CLN/ASV: avoid deprecation warnings in ASVs (#54301)

avoid deprecation warnings in ASVs

Author: lukemanley

asv_bench/benchmarks/groupby.py

@@ -408,7 +408,7 @@ def time_multi_size(self):
         self.df.groupby(["key1", "key2"]).size()
 
     def time_category_size(self):
-        self.draws.groupby(self.cats).size()
+        self.draws.groupby(self.cats, observed=True).size()
 
 
 class Shift:
@@ -767,7 +767,10 @@ def time_str_func(self, dtype, method):
 
 
 class Categories:
-    def setup(self):
+    params = [True, False]
+    param_names = ["observed"]
+
+    def setup(self, observed):
         N = 10**5
         arr = np.random.random(N)
         data = {"a": Categorical(np.random.randint(10000, size=N)), "b": arr}
@@ -785,23 +788,23 @@ def setup(self):
         }
         self.df_extra_cat = DataFrame(data)
 
-    def time_groupby_sort(self):
-        self.df.groupby("a")["b"].count()
+    def time_groupby_sort(self, observed):
+        self.df.groupby("a", observed=observed)["b"].count()
 
-    def time_groupby_nosort(self):
-        self.df.groupby("a", sort=False)["b"].count()
+    def time_groupby_nosort(self, observed):
+        self.df.groupby("a", observed=observed, sort=False)["b"].count()
 
-    def time_groupby_ordered_sort(self):
-        self.df_ordered.groupby("a")["b"].count()
+    def time_groupby_ordered_sort(self, observed):
+        self.df_ordered.groupby("a", observed=observed)["b"].count()
 
-    def time_groupby_ordered_nosort(self):
-        self.df_ordered.groupby("a", sort=False)["b"].count()
+    def time_groupby_ordered_nosort(self, observed):
+        self.df_ordered.groupby("a", observed=observed, sort=False)["b"].count()
 
-    def time_groupby_extra_cat_sort(self):
-        self.df_extra_cat.groupby("a")["b"].count()
+    def time_groupby_extra_cat_sort(self, observed):
+        self.df_extra_cat.groupby("a", observed=observed)["b"].count()
 
-    def time_groupby_extra_cat_nosort(self):
-        self.df_extra_cat.groupby("a", sort=False)["b"].count()
+    def time_groupby_extra_cat_nosort(self, observed):
+        self.df_extra_cat.groupby("a", observed=observed, sort=False)["b"].count()
 
 
 class Datelike:

asv_bench/benchmarks/io/csv.py

@@ -226,26 +226,26 @@ def data(self, stringio_object):
 
 
 class ReadCSVDInferDatetimeFormat(StringIORewind):
-    params = ([True, False], ["custom", "iso8601", "ymd"])
-    param_names = ["infer_datetime_format", "format"]
+    params = [None, "custom", "iso8601", "ymd"]
+    param_names = ["format"]
 
-    def setup(self, infer_datetime_format, format):
+    def setup(self, format):
         rng = date_range("1/1/2000", periods=1000)
         formats = {
+            None: None,
             "custom": "%m/%d/%Y %H:%M:%S.%f",
             "iso8601": "%Y-%m-%d %H:%M:%S",
             "ymd": "%Y%m%d",
         }
         dt_format = formats[format]
         self.StringIO_input = StringIO("\n".join(rng.strftime(dt_format).tolist()))
 
-    def time_read_csv(self, infer_datetime_format, format):
+    def time_read_csv(self, format):
         read_csv(
             self.data(self.StringIO_input),
             header=None,
             names=["foo"],
             parse_dates=["foo"],
-            infer_datetime_format=infer_datetime_format,
         )
 
 
@@ -262,7 +262,6 @@ def time_read_csv(self):
             header=None,
             names=["foo"],
             parse_dates=["foo"],
-            infer_datetime_format=False,
         )
 
 
@@ -279,7 +278,6 @@ def time_read_csv(self, bad_date_value):
             header=None,
             names=["foo", "bar"],
             parse_dates=["foo"],
-            infer_datetime_format=False,
         )
 
 

asv_bench/benchmarks/replace.py

@@ -42,7 +42,7 @@ class ReplaceList:
     param_names = ["inplace"]
 
     def setup(self, inplace):
-        self.df = pd.DataFrame({"A": 0, "B": 0}, index=range(4 * 10**7))
+        self.df = pd.DataFrame({"A": 0, "B": 0}, index=range(10**7))
 
     def time_replace_list(self, inplace):
         self.df.replace([np.inf, -np.inf], np.nan, inplace=inplace)