PERF: add initial asv config and vbench->asv conversion script

Author: qwhelan

asv_bench/asv.conf.json

@@ -0,0 +1,64 @@
+{
+    // The version of the config file format.  Do not change, unless
+    // you know what you are doing.
+    "version": 1,
+
+    // The name of the project being benchmarked
+    "project": "pandas",
+
+    // The project's homepage
+    "project_url": "http://pandas.pydata.org/",
+
+    // The URL of the source code repository for the project being
+    // benchmarked
+    "repo": "..",
+
+    // The tool to use to create environments.  May be "conda",
+    // "virtualenv" or other value depending on the plugins in use.
+    // If missing or the empty string, the tool will be automatically
+    // determined by looking for tools on the PATH environment
+    // variable.
+    "environment_type": "conda",
+
+    // the base URL to show a commit for the project.
+    "show_commit_url": "https://github.com/pydata/pandas/commit/",
+
+    // 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"],
+
+    // The matrix of dependencies to test.  Each key is the name of a
+    // package (in PyPI) and the values are version numbers.  An empty
+    // list indicates to just test against the default (latest)
+    // version.
+    "matrix": {
+        // To run against multiple versions, replace with
+        // "numpy": ["1.7", "1.9"],
+        "numpy": [],
+        "Cython": [],
+        "matplotlib": [],
+        "sqlalchemy": [],
+        "scipy": [],
+        "pytables": [],
+    },
+
+    // The directory (relative to the current directory) that benchmarks are
+    // stored in.  If not provided, defaults to "benchmarks"
+    // "benchmark_dir": "benchmarks",
+
+    // The directory (relative to the current directory) to cache the Python
+    // environments in.  If not provided, defaults to "env"
+    // "env_dir": "env",
+
+
+    // The directory (relative to the current directory) that raw benchmark
+    // results are stored in.  If not provided, defaults to "results".
+    // "results_dir": "results",
+
+    // The directory (relative to the current directory) that the html tree
+    // should be written to.  If not provided, defaults to "html".
+    // "html_dir": "html",
+
+    // The number of characters to retain in the commit hashes.
+    // "hash_length": 8
+}

asv_bench/benchmarks/__init__.py

@@ -0,0 +1,23 @@
+from pandas_vb_common import *
+
+
+class getattr_dataframe_index(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(10, 6))
+        self.cur_index = self.df.index
+
+    def time_getattr_dataframe_index(self):
+        self.foo = self.df.index
+
+
+class setattr_dataframe_index(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(10, 6))
+        self.cur_index = self.df.index
+
+    def time_setattr_dataframe_index(self):
+        self.df.index = self.cur_index

asv_bench/benchmarks/attrs_caching.py

@@ -0,0 +1,236 @@
+from pandas_vb_common import *
+import pandas.computation.expressions as expr
+
+
+class frame_add(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(20000, 100))
+        self.df2 = DataFrame(np.random.randn(20000, 100))
+
+    def time_frame_add(self):
+        (self.df + self.df2)
+
+
+class frame_add_no_ne(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(20000, 100))
+        self.df2 = DataFrame(np.random.randn(20000, 100))
+        expr.set_use_numexpr(False)
+
+    def time_frame_add_no_ne(self):
+        (self.df + self.df2)
+
+    def teardown(self):
+        expr.set_use_numexpr(True)
+
+
+class frame_add_st(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(20000, 100))
+        self.df2 = DataFrame(np.random.randn(20000, 100))
+        expr.set_numexpr_threads(1)
+
+    def time_frame_add_st(self):
+        (self.df + self.df2)
+
+    def teardown(self):
+        expr.set_numexpr_threads()
+
+
+class frame_float_div(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(1000, 1000))
+        self.df2 = DataFrame(np.random.randn(1000, 1000))
+
+    def time_frame_float_div(self):
+        (self.df // self.df2)
+
+
+class frame_float_div_by_zero(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(1000, 1000))
+
+    def time_frame_float_div_by_zero(self):
+        (self.df / 0)
+
+
+class frame_float_floor_by_zero(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(1000, 1000))
+
+    def time_frame_float_floor_by_zero(self):
+        (self.df // 0)
+
+
+class frame_float_mod(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(1000, 1000))
+        self.df2 = DataFrame(np.random.randn(1000, 1000))
+
+    def time_frame_float_mod(self):
+        (self.df / self.df2)
+
+
+class frame_int_div_by_zero(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.random_integers(np.iinfo(np.int16).min, np.iinfo(np.int16).max, size=(1000, 1000)))
+
+    def time_frame_int_div_by_zero(self):
+        (self.df / 0)
+
+
+class frame_int_mod(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.random_integers(np.iinfo(np.int16).min, np.iinfo(np.int16).max, size=(1000, 1000)))
+        self.df2 = DataFrame(np.random.random_integers(np.iinfo(np.int16).min, np.iinfo(np.int16).max, size=(1000, 1000)))
+
+    def time_frame_int_mod(self):
+        (self.df / self.df2)
+
+
+class frame_mult(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(20000, 100))
+        self.df2 = DataFrame(np.random.randn(20000, 100))
+
+    def time_frame_mult(self):
+        (self.df * self.df2)
+
+
+class frame_mult_no_ne(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(20000, 100))
+        self.df2 = DataFrame(np.random.randn(20000, 100))
+        expr.set_use_numexpr(False)
+
+    def time_frame_mult_no_ne(self):
+        (self.df * self.df2)
+
+    def teardown(self):
+        expr.set_use_numexpr(True)
+
+
+class frame_mult_st(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(20000, 100))
+        self.df2 = DataFrame(np.random.randn(20000, 100))
+        expr.set_numexpr_threads(1)
+
+    def time_frame_mult_st(self):
+        (self.df * self.df2)
+
+    def teardown(self):
+        expr.set_numexpr_threads()
+
+
+class frame_multi_and(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(20000, 100))
+        self.df2 = DataFrame(np.random.randn(20000, 100))
+
+    def time_frame_multi_and(self):
+        self.df[((self.df > 0) & (self.df2 > 0))]
+
+
+class frame_multi_and_no_ne(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(20000, 100))
+        self.df2 = DataFrame(np.random.randn(20000, 100))
+        expr.set_use_numexpr(False)
+
+    def time_frame_multi_and_no_ne(self):
+        self.df[((self.df > 0) & (self.df2 > 0))]
+
+    def teardown(self):
+        expr.set_use_numexpr(True)
+
+
+class frame_multi_and_st(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.df = DataFrame(np.random.randn(20000, 100))
+        self.df2 = DataFrame(np.random.randn(20000, 100))
+        expr.set_numexpr_threads(1)
+
+    def time_frame_multi_and_st(self):
+        self.df[((self.df > 0) & (self.df2 > 0))]
+
+    def teardown(self):
+        expr.set_numexpr_threads()
+
+
+class series_timestamp_compare(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.N = 1000000
+        self.halfway = ((self.N // 2) - 1)
+        self.s = Series(date_range('20010101', periods=self.N, freq='T'))
+        self.ts = self.s[self.halfway]
+
+    def time_series_timestamp_compare(self):
+        (self.s <= self.ts)
+
+
+class timestamp_ops_diff1(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.N = 1000000
+        self.s = Series(date_range('20010101', periods=self.N, freq='s'))
+
+    def time_timestamp_ops_diff1(self):
+        self.s.diff()
+
+
+class timestamp_ops_diff2(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.N = 1000000
+        self.s = Series(date_range('20010101', periods=self.N, freq='s'))
+
+    def time_timestamp_ops_diff2(self):
+        (self.s - self.s.shift())
+
+
+class timestamp_series_compare(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.N = 1000000
+        self.halfway = ((self.N // 2) - 1)
+        self.s = Series(date_range('20010101', periods=self.N, freq='T'))
+        self.ts = self.s[self.halfway]
+
+    def time_timestamp_series_compare(self):
+        (self.ts >= self.s)

asv_bench/benchmarks/binary_ops.py

@@ -0,0 +1,11 @@
+from pandas_vb_common import *
+
+
+class concat_categorical(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.s = pd.Series((list('aabbcd') * 1000000)).astype('category')
+
+    def time_concat_categorical(self):
+        concat([self.s, self.s])

asv_bench/benchmarks/categoricals.py

@@ -0,0 +1,52 @@
+from pandas_vb_common import *
+
+
+class frame_constructor_ndarray(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.arr = np.random.randn(100, 100)
+
+    def time_frame_constructor_ndarray(self):
+        DataFrame(self.arr)
+
+
+class ctor_index_array_string(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.data = np.array(['foo', 'bar', 'baz'], dtype=object)
+
+    def time_ctor_index_array_string(self):
+        Index(self.data)
+
+
+class series_constructor_ndarray(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.data = np.random.randn(100)
+        self.index = Index(np.arange(100))
+
+    def time_series_constructor_ndarray(self):
+        Series(self.data, index=self.index)
+
+
+class dtindex_from_series_ctor(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.s = Series(([Timestamp('20110101'), Timestamp('20120101'), Timestamp('20130101')] * 1000))
+
+    def time_dtindex_from_series_ctor(self):
+        DatetimeIndex(self.s)
+
+
+class index_from_series_ctor(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.s = Series(([Timestamp('20110101'), Timestamp('20120101'), Timestamp('20130101')] * 1000))
+
+    def time_index_from_series_ctor(self):
+        Index(self.s)