Merge remote-tracking branch 'pandas-dev/master' into bigquery-udf-resources

Author: necnec

.gitignore

@@ -27,6 +27,7 @@
 *.class
 *.dll
 *.exe
+*.pxi
 *.o
 *.py[ocd]
 *.so

.travis.yml

@@ -14,13 +14,9 @@ cache:
 
 env:
   global:
-  # scatterci API key
-  #- secure: "Bx5umgo6WjuGY+5XFa004xjCiX/vq0CyMZ/ETzcs7EIBI1BE/0fIDXOoWhoxbY9HPfdPGlDnDgB9nGqr5wArO2s+BavyKBWg6osZ3dmkfuJPMOWeyCa92EeP+sfKw8e5HSU5MizW9e319wHWOF/xkzdHR7T67Qd5erhv91x4DnQ="
-  # ironcache API key
-  #- secure: "e4eEFn9nDQc3Xa5BWYkzfX37jaWVq89XidVX+rcCNEr5OlOImvveeXnF1IzbRXznH4Sv0YsLwUd8RGUWOmyCvkONq/VJeqCHWtTMyfaCIdqSyhIP9Odz8r9ahch+Y0XFepBey92AJHmlnTh+2GjCDgIiqq4fzglojnp56Vg1ojA="
-  #- secure: "CjmYmY5qEu3KrvMtel6zWFEtMq8ORBeS1S1odJHnjQpbwT1KY2YFZRVlLphfyDQXSz6svKUdeRrCNp65baBzs3DQNA8lIuXGIBYFeJxqVGtYAZZs6+TzBPfJJK798sGOj5RshrOJkFG2rdlWNuTq/XphI0JOrN3nPUkRrdQRpAw="
-  # pandas-docs-bot GH
-  - secure: "PCzUFR8CHmw9lH84p4ygnojdF7Z8U5h7YfY0RyT+5K/aiQ1ZTU3ZkDTPI0/rR5FVMxsEEKEQKMcc5fvqW0PeD7Q2wRmluloKgT9w4EVEJ1ppKf7lITPcvZR2QgVOvjv4AfDtibLHFNiaSjzoqyJVjM4igjOu8WTlF3JfZcmOQjQ="
+
+  # pandas-docs-travis GH
+  - secure: "YvvTc+FrSYHgdxqoxn9s8VOaCWjvZzlkaf6k55kkmQqCYR9dPiLMsot1F96/N7o3YlD1s0znPQCak93Du8HHi/8809zAXloTaMSZrWz4R4qn96xlZFRE88O/w/Z1t3VVYpKX3MHlCggBc8MtXrqmvWKJMAqXyysZ4TTzoiJDPvE="
 
 git:
     # for cloning

asv_bench/benchmarks/algorithms.py

@@ -1,8 +1,9 @@
 import numpy as np
 import pandas as pd
+from pandas.util import testing as tm
 
 
-class algorithm(object):
+class Algorithms(object):
     goal_time = 0.2
 
     def setup(self):
@@ -23,21 +24,28 @@ def setup(self):
         self.arrneg = np.arange(-1000000, 0)
         self.arrmixed = np.array([1, -1]).repeat(500000)
 
-    def time_int_factorize(self):
+        # match
+        self.uniques = tm.makeStringIndex(1000).values
+        self.all = self.uniques.repeat(10)
+
+    def time_factorize_int(self):
         self.int.factorize()
 
-    def time_float_factorize(self):
+    def time_factorize_float(self):
         self.int.factorize()
 
-    def time_int_unique_duplicated(self):
+    def time_duplicated_int_unique(self):
         self.int_unique.duplicated()
 
-    def time_int_duplicated(self):
+    def time_duplicated_int(self):
         self.int.duplicated()
 
-    def time_float_duplicated(self):
+    def time_duplicated_float(self):
         self.float.duplicated()
 
+    def time_match_strings(self):
+        pd.match(self.all, self.uniques)
+
     def time_add_overflow_pos_scalar(self):
         self.checked_add(self.arr, 1)
 
@@ -55,3 +63,35 @@ def time_add_overflow_neg_arr(self):
 
     def time_add_overflow_mixed_arr(self):
         self.checked_add(self.arr, self.arrmixed)
+
+
+class Hashing(object):
+    goal_time = 0.2
+
+    def setup(self):
+        N = 100000
+
+        self.df = pd.DataFrame(
+            {'A': pd.Series(tm.makeStringIndex(100).take(
+                np.random.randint(0, 100, size=N))),
+             'B': pd.Series(tm.makeStringIndex(10000).take(
+                 np.random.randint(0, 10000, size=N))),
+             'D': np.random.randn(N),
+             'E': np.arange(N),
+             'F': pd.date_range('20110101', freq='s', periods=N),
+             'G': pd.timedelta_range('1 day', freq='s', periods=N),
+             })
+        self.df['C'] = self.df['B'].astype('category')
+        self.df.iloc[10:20] = np.nan
+
+    def time_frame(self):
+        self.df.hash()
+
+    def time_series_int(self):
+        self.df.E.hash()
+
+    def time_series_string(self):
+        self.df.B.hash()
+
+    def time_series_categorical(self):
+        self.df.C.hash()

asv_bench/benchmarks/attrs_caching.py

@@ -1,23 +1,32 @@
 from .pandas_vb_common import *
+from pandas.util.decorators import cache_readonly
 
 
-class getattr_dataframe_index(object):
+class DataFrameAttributes(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):
+    def time_get_index(self):
         self.foo = self.df.index
 
+    def time_set_index(self):
+        self.df.index = self.cur_index
+
 
-class setattr_dataframe_index(object):
+class CacheReadonly(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
+        class Foo:
+
+            @cache_readonly
+            def prop(self):
+                return 5
+        self.obj = Foo()
+
+    def time_cache_readonly(self):
+        self.obj.prop