TST/CLN: Remove makeStringIndex (#56155)

* TST/CLN: Remove makeStringIndex

* Fix failures

* Fix one more test

* Remove makeBoolIndex too

* Remove name

* Adjust test

* Fix benchmarks

* Fix another benchmark

Author: mroeschke

asv_bench/benchmarks/algorithms.py

@@ -4,8 +4,6 @@
 
 import pandas as pd
 
-from .pandas_vb_common import tm
-
 for imp in ["pandas.util", "pandas.tools.hashing"]:
     try:
         hashing = import_module(imp)
@@ -47,9 +45,12 @@ def setup(self, unique, sort, dtype):
         elif dtype == "datetime64[ns, tz]":
             data = pd.date_range("2011-01-01", freq="h", periods=N, tz="Asia/Tokyo")
         elif dtype == "object_str":
-            data = tm.makeStringIndex(N)
+            data = pd.Index([f"i-{i}" for i in range(N)], dtype=object)
         elif dtype == "string[pyarrow]":
-            data = pd.array(tm.makeStringIndex(N), dtype="string[pyarrow]")
+            data = pd.array(
+                pd.Index([f"i-{i}" for i in range(N)], dtype=object),
+                dtype="string[pyarrow]",
+            )
         else:
             raise NotImplementedError
 
@@ -88,7 +89,7 @@ def setup(self, unique, keep, dtype):
         elif dtype == "float64":
             data = pd.Index(np.random.randn(N), dtype="float64")
         elif dtype == "string":
-            data = tm.makeStringIndex(N)
+            data = pd.Index([f"i-{i}" for i in range(N)], dtype=object)
         elif dtype == "datetime64[ns]":
             data = pd.date_range("2011-01-01", freq="h", periods=N)
         elif dtype == "datetime64[ns, tz]":
@@ -136,7 +137,9 @@ def setup_cache(self):
         df = pd.DataFrame(
             {
                 "strings": pd.Series(
-                    tm.makeStringIndex(10000).take(np.random.randint(0, 10000, size=N))
+                    pd.Index([f"i-{i}" for i in range(10000)], dtype=object).take(
+                        np.random.randint(0, 10000, size=N)
+                    )
                 ),
                 "floats": np.random.randn(N),
                 "ints": np.arange(N),

asv_bench/benchmarks/algos/isin.py

@@ -8,8 +8,6 @@
     date_range,
 )
 
-from ..pandas_vb_common import tm
-
 
 class IsIn:
     params = [
@@ -60,7 +58,9 @@ def setup(self, dtype):
 
         elif dtype in ["str", "string[python]", "string[pyarrow]"]:
             try:
-                self.series = Series(tm.makeStringIndex(N), dtype=dtype)
+                self.series = Series(
+                    Index([f"i-{i}" for i in range(N)], dtype=object), dtype=dtype
+                )
             except ImportError:
                 raise NotImplementedError
             self.values = list(self.series[:2])

asv_bench/benchmarks/ctors.py

@@ -9,8 +9,6 @@
     date_range,
 )
 
-from .pandas_vb_common import tm
-
 
 def no_change(arr):
     return arr
@@ -115,7 +113,7 @@ def time_dtindex_from_index_with_series(self):
 class MultiIndexConstructor:
     def setup(self):
         N = 10**4
-        self.iterables = [tm.makeStringIndex(N), range(20)]
+        self.iterables = [Index([f"i-{i}" for i in range(N)], dtype=object), range(20)]
 
     def time_multiindex_from_iterables(self):
         MultiIndex.from_product(self.iterables)

asv_bench/benchmarks/dtypes.py

@@ -3,7 +3,10 @@
 import numpy as np
 
 import pandas as pd
-from pandas import DataFrame
+from pandas import (
+    DataFrame,
+    Index,
+)
 import pandas._testing as tm
 from pandas.api.types import (
     is_extension_array_dtype,
@@ -73,8 +76,8 @@ class SelectDtypes:
 
     def setup(self, dtype):
         N, K = 5000, 50
-        self.index = tm.makeStringIndex(N)
-        self.columns = tm.makeStringIndex(K)
+        self.index = Index([f"i-{i}" for i in range(N)], dtype=object)
+        self.columns = Index([f"i-{i}" for i in range(K)], dtype=object)
 
         def create_df(data):
             return DataFrame(data, index=self.index, columns=self.columns)

asv_bench/benchmarks/frame_ctor.py

@@ -12,8 +12,6 @@
     date_range,
 )
 
-from .pandas_vb_common import tm
-
 try:
     from pandas.tseries.offsets import (
         Hour,
@@ -30,8 +28,8 @@
 class FromDicts:
     def setup(self):
         N, K = 5000, 50
-        self.index = tm.makeStringIndex(N)
-        self.columns = tm.makeStringIndex(K)
+        self.index = pd.Index([f"i-{i}" for i in range(N)], dtype=object)
+        self.columns = pd.Index([f"i-{i}" for i in range(K)], dtype=object)
         frame = DataFrame(np.random.randn(N, K), index=self.index, columns=self.columns)
         self.data = frame.to_dict()
         self.dict_list = frame.to_dict(orient="records")

asv_bench/benchmarks/frame_methods.py

@@ -5,6 +5,7 @@
 
 from pandas import (
     DataFrame,
+    Index,
     MultiIndex,
     NaT,
     Series,
@@ -14,8 +15,6 @@
     timedelta_range,
 )
 
-from .pandas_vb_common import tm
-
 
 class AsType:
     params = [
@@ -703,8 +702,12 @@ def setup(self, monotonic):
         K = 10
         df = DataFrame(
             {
-                "key1": tm.makeStringIndex(N).values.repeat(K),
-                "key2": tm.makeStringIndex(N).values.repeat(K),
+                "key1": Index([f"i-{i}" for i in range(N)], dtype=object).values.repeat(
+                    K
+                ),
+                "key2": Index([f"i-{i}" for i in range(N)], dtype=object).values.repeat(
+                    K
+                ),
                 "value": np.random.randn(N * K),
             }
         )

asv_bench/benchmarks/gil.py

@@ -5,15 +5,14 @@
 
 from pandas import (
     DataFrame,
+    Index,
     Series,
     date_range,
     factorize,
     read_csv,
 )
 from pandas.core.algorithms import take_nd
 
-from .pandas_vb_common import tm
-
 try:
     from pandas import (
         rolling_kurt,
@@ -34,7 +33,6 @@
 except ImportError:
     from pandas import algos
 
-
 from .pandas_vb_common import BaseIO  # isort:skip
 
 
@@ -305,7 +303,7 @@ class ParallelFactorize:
     param_names = ["threads"]
 
     def setup(self, threads):
-        strings = tm.makeStringIndex(100000)
+        strings = Index([f"i-{i}" for i in range(100000)], dtype=object)
 
         @test_parallel(num_threads=threads)
         def parallel():

asv_bench/benchmarks/groupby.py

@@ -17,8 +17,6 @@
     to_timedelta,
 )
 
-from .pandas_vb_common import tm
-
 method_blocklist = {
     "object": {
         "diff",
@@ -167,10 +165,14 @@ def setup_cache(self):
             "int64_small": Series(np.random.randint(0, 100, size=size)),
             "int64_large": Series(np.random.randint(0, 10000, size=size)),
             "object_small": Series(
-                tm.makeStringIndex(100).take(np.random.randint(0, 100, size=size))
+                Index([f"i-{i}" for i in range(100)], dtype=object).take(
+                    np.random.randint(0, 100, size=size)
+                )
             ),
             "object_large": Series(
-                tm.makeStringIndex(10000).take(np.random.randint(0, 10000, size=size))
+                Index([f"i-{i}" for i in range(10000)], dtype=object).take(
+                    np.random.randint(0, 10000, size=size)
+                )
             ),
         }
         return data
@@ -912,7 +914,7 @@ def setup(self):
         n1 = 400
         n2 = 250
         index = MultiIndex(
-            levels=[np.arange(n1), tm.makeStringIndex(n2)],
+            levels=[np.arange(n1), Index([f"i-{i}" for i in range(n2)], dtype=object)],
             codes=[np.repeat(range(n1), n2).tolist(), list(range(n2)) * n1],
             names=["lev1", "lev2"],
         )

asv_bench/benchmarks/index_object.py

@@ -12,8 +12,6 @@
     date_range,
 )
 
-from .pandas_vb_common import tm
-
 
 class SetOperations:
     params = (
@@ -30,7 +28,7 @@ def setup(self, index_structure, dtype, method):
         date_str_left = Index(dates_left.strftime(fmt))
         int_left = Index(np.arange(N))
         ea_int_left = Index(np.arange(N), dtype="Int64")
-        str_left = tm.makeStringIndex(N)
+        str_left = Index([f"i-{i}" for i in range(N)], dtype=object)
 
         data = {
             "datetime": dates_left,
@@ -155,7 +153,12 @@ class Indexing:
 
     def setup(self, dtype):
         N = 10**6
-        self.idx = getattr(tm, f"make{dtype}Index")(N)
+        if dtype == "String":
+            self.idx = Index([f"i-{i}" for i in range(N)], dtype=object)
+        elif dtype == "Float":
+            self.idx = Index(np.arange(N), dtype=np.float64)
+        elif dtype == "Int":
+            self.idx = Index(np.arange(N), dtype=np.int64)
         self.array_mask = (np.arange(N) % 3) == 0
         self.series_mask = Series(self.array_mask)
         self.sorted = self.idx.sort_values()

asv_bench/benchmarks/indexing.py

@@ -22,8 +22,6 @@
     period_range,
 )
 
-from .pandas_vb_common import tm
-
 
 class NumericSeriesIndexing:
     params = [
@@ -124,7 +122,7 @@ class NonNumericSeriesIndexing:
     def setup(self, index, index_structure):
         N = 10**6
         if index == "string":
-            index = tm.makeStringIndex(N)
+            index = Index([f"i-{i}" for i in range(N)], dtype=object)
         elif index == "datetime":
             index = date_range("1900", periods=N, freq="s")
         elif index == "period":
@@ -156,8 +154,8 @@ def time_getitem_list_like(self, index, index_structure):
 
 class DataFrameStringIndexing:
     def setup(self):
-        index = tm.makeStringIndex(1000)
-        columns = tm.makeStringIndex(30)
+        index = Index([f"i-{i}" for i in range(1000)], dtype=object)
+        columns = Index([f"i-{i}" for i in range(30)], dtype=object)
         with warnings.catch_warnings(record=True):
             self.df = DataFrame(np.random.randn(1000, 30), index=index, columns=columns)
         self.idx_scalar = index[100]

asv_bench/benchmarks/inference.py

@@ -9,6 +9,7 @@
 import numpy as np
 
 from pandas import (
+    Index,
     NaT,
     Series,
     date_range,
@@ -17,10 +18,7 @@
     to_timedelta,
 )
 
-from .pandas_vb_common import (
-    lib,
-    tm,
-)
+from .pandas_vb_common import lib
 
 
 class ToNumeric:
@@ -31,7 +29,7 @@ def setup(self, errors):
         N = 10000
         self.float = Series(np.random.randn(N))
         self.numstr = self.float.astype("str")
-        self.str = Series(tm.makeStringIndex(N))
+        self.str = Series(Index([f"i-{i}" for i in range(N)], dtype=object))
 
     def time_from_float(self, errors):
         to_numeric(self.float, errors=errors)

asv_bench/benchmarks/io/csv.py

@@ -10,17 +10,15 @@
 from pandas import (
     Categorical,
     DataFrame,
+    Index,
     concat,
     date_range,
     period_range,
     read_csv,
     to_datetime,
 )
 
-from ..pandas_vb_common import (
-    BaseIO,
-    tm,
-)
+from ..pandas_vb_common import BaseIO
 
 
 class ToCSV(BaseIO):
@@ -288,7 +286,7 @@ class ReadCSVSkipRows(BaseIO):
 
     def setup(self, skiprows, engine):
         N = 20000
-        index = tm.makeStringIndex(N)
+        index = Index([f"i-{i}" for i in range(N)], dtype=object)
         df = DataFrame(
             {
                 "float1": np.random.randn(N),

asv_bench/benchmarks/io/excel.py

@@ -12,12 +12,11 @@
 from pandas import (
     DataFrame,
     ExcelWriter,
+    Index,
     date_range,
     read_excel,
 )
 
-from ..pandas_vb_common import tm
-
 
 def _generate_dataframe():
     N = 2000
@@ -27,7 +26,7 @@ def _generate_dataframe():
         columns=[f"float{i}" for i in range(C)],
         index=date_range("20000101", periods=N, freq="h"),
     )
-    df["object"] = tm.makeStringIndex(N)
+    df["object"] = Index([f"i-{i}" for i in range(N)], dtype=object)
     return df