CLN: Add teardowns for some benchmarks (#17616)

Added teardowns for hdfstore, io and packers benchmarks.

Author: dmanikowski-reef

asv_bench/benchmarks/hdfstore_bench.py

@@ -40,6 +40,7 @@ def setup(self):
 
     def teardown(self):
         self.store.close()
+        self.remove(self.f)
 
     def remove(self, f):
         try:
@@ -115,6 +116,7 @@ def setup(self):
 
     def teardown(self):
         self.store.close()
+        self.remove(self.f)
 
     def remove(self, f):
         try:

asv_bench/benchmarks/io_bench.py

@@ -10,16 +10,21 @@
 
 class frame_to_csv(object):
     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)
+
+    def teardown(self):
+        os.remove(self.fname)
 
 
 class frame_to_csv2(object):
     goal_time = 0.2
+    fname = '__test__.csv'
 
     def setup(self):
         self.df = DataFrame({'A': range(50000), })
@@ -28,22 +33,30 @@ 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)
+
+    def teardown(self):
+        os.remove(self.fname)
 
 
 class frame_to_csv_date_formatting(object):
     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')
+
+    def teardown(self):
+        os.remove(self.fname)
 
 
 class frame_to_csv_mixed(object):
     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'))
@@ -55,11 +68,14 @@ 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)]
 
+    def teardown(self):
+        os.remove(self.fname)
+
 
 class read_csv_infer_datetime_format_custom(object):
     goal_time = 0.2
@@ -96,26 +112,34 @@ def time_read_csv_infer_datetime_format_ymd(self):
 
 class read_csv_skiprows(object):
     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)
+
+    def teardown(self):
+        os.remove(self.fname)
 
 
 class read_csv_standard(object):
     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)
+
+    def teardown(self):
+        os.remove(self.fname)
 
 
 class read_parse_dates_iso8601(object):
@@ -154,13 +178,17 @@ def time_read_uint64_na_values(self):
 
 class write_csv_standard(object):
     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)
+
+    def teardown(self):
+        os.remove(self.fname)
 
 
 class read_csv_from_s3(object):

asv_bench/benchmarks/packers.py

@@ -9,6 +9,7 @@
 import numpy as np
 from random import randrange
 
+
 class _Packers(object):
     goal_time = 0.2
 
@@ -28,8 +29,11 @@ def remove(self, 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)

doc/source/whatsnew/v0.22.0.txt

@@ -167,5 +167,5 @@ Other
 ^^^^^
 
 - Improved error message when attempting to use a Python keyword as an identifier in a numexpr query (:issue:`18221`)
--
+- Added teardown functions in asv benchmarks for hdfstore, io and packers benches.
 -