ASV: avoid "H" and "S" freq deprecations (#55921) · pandas-dev/pandas@b2d9ec1 (original) (raw)

18 files changed

lines changed

Original file line number Diff line number Diff line change
@@ -50,9 +50,9 @@ def setup(self, unique, sort, dtype):
50 50 "float": pd.Index(np.random.randn(N), dtype="float64"),
51 51 "object_str": string_index,
52 52 "object": pd.Index(np.arange(N), dtype="object"),
53 -"datetime64[ns]": pd.date_range("2011-01-01", freq="H", periods=N),
53 +"datetime64[ns]": pd.date_range("2011-01-01", freq="h", periods=N),
54 54 "datetime64[ns, tz]": pd.date_range(
55 -"2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
55 +"2011-01-01", freq="h", periods=N, tz="Asia/Tokyo"
56 56 ),
57 57 "Int64": pd.array(np.arange(N), dtype="Int64"),
58 58 "boolean": pd.array(np.random.randint(0, 2, N), dtype="boolean"),
@@ -93,9 +93,9 @@ def setup(self, unique, keep, dtype):
93 93 "uint": pd.Index(np.arange(N), dtype="uint64"),
94 94 "float": pd.Index(np.random.randn(N), dtype="float64"),
95 95 "string": tm.makeStringIndex(N),
96 -"datetime64[ns]": pd.date_range("2011-01-01", freq="H", periods=N),
96 +"datetime64[ns]": pd.date_range("2011-01-01", freq="h", periods=N),
97 97 "datetime64[ns, tz]": pd.date_range(
98 -"2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
98 +"2011-01-01", freq="h", periods=N, tz="Asia/Tokyo"
99 99 ),
100 100 "timestamp[ms][pyarrow]": pd.Index(
101 101 np.arange(N), dtype=pd.ArrowDtype(pa.timestamp("ms"))
Original file line number Diff line number Diff line change
@@ -491,7 +491,7 @@ class BinaryOpsMultiIndex:
491 491 param_names = ["func"]
492 492
493 493 def setup(self, func):
494 -array = date_range("20200101 00:00", "20200102 0:00", freq="S")
494 +array = date_range("20200101 00:00", "20200102 0:00", freq="s")
495 495 level_0_names = [str(i) for i in range(30)]
496 496
497 497 index = pd.MultiIndex.from_product([level_0_names, array])
Original file line number Diff line number Diff line change
@@ -439,9 +439,9 @@ def setup(self, inplace, dtype):
439 439 N, M = 10000, 100
440 440 if dtype in ("datetime64[ns]", "datetime64[ns, tz]", "timedelta64[ns]"):
441 441 data = {
442 -"datetime64[ns]": date_range("2011-01-01", freq="H", periods=N),
442 +"datetime64[ns]": date_range("2011-01-01", freq="h", periods=N),
443 443 "datetime64[ns, tz]": date_range(
444 -"2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
444 +"2011-01-01", freq="h", periods=N, tz="Asia/Tokyo"
445 445 ),
446 446 "timedelta64[ns]": timedelta_range(start="1 day", periods=N, freq="1D"),
447 447 }
@@ -649,7 +649,7 @@ def time_series_nunique_nan(self):
649 649 class Duplicated:
650 650 def setup(self):
651 651 n = 1 << 20
652 -t = date_range("2015-01-01", freq="S", periods=(n // 64))
652 +t = date_range("2015-01-01", freq="s", periods=(n // 64))
653 653 xs = np.random.randn(n // 64).round(2)
654 654 self.df = DataFrame(
655 655 {
Original file line number Diff line number Diff line change
@@ -212,7 +212,7 @@ def run(dti):
212 212 def time_datetime_to_period(self):
213 213 @test_parallel(num_threads=2)
214 214 def run(dti):
215 -dti.to_period("S")
215 +dti.to_period("s")
216 216
217 217 run(self.dti)
218 218
Original file line number Diff line number Diff line change
@@ -238,7 +238,7 @@ def time_series_nth(self, dtype):
238 238
239 239 class DateAttributes:
240 240 def setup(self):
241 -rng = date_range("1/1/2000", "12/31/2005", freq="H")
241 +rng = date_range("1/1/2000", "12/31/2005", freq="h")
242 242 self.year, self.month, self.day = rng.year, rng.month, rng.day
243 243 self.ts = Series(np.random.randn(len(rng)), index=rng)
244 244
Original file line number Diff line number Diff line change
@@ -232,7 +232,7 @@ def setup(self, index):
232 232 N = 100000
233 233 indexes = {
234 234 "int": Index(np.arange(N), dtype=np.int64),
235 -"datetime": date_range("2011-01-01", freq="S", periods=N),
235 +"datetime": date_range("2011-01-01", freq="s", periods=N),
236 236 }
237 237 index = indexes[index]
238 238 self.s = Series(np.random.rand(N), index=index)
@@ -465,7 +465,7 @@ def time_loc_row(self, unique_cols):
465 465 class AssignTimeseriesIndex:
466 466 def setup(self):
467 467 N = 100000
468 -idx = date_range("1/1/2000", periods=N, freq="H")
468 +idx = date_range("1/1/2000", periods=N, freq="h")
469 469 self.df = DataFrame(np.random.randn(N, 1), columns=["A"], index=idx)
470 470
471 471 def time_frame_assign_timeseries_index(self):
Original file line number Diff line number Diff line change
@@ -164,7 +164,7 @@ def time_unique_date_strings(self, cache, count):
164 164
165 165 class ToDatetimeISO8601:
166 166 def setup(self):
167 -rng = date_range(start="1/1/2000", periods=20000, freq="H")
167 +rng = date_range(start="1/1/2000", periods=20000, freq="h")
168 168 self.strings = rng.strftime("%Y-%m-%d %H:%M:%S").tolist()
169 169 self.strings_nosep = rng.strftime("%Y%m%d %H:%M:%S").tolist()
170 170 self.strings_tz_space = [
@@ -276,7 +276,7 @@ def time_dup_string_tzoffset_dates(self, cache):
276 276 # GH 43901
277 277 class ToDatetimeInferDatetimeFormat:
278 278 def setup(self):
279 -rng = date_range(start="1/1/2000", periods=100000, freq="H")
279 +rng = date_range(start="1/1/2000", periods=100000, freq="h")
280 280 self.strings = rng.strftime("%Y-%m-%d %H:%M:%S").tolist()
281 281
282 282 def time_infer_datetime_format(self):
Original file line number Diff line number Diff line change
@@ -89,7 +89,7 @@ class ToCSVDatetimeIndex(BaseIO):
89 89 fname = "__test__.csv"
90 90
91 91 def setup(self):
92 -rng = date_range("2000", periods=100_000, freq="S")
92 +rng = date_range("2000", periods=100_000, freq="s")
93 93 self.data = DataFrame({"a": 1}, index=rng)
94 94
95 95 def time_frame_date_formatting_index(self):
@@ -102,15 +102,15 @@ def time_frame_date_no_format_index(self):
102 102 class ToCSVPeriod(BaseIO):
103 103 fname = "__test__.csv"
104 104
105 -params = ([1000, 10000], ["D", "H"])
105 +params = ([1000, 10000], ["D", "h"])
106 106 param_names = ["nobs", "freq"]
107 107
108 108 def setup(self, nobs, freq):
109 109 rng = period_range(start="2000-01-01", periods=nobs, freq=freq)
110 110 self.data = DataFrame(rng)
111 111 if freq == "D":
112 112 self.default_fmt = "%Y-%m-%d"
113 -elif freq == "H":
113 +elif freq == "h":
114 114 self.default_fmt = "%Y-%m-%d %H:00"
115 115
116 116 def time_frame_period_formatting_default(self, nobs, freq):
@@ -130,15 +130,15 @@ def time_frame_period_formatting(self, nobs, freq):
130 130 class ToCSVPeriodIndex(BaseIO):
131 131 fname = "__test__.csv"
132 132
133 -params = ([1000, 10000], ["D", "H"])
133 +params = ([1000, 10000], ["D", "h"])
134 134 param_names = ["nobs", "freq"]
135 135
136 136 def setup(self, nobs, freq):
137 137 rng = period_range(start="2000-01-01", periods=nobs, freq=freq)
138 138 self.data = DataFrame({"a": 1}, index=rng)
139 139 if freq == "D":
140 140 self.default_fmt = "%Y-%m-%d"
141 -elif freq == "H":
141 +elif freq == "h":
142 142 self.default_fmt = "%Y-%m-%d %H:00"
143 143
144 144 def time_frame_period_formatting_index(self, nobs, freq):
@@ -253,7 +253,7 @@ class ReadCSVConcatDatetime(StringIORewind):
253 253 iso8601 = "%Y-%m-%d %H:%M:%S"
254 254
255 255 def setup(self):
256 -rng = date_range("1/1/2000", periods=50000, freq="S")
256 +rng = date_range("1/1/2000", periods=50000, freq="s")
257 257 self.StringIO_input = StringIO("\n".join(rng.strftime(self.iso8601).tolist()))
258 258
259 259 def time_read_csv(self):
Original file line number Diff line number Diff line change
@@ -25,7 +25,7 @@ def _generate_dataframe():
25 25 df = DataFrame(
26 26 np.random.randn(N, C),
27 27 columns=[f"float{i}" for i in range(C)],
28 -index=date_range("20000101", periods=N, freq="H"),
28 +index=date_range("20000101", periods=N, freq="h"),
29 29 )
30 30 df["object"] = tm.makeStringIndex(N)
31 31 return df
Original file line number Diff line number Diff line change
@@ -122,7 +122,7 @@ def setup(self, format):
122 122 self.df = DataFrame(
123 123 np.random.randn(N, C),
124 124 columns=[f"float{i}" for i in range(C)],
125 -index=date_range("20000101", periods=N, freq="H"),
125 +index=date_range("20000101", periods=N, freq="h"),
126 126 )
127 127 self.df["object"] = tm.makeStringIndex(N)
128 128 self.df.to_hdf(self.fname, "df", format=format)
Original file line number Diff line number Diff line change
@@ -26,7 +26,7 @@ def setup(self, orient, index):
26 26 N = 100000
27 27 indexes = {
28 28 "int": np.arange(N),
29 -"datetime": date_range("20000101", periods=N, freq="H"),
29 +"datetime": date_range("20000101", periods=N, freq="h"),
30 30 }
31 31 df = DataFrame(
32 32 np.random.randn(N, 5),
@@ -48,7 +48,7 @@ def setup(self, index):
48 48 N = 100000
49 49 indexes = {
50 50 "int": np.arange(N),
51 -"datetime": date_range("20000101", periods=N, freq="H"),
51 +"datetime": date_range("20000101", periods=N, freq="h"),
52 52 }
53 53 df = DataFrame(
54 54 np.random.randn(N, 5),
@@ -108,7 +108,7 @@ class ToJSON(BaseIO):
108 108 def setup(self, orient, frame):
109 109 N = 10**5
110 110 ncols = 5
111 -index = date_range("20000101", periods=N, freq="H")
111 +index = date_range("20000101", periods=N, freq="h")
112 112 timedeltas = timedelta_range(start=1, periods=N, freq="s")
113 113 datetimes = date_range(start=1, periods=N, freq="s")
114 114 ints = np.random.randint(100000000, size=N)
@@ -191,7 +191,7 @@ class ToJSONISO(BaseIO):
191 191
192 192 def setup(self, orient):
193 193 N = 10**5
194 -index = date_range("20000101", periods=N, freq="H")
194 +index = date_range("20000101", periods=N, freq="h")
195 195 timedeltas = timedelta_range(start=1, periods=N, freq="s")
196 196 datetimes = date_range(start=1, periods=N, freq="s")
197 197 self.df = DataFrame(
@@ -214,7 +214,7 @@ class ToJSONLines(BaseIO):
214 214 def setup(self):
215 215 N = 10**5
216 216 ncols = 5
217 -index = date_range("20000101", periods=N, freq="H")
217 +index = date_range("20000101", periods=N, freq="h")
218 218 timedeltas = timedelta_range(start=1, periods=N, freq="s")
219 219 datetimes = date_range(start=1, periods=N, freq="s")
220 220 ints = np.random.randint(100000000, size=N)
Original file line number Diff line number Diff line change
@@ -20,7 +20,7 @@ def setup(self):
20 20 self.df = DataFrame(
21 21 np.random.randn(N, C),
22 22 columns=[f"float{i}" for i in range(C)],
23 -index=date_range("20000101", periods=N, freq="H"),
23 +index=date_range("20000101", periods=N, freq="h"),
24 24 )
25 25 self.df["object"] = tm.makeStringIndex(N)
26 26 self.df.to_pickle(self.fname)
Original file line number Diff line number Diff line change
@@ -23,7 +23,7 @@ def setup(self, convert_dates):
23 23 self.df = DataFrame(
24 24 np.random.randn(N, C),
25 25 columns=[f"float{i}" for i in range(C)],
26 -index=date_range("20000101", periods=N, freq="H"),
26 +index=date_range("20000101", periods=N, freq="h"),
27 27 )
28 28 self.df["object"] = tm.makeStringIndex(self.N)
29 29 self.df["int8_"] = np.random.randint(
Original file line number Diff line number Diff line change
@@ -213,7 +213,7 @@ class JoinNonUnique:
213 213 # GH 6329
214 214 def setup(self):
215 215 date_index = date_range("01-Jan-2013", "23-Jan-2013", freq="min")
216 -daily_dates = date_index.to_period("D").to_timestamp("S", "S")
216 +daily_dates = date_index.to_period("D").to_timestamp("s", "s")
217 217 self.fracofday = date_index.values - daily_dates.values
218 218 self.fracofday = self.fracofday.astype("timedelta64[ns]")
219 219 self.fracofday = self.fracofday.astype(np.float64) / 86_400_000_000_000
Original file line number Diff line number Diff line change
@@ -45,7 +45,7 @@ def time_from_ints_daily(self, freq, is_offset):
45 45
46 46 class DataFramePeriodColumn:
47 47 def setup(self):
48 -self.rng = period_range(start="1/1/1990", freq="S", periods=20000)
48 +self.rng = period_range(start="1/1/1990", freq="s", periods=20000)
49 49 self.df = DataFrame(index=range(len(self.rng)))
50 50
51 51 def time_setitem_period_column(self):
Original file line number Diff line number Diff line change
@@ -64,7 +64,7 @@ def setup(self, dtype):
64 64 N = 10**6
65 65 data = {
66 66 "int": np.random.randint(1, 10, N),
67 -"datetime": date_range("2000-01-01", freq="S", periods=N),
67 +"datetime": date_range("2000-01-01", freq="s", periods=N),
68 68 }
69 69 self.s = Series(data[dtype])
70 70 if dtype == "datetime":
@@ -92,7 +92,7 @@ class Fillna:
92 92 def setup(self, dtype):
93 93 N = 10**6
94 94 if dtype == "datetime64[ns]":
95 -data = date_range("2000-01-01", freq="S", periods=N)
95 +data = date_range("2000-01-01", freq="s", periods=N)
96 96 na_value = NaT
97 97 elif dtype in ("float64", "Float64"):
98 98 data = np.random.randn(N)
Original file line number Diff line number Diff line change
@@ -53,7 +53,7 @@ def time_frame_datetime_formatting_custom(self, nobs):
53 53
54 54 class PeriodStrftime:
55 55 timeout = 1500
56 -params = ([1000, 10000], ["D", "H"])
56 +params = ([1000, 10000], ["D", "h"])
57 57 param_names = ["nobs", "freq"]
58 58
59 59 def setup(self, nobs, freq):
@@ -67,7 +67,7 @@ def setup(self, nobs, freq):
67 67 self.data.set_index("i", inplace=True)
68 68 if freq == "D":
69 69 self.default_fmt = "%Y-%m-%d"
70 -elif freq == "H":
70 +elif freq == "h":
71 71 self.default_fmt = "%Y-%m-%d %H:00"
72 72
73 73 def time_frame_period_to_str(self, nobs, freq):
Original file line number Diff line number Diff line change
@@ -27,7 +27,7 @@ def setup(self, index_type):
27 27 N = 100000
28 28 dtidxes = {
29 29 "dst": date_range(
30 -start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="S"
30 +start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="s"
31 31 ),
32 32 "repeated": date_range(start="2000", periods=N / 10, freq="s").repeat(10),
33 33 "tz_aware": date_range(start="2000", periods=N, freq="s", tz="US/Eastern"),
@@ -72,13 +72,13 @@ class TzLocalize:
72 72
73 73 def setup(self, tz):
74 74 dst_rng = date_range(
75 -start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="S"
75 +start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="s"
76 76 )
77 -self.index = date_range(start="10/29/2000", end="10/29/2000 00:59:59", freq="S")
77 +self.index = date_range(start="10/29/2000", end="10/29/2000 00:59:59", freq="s")
78 78 self.index = self.index.append(dst_rng)
79 79 self.index = self.index.append(dst_rng)
80 80 self.index = self.index.append(
81 -date_range(start="10/29/2000 2:00:00", end="10/29/2000 3:00:00", freq="S")
81 +date_range(start="10/29/2000 2:00:00", end="10/29/2000 3:00:00", freq="s")
82 82 )
83 83
84 84 def time_infer_dst(self, tz):
@@ -90,7 +90,7 @@ class ResetIndex:
90 90 param_names = "tz"
91 91
92 92 def setup(self, tz):
93 -idx = date_range(start="1/1/2000", periods=1000, freq="H", tz=tz)
93 +idx = date_range(start="1/1/2000", periods=1000, freq="h", tz=tz)
94 94 self.df = DataFrame(np.random.randn(1000, 2), index=idx)
95 95
96 96 def time_reset_datetimeindex(self, tz):
@@ -255,7 +255,7 @@ def time_get_slice(self, monotonic):
255 255 class Lookup:
256 256 def setup(self):
257 257 N = 1500000
258 -rng = date_range(start="1/1/2000", periods=N, freq="S")
258 +rng = date_range(start="1/1/2000", periods=N, freq="s")
259 259 self.ts = Series(1, index=rng)
260 260 self.lookup_val = rng[N // 2]
261 261