BUG: groupby.hist legend should use group keys

Author: rhshadrach

.travis.yml

@@ -27,6 +27,11 @@ matrix:
   fast_finish: true
 
   include:
+    # In allowed failures
+    - dist: bionic
+      python: 3.9-dev
+      env:
+        - JOB="3.9-dev" PATTERN="(not slow and not network and not clipboard)"
     - env:
         - JOB="3.8" ENV_FILE="ci/deps/travis-38.yaml" PATTERN="(not slow and not network and not clipboard)"
 
@@ -53,6 +58,11 @@ matrix:
       services:
         - mysql
         - postgresql
+  allow_failures:
+  - dist: bionic
+    python: 3.9-dev
+    env:
+        - JOB="3.9-dev" PATTERN="(not slow and not network)"
 
 before_install:
   - echo "before_install"
@@ -83,7 +93,7 @@ install:
 script:
   - echo "script start"
   - echo "$JOB"
-  - source activate pandas-dev
+  - if [ "$JOB" != "3.9-dev" ]; then source activate pandas-dev; fi
   - ci/run_tests.sh
 
 after_script:

asv_bench/benchmarks/algorithms.py

@@ -34,7 +34,16 @@ class Factorize:
     params = [
         [True, False],
         [True, False],
-        ["int", "uint", "float", "string", "datetime64[ns]", "datetime64[ns, tz]"],
+        [
+            "int",
+            "uint",
+            "float",
+            "string",
+            "datetime64[ns]",
+            "datetime64[ns, tz]",
+            "Int64",
+            "boolean",
+        ],
     ]
     param_names = ["unique", "sort", "dtype"]
 
@@ -49,13 +58,15 @@ def setup(self, unique, sort, dtype):
             "datetime64[ns, tz]": pd.date_range(
                 "2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
             ),
+            "Int64": pd.array(np.arange(N), dtype="Int64"),
+            "boolean": pd.array(np.random.randint(0, 2, N), dtype="boolean"),
         }[dtype]
         if not unique:
             data = data.repeat(5)
-        self.idx = data
+        self.data = data
 
     def time_factorize(self, unique, sort, dtype):
-        self.idx.factorize(sort=sort)
+        pd.factorize(self.data, sort=sort)
 
 
 class Duplicated:

asv_bench/benchmarks/arithmetic.py

@@ -67,7 +67,7 @@ def time_series_op_with_fill_value_no_nas(self):
         self.ser.add(self.ser, fill_value=4)
 
 
-class MixedFrameWithSeriesAxis0:
+class MixedFrameWithSeriesAxis:
     params = [
         [
             "eq",
@@ -78,7 +78,7 @@ class MixedFrameWithSeriesAxis0:
             "gt",
             "add",
             "sub",
-            "div",
+            "truediv",
             "floordiv",
             "mul",
             "pow",
@@ -87,15 +87,19 @@ class MixedFrameWithSeriesAxis0:
     param_names = ["opname"]
 
     def setup(self, opname):
-        arr = np.arange(10 ** 6).reshape(100, -1)
+        arr = np.arange(10 ** 6).reshape(1000, -1)
         df = DataFrame(arr)
         df["C"] = 1.0
         self.df = df
         self.ser = df[0]
+        self.row = df.iloc[0]
 
     def time_frame_op_with_series_axis0(self, opname):
         getattr(self.df, opname)(self.ser, axis=0)
 
+    def time_frame_op_with_series_axis1(self, opname):
+        getattr(operator, opname)(self.df, self.ser)
+
 
 class Ops:
 

asv_bench/benchmarks/frame_methods.py

@@ -564,7 +564,7 @@ def setup(self):
 
     def time_frame_get_dtype_counts(self):
         with warnings.catch_warnings(record=True):
-            self.df._data.get_dtype_counts()
+            self.df.dtypes.value_counts()
 
     def time_info(self):
         self.df.info()

asv_bench/benchmarks/groupby.py

@@ -626,4 +626,96 @@ def time_first(self):
         self.df_nans.groupby("key").transform("first")
 
 
+class TransformEngine:
+    def setup(self):
+        N = 10 ** 3
+        data = DataFrame(
+            {0: [str(i) for i in range(100)] * N, 1: list(range(100)) * N},
+            columns=[0, 1],
+        )
+        self.grouper = data.groupby(0)
+
+    def time_series_numba(self):
+        def function(values, index):
+            return values * 5
+
+        self.grouper[1].transform(function, engine="numba")
+
+    def time_series_cython(self):
+        def function(values):
+            return values * 5
+
+        self.grouper[1].transform(function, engine="cython")
+
+    def time_dataframe_numba(self):
+        def function(values, index):
+            return values * 5
+
+        self.grouper.transform(function, engine="numba")
+
+    def time_dataframe_cython(self):
+        def function(values):
+            return values * 5
+
+        self.grouper.transform(function, engine="cython")
+
+
+class AggEngine:
+    def setup(self):
+        N = 10 ** 3
+        data = DataFrame(
+            {0: [str(i) for i in range(100)] * N, 1: list(range(100)) * N},
+            columns=[0, 1],
+        )
+        self.grouper = data.groupby(0)
+
+    def time_series_numba(self):
+        def function(values, index):
+            total = 0
+            for i, value in enumerate(values):
+                if i % 2:
+                    total += value + 5
+                else:
+                    total += value * 2
+            return total
+
+        self.grouper[1].agg(function, engine="numba")
+
+    def time_series_cython(self):
+        def function(values):
+            total = 0
+            for i, value in enumerate(values):
+                if i % 2:
+                    total += value + 5
+                else:
+                    total += value * 2
+            return total
+
+        self.grouper[1].agg(function, engine="cython")
+
+    def time_dataframe_numba(self):
+        def function(values, index):
+            total = 0
+            for i, value in enumerate(values):
+                if i % 2:
+                    total += value + 5
+                else:
+                    total += value * 2
+            return total
+
+        self.grouper.agg(function, engine="numba")
+
+    def time_dataframe_cython(self):
+        def function(values):
+            total = 0
+            for i, value in enumerate(values):
+                if i % 2:
+                    total += value + 5
+                else:
+                    total += value * 2
+            return total
+
+        self.grouper.agg(function, engine="cython")
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/io/parsers.py

@@ -2,7 +2,7 @@
 
 try:
     from pandas._libs.tslibs.parsing import (
-        _concat_date_cols,
+        concat_date_cols,
         _does_string_look_like_datetime,
     )
 except ImportError:
@@ -39,4 +39,4 @@ def setup(self, value, dim):
             )
 
     def time_check_concat(self, value, dim):
-        _concat_date_cols(self.object)
+        concat_date_cols(self.object)

asv_bench/benchmarks/rolling.py

@@ -150,19 +150,18 @@ def time_quantile(self, constructor, window, dtype, percentile, interpolation):
         self.roll.quantile(percentile, interpolation=interpolation)
 
 
-class PeakMemFixed:
-    def setup(self):
-        N = 10
-        arr = 100 * np.random.random(N)
-        self.roll = pd.Series(arr).rolling(10)
-
-    def peakmem_fixed(self):
-        # GH 25926
-        # This is to detect memory leaks in rolling operations.
-        # To save time this is only ran on one method.
-        # 6000 iterations is enough for most types of leaks to be detected
-        for x in range(6000):
-            self.roll.max()
+class PeakMemFixedWindowMinMax:
+
+    params = ["min", "max"]
+
+    def setup(self, operation):
+        N = int(1e6)
+        arr = np.random.random(N)
+        self.roll = pd.Series(arr).rolling(2)
+
+    def peakmem_fixed(self, operation):
+        for x in range(5):
+            getattr(self.roll, operation)()
 
 
 class ForwardWindowMethods:

asv_bench/benchmarks/stat_ops.py

@@ -11,8 +11,8 @@ class FrameOps:
     param_names = ["op", "dtype", "axis"]
 
     def setup(self, op, dtype, axis):
-        if op == "mad" and dtype == "Int64" and axis == 1:
-            # GH-33036
+        if op == "mad" and dtype == "Int64":
+            # GH-33036, GH#33600
             raise NotImplementedError
         values = np.random.randn(100000, 4)
         if dtype == "Int64":

ci/build39.sh

@@ -0,0 +1,21 @@
+#!/bin/bash -e
+# Special build for python3.9 until numpy puts its own wheels up
+
+sudo apt-get install build-essential gcc xvfb
+pip install --no-deps -U pip wheel setuptools
+pip install python-dateutil pytz pytest pytest-xdist hypothesis
+pip install cython --pre # https://github.com/cython/cython/issues/3395
+
+git clone https://github.com/numpy/numpy
+cd numpy
+python setup.py build_ext --inplace
+python setup.py install
+cd ..
+rm -rf numpy
+
+python setup.py build_ext -inplace
+python -m pip install --no-build-isolation -e .
+
+python -c "import sys; print(sys.version_info)"
+python -c "import pandas as pd"
+python -c "import hypothesis"

ci/code_checks.sh

@@ -150,7 +150,13 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     # Check for imports from pandas._testing instead of `import pandas._testing as tm`
     invgrep -R --include="*.py*" -E "from pandas._testing import" pandas/tests
     RET=$(($RET + $?)) ; echo $MSG "DONE"
-    invgrep -R --include="*.py*" -E "from pandas.util import testing as tm" pandas/tests
+    invgrep -R --include="*.py*" -E "from pandas import _testing as tm" pandas/tests
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
+    # No direct imports from conftest
+    invgrep -R --include="*.py*" -E "conftest import" pandas/tests
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+    invgrep -R --include="*.py*" -E "import conftest" pandas/tests
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Check for use of exec' ; echo $MSG
@@ -347,8 +353,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA02, SA03, SA05)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA02,SA03,SA05
+    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA02, SA03)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA02,SA03
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Validate correct capitalization among titles in documentation' ; echo $MSG

ci/deps/azure-36-minimum_versions.yaml

@@ -1,6 +1,5 @@
 name: pandas-dev
 channels:
-  - defaults
   - conda-forge
 dependencies:
   - python=3.6.1
@@ -19,12 +18,12 @@ dependencies:
   - jinja2=2.8
   - numba=0.46.0
   - numexpr=2.6.2
-  - numpy=1.13.3
+  - numpy=1.15.4
   - openpyxl=2.5.7
-  - pytables=3.4.2
+  - pytables=3.4.3
   - python-dateutil=2.7.3
   - pytz=2017.2
-  - scipy=0.19.0
+  - scipy=1.2
   - xlrd=1.1.0
   - xlsxwriter=0.9.8
   - xlwt=1.2.0

ci/deps/azure-37-numpydev.yaml

@@ -14,8 +14,7 @@ dependencies:
   - pytz
   - pip
   - pip:
-    - cython==0.29.16
-    # GH#33507 cython 3.0a1 is causing TypeErrors 2020-04-13
+    - cython==0.29.16 # GH#34014
     - "git+git://github.com/dateutil/dateutil.git"
     - "-f https://7933911d6844c6c53a7d-47bd50c35cd79bd838daf386af554a83.ssl.cf2.rackcdn.com"
     - "--pre"

ci/deps/azure-macos-36.yaml

@@ -19,7 +19,7 @@ dependencies:
   - matplotlib=2.2.3
   - nomkl
   - numexpr
-  - numpy=1.14
+  - numpy=1.15.4
   - openpyxl
   - pyarrow>=0.13.0
   - pytables

ci/setup_env.sh

@@ -1,5 +1,10 @@
 #!/bin/bash -e
 
+if [ "$JOB" == "3.9-dev" ]; then
+    /bin/bash ci/build39.sh
+    exit 0
+fi
+
 # edit the locale file if needed
 if [[ "$(uname)" == "Linux" && -n "$LC_ALL" ]]; then
     echo "Adding locale to the first line of pandas/__init__.py"
@@ -128,7 +133,7 @@ conda list pandas
 echo "[Build extensions]"
 python setup.py build_ext -q -i -j2
 
-# XXX: Some of our environments end up with old versions of pip (10.x)
+# TODO: Some of our environments end up with old versions of pip (10.x)
 # Adding a new enough version of pip to the requirements explodes the
 # solve time. Just using pip to update itself.
 # - py35_macos

conda.recipe/meta.yaml

@@ -20,12 +20,12 @@ requirements:
     - cython
     - numpy
     - setuptools >=3.3
-    - python-dateutil >=2.5.0
+    - python-dateutil >=2.7.3
     - pytz
   run:
     - python {{ python }}
     - {{ pin_compatible('numpy') }}
-    - python-dateutil >=2.5.0
+    - python-dateutil >=2.7.3
     - pytz
 
 test: