TST: Ensure makeCategoricalIndex categories are unique (pandas-dev#46429)

Author: mroeschke

asv_bench/benchmarks/categoricals.py

@@ -187,7 +187,7 @@ def time_remove_categories(self):
 class Rank:
     def setup(self):
         N = 10**5
-        ncats = 100
+        ncats = 20
 
         self.s_str = pd.Series(tm.makeCategoricalIndex(N, ncats)).astype(str)
         self.s_str_cat = pd.Series(self.s_str, dtype="category")

pandas/_testing/__init__.py

@@ -305,7 +305,7 @@ def makeUnicodeIndex(k=10, name=None):
 
 def makeCategoricalIndex(k=10, n=3, name=None, **kwargs):
     """make a length k index or n categories"""
-    x = rands_array(nchars=4, size=n)
+    x = rands_array(nchars=4, size=n, replace=False)
     return CategoricalIndex(
         Categorical.from_codes(np.arange(k) % n, categories=x), name=name, **kwargs
     )

pandas/_testing/_random.py

@@ -14,12 +14,12 @@ def randbool(size=(), p: float = 0.5):
 )
 
 
-def rands_array(nchars, size, dtype="O"):
+def rands_array(nchars, size, dtype="O", replace=True):
     """
     Generate an array of byte strings.
     """
     retval = (
-        np.random.choice(RANDS_CHARS, size=nchars * np.prod(size))
+        np.random.choice(RANDS_CHARS, size=nchars * np.prod(size), replace=replace)
         .view((np.str_, nchars))
         .reshape(size)
     )