conflict PR pandas-dev#14856 resolved

Author: ischurov

.travis.yml

@@ -16,7 +16,7 @@ env:
   global:
 
   # pandas-docs-travis GH
-  - secure: "UJK7kUtkcnV9PFP4IBXAvgmRQKdwARlfqF4UZQ5tBwrpnD1a3n7FLBijcuXQ3jkvwpEc/FZB9RJDXmsqYXJPvq3BC++2Cv2tFDvKr/c+y8KffszAyVk47jKEHMNmGgauwaNMggsE/rH8YHe4so9LsJHTRbzmLo8lXPNTldoIu5s="
+  - secure: "YvvTc+FrSYHgdxqoxn9s8VOaCWjvZzlkaf6k55kkmQqCYR9dPiLMsot1F96/N7o3YlD1s0znPQCak93Du8HHi/8809zAXloTaMSZrWz4R4qn96xlZFRE88O/w/Z1t3VVYpKX3MHlCggBc8MtXrqmvWKJMAqXyysZ4TTzoiJDPvE="
 
 git:
     # for cloning
@@ -66,19 +66,6 @@ matrix:
         apt:
           packages:
           - python-gtk2
-    - python: 3.4
-      env:
-        - PYTHON_VERSION=3.4
-        - JOB_NAME: "34_nslow"
-        - NOSE_ARGS="not slow and not disabled"
-        - FULL_DEPS=true
-        - CLIPBOARD=xsel
-        - CACHE_NAME="34_nslow"
-        - USE_CACHE=true
-      addons:
-        apt:
-          packages:
-          - xsel
     - python: 3.5
       env:
         - PYTHON_VERSION=3.5
@@ -93,6 +80,33 @@ matrix:
         apt:
           packages:
           - xsel
+    - python: 3.6-dev
+      env:
+        - PYTHON_VERSION=3.6
+        - JOB_NAME: "36_dev"
+        - JOB_TAG=_DEV
+        - NOSE_ARGS="not slow and not network and not disabled"
+        - PANDAS_TESTING_MODE="deprecate"
+      addons:
+        apt:
+          packages:
+          - libatlas-base-dev
+          - gfortran
+#    In allow_failures
+    - python: 2.7
+      env:
+        - PYTHON_VERSION=2.7
+        - JOB_NAME: "27_nslow_nnet_COMPAT"
+        - NOSE_ARGS="not slow and not network and not disabled"
+        - LOCALE_OVERRIDE="it_IT.UTF-8"
+        - INSTALL_TEST=true
+        - JOB_TAG=_COMPAT
+        - CACHE_NAME="27_nslow_nnet_COMPAT"
+        - USE_CACHE=true
+      addons:
+        apt:
+          packages:
+          - language-pack-it
 #    In allow_failures
     - python: 2.7
       env:
@@ -103,45 +117,46 @@ matrix:
         - FULL_DEPS=true
         - CACHE_NAME="27_slow"
         - USE_CACHE=true
+#    In allow_failures
+    - python: 2.7
+      env:
+        - PYTHON_VERSION=2.7
+        - JOB_NAME: "27_build_test_conda"
+        - JOB_TAG=_BUILD_TEST
+        - NOSE_ARGS="not slow and not disabled"
+        - FULL_DEPS=true
+        - BUILD_TEST=true
+        - CACHE_NAME="27_build_test_conda"
+        - USE_CACHE=true
 #    In allow_failures
     - python: 3.4
       env:
         - PYTHON_VERSION=3.4
-        - JOB_NAME: "34_slow"
-        - JOB_TAG=_SLOW
-        - NOSE_ARGS="slow and not network and not disabled"
+        - JOB_NAME: "34_nslow"
+        - NOSE_ARGS="not slow and not disabled"
         - FULL_DEPS=true
         - CLIPBOARD=xsel
-        - CACHE_NAME="34_slow"
+        - CACHE_NAME="34_nslow"
         - USE_CACHE=true
       addons:
         apt:
           packages:
           - xsel
 #    In allow_failures
-    - python: 2.7
+    - python: 3.4
       env:
-        - PYTHON_VERSION=2.7
-        - JOB_NAME: "27_build_test_conda"
-        - JOB_TAG=_BUILD_TEST
-        - NOSE_ARGS="not slow and not disabled"
+        - PYTHON_VERSION=3.4
+        - JOB_NAME: "34_slow"
+        - JOB_TAG=_SLOW
+        - NOSE_ARGS="slow and not network and not disabled"
         - FULL_DEPS=true
-        - BUILD_TEST=true
-        - CACHE_NAME="27_build_test_conda"
+        - CLIPBOARD=xsel
+        - CACHE_NAME="34_slow"
         - USE_CACHE=true
-#    In allow_failures
-    - python: 3.6-dev
-      env:
-        - PYTHON_VERSION=3.6
-        - JOB_NAME: "36_dev"
-        - JOB_TAG=_DEV
-        - NOSE_ARGS="not slow and not network and not disabled"
-        - PANDAS_TESTING_MODE="deprecate"
       addons:
         apt:
           packages:
-          - libatlas-base-dev
-          - gfortran
+          - xsel
 #    In allow_failures
     - python: 3.5
       env:
@@ -157,21 +172,6 @@ matrix:
           packages:
           - libatlas-base-dev
           - gfortran
-#    In allow_failures
-    - python: 2.7
-      env:
-        - PYTHON_VERSION=2.7
-        - JOB_NAME: "27_nslow_nnet_COMPAT"
-        - NOSE_ARGS="not slow and not network and not disabled"
-        - LOCALE_OVERRIDE="it_IT.UTF-8"
-        - INSTALL_TEST=true
-        - JOB_TAG=_COMPAT
-        - CACHE_NAME="27_nslow_nnet_COMPAT"
-        - USE_CACHE=true
-      addons:
-        apt:
-          packages:
-          - language-pack-it
 #    In allow_failures
     - python: 3.5
       env:
@@ -226,18 +226,19 @@ matrix:
         - BUILD_TEST=true
         - CACHE_NAME="27_build_test_conda"
         - USE_CACHE=true
-      - python: 3.6-dev
+      - python: 3.4
         env:
-        - PYTHON_VERSION=3.6
-        - JOB_NAME: "36_dev"
-        - JOB_TAG=_DEV
-        - NOSE_ARGS="not slow and not network and not disabled"
-        - PANDAS_TESTING_MODE="deprecate"
+          - PYTHON_VERSION=3.4
+          - JOB_NAME: "34_nslow"
+          - NOSE_ARGS="not slow and not disabled"
+          - FULL_DEPS=true
+          - CLIPBOARD=xsel
+          - CACHE_NAME="34_nslow"
+          - USE_CACHE=true
         addons:
           apt:
             packages:
-            - libatlas-base-dev
-            - gfortran
+            - xsel
       - python: 3.5
         env:
           - PYTHON_VERSION=3.5

asv_bench/benchmarks/algorithms.py

@@ -3,11 +3,12 @@
 from pandas.util import testing as tm
 
 
-class algorithm(object):
+class Algorithms(object):
     goal_time = 0.2
 
     def setup(self):
         N = 100000
+        np.random.seed(1234)
 
         self.int_unique = pd.Int64Index(np.arange(N * 5))
         # cache is_unique
@@ -17,28 +18,42 @@ def setup(self):
         self.float = pd.Float64Index(np.random.randn(N).repeat(5))
 
         # Convenience naming.
-        self.checked_add = pd.core.nanops._checked_add_with_arr
+        self.checked_add = pd.core.algorithms.checked_add_with_arr
 
         self.arr = np.arange(1000000)
         self.arrpos = np.arange(1000000)
         self.arrneg = np.arange(-1000000, 0)
         self.arrmixed = np.array([1, -1]).repeat(500000)
+        self.strings = tm.makeStringIndex(100000)
 
-    def time_int_factorize(self):
+        self.arr_nan = np.random.choice([True, False], size=1000000)
+        self.arrmixed_nan = np.random.choice([True, False], size=1000000)
+
+        # match
+        self.uniques = tm.makeStringIndex(1000).values
+        self.all = self.uniques.repeat(10)
+
+    def time_factorize_string(self):
+        self.strings.factorize()
+
+    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)
 
@@ -57,8 +72,18 @@ def time_add_overflow_neg_arr(self):
     def time_add_overflow_mixed_arr(self):
         self.checked_add(self.arr, self.arrmixed)
 
+    def time_add_overflow_first_arg_nan(self):
+        self.checked_add(self.arr, self.arrmixed, arr_mask=self.arr_nan)
+
+    def time_add_overflow_second_arg_nan(self):
+        self.checked_add(self.arr, self.arrmixed, b_mask=self.arrmixed_nan)
+
+    def time_add_overflow_both_arg_nan(self):
+        self.checked_add(self.arr, self.arrmixed, arr_mask=self.arr_nan,
+                         b_mask=self.arrmixed_nan)
+
 
-class hashing(object):
+class Hashing(object):
     goal_time = 0.2
 
     def setup(self):

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