Merge branch 'master' into assign

Author: howsiwei

.github/workflows/ci.yml

@@ -15,12 +15,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
 
+    - name: Setting conda path
+      run: echo "::add-path::${HOME}/miniconda3/bin"
+
     - name: Checkout
       uses: actions/checkout@v1
 
-    - name: Setting conda path
-      run: echo "::set-env name=PATH::${HOME}/miniconda3/bin:${PATH}"
-
     - name: Looking for unwanted patterns
       run: ci/code_checks.sh patterns
       if: true

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

@@ -0,0 +1,23 @@
+import numpy as np
+
+import pandas as pd
+
+
+class BooleanArray:
+    def setup(self):
+        self.values_bool = np.array([True, False, True, False])
+        self.values_float = np.array([1.0, 0.0, 1.0, 0.0])
+        self.values_integer = np.array([1, 0, 1, 0])
+        self.values_integer_like = [1, 0, 1, 0]
+
+    def time_from_bool_array(self):
+        pd.array(self.values_bool, dtype="boolean")
+
+    def time_from_integer_array(self):
+        pd.array(self.values_integer, dtype="boolean")
+
+    def time_from_integer_like(self):
+        pd.array(self.values_integer_like, dtype="boolean")
+
+    def time_from_float_array(self):
+        pd.array(self.values_float, dtype="boolean")

MANIFEST.in

@@ -0,0 +1,32 @@
+import numpy as np
+
+import pandas as pd
+
+
+class TimeLogicalOps:
+    def setup(self):
+        N = 10_000
+        left, right, lmask, rmask = np.random.randint(0, 2, size=(4, N)).astype("bool")
+        self.left = pd.arrays.BooleanArray(left, lmask)
+        self.right = pd.arrays.BooleanArray(right, rmask)
+
+    def time_or_scalar(self):
+        self.left | True
+        self.left | False
+
+    def time_or_array(self):
+        self.left | self.right
+
+    def time_and_scalar(self):
+        self.left & True
+        self.left & False
+
+    def time_and_array(self):
+        self.left & self.right
+
+    def time_xor_scalar(self):
+        self.left ^ True
+        self.left ^ False
+
+    def time_xor_array(self):
+        self.left ^ self.right

asv_bench/benchmarks/array.py

@@ -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

asv_bench/benchmarks/boolean.py

@@ -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"
 
@@ -565,7 +563,7 @@ def setup(self):
 
     def time_frame_get_dtype_counts(self):
         with warnings.catch_warnings(record=True):
-            self.df.get_dtype_counts()
+            self.df._data.get_dtype_counts()
 
     def time_info(self):
         self.df.info()

asv_bench/benchmarks/frame_ctor.py

@@ -7,6 +7,7 @@
     Float64Index,
     Index,
     IntervalIndex,
+    MultiIndex,
     RangeIndex,
     Series,
     date_range,
@@ -111,6 +112,18 @@ def time_get_loc_dec(self):
         self.idx_dec.get_loc(100000)
 
 
+class IndexEquals:
+    def setup(self):
+        idx_large_fast = RangeIndex(100000)
+        idx_small_slow = date_range(start="1/1/2012", periods=1)
+        self.mi_large_slow = MultiIndex.from_product([idx_large_fast, idx_small_slow])
+
+        self.idx_non_object = RangeIndex(1)
+
+    def time_non_object_equals_multiindex(self):
+        self.idx_non_object.equals(self.mi_large_slow)
+
+
 class IndexAppend:
     def setup(self):
 

asv_bench/benchmarks/frame_methods.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/index_object.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

@@ -2,7 +2,7 @@
 
 import numpy as np
 
-from pandas import DataFrame, MultiIndex, date_range
+from pandas import DataFrame, MultiIndex, RangeIndex, date_range
 import pandas.util.testing as tm
 
 
@@ -147,4 +147,16 @@ def time_categorical_level(self):
         self.df.set_index(["a", "b"])
 
 
+class Equals:
+    def setup(self):
+        idx_large_fast = RangeIndex(100000)
+        idx_small_slow = date_range(start="1/1/2012", periods=1)
+        self.mi_large_slow = MultiIndex.from_product([idx_large_fast, idx_small_slow])
+
+        self.idx_non_object = RangeIndex(1)
+
+    def time_equals_non_object_index(self):
+        self.mi_large_slow.equals(self.idx_non_object)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip