Merge branch 'main' into ref-plotting-logargs

asv_bench/benchmarks/algorithms.py

@@ -50,9 +50,9 @@ def setup(self, unique, sort, dtype):
             "float": pd.Index(np.random.randn(N), dtype="float64"),
             "object_str": string_index,
             "object": pd.Index(np.arange(N), dtype="object"),
-            "datetime64[ns]": pd.date_range("2011-01-01", freq="H", periods=N),
+            "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"
+                "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"),
@@ -93,9 +93,9 @@ def setup(self, unique, keep, dtype):
             "uint": pd.Index(np.arange(N), dtype="uint64"),
             "float": pd.Index(np.random.randn(N), dtype="float64"),
             "string": tm.makeStringIndex(N),
-            "datetime64[ns]": pd.date_range("2011-01-01", freq="H", periods=N),
+            "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"
+                "2011-01-01", freq="h", periods=N, tz="Asia/Tokyo"
             ),
             "timestamp[ms][pyarrow]": pd.Index(
                 np.arange(N), dtype=pd.ArrowDtype(pa.timestamp("ms"))

asv_bench/benchmarks/arithmetic.py

@@ -491,7 +491,7 @@ class BinaryOpsMultiIndex:
     param_names = ["func"]
 
     def setup(self, func):
-        array = date_range("20200101 00:00", "20200102 0:00", freq="S")
+        array = date_range("20200101 00:00", "20200102 0:00", freq="s")
         level_0_names = [str(i) for i in range(30)]
 
         index = pd.MultiIndex.from_product([level_0_names, array])

asv_bench/benchmarks/frame_methods.py

@@ -439,9 +439,9 @@ def setup(self, inplace, dtype):
         N, M = 10000, 100
         if dtype in ("datetime64[ns]", "datetime64[ns, tz]", "timedelta64[ns]"):
             data = {
-                "datetime64[ns]": date_range("2011-01-01", freq="H", periods=N),
+                "datetime64[ns]": date_range("2011-01-01", freq="h", periods=N),
                 "datetime64[ns, tz]": date_range(
-                    "2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
+                    "2011-01-01", freq="h", periods=N, tz="Asia/Tokyo"
                 ),
                 "timedelta64[ns]": timedelta_range(start="1 day", periods=N, freq="1D"),
             }
@@ -649,7 +649,7 @@ def time_series_nunique_nan(self):
 class Duplicated:
     def setup(self):
         n = 1 << 20
-        t = date_range("2015-01-01", freq="S", periods=(n // 64))
+        t = date_range("2015-01-01", freq="s", periods=(n // 64))
         xs = np.random.randn(n // 64).round(2)
         self.df = DataFrame(
             {

asv_bench/benchmarks/gil.py

@@ -212,7 +212,7 @@ def run(dti):
     def time_datetime_to_period(self):
         @test_parallel(num_threads=2)
         def run(dti):
-            dti.to_period("S")
+            dti.to_period("s")
 
         run(self.dti)
 

asv_bench/benchmarks/groupby.py

@@ -238,7 +238,7 @@ def time_series_nth(self, dtype):
 
 class DateAttributes:
     def setup(self):
-        rng = date_range("1/1/2000", "12/31/2005", freq="H")
+        rng = date_range("1/1/2000", "12/31/2005", freq="h")
         self.year, self.month, self.day = rng.year, rng.month, rng.day
         self.ts = Series(np.random.randn(len(rng)), index=rng)
 

asv_bench/benchmarks/indexing.py

@@ -232,7 +232,7 @@ def setup(self, index):
         N = 100000
         indexes = {
             "int": Index(np.arange(N), dtype=np.int64),
-            "datetime": date_range("2011-01-01", freq="S", periods=N),
+            "datetime": date_range("2011-01-01", freq="s", periods=N),
         }
         index = indexes[index]
         self.s = Series(np.random.rand(N), index=index)
@@ -465,7 +465,7 @@ def time_loc_row(self, unique_cols):
 class AssignTimeseriesIndex:
     def setup(self):
         N = 100000
-        idx = date_range("1/1/2000", periods=N, freq="H")
+        idx = date_range("1/1/2000", periods=N, freq="h")
         self.df = DataFrame(np.random.randn(N, 1), columns=["A"], index=idx)
 
     def time_frame_assign_timeseries_index(self):

asv_bench/benchmarks/inference.py

@@ -164,7 +164,7 @@ def time_unique_date_strings(self, cache, count):
 
 class ToDatetimeISO8601:
     def setup(self):
-        rng = date_range(start="1/1/2000", periods=20000, freq="H")
+        rng = date_range(start="1/1/2000", periods=20000, freq="h")
         self.strings = rng.strftime("%Y-%m-%d %H:%M:%S").tolist()
         self.strings_nosep = rng.strftime("%Y%m%d %H:%M:%S").tolist()
         self.strings_tz_space = [
@@ -276,7 +276,7 @@ def time_dup_string_tzoffset_dates(self, cache):
 # GH 43901
 class ToDatetimeInferDatetimeFormat:
     def setup(self):
-        rng = date_range(start="1/1/2000", periods=100000, freq="H")
+        rng = date_range(start="1/1/2000", periods=100000, freq="h")
         self.strings = rng.strftime("%Y-%m-%d %H:%M:%S").tolist()
 
     def time_infer_datetime_format(self):

asv_bench/benchmarks/io/csv.py

@@ -89,7 +89,7 @@ class ToCSVDatetimeIndex(BaseIO):
     fname = "__test__.csv"
 
     def setup(self):
-        rng = date_range("2000", periods=100_000, freq="S")
+        rng = date_range("2000", periods=100_000, freq="s")
         self.data = DataFrame({"a": 1}, index=rng)
 
     def time_frame_date_formatting_index(self):
@@ -102,15 +102,15 @@ def time_frame_date_no_format_index(self):
 class ToCSVPeriod(BaseIO):
     fname = "__test__.csv"
 
-    params = ([1000, 10000], ["D", "H"])
+    params = ([1000, 10000], ["D", "h"])
     param_names = ["nobs", "freq"]
 
     def setup(self, nobs, freq):
         rng = period_range(start="2000-01-01", periods=nobs, freq=freq)
         self.data = DataFrame(rng)
         if freq == "D":
             self.default_fmt = "%Y-%m-%d"
-        elif freq == "H":
+        elif freq == "h":
             self.default_fmt = "%Y-%m-%d %H:00"
 
     def time_frame_period_formatting_default(self, nobs, freq):
@@ -130,15 +130,15 @@ def time_frame_period_formatting(self, nobs, freq):
 class ToCSVPeriodIndex(BaseIO):
     fname = "__test__.csv"
 
-    params = ([1000, 10000], ["D", "H"])
+    params = ([1000, 10000], ["D", "h"])
     param_names = ["nobs", "freq"]
 
     def setup(self, nobs, freq):
         rng = period_range(start="2000-01-01", periods=nobs, freq=freq)
         self.data = DataFrame({"a": 1}, index=rng)
         if freq == "D":
             self.default_fmt = "%Y-%m-%d"
-        elif freq == "H":
+        elif freq == "h":
             self.default_fmt = "%Y-%m-%d %H:00"
 
     def time_frame_period_formatting_index(self, nobs, freq):
@@ -253,7 +253,7 @@ class ReadCSVConcatDatetime(StringIORewind):
     iso8601 = "%Y-%m-%d %H:%M:%S"
 
     def setup(self):
-        rng = date_range("1/1/2000", periods=50000, freq="S")
+        rng = date_range("1/1/2000", periods=50000, freq="s")
         self.StringIO_input = StringIO("\n".join(rng.strftime(self.iso8601).tolist()))
 
     def time_read_csv(self):

asv_bench/benchmarks/io/excel.py

@@ -25,7 +25,7 @@ def _generate_dataframe():
     df = DataFrame(
         np.random.randn(N, C),
         columns=[f"float{i}" for i in range(C)],
-        index=date_range("20000101", periods=N, freq="H"),
+        index=date_range("20000101", periods=N, freq="h"),
     )
     df["object"] = tm.makeStringIndex(N)
     return df

asv_bench/benchmarks/io/hdf.py

@@ -122,7 +122,7 @@ def setup(self, format):
         self.df = DataFrame(
             np.random.randn(N, C),
             columns=[f"float{i}" for i in range(C)],
-            index=date_range("20000101", periods=N, freq="H"),
+            index=date_range("20000101", periods=N, freq="h"),
         )
         self.df["object"] = tm.makeStringIndex(N)
         self.df.to_hdf(self.fname, "df", format=format)

asv_bench/benchmarks/io/json.py

@@ -26,7 +26,7 @@ def setup(self, orient, index):
         N = 100000
         indexes = {
             "int": np.arange(N),
-            "datetime": date_range("20000101", periods=N, freq="H"),
+            "datetime": date_range("20000101", periods=N, freq="h"),
         }
         df = DataFrame(
             np.random.randn(N, 5),
@@ -48,7 +48,7 @@ def setup(self, index):
         N = 100000
         indexes = {
             "int": np.arange(N),
-            "datetime": date_range("20000101", periods=N, freq="H"),
+            "datetime": date_range("20000101", periods=N, freq="h"),
         }
         df = DataFrame(
             np.random.randn(N, 5),
@@ -108,7 +108,7 @@ class ToJSON(BaseIO):
     def setup(self, orient, frame):
         N = 10**5
         ncols = 5
-        index = date_range("20000101", periods=N, freq="H")
+        index = date_range("20000101", periods=N, freq="h")
         timedeltas = timedelta_range(start=1, periods=N, freq="s")
         datetimes = date_range(start=1, periods=N, freq="s")
         ints = np.random.randint(100000000, size=N)
@@ -191,7 +191,7 @@ class ToJSONISO(BaseIO):
 
     def setup(self, orient):
         N = 10**5
-        index = date_range("20000101", periods=N, freq="H")
+        index = date_range("20000101", periods=N, freq="h")
         timedeltas = timedelta_range(start=1, periods=N, freq="s")
         datetimes = date_range(start=1, periods=N, freq="s")
         self.df = DataFrame(
@@ -214,7 +214,7 @@ class ToJSONLines(BaseIO):
     def setup(self):
         N = 10**5
         ncols = 5
-        index = date_range("20000101", periods=N, freq="H")
+        index = date_range("20000101", periods=N, freq="h")
         timedeltas = timedelta_range(start=1, periods=N, freq="s")
         datetimes = date_range(start=1, periods=N, freq="s")
         ints = np.random.randint(100000000, size=N)

asv_bench/benchmarks/io/pickle.py

@@ -20,7 +20,7 @@ def setup(self):
         self.df = DataFrame(
             np.random.randn(N, C),
             columns=[f"float{i}" for i in range(C)],
-            index=date_range("20000101", periods=N, freq="H"),
+            index=date_range("20000101", periods=N, freq="h"),
         )
         self.df["object"] = tm.makeStringIndex(N)
         self.df.to_pickle(self.fname)

asv_bench/benchmarks/io/stata.py

@@ -23,7 +23,7 @@ def setup(self, convert_dates):
         self.df = DataFrame(
             np.random.randn(N, C),
             columns=[f"float{i}" for i in range(C)],
-            index=date_range("20000101", periods=N, freq="H"),
+            index=date_range("20000101", periods=N, freq="h"),
         )
         self.df["object"] = tm.makeStringIndex(self.N)
         self.df["int8_"] = np.random.randint(

asv_bench/benchmarks/join_merge.py

@@ -213,7 +213,7 @@ class JoinNonUnique:
     # GH 6329
     def setup(self):
         date_index = date_range("01-Jan-2013", "23-Jan-2013", freq="min")
-        daily_dates = date_index.to_period("D").to_timestamp("S", "S")
+        daily_dates = date_index.to_period("D").to_timestamp("s", "s")
         self.fracofday = date_index.values - daily_dates.values
         self.fracofday = self.fracofday.astype("timedelta64[ns]")
         self.fracofday = self.fracofday.astype(np.float64) / 86_400_000_000_000

asv_bench/benchmarks/period.py

@@ -45,7 +45,7 @@ def time_from_ints_daily(self, freq, is_offset):
 
 class DataFramePeriodColumn:
     def setup(self):
-        self.rng = period_range(start="1/1/1990", freq="S", periods=20000)
+        self.rng = period_range(start="1/1/1990", freq="s", periods=20000)
         self.df = DataFrame(index=range(len(self.rng)))
 
     def time_setitem_period_column(self):

asv_bench/benchmarks/series_methods.py

@@ -64,7 +64,7 @@ def setup(self, dtype):
         N = 10**6
         data = {
             "int": np.random.randint(1, 10, N),
-            "datetime": date_range("2000-01-01", freq="S", periods=N),
+            "datetime": date_range("2000-01-01", freq="s", periods=N),
         }
         self.s = Series(data[dtype])
         if dtype == "datetime":
@@ -92,7 +92,7 @@ class Fillna:
     def setup(self, dtype):
         N = 10**6
         if dtype == "datetime64[ns]":
-            data = date_range("2000-01-01", freq="S", periods=N)
+            data = date_range("2000-01-01", freq="s", periods=N)
             na_value = NaT
         elif dtype in ("float64", "Float64"):
             data = np.random.randn(N)

asv_bench/benchmarks/strftime.py

@@ -53,7 +53,7 @@ def time_frame_datetime_formatting_custom(self, nobs):
 
 class PeriodStrftime:
     timeout = 1500
-    params = ([1000, 10000], ["D", "H"])
+    params = ([1000, 10000], ["D", "h"])
     param_names = ["nobs", "freq"]
 
     def setup(self, nobs, freq):
@@ -67,7 +67,7 @@ def setup(self, nobs, freq):
         self.data.set_index("i", inplace=True)
         if freq == "D":
             self.default_fmt = "%Y-%m-%d"
-        elif freq == "H":
+        elif freq == "h":
             self.default_fmt = "%Y-%m-%d %H:00"
 
     def time_frame_period_to_str(self, nobs, freq):

asv_bench/benchmarks/timeseries.py

@@ -27,7 +27,7 @@ def setup(self, index_type):
         N = 100000
         dtidxes = {
             "dst": date_range(
-                start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="S"
+                start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="s"
             ),
             "repeated": date_range(start="2000", periods=N / 10, freq="s").repeat(10),
             "tz_aware": date_range(start="2000", periods=N, freq="s", tz="US/Eastern"),
@@ -72,13 +72,13 @@ class TzLocalize:
 
     def setup(self, tz):
         dst_rng = date_range(
-            start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="S"
+            start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="s"
         )
-        self.index = date_range(start="10/29/2000", end="10/29/2000 00:59:59", freq="S")
+        self.index = date_range(start="10/29/2000", end="10/29/2000 00:59:59", freq="s")
         self.index = self.index.append(dst_rng)
         self.index = self.index.append(dst_rng)
         self.index = self.index.append(
-            date_range(start="10/29/2000 2:00:00", end="10/29/2000 3:00:00", freq="S")
+            date_range(start="10/29/2000 2:00:00", end="10/29/2000 3:00:00", freq="s")
         )
 
     def time_infer_dst(self, tz):
@@ -90,7 +90,7 @@ class ResetIndex:
     param_names = "tz"
 
     def setup(self, tz):
-        idx = date_range(start="1/1/2000", periods=1000, freq="H", tz=tz)
+        idx = date_range(start="1/1/2000", periods=1000, freq="h", tz=tz)
         self.df = DataFrame(np.random.randn(1000, 2), index=idx)
 
     def time_reset_datetimeindex(self, tz):
@@ -255,7 +255,7 @@ def time_get_slice(self, monotonic):
 class Lookup:
     def setup(self):
         N = 1500000
-        rng = date_range(start="1/1/2000", periods=N, freq="S")
+        rng = date_range(start="1/1/2000", periods=N, freq="s")
         self.ts = Series(1, index=rng)
         self.lookup_val = rng[N // 2]
 

pandas/io/parsers/arrow_parser_wrapper.py

@@ -13,6 +13,7 @@
 )
 from pandas.util._exceptions import find_stack_level
 
+from pandas.core.dtypes.common import pandas_dtype
 from pandas.core.dtypes.inference import is_integer
 
 import pandas as pd
@@ -203,7 +204,13 @@ def _finalize_pandas_output(self, frame: DataFrame) -> DataFrame:
             # Ignore non-existent columns from dtype mapping
             # like other parsers do
             if isinstance(self.dtype, dict):
-                self.dtype = {k: v for k, v in self.dtype.items() if k in frame.columns}
+                self.dtype = {
+                    k: pandas_dtype(v)
+                    for k, v in self.dtype.items()
+                    if k in frame.columns
+                }
+            else:
+                self.dtype = pandas_dtype(self.dtype)
             try:
                 frame = frame.astype(self.dtype)
             except TypeError as e: