Now supporting %y (short year), %I (12h clock hour) and %p (AM/PM). Note that the latter is locale-specific... Fixed Period.strftime %l %m and %n : Fixed pandas-dev#46252

Author: Sylvain MARIE

pandas/_libs/tslib.pyx

@@ -128,7 +128,7 @@ def format_array_from_datetime(
     np.ndarray[object]
     """
     cdef:
-        int64_t val, ns, N = len(values)
+        int64_t val, ns, y, h, N = len(values)
         ndarray[int64_t] consider_values
         bint show_ms = False, show_us = False, show_ns = False
         bint basic_format = False
@@ -203,10 +203,20 @@ def format_array_from_datetime(
                 dt64_to_dtstruct(val, &dts)
 
                 # Use string formatting for faster strftime
-                result[i] = str_format % dict(
-                    year=dts.year, month=dts.month, day=dts.day, hour=dts.hour,
-                    min=dts.min, sec=dts.sec, us=dts.us
-                )
+                y = dts.year
+                h = dts.hour
+                result[i] = str_format % {
+                    "year": y,
+                    "shortyear": y % 100,
+                    "month": dts.month,
+                    "day": dts.day,
+                    "hour": dts.hour,
+                    "hour12": 12 if h in (0, 12) else (h % 12),
+                    "ampm": "PM" if (h // 12) else "AM",
+                    "min": dts.min,
+                    "sec": dts.sec,
+                    "us": dts.us,
+                }
             else:
                 ts = Timestamp(val, tz=tz)
 

pandas/_libs/tslibs/period.pyx

@@ -1251,19 +1251,19 @@ cdef str _period_fast_strftime(int64_t value, int freq):
         # fmt = b'%Y-%m-%d %H:%M:%S.%l'
         return (f"{dts.year}-{dts.month:02d}-{dts.day:02d} "
                 f"{dts.hour:02d}:{dts.min:02d}:{dts.sec:02d}"
-                f".{(value % 1_000):03d}")
+                f".{(dts.us // 1_000):03d}")
 
     elif freq_group == FR_US:
         # fmt = b'%Y-%m-%d %H:%M:%S.%u'
         return (f"{dts.year}-{dts.month:02d}-{dts.day:02d} "
                 f"{dts.hour:02d}:{dts.min:02d}:{dts.sec:02d}"
-                f".{(value % 1_000_000):06d}")
+                f".{(dts.us):06d}")
 
     elif freq_group == FR_NS:
         # fmt = b'%Y-%m-%d %H:%M:%S.%n'
         return (f"{dts.year}-{dts.month:02d}-{dts.day:02d} "
                 f"{dts.hour:02d}:{dts.min:02d}:{dts.sec:02d}"
-                f".{(value % 1_000_000_000):09d}")
+                f".{((dts.us * 1000) + (dts.ps // 1000)):09d}")
 
     else:
         raise ValueError(f"Unknown freq: {freq}")
@@ -1323,11 +1323,11 @@ cdef str _period_strftime(int64_t value, int freq, bytes fmt):
             elif i == 2:  # %F, 'Fiscal' year with a century
                 repl = str(dts.year)
             elif i == 3:  # %l, milliseconds
-                repl = f"{(value % 1_000):03d}"
+                repl = f"{(dts.us // 1_000):03d}"
             elif i == 4:  # %u, microseconds
-                repl = f"{(value % 1_000_000):06d}"
+                repl = f"{(dts.us):06d}"
             elif i == 5:  # %n, nanoseconds
-                repl = f"{(value % 1_000_000_000):09d}"
+                repl = f"{((dts.us * 1000) + (dts.ps // 1000)):09d}"
 
             result = result.replace(str_extra_fmts[i], repl)
 
@@ -2418,7 +2418,7 @@ cdef class _Period(PeriodMixin):
 
         cdef:
             npy_datetimestruct dts, dts2
-            int quarter
+            int quarter, y, h
 
         # Fill dts with all fields
         get_date_info(value, freq, &dts)
@@ -2427,12 +2427,25 @@ cdef class _Period(PeriodMixin):
         quarter = get_yq(value, freq, &dts2)
 
         # Finally use the string template
-        return fmt_str % dict(
-            year=dts.year, month=dts.month, day=dts.day, hour=dts.hour,
-            min=dts.min, sec=dts.sec,
-            ms=dts.us // 1000, us=dts.us, ns=dts.us * 1000,
-            q=quarter, Fyear=dts2.year, fyear=dts2.year % 100
-        )
+        y = dts.year
+        h = dts.hour
+        return fmt_str % {
+            "year": y,
+            "shortyear": y % 100,
+            "month": dts.month,
+            "day": dts.day,
+            "hour": h,
+            "hour12": 12 if h in (0, 12) else (h % 12),
+            "ampm": "PM" if (h // 12) else "AM",
+            "min": dts.min,
+            "sec": dts.sec,
+            "ms": dts.us // 1000,
+            "us": dts.us,
+            "ns": (dts.us * 1000) + (dts.ps // 1000),
+            "q": quarter,
+            "Fyear": dts2.year,
+            "fyear": dts2.year % 100,
+        }
 
     def strftime(self, fmt: str) -> str:
         r"""

pandas/_libs/tslibs/strftime.py

@@ -7,20 +7,16 @@ class UnsupportedStrFmtDirective(ValueError):
 
 
 _COMMON_UNSUPPORTED = (
-    # All of these below are names and therefore are not in the numpy or datetime attr representation
+    # 1- Names not in the numpy or datetime attr representation
     "%a",  # Weekday as locale’s abbreviated name.
     "%A",  # Weekday as locale’s full name.
     "%w",  # Weekday as a decimal number, where 0 is Sunday and 6 is Saturday.
     "%b",  # Month as locale’s abbreviated name.
     "%B",  # Month as locale’s full name.
-    # TODO All of those below can probably be derived easily from the numbers on the instance
-    "%y",  # Year without century as a zero-padded decimal number.  >> year % 100
-    "%I",  # Hour (12-hour clock) as a zero-padded decimal number. >> hour % 12
-    "%p",  # Locale’s equivalent of either AM or PM.  >> "pm" if (hour // 12) else "am"
-    # TODO Below Time offset and timezone information ... but may be hard
-    "%z",  # UTC offset in the form ±HHMM[SS[.ffffff]] (empty string if the object is naive).
-    "%Z",  # Time zone name (empty string if the object is naive).
-    # We do not want to enter into these below, we do not want to re-create the datetime implementation
+    # 2- TODO Below Time offset and timezone information ... but may be hard
+    "%z",  # UTC offset in the form ±HHMM[SS[.ffffff]] ("" if tz naive).
+    "%Z",  # Time zone name ("" if tz naive).
+    # 3- Probably too complex ones for now
     "%j",  # Day of the year as a zero-padded decimal number.
     "%U",  # Week number of the year (Sunday as the first day of the week) as a zero-padded decimal number. All days in a new year preceding the first Sunday are considered to be in week 0.
     "%W",  # Week number of the year (Monday as the first day of the week) as a zero-padded decimal number. All days in a new year preceding the first Monday are considered to be in week 0.
@@ -34,13 +30,16 @@ class UnsupportedStrFmtDirective(ValueError):
     "%d": ("day", "02d"),  # Day of the month as a zero-padded decimal number.
     "%m": ("month", "02d"),  # Month as a zero-padded decimal number.
     "%Y": ("year", "d"),  # Year with century as a decimal number.
-    "%H": ("hour", "02d"),  # Hour (24-hour clock) as a zero-padded decimal number.
+    "%y": ("shortyear", "02d"),  # Year without century as 0-padded decimal nb.
+    "%H": ("hour", "02d"),  # Hour (24-hour clock) as 0-padded decimal number.
+    "%I": ("hour12", "02d"),  # Hour (12-hour clock) as a 0-padded decimal nb.
+    "%p": ("ampm", "s"),  # Locale’s equivalent of either AM or PM.
     "%M": ("min", "02d"),  # Minute as a zero-padded decimal number.
     "%S": ("sec", "02d"),  # Second as a zero-padded decimal number.
 }
 
 _DATETIME_MAP = {
-    "%f": ("us", "06d"),  # Microsecond as a decimal number, zero-padded to 6 digits.
+    "%f": ("us", "06d"),  # Microsecond as decimal number, 0-padded to 6 digits
 }
 
 _PERIOD_MAP = {
@@ -50,9 +49,9 @@ class UnsupportedStrFmtDirective(ValueError):
     ),  # 'Fiscal' year without century as zero-padded decimal number [00,99]
     "%F": ("Fyear", "d"),  # 'Fiscal' year with century as a decimal number
     "%q": ("q", "d"),  # Quarter as a decimal number [1,4]
-    "%l": ("ms", "03d"),  # Microsecond as a decimal number, zero-padded to 3 digits.
-    "%u": ("us", "06d"),  # Microsecond as a decimal number, zero-padded to 6 digits.
-    "%n": ("ns", "09d"),  # Microsecond as a decimal number, zero-padded to 9 digits.
+    "%l": ("ms", "03d"),  # Millisecond as decimal number, 0-padded 3 digits
+    "%u": ("us", "06d"),  # Microsecond as decimal number, 0-padded 6 digits
+    "%n": ("ns", "09d"),  # Nanosecond as decimal number, 0-padded 9 digits
 }
 
 

pandas/_libs/tslibs/timestamps.pyx

@@ -1210,10 +1210,20 @@ class Timestamp(_Timestamp):
         >>> ts.fast_strftime(fmt)
         '2020-03-14T15:32:52'
         """
-        return fmt_str % dict(
-            year=self.year, month=self.month, day=self.day, hour=self.hour,
-            min=self.minute, sec=self.second, us=self.microsecond
-        )
+        y = self.year
+        h = self.hour
+        return fmt_str % {
+            "year": y,
+            "shortyear": y % 100,
+            "month": self.month,
+            "day": self.day,
+            "hour": h,
+            "hour12": 12 if h in (0, 12) else (h % 12),
+            "ampm": "PM" if (h // 12) else "AM",
+            "min": self.minute,
+            "sec": self.second,
+            "us": self.microsecond,
+        }
 
     def strftime(self, format):
         """

pandas/core/tools/datetimes.py

@@ -1315,15 +1315,20 @@ def fast_strftime(
        `datetime.strftime`.
     """
     # common dict used for formatting
-    fmt_dct = dict(
-        year=dt.year,
-        month=dt.month,
-        day=dt.day,
-        hour=dt.hour,
-        min=dt.minute,
-        sec=dt.second,
-        us=dt.microsecond,
-    )
+    y = dt.year
+    h = dt.hour
+    fmt_dct = {
+        "year": y,
+        "shortyear": y % 100,
+        "month": dt.month,
+        "day": dt.day,
+        "hour": h,
+        "hour12": 12 if h in (0, 12) else (h % 12),
+        "ampm": "PM" if (h // 12) else "AM",
+        "min": dt.minute,
+        "sec": dt.second,
+        "us": dt.microsecond,
+    }
 
     # get the formatting template
     fmt_str = convert_strftime_format(fmt, new_style_fmt=new_style_fmt)

pandas/tests/io/formats/test_format.py

@@ -3169,6 +3169,58 @@ def test_str(self):
         assert str(NaT) == "NaT"
 
 
+class TestPeriodIndexFormat:
+
+    def test_period(self):
+        p = pd.PeriodIndex([datetime(2003, 1, 1, 12), None], freq='H')
+        formatted = p.format()
+        assert formatted[0] == "2003-01-01 12:00"  # default: minutes not shown
+        assert formatted[1] == "NaT"
+
+        p = pd.period_range("2003-01-01 12:01:01.123456789", periods=2,
+                            freq="n")
+        formatted = p.format()
+        assert formatted[0] == '2003-01-01 12:01:01.123456789'
+        assert formatted[1] == '2003-01-01 12:01:01.123456790'
+
+    @pytest.mark.parametrize("fast_strftime", (False, True))
+    def test_period_custom(self, fast_strftime):
+        # GH46252
+        p = pd.period_range("2003-01-01 12:01:01.123", periods=2, freq="l")
+        formatted = p.format(date_format="%y %I:%M:%S%p (ms=%l us=%u ns=%n)",
+                             fast_strftime=fast_strftime)
+        assert formatted[0] == "03 12:01:01PM (ms=123 us=123000 ns=123000000)"
+        assert formatted[1] == "03 12:01:01PM (ms=124 us=124000 ns=124000000)"
+
+        p = pd.period_range("2003-01-01 12:01:01.123456789", periods=2, freq="n")
+        formatted = p.format(date_format="%y %I:%M:%S%p (ms=%l us=%u ns=%n)",
+                             fast_strftime=fast_strftime)
+        assert formatted[0] == "03 12:01:01PM (ms=123 us=123456 ns=123456789)"
+        assert formatted[1] == "03 12:01:01PM (ms=123 us=123456 ns=123456790)"
+
+        p = pd.period_range("2003-01-01 12:01:01.123456", periods=2, freq="u")
+        formatted = p.format(date_format="%y %I:%M:%S%p (ms=%l us=%u ns=%n)",
+                             fast_strftime=fast_strftime)
+        assert formatted[0] == "03 12:01:01PM (ms=123 us=123456 ns=123456000)"
+        assert formatted[1] == "03 12:01:01PM (ms=123 us=123457 ns=123457000)"
+
+    def test_period_tz(self):
+        """Test formatting periods created from a datetime with timezone"""
+
+        # This timestamp is in 2013 in Europe/Paris but is 2012 in UTC
+        dt = pd.to_datetime(["2013-01-01 00:00:00+01:00"], utc=True)
+
+        # Converting to a period looses the timezone information
+        # Since tz is currently set as utc, we'll see 2012
+        p = dt.to_period(freq="H")
+        assert p.format()[0] == "2012-12-31 23:00"
+
+        # If tz is currently set as paris before conversion, we'll see 2013
+        dt = dt.tz_convert("Europe/Paris")
+        p = dt.to_period(freq="H")
+        assert p.format()[0] == "2013-01-01 00:00"
+
+
 class TestDatetimeIndexFormat:
     def test_datetime(self):
         formatted = pd.to_datetime([datetime(2003, 1, 1, 12), NaT]).format()