csv'
 
     def setup(self):
         self.df = DataFrame(np.random.randn(3000, 30))
 
     def time_frame_to_csv(self):
-        self.df.to_csv('__test__.csv')
+        self.df.to_csv(self.fname)
 
 
-class frame_to_csv2(object):
+class frame_to_csv2(_BenchTeardown):
     goal_time = 0.2
+    fname = '__test__.csv'
 
     def setup(self):
         self.df = DataFrame({'A': range(50000), })
@@ -28,22 +46,24 @@ def setup(self):
         self.df['D'] = (self.df.A + 3.0)
 
     def time_frame_to_csv2(self):
-        self.df.to_csv('__test__.csv')
+        self.df.to_csv(self.fname)
 
 
-class frame_to_csv_date_formatting(object):
+class frame_to_csv_date_formatting(_BenchTeardown):
     goal_time = 0.2
+    fname = '__test__.csv'
 
     def setup(self):
         self.rng = date_range('1/1/2000', periods=1000)
         self.data = DataFrame(self.rng, index=self.rng)
 
     def time_frame_to_csv_date_formatting(self):
-        self.data.to_csv('__test__.csv', date_format='%Y%m%d')
+        self.data.to_csv(self.fname, date_format='%Y%m%d')
 
 
-class frame_to_csv_mixed(object):
+class frame_to_csv_mixed(_BenchTeardown):
     goal_time = 0.2
+    fname = '__test__.csv'
 
     def setup(self):
         self.df_float = DataFrame(np.random.randn(5000, 5), dtype='float64', columns=self.create_cols('float'))
@@ -55,7 +75,7 @@ def setup(self):
         self.df = concat([self.df_float, self.df_int, self.df_bool, self.df_object, self.df_dt], axis=1)
 
     def time_frame_to_csv_mixed(self):
-        self.df.to_csv('__test__.csv')
+        self.df.to_csv(self.fname)
 
     def create_cols(self, name):
         return [('%s%03d' % (name, i)) for i in range(5)]
@@ -94,28 +114,30 @@ def time_read_csv_infer_datetime_format_ymd(self):
         read_csv(StringIO(self.data), header=None, names=['foo'], parse_dates=['foo'], infer_datetime_format=True)
 
 
-class read_csv_skiprows(object):
+class read_csv_skiprows(_BenchTeardown):
     goal_time = 0.2
+    fname = '__test__.csv'
 
     def setup(self):
         self.index = tm.makeStringIndex(20000)
         self.df = DataFrame({'float1': randn(20000), 'float2': randn(20000), 'string1': (['foo'] * 20000), 'bool1': ([True] * 20000), 'int1': np.random.randint(0, 200000, size=20000), }, index=self.index)
-        self.df.to_csv('__test__.csv')
+        self.df.to_csv(self.fname)
 
     def time_read_csv_skiprows(self):
-        read_csv('__test__.csv', skiprows=10000)
+        read_csv(self.fname, skiprows=10000)
 
 
-class read_csv_standard(object):
+class read_csv_standard(_BenchTeardown):
     goal_time = 0.2
+    fname = '__test__.csv'
 
     def setup(self):
         self.index = tm.makeStringIndex(10000)
         self.df = DataFrame({'float1': randn(10000), 'float2': randn(10000), 'string1': (['foo'] * 10000), 'bool1': ([True] * 10000), 'int1': np.random.randint(0, 100000, size=10000), }, index=self.index)
-        self.df.to_csv('__test__.csv')
+        self.df.to_csv(self.fname)
 
     def time_read_csv_standard(self):
-        read_csv('__test__.csv')
+        read_csv(self.fname)
 
 
 class read_parse_dates_iso8601(object):
@@ -152,15 +174,16 @@ def time_read_uint64_na_values(self):
         read_csv(StringIO(self.data1), header=None, na_values=self.na_values)
 
 
-class write_csv_standard(object):
+class write_csv_standard(_BenchTeardown):
     goal_time = 0.2
+    fname = '__test__.csv'
 
     def setup(self):
         self.index = tm.makeStringIndex(10000)
         self.df = DataFrame({'float1': randn(10000), 'float2': randn(10000), 'string1': (['foo'] * 10000), 'bool1': ([True] * 10000), 'int1': np.random.randint(0, 100000, size=10000), }, index=self.index)
 
     def time_write_csv_standard(self):
-        self.df.to_csv('__test__.csv')
+        self.df.to_csv(self.fname)
 
 
 class read_csv_from_s3(object):
@@ -195,22 +218,16 @@ def time_read_nrows(self, compression, engine):
                     compression=compression, engine=engine)
 
 
-class read_json_lines(object):
+class read_json_lines(_BenchTeardown):
     goal_time = 0.2
     fname = "__test__.json"
 
     def setup(self):
         self.N = 100000
         self.C = 5
-        self.df = DataFrame(dict([('float{0}'.format(i), randn(self.N)) for i in range(self.C)]))
+        self.df = DataFrame({('float{0}'.format(i), randn(self.N)) for i in range(self.C)})
         self.df.to_json(self.fname,orient="records",lines=True)
 
-    def teardown(self):
-        try:
-            os.remove(self.fname)
-        except:
-            pass
-
     def time_read_json_lines(self):
         pd.read_json(self.fname, lines=True)
 

asv_bench/benchmarks/packers.py

@@ -9,6 +9,7 @@
 import numpy as np
 from random import randrange
 
+
 class _Packers(object):
     goal_time = 0.2
 
@@ -17,19 +18,22 @@ def _setup(self):
         self.N = 100000
         self.C = 5
         self.index = date_range('20000101', periods=self.N, freq='H')
-        self.df = DataFrame(dict([('float{0}'.format(i), randn(self.N)) for i in range(self.C)]), index=self.index)
+        self.df = DataFrame(dict(('float{0}'.format(i), randn(self.N)) for i in range(self.C)), index=self.index)
         self.df2 = self.df.copy()
         self.df2['object'] = [('%08x' % randrange((16 ** 8))) for _ in range(self.N)]
         self.remove(self.f)
 
     def remove(self, f):
         try:
-            os.remove(self.f)
+            os.remove(f)
         except:
             pass
 
+    def teardown(self):
+        self.remove(self.f)
+
+
 class Packers(_Packers):
-    goal_time = 0.2
 
     def setup(self):
         self._setup()
@@ -38,8 +42,8 @@ def setup(self):
     def time_packers_read_csv(self):
         pd.read_csv(self.f)
 
+
 class packers_read_excel(_Packers):
-    goal_time = 0.2
 
     def setup(self):
         self._setup()
@@ -54,7 +58,6 @@ def time_packers_read_excel(self):
 
 
 class packers_read_hdf_store(_Packers):
-    goal_time = 0.2
 
     def setup(self):
         self._setup()
@@ -115,6 +118,7 @@ def setup(self):
     def time_packers_read_pickle(self):
         pd.read_pickle(self.f)
 
+
 class packers_read_sql(_Packers):
 
     def setup(self):
@@ -177,9 +181,6 @@ def setup(self):
     def time_write_csv(self):
         self.df.to_csv(self.f)
 
-    def teardown(self):
-        self.remove(self.f)
-
 
 class Excel(_Packers):
 
@@ -217,8 +218,6 @@ def time_write_hdf_store(self):
     def time_write_hdf_table(self):
         self.df2.to_hdf(self.f, 'df', table=True)
 
-    def teardown(self):
-        self.remove(self.f)
 
 class JSON(_Packers):
 
@@ -259,9 +258,6 @@ def time_write_json_mixed_float_int_str(self):
     def time_write_json_lines(self):
         self.df.to_json(self.f, orient="records", lines=True)
 
-    def teardown(self):
-        self.remove(self.f)
-
 
 class MsgPack(_Packers):
 
@@ -271,9 +267,6 @@ def setup(self):
     def time_write_msgpack(self):
         self.df2.to_msgpack(self.f)
 
-    def teardown(self):
-        self.remove(self.f)
-
 
 class Pickle(_Packers):
 
@@ -283,9 +276,6 @@ def setup(self):
     def time_write_pickle(self):
         self.df2.to_pickle(self.f)
 
-    def teardown(self):
-        self.remove(self.f)
-
 
 class SQL(_Packers):
 
@@ -313,6 +303,3 @@ def time_write_stata(self):
 
     def time_write_stata_with_validation(self):
         self.df3.to_stata(self.f, {'index': 'tc', })
-
-    def teardown(self):
-        self.remove(self.f)