Merge remote-tracking branch 'upstream/master' into segfault_memory_usage

Author: hexgnu

asv_bench/benchmarks/replace.py

@@ -44,15 +44,15 @@ class Convert(object):
 
     goal_time = 0.5
     params = (['DataFrame', 'Series'], ['Timestamp', 'Timedelta'])
-    param_names = ['contructor', 'replace_data']
+    param_names = ['constructor', 'replace_data']
 
-    def setup(self, contructor, replace_data):
+    def setup(self, constructor, replace_data):
         N = 10**3
         data = {'Series': pd.Series(np.random.randint(N, size=N)),
                 'DataFrame': pd.DataFrame({'A': np.random.randint(N, size=N),
                                            'B': np.random.randint(N, size=N)})}
         self.to_replace = {i: getattr(pd, replace_data) for i in range(N)}
-        self.data = data[contructor]
+        self.data = data[constructor]
 
-    def time_replace(self, contructor, replace_data):
+    def time_replace(self, constructor, replace_data):
         self.data.replace(self.to_replace)

asv_bench/benchmarks/rolling.py

@@ -11,31 +11,52 @@ class Methods(object):
               [10, 1000],
               ['int', 'float'],
               ['median', 'mean', 'max', 'min', 'std', 'count', 'skew', 'kurt',
-               'sum', 'corr', 'cov'])
+               'sum'])
     param_names = ['contructor', 'window', 'dtype', 'method']
 
-    def setup(self, contructor, window, dtype, method):
+    def setup(self, constructor, window, dtype, method):
         N = 10**5
         arr = np.random.random(N).astype(dtype)
-        self.roll = getattr(pd, contructor)(arr).rolling(window)
+        self.roll = getattr(pd, constructor)(arr).rolling(window)
 
-    def time_rolling(self, contructor, window, dtype, method):
+    def time_rolling(self, constructor, window, dtype, method):
         getattr(self.roll, method)()
 
 
+class Pairwise(object):
+
+    sample_time = 0.2
+    params = ([10, 1000, None],
+              ['corr', 'cov'],
+              [True, False])
+    param_names = ['window', 'method', 'pairwise']
+
+    def setup(self, window, method, pairwise):
+        N = 10**4
+        arr = np.random.random(N)
+        self.df = pd.DataFrame(arr)
+
+    def time_pairwise(self, window, method, pairwise):
+        if window is None:
+            r = self.df.expanding()
+        else:
+            r = self.df.rolling(window=window)
+        getattr(r, method)(self.df, pairwise=pairwise)
+
+
 class Quantile(object):
 
     sample_time = 0.2
     params = (['DataFrame', 'Series'],
               [10, 1000],
               ['int', 'float'],
               [0, 0.5, 1])
-    param_names = ['contructor', 'window', 'dtype', 'percentile']
+    param_names = ['constructor', 'window', 'dtype', 'percentile']
 
-    def setup(self, contructor, window, dtype, percentile):
+    def setup(self, constructor, window, dtype, percentile):
         N = 10**5
         arr = np.random.random(N).astype(dtype)
-        self.roll = getattr(pd, contructor)(arr).rolling(window)
+        self.roll = getattr(pd, constructor)(arr).rolling(window)
 
-    def time_quantile(self, contructor, window, dtype, percentile):
+    def time_quantile(self, constructor, window, dtype, percentile):
         self.roll.quantile(percentile)

ci/requirements-3.6.run

@@ -13,7 +13,7 @@ lxml
 html5lib
 jinja2
 sqlalchemy
-pymysql
+pymysql<0.8.0
 feather-format
 pyarrow
 psycopg2

doc/source/10min.rst

@@ -154,7 +154,7 @@ Selection
    While standard Python / Numpy expressions for selecting and setting are
    intuitive and come in handy for interactive work, for production code, we
    recommend the optimized pandas data access methods, ``.at``, ``.iat``,
-   ``.loc``, ``.iloc`` and ``.ix``.
+   ``.loc`` and ``.iloc``.
 
 See the indexing documentation :ref:`Indexing and Selecting Data <indexing>` and :ref:`MultiIndex / Advanced Indexing <advanced>`.
 

doc/source/api.rst

@@ -2500,7 +2500,7 @@ Scalar introspection
 Extensions
 ----------
 
-These are primarily intented for library authors looking to extend pandas
+These are primarily intended for library authors looking to extend pandas
 objects.
 
 .. currentmodule:: pandas