update algorithms.Factorize.time_factorize

asv_bench/benchmarks/algorithms.py

@@ -5,6 +5,7 @@
 from pandas._libs import lib
 
 import pandas as pd
+from pandas.core.arrays.string_arrow import ArrowStringDtype
 
 from .pandas_vb_common import tm
 
@@ -43,23 +44,34 @@ class Factorize:
  "datetime64[ns, tz]",
  "Int64",
  "boolean",
+ "string_arrow",
  ],
  ]
  param_names = ["unique", "sort", "dtype"]
 
  def setup(self, unique, sort, dtype):
  N = 10 ** 5
+ string_index = tm.makeStringIndex(N)
+ try:
+ string_arrow = pd.array(string_index, dtype=ArrowStringDtype())
+ except ImportError:
+ string_arrow = None
+
+ if dtype == "string_arrow" and not string_arrow:
+ raise NotImplementedError
+
  data = {
  "int": pd.Int64Index(np.arange(N)),
  "uint": pd.UInt64Index(np.arange(N)),
  "float": pd.Float64Index(np.random.randn(N)),
- "string": tm.makeStringIndex(N),
+ "string": string_index,
  "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"
  ),
  "Int64": pd.array(np.arange(N), dtype="Int64"),
  "boolean": pd.array(np.random.randint(0, 2, N), dtype="boolean"),
+ "string_arrow": string_arrow,
  }[dtype]
  if not unique:
  data = data.repeat(5)