Merge branch 'master' into gh-29403

Author: nathalier

.github/workflows/ci.yml

@@ -8,15 +8,16 @@ on:
 
 env:
   ENV_FILE: environment.yml
-  # TODO: remove export PATH=... in each step once this works
-  # PATH: $HOME/miniconda3/bin:$PATH
 
 jobs:
   checks:
     name: Checks
     runs-on: ubuntu-latest
     steps:
 
+    - name: Setting conda path
+      run: echo "::add-path::${HOME}/miniconda3/bin"
+
     - name: Checkout
       uses: actions/checkout@v1
 
@@ -25,79 +26,72 @@ jobs:
       if: true
 
     - name: Setup environment and build pandas
-      run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
-        ci/setup_env.sh
+      run: ci/setup_env.sh
       if: true
 
     - name: Linting
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh lint
       if: true
 
     - name: Dependencies consistency
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh dependencies
       if: true
 
     - name: Checks on imported code
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh code
       if: true
 
     - name: Running doctests
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh doctests
       if: true
 
     - name: Docstring validation
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh docstrings
       if: true
 
     - name: Typing validation
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh typing
       if: true
 
     - name: Testing docstring validation script
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         pytest --capture=no --strict scripts
       if: true
 
     - name: Running benchmarks
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         cd asv_bench
         asv check -E existing
         git remote add upstream https://github.com/pandas-dev/pandas.git
         git fetch upstream
         if git diff upstream/master --name-only | grep -q "^asv_bench/"; then
             asv machine --yes
-            ASV_OUTPUT="$(asv dev)"
-            if [[ $(echo "$ASV_OUTPUT" | grep "failed") ]]; then
-                echo "##vso[task.logissue type=error]Benchmarks run with errors"
-                echo "$ASV_OUTPUT"
+            asv dev | sed "/failed$/ s/^/##[error]/" | tee benchmarks.log
+            if grep "failed" benchmarks.log > /dev/null ; then
                 exit 1
-            else
-                echo "Benchmarks run without errors"
             fi
         else
             echo "Benchmarks did not run, no changes detected"
         fi
       if: true
+
+    - name: Publish benchmarks artifact
+      uses: actions/upload-artifact@master
+      with:
+        name: Benchmarks log
+        path: asv_bench/benchmarks.log
+      if: failure()

README.md

@@ -164,12 +164,11 @@ pip install pandas
 ```
 
 ## Dependencies
-- [NumPy](https://www.numpy.org): 1.13.3 or higher
-- [python-dateutil](https://labix.org/python-dateutil): 2.5.0 or higher
-- [pytz](https://pythonhosted.org/pytz): 2015.4 or higher
+- [NumPy](https://www.numpy.org)
+- [python-dateutil](https://labix.org/python-dateutil)
+- [pytz](https://pythonhosted.org/pytz)
 
-See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies)
-for recommended and optional dependencies.
+See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies) for minimum supported versions of required, recommended and optional dependencies.
 
 ## Installation from sources
 To install pandas from source you need Cython in addition to the normal

asv_bench/benchmarks/categoricals.py

@@ -14,21 +14,6 @@
         pass
 
 
-class Concat:
-    def setup(self):
-        N = 10 ** 5
-        self.s = pd.Series(list("aabbcd") * N).astype("category")
-
-        self.a = pd.Categorical(list("aabbcd") * N)
-        self.b = pd.Categorical(list("bbcdjk") * N)
-
-    def time_concat(self):
-        pd.concat([self.s, self.s])
-
-    def time_union(self):
-        union_categoricals([self.a, self.b])
-
-
 class Constructor:
     def setup(self):
         N = 10 ** 5
@@ -77,6 +62,33 @@ def time_existing_series(self):
         pd.Categorical(self.series)
 
 
+class CategoricalOps:
+    params = ["__lt__", "__le__", "__eq__", "__ne__", "__ge__", "__gt__"]
+    param_names = ["op"]
+
+    def setup(self, op):
+        N = 10 ** 5
+        self.cat = pd.Categorical(list("aabbcd") * N, ordered=True)
+
+    def time_categorical_op(self, op):
+        getattr(self.cat, op)("b")
+
+
+class Concat:
+    def setup(self):
+        N = 10 ** 5
+        self.s = pd.Series(list("aabbcd") * N).astype("category")
+
+        self.a = pd.Categorical(list("aabbcd") * N)
+        self.b = pd.Categorical(list("bbcdjk") * N)
+
+    def time_concat(self):
+        pd.concat([self.s, self.s])
+
+    def time_union(self):
+        union_categoricals([self.a, self.b])
+
+
 class ValueCounts:
 
     params = [True, False]

asv_bench/benchmarks/frame_methods.py

@@ -565,7 +565,7 @@ 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/index_object.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/multiindex_object.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

asv_bench/benchmarks/stat_ops.py

@@ -7,20 +7,14 @@
 
 class FrameOps:
 
-    params = [ops, ["float", "int"], [0, 1], [True, False]]
-    param_names = ["op", "dtype", "axis", "use_bottleneck"]
+    params = [ops, ["float", "int"], [0, 1]]
+    param_names = ["op", "dtype", "axis"]
 
-    def setup(self, op, dtype, axis, use_bottleneck):
+    def setup(self, op, dtype, axis):
         df = pd.DataFrame(np.random.randn(100000, 4)).astype(dtype)
-        try:
-            pd.options.compute.use_bottleneck = use_bottleneck
-        except TypeError:
-            from pandas.core import nanops
-
-            nanops._USE_BOTTLENECK = use_bottleneck
         self.df_func = getattr(df, op)
 
-    def time_op(self, op, dtype, axis, use_bottleneck):
+    def time_op(self, op, dtype, axis):
         self.df_func(axis=axis)
 
 
@@ -46,20 +40,14 @@ def time_op(self, level, op):
 
 class SeriesOps:
 
-    params = [ops, ["float", "int"], [True, False]]
-    param_names = ["op", "dtype", "use_bottleneck"]
+    params = [ops, ["float", "int"]]
+    param_names = ["op", "dtype"]
 
-    def setup(self, op, dtype, use_bottleneck):
+    def setup(self, op, dtype):
         s = pd.Series(np.random.randn(100000)).astype(dtype)
-        try:
-            pd.options.compute.use_bottleneck = use_bottleneck
-        except TypeError:
-            from pandas.core import nanops
-
-            nanops._USE_BOTTLENECK = use_bottleneck
         self.s_func = getattr(s, op)
 
-    def time_op(self, op, dtype, use_bottleneck):
+    def time_op(self, op, dtype):
         self.s_func()
 
 
@@ -101,61 +89,49 @@ def time_average_old(self, constructor, pct):
 
 class Correlation:
 
-    params = [["spearman", "kendall", "pearson"], [True, False]]
-    param_names = ["method", "use_bottleneck"]
+    params = [["spearman", "kendall", "pearson"]]
+    param_names = ["method"]
 
-    def setup(self, method, use_bottleneck):
-        try:
-            pd.options.compute.use_bottleneck = use_bottleneck
-        except TypeError:
-            from pandas.core import nanops
+    def setup(self, method):
+        self.df = pd.DataFrame(np.random.randn(500, 15))
+        self.df2 = pd.DataFrame(np.random.randn(500, 15))
+        self.df_wide = pd.DataFrame(np.random.randn(500, 100))
+        self.df_wide_nans = self.df_wide.where(np.random.random((500, 100)) < 0.9)
+        self.s = pd.Series(np.random.randn(500))
+        self.s2 = pd.Series(np.random.randn(500))
 
-            nanops._USE_BOTTLENECK = use_bottleneck
-        self.df = pd.DataFrame(np.random.randn(1000, 30))
-        self.df2 = pd.DataFrame(np.random.randn(1000, 30))
-        self.df_wide = pd.DataFrame(np.random.randn(1000, 200))
-        self.df_wide_nans = self.df_wide.where(np.random.random((1000, 200)) < 0.9)
-        self.s = pd.Series(np.random.randn(1000))
-        self.s2 = pd.Series(np.random.randn(1000))
-
-    def time_corr(self, method, use_bottleneck):
+    def time_corr(self, method):
         self.df.corr(method=method)
 
-    def time_corr_wide(self, method, use_bottleneck):
+    def time_corr_wide(self, method):
         self.df_wide.corr(method=method)
 
-    def time_corr_wide_nans(self, method, use_bottleneck):
+    def time_corr_wide_nans(self, method):
         self.df_wide_nans.corr(method=method)
 
-    def peakmem_corr_wide(self, method, use_bottleneck):
+    def peakmem_corr_wide(self, method):
         self.df_wide.corr(method=method)
 
-    def time_corr_series(self, method, use_bottleneck):
+    def time_corr_series(self, method):
         self.s.corr(self.s2, method=method)
 
-    def time_corrwith_cols(self, method, use_bottleneck):
+    def time_corrwith_cols(self, method):
         self.df.corrwith(self.df2, method=method)
 
-    def time_corrwith_rows(self, method, use_bottleneck):
+    def time_corrwith_rows(self, method):
         self.df.corrwith(self.df2, axis=1, method=method)
 
 
 class Covariance:
 
-    params = [[True, False]]
-    param_names = ["use_bottleneck"]
-
-    def setup(self, use_bottleneck):
-        try:
-            pd.options.compute.use_bottleneck = use_bottleneck
-        except TypeError:
-            from pandas.core import nanops
+    params = []
+    param_names = []
 
-            nanops._USE_BOTTLENECK = use_bottleneck
+    def setup(self):
         self.s = pd.Series(np.random.randn(100000))
         self.s2 = pd.Series(np.random.randn(100000))
 
-    def time_cov_series(self, use_bottleneck):
+    def time_cov_series(self):
         self.s.cov(self.s2)
 
 

asv_bench/benchmarks/timeseries.py

@@ -113,7 +113,7 @@ class InferFreq:
     def setup(self, freq):
         if freq is None:
             self.idx = date_range(start="1/1/1700", freq="D", periods=10000)
-            self.idx.freq = None
+            self.idx._data._freq = None
         else:
             self.idx = date_range(start="1/1/1700", freq=freq, periods=10000)