Merge pull request #1 from pandas-dev/master

update fork

Author: lithomas1

LICENSES/MSGPACK_LICENSE

@@ -20,7 +20,6 @@ global-exclude *.gz
 global-exclude *.h5
 global-exclude *.html
 global-exclude *.json
-global-exclude *.msgpack
 global-exclude *.pickle
 global-exclude *.png
 global-exclude *.pyc

LICENSES/MSGPACK_NUMPY_LICENSE

@@ -105,4 +105,16 @@ def time_frame_from_lists(self):
         self.df = DataFrame(self.data)
 
 
+class FromRange:
+
+    goal_time = 0.2
+
+    def setup(self):
+        N = 1_000_000
+        self.data = range(N)
+
+    def time_frame_from_range(self):
+        self.df = DataFrame(self.data)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

MANIFEST.in

@@ -321,10 +321,9 @@ class Dropna:
 
     def setup(self, how, axis):
         self.df = DataFrame(np.random.randn(10000, 1000))
-        with warnings.catch_warnings(record=True):
-            self.df.ix[50:1000, 20:50] = np.nan
-            self.df.ix[2000:3000] = np.nan
-            self.df.ix[:, 60:70] = np.nan
+        self.df.iloc[50:1000, 20:50] = np.nan
+        self.df.iloc[2000:3000] = np.nan
+        self.df.iloc[:, 60:70] = np.nan
         self.df_mixed = self.df.copy()
         self.df_mixed["foo"] = "bar"
 
@@ -342,10 +341,9 @@ class Count:
 
     def setup(self, axis):
         self.df = DataFrame(np.random.randn(10000, 1000))
-        with warnings.catch_warnings(record=True):
-            self.df.ix[50:1000, 20:50] = np.nan
-            self.df.ix[2000:3000] = np.nan
-            self.df.ix[:, 60:70] = np.nan
+        self.df.iloc[50:1000, 20:50] = np.nan
+        self.df.iloc[2000:3000] = np.nan
+        self.df.iloc[:, 60:70] = np.nan
         self.df_mixed = self.df.copy()
         self.df_mixed["foo"] = "bar"
 

asv_bench/benchmarks/frame_ctor.py

@@ -67,22 +67,6 @@ def time_iloc_scalar(self, index, index_structure):
     def time_iloc_slice(self, index, index_structure):
         self.data.iloc[:800000]
 
-    def time_ix_array(self, index, index_structure):
-        with warnings.catch_warnings(record=True):
-            self.data.ix[self.array]
-
-    def time_ix_list_like(self, index, index_structure):
-        with warnings.catch_warnings(record=True):
-            self.data.ix[[800000]]
-
-    def time_ix_scalar(self, index, index_structure):
-        with warnings.catch_warnings(record=True):
-            self.data.ix[800000]
-
-    def time_ix_slice(self, index, index_structure):
-        with warnings.catch_warnings(record=True):
-            self.data.ix[:800000]
-
     def time_loc_array(self, index, index_structure):
         self.data.loc[self.array]
 
@@ -148,10 +132,6 @@ def setup(self):
         self.bool_indexer = self.df[self.col_scalar] > 0
         self.bool_obj_indexer = self.bool_indexer.astype(object)
 
-    def time_ix(self):
-        with warnings.catch_warnings(record=True):
-            self.df.ix[self.idx_scalar, self.col_scalar]
-
     def time_loc(self):
         self.df.loc[self.idx_scalar, self.col_scalar]
 
@@ -228,14 +208,6 @@ def setup(self):
         self.idx = IndexSlice[20000:30000, 20:30, 35:45, 30000:40000]
         self.mdt = self.mdt.set_index(["A", "B", "C", "D"]).sort_index()
 
-    def time_series_ix(self):
-        with warnings.catch_warnings(record=True):
-            self.s.ix[999]
-
-    def time_frame_ix(self):
-        with warnings.catch_warnings(record=True):
-            self.df.ix[999]
-
     def time_index_slice(self):
         self.mdt.loc[self.idx, :]
 
@@ -310,10 +282,6 @@ def setup_cache(self):
     def time_lookup_iloc(self, s):
         s.iloc
 
-    def time_lookup_ix(self, s):
-        with warnings.catch_warnings(record=True):
-            s.ix
-
     def time_lookup_loc(self, s):
         s.loc
 

asv_bench/benchmarks/frame_methods.py

@@ -26,5 +26,5 @@ def setup(self, format):
         ]
         self.f = os.path.join(*paths)
 
-    def time_read_msgpack(self, format):
+    def time_read_sas(self, format):
         read_sas(self.f, format=format)

asv_bench/benchmarks/indexing.py

@@ -44,15 +44,13 @@ jobs:
           PATTERN: "not slow and not network"
           LOCALE_OVERRIDE: "zh_CN.UTF-8"
 
-        # Disabled for NumPy object-dtype warning.
-        # https://github.com/pandas-dev/pandas/issues/30043
-        # py37_np_dev:
-        #   ENV_FILE: ci/deps/azure-37-numpydev.yaml
-        #   CONDA_PY: "37"
-        #   PATTERN: "not slow and not network"
-        #   TEST_ARGS: "-W error"
-        #   PANDAS_TESTING_MODE: "deprecate"
-        #   EXTRA_APT: "xsel"
+        py37_np_dev:
+          ENV_FILE: ci/deps/azure-37-numpydev.yaml
+          CONDA_PY: "37"
+          PATTERN: "not slow and not network"
+          TEST_ARGS: "-W error"
+          PANDAS_TESTING_MODE: "deprecate"
+          EXTRA_APT: "xsel"
 
   steps:
     - script: |

asv_bench/benchmarks/io/msgpack.py

@@ -94,10 +94,10 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
 
     # We don't lint all C files because we don't want to lint any that are built
     # from Cython files nor do we want to lint C files that we didn't modify for
-    # this particular codebase (e.g. src/headers, src/klib, src/msgpack). However,
+    # this particular codebase (e.g. src/headers, src/klib). However,
     # we can lint all header files since they aren't "generated" like C files are.
     MSG='Linting .c and .h' ; echo $MSG
-    cpplint --quiet --extensions=c,h --headers=h --recursive --filter=-readability/casting,-runtime/int,-build/include_subdir pandas/_libs/src/*.h pandas/_libs/src/parser pandas/_libs/ujson pandas/_libs/tslibs/src/datetime pandas/io/msgpack pandas/_libs/*.cpp pandas/util
+    cpplint --quiet --extensions=c,h --headers=h --recursive --filter=-readability/casting,-runtime/int,-build/include_subdir pandas/_libs/src/*.h pandas/_libs/src/parser pandas/_libs/ujson pandas/_libs/tslibs/src/datetime pandas/_libs/*.cpp
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     echo "isort --version-number"
@@ -281,6 +281,10 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
     pytest -q --doctest-modules pandas/core/arrays/string_.py
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Doctests arrays/boolean.py' ; echo $MSG
+    pytest -q --doctest-modules pandas/core/arrays/boolean.py
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
 fi
 
 ### DOCSTRINGS ###