updates from upstream

.github/workflows/ci.yml

@@ -125,35 +125,32 @@ jobs:
     - name: Check ipython directive errors
       run: "! grep -B1 \"^<<<-------------------------------------------------------------------------$\" sphinx.log"
 
-    - name: Merge website and docs
-      run: |
-        mkdir -p pandas_web/docs
-        cp -r web/build/* pandas_web/
-        cp -r doc/build/html/* pandas_web/docs/
-      if: github.event_name == 'push'
-
     - name: Install Rclone
       run: sudo apt install rclone -y
       if: github.event_name == 'push'
 
     - name: Set up Rclone
       run: |
-        RCLONE_CONFIG_PATH=$HOME/.config/rclone/rclone.conf
-        mkdir -p `dirname $RCLONE_CONFIG_PATH`
-        echo "[ovh_cloud_pandas_web]" > $RCLONE_CONFIG_PATH
-        echo "type = swift" >> $RCLONE_CONFIG_PATH
-        echo "env_auth = false" >> $RCLONE_CONFIG_PATH
-        echo "auth_version = 3" >> $RCLONE_CONFIG_PATH
-        echo "auth = https://auth.cloud.ovh.net/v3/" >> $RCLONE_CONFIG_PATH
-        echo "endpoint_type = public" >> $RCLONE_CONFIG_PATH
-        echo "tenant_domain = default" >> $RCLONE_CONFIG_PATH
-        echo "tenant = 2977553886518025" >> $RCLONE_CONFIG_PATH
-        echo "domain = default" >> $RCLONE_CONFIG_PATH
-        echo "user = w4KGs3pmDxpd" >> $RCLONE_CONFIG_PATH
-        echo "key = ${{ secrets.ovh_object_store_key }}" >> $RCLONE_CONFIG_PATH
-        echo "region = BHS" >> $RCLONE_CONFIG_PATH
+        CONF=$HOME/.config/rclone/rclone.conf
+        mkdir -p `dirname $CONF`
+        echo "[ovh_host]" > $CONF
+        echo "type = swift" >> $CONF
+        echo "env_auth = false" >> $CONF
+        echo "auth_version = 3" >> $CONF
+        echo "auth = https://auth.cloud.ovh.net/v3/" >> $CONF
+        echo "endpoint_type = public" >> $CONF
+        echo "tenant_domain = default" >> $CONF
+        echo "tenant = 2977553886518025" >> $CONF
+        echo "domain = default" >> $CONF
+        echo "user = w4KGs3pmDxpd" >> $CONF
+        echo "key = ${{ secrets.ovh_object_store_key }}" >> $CONF
+        echo "region = BHS" >> $CONF
+      if: github.event_name == 'push'
+
+    - name: Sync web with OVH
+      run: rclone sync --exclude pandas-docs/** web/build ovh_host:prod
       if: github.event_name == 'push'
 
-    - name: Sync web
-      run: rclone sync pandas_web ovh_cloud_pandas_web:dev
+    - name: Sync dev docs with OVH
+      run: rclone sync doc/build/html ovh_host:prod/pandas-docs/dev
       if: github.event_name == 'push'

.pre-commit-config.yaml

@@ -10,6 +10,20 @@ repos:
     -   id: flake8
         language: python_venv
         additional_dependencies: [flake8-comprehensions>=3.1.0]
+    -   id: flake8
+        name: flake8-pyx
+        language: python_venv
+        files: \.(pyx|pxd)$
+        types:
+          - file
+        args: [--append-config=flake8/cython.cfg]
+    -   id: flake8
+        name: flake8-pxd
+        language: python_venv
+        files: \.pxi\.in$
+        types:
+          - file
+        args: [--append-config=flake8/cython-template.cfg]
 -   repo: https://github.com/pre-commit/mirrors-isort
     rev: v4.3.21
     hooks:

asv_bench/benchmarks/algorithms.py

@@ -31,83 +31,62 @@ def time_maybe_convert_objects(self):
 
 class Factorize:
 
-    params = [[True, False], ["int", "uint", "float", "string"]]
-    param_names = ["sort", "dtype"]
-
-    def setup(self, sort, dtype):
-        N = 10 ** 5
-        data = {
-            "int": pd.Int64Index(np.arange(N).repeat(5)),
-            "uint": pd.UInt64Index(np.arange(N).repeat(5)),
-            "float": pd.Float64Index(np.random.randn(N).repeat(5)),
-            "string": tm.makeStringIndex(N).repeat(5),
-        }
-        self.idx = data[dtype]
-
-    def time_factorize(self, sort, dtype):
-        self.idx.factorize(sort=sort)
-
-
-class FactorizeUnique:
-
-    params = [[True, False], ["int", "uint", "float", "string"]]
-    param_names = ["sort", "dtype"]
+    params = [
+        [True, False],
+        [True, False],
+        ["int", "uint", "float", "string", "datetime64[ns]", "datetime64[ns, tz]"],
+    ]
+    param_names = ["unique", "sort", "dtype"]
 
-    def setup(self, sort, dtype):
+    def setup(self, unique, sort, dtype):
         N = 10 ** 5
         data = {
             "int": pd.Int64Index(np.arange(N)),
             "uint": pd.UInt64Index(np.arange(N)),
-            "float": pd.Float64Index(np.arange(N)),
+            "float": pd.Float64Index(np.random.randn(N)),
             "string": tm.makeStringIndex(N),
-        }
-        self.idx = data[dtype]
-        assert self.idx.is_unique
-
-    def time_factorize(self, sort, dtype):
+            "datetime64[ns]": pd.date_range("2011-01-01", freq="H", periods=N),
+            "datetime64[ns, tz]": pd.date_range(
+                "2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
+            ),
+        }[dtype]
+        if not unique:
+            data = data.repeat(5)
+        self.idx = data
+
+    def time_factorize(self, unique, sort, dtype):
         self.idx.factorize(sort=sort)
 
 
 class Duplicated:
 
-    params = [["first", "last", False], ["int", "uint", "float", "string"]]
-    param_names = ["keep", "dtype"]
-
-    def setup(self, keep, dtype):
-        N = 10 ** 5
-        data = {
-            "int": pd.Int64Index(np.arange(N).repeat(5)),
-            "uint": pd.UInt64Index(np.arange(N).repeat(5)),
-            "float": pd.Float64Index(np.random.randn(N).repeat(5)),
-            "string": tm.makeStringIndex(N).repeat(5),
-        }
-        self.idx = data[dtype]
-        # cache is_unique
-        self.idx.is_unique
-
-    def time_duplicated(self, keep, dtype):
-        self.idx.duplicated(keep=keep)
-
-
-class DuplicatedUniqueIndex:
-
-    params = ["int", "uint", "float", "string"]
-    param_names = ["dtype"]
+    params = [
+        [True, False],
+        ["first", "last", False],
+        ["int", "uint", "float", "string", "datetime64[ns]", "datetime64[ns, tz]"],
+    ]
+    param_names = ["unique", "keep", "dtype"]
 
-    def setup(self, dtype):
+    def setup(self, unique, keep, dtype):
         N = 10 ** 5
         data = {
             "int": pd.Int64Index(np.arange(N)),
             "uint": pd.UInt64Index(np.arange(N)),
             "float": pd.Float64Index(np.random.randn(N)),
             "string": tm.makeStringIndex(N),
-        }
-        self.idx = data[dtype]
+            "datetime64[ns]": pd.date_range("2011-01-01", freq="H", periods=N),
+            "datetime64[ns, tz]": pd.date_range(
+                "2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
+            ),
+        }[dtype]
+        if not unique:
+            data = data.repeat(5)
+        self.idx = data
         # cache is_unique
         self.idx.is_unique
 
-    def time_duplicated_unique(self, dtype):
-        self.idx.duplicated()
+    def time_duplicated(self, unique, keep, dtype):
+        self.idx.duplicated(keep=keep)
 
 
 class Hashing: