Merge remote-tracking branch 'upstream/master' into use-doc-decorator

Author: HH-MWB

.github/workflows/ci.yml

@@ -154,6 +154,39 @@ jobs:
         echo "region = BHS" >> $RCLONE_CONFIG_PATH
       if: github.event_name == 'push'
 
-    - name: Sync web
+    - name: Sync web with OVH
       run: rclone sync pandas_web ovh_cloud_pandas_web:dev
       if: github.event_name == 'push'
+
+    - name: Create git repo to upload the built docs to GitHub pages
+      run: |
+        cd pandas_web
+        git init
+        touch .nojekyll
+        echo "dev.pandas.io" > CNAME
+        printf "User-agent: *\nDisallow: /" > robots.txt
+        git add --all .
+        git config user.email "[email protected]"
+        git config user.name "pandas-bot"
+        git commit -m "pandas web and documentation in master"
+      if: github.event_name == 'push'
+
+    # For this task to work, next steps are required:
+    # 1. Generate a pair of private/public keys (i.e. `ssh-keygen -t rsa -b 4096 -C "[email protected]"`)
+    # 2. Go to https://github.com/pandas-dev/pandas/settings/secrets
+    # 3. Click on "Add a new secret"
+    # 4. Name: "github_pagas_ssh_key", Value: <Content of the private ssh key>
+    # 5. The public key needs to be upladed to https://github.com/pandas-dev/pandas-dev.github.io/settings/keys
+    - name: Install GitHub pages ssh deployment key
+      uses: shimataro/ssh-key-action@v2
+      with:
+        key: ${{ secrets.github_pages_ssh_key }}
+        known_hosts: 'github.com,192.30.252.128 ssh-rsa AAAAB3NzaC1yc2EAAAABIwAAAQEAq2A7hRGmdnm9tUDbO9IDSwBK6TbQa+PXYPCPy6rbTrTtw7PHkccKrpp0yVhp5HdEIcKr6pLlVDBfOLX9QUsyCOV0wzfjIJNlGEYsdlLJizHhbn2mUjvSAHQqZETYP81eFzLQNnPHt4EVVUh7VfDESU84KezmD5QlWpXLmvU31/yMf+Se8xhHTvKSCZIFImWwoG6mbUoWf9nzpIoaSjB+weqqUUmpaaasXVal72J+UX2B+2RPW3RcT0eOzQgqlJL3RKrTJvdsjE3JEAvGq3lGHSZXy28G3skua2SmVi/w4yCE6gbODqnTWlg7+wC604ydGXA8VJiS5ap43JXiUFFAaQ=='
+      if: github.event_name == 'push'
+
+    - name: Publish web and docs to GitHub pages
+      run: |
+        cd pandas_web
+        git remote add origin [email protected]:pandas-dev/pandas-dev.github.io.git
+        git push -f origin master || true
+      if: github.event_name == 'push'

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: