Easy parts of pandas-dev#23368

Author: jbrockmendel

pandas/_libs/hashtable_func_helper.pxi.in

@@ -151,12 +151,12 @@ def duplicated_{{dtype}}({{scalar}}[:] values, object keep='first'):
 
     if keep == 'last':
         {{if dtype == 'object'}}
-        for i in range(n):
+        for i from n > i >= 0:
             kh_put_{{ttype}}(table, <PyObject*>values[i], &ret)
             out[i] = ret == 0
         {{else}}
         with nogil:
-            for i in range(n):
+            for i from n > i >= 0:
                 kh_put_{{ttype}}(table, values[i], &ret)
                 out[i] = ret == 0
         {{endif}}

pandas/_libs/tslibs/ccalendar.pyx

@@ -54,7 +54,7 @@ weekday_to_int = {int_to_weekday[key]: key for key in int_to_weekday}
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-cpdef inline int32_t get_days_in_month(int year, Py_ssize_t month) nogil:
+cpdef int32_t get_days_in_month(int year, Py_ssize_t month) nogil:
     """Return the number of days in the given month of the given year.
 
     Parameters

pandas/_libs/tslibs/conversion.pyx

@@ -75,7 +75,7 @@ cdef inline int64_t get_datetime64_nanos(object val) except? -1:
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-def ensure_datetime64ns(ndarray arr, copy=True):
+def ensure_datetime64ns(arr: ndarray, copy: bool=True):
     """
     Ensure a np.datetime64 array has dtype specifically 'datetime64[ns]'
 
@@ -122,7 +122,7 @@ def ensure_datetime64ns(ndarray arr, copy=True):
     return result
 
 
-def ensure_timedelta64ns(ndarray arr, copy=True):
+def ensure_timedelta64ns(arr: ndarray, copy: bool=True):
     """
     Ensure a np.timedelta64 array has dtype specifically 'timedelta64[ns]'
 
@@ -137,11 +137,12 @@ def ensure_timedelta64ns(ndarray arr, copy=True):
 
     """
     return arr.astype(TD_DTYPE, copy=copy)
+    # TODO: check for overflows when going from a lower-resolution to nanos
 
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-def datetime_to_datetime64(object[:] values):
+def datetime_to_datetime64(values: object[:]):
     """
     Convert ndarray of datetime-like objects to int64 array representing
     nanosecond timestamps.
@@ -614,6 +615,8 @@ cpdef inline datetime localize_pydatetime(datetime dt, object tz):
 # ----------------------------------------------------------------------
 # Timezone Conversion
 
+@cython.boundscheck(False)
+@cython.wraparound(False)
 cdef inline int64_t[:] _tz_convert_dst(int64_t[:] values, tzinfo tz,
                                        bint to_utc=True):
     """
@@ -1220,7 +1223,7 @@ cdef inline int64_t _normalized_stamp(npy_datetimestruct *dts) nogil:
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def is_date_array_normalized(int64_t[:] stamps, tz=None):
+def is_date_array_normalized(int64_t[:] stamps, object tz=None):
     """
     Check if all of the given (nanosecond) timestamps are normalized to
     midnight, i.e. hour == minute == second == 0.  If the optional timezone

pandas/_libs/tslibs/fields.pyx

@@ -114,7 +114,7 @@ def get_date_name_field(int64_t[:] dtindex, object field, object locale=None):
             dt64_to_dtstruct(dtindex[i], &dts)
             dow = dayofweek(dts.year, dts.month, dts.day)
             out[i] = names[dow].capitalize()
-        return out
+
     elif field == 'month_name':
         if locale is None:
             names = np.array(MONTHS_FULL, dtype=np.object_)
@@ -128,12 +128,15 @@ def get_date_name_field(int64_t[:] dtindex, object field, object locale=None):
 
             dt64_to_dtstruct(dtindex[i], &dts)
             out[i] = names[dts.month].capitalize()
-        return out
 
-    raise ValueError("Field %s not supported" % field)
+    else:
+        raise ValueError("Field {field} not supported".format(field=field))
+
+    return out
 
 
 @cython.wraparound(False)
+@cython.boundscheck(False)
 def get_start_end_field(int64_t[:] dtindex, object field,
                         object freqstr=None, int month_kw=12):
     """
@@ -163,8 +166,8 @@ def get_start_end_field(int64_t[:] dtindex, object field,
 
     if freqstr:
         if freqstr == 'C':
-            raise ValueError(
-                "Custom business days is not supported by %s" % field)
+            raise ValueError("Custom business days is not supported by {field}"
+                             .format(field=field))
         is_business = freqstr[0] == 'B'
 
         # YearBegin(), BYearBegin() use month = starting month of year.
@@ -196,7 +199,7 @@ def get_start_end_field(int64_t[:] dtindex, object field,
 
                 if (dom == 1 and dow < 5) or (dom <= 3 and dow == 0):
                     out[i] = 1
-            return out.view(bool)
+
         else:
             for i in range(count):
                 if dtindex[i] == NPY_NAT:
@@ -208,7 +211,6 @@ def get_start_end_field(int64_t[:] dtindex, object field,
 
                 if dom == 1:
                     out[i] = 1
-            return out.view(bool)
 
     elif field == 'is_month_end':
         if is_business:
@@ -228,7 +230,7 @@ def get_start_end_field(int64_t[:] dtindex, object field,
                 if (ldom == doy and dow < 5) or (
                         dow == 4 and (ldom - doy <= 2)):
                     out[i] = 1
-            return out.view(bool)
+
         else:
             for i in range(count):
                 if dtindex[i] == NPY_NAT:
@@ -244,7 +246,6 @@ def get_start_end_field(int64_t[:] dtindex, object field,
 
                 if ldom == doy:
                     out[i] = 1
-            return out.view(bool)
 
     elif field == 'is_quarter_start':
         if is_business:
@@ -260,7 +261,7 @@ def get_start_end_field(int64_t[:] dtindex, object field,
                 if ((dts.month - start_month) % 3 == 0) and (
                         (dom == 1 and dow < 5) or (dom <= 3 and dow == 0)):
                     out[i] = 1
-            return out.view(bool)
+
         else:
             for i in range(count):
                 if dtindex[i] == NPY_NAT:
@@ -272,7 +273,6 @@ def get_start_end_field(int64_t[:] dtindex, object field,
 
                 if ((dts.month - start_month) % 3 == 0) and dom == 1:
                     out[i] = 1
-            return out.view(bool)
 
     elif field == 'is_quarter_end':
         if is_business:
@@ -293,7 +293,7 @@ def get_start_end_field(int64_t[:] dtindex, object field,
                         (ldom == doy and dow < 5) or (
                             dow == 4 and (ldom - doy <= 2))):
                     out[i] = 1
-            return out.view(bool)
+
         else:
             for i in range(count):
                 if dtindex[i] == NPY_NAT:
@@ -309,7 +309,6 @@ def get_start_end_field(int64_t[:] dtindex, object field,
 
                 if ((dts.month - end_month) % 3 == 0) and (ldom == doy):
                     out[i] = 1
-            return out.view(bool)
 
     elif field == 'is_year_start':
         if is_business:
@@ -325,7 +324,7 @@ def get_start_end_field(int64_t[:] dtindex, object field,
                 if (dts.month == start_month) and (
                         (dom == 1 and dow < 5) or (dom <= 3 and dow == 0)):
                     out[i] = 1
-            return out.view(bool)
+
         else:
             for i in range(count):
                 if dtindex[i] == NPY_NAT:
@@ -337,7 +336,6 @@ def get_start_end_field(int64_t[:] dtindex, object field,
 
                 if (dts.month == start_month) and dom == 1:
                     out[i] = 1
-            return out.view(bool)
 
     elif field == 'is_year_end':
         if is_business:
@@ -358,7 +356,7 @@ def get_start_end_field(int64_t[:] dtindex, object field,
                         (ldom == doy and dow < 5) or (
                             dow == 4 and (ldom - doy <= 2))):
                     out[i] = 1
-            return out.view(bool)
+
         else:
             for i in range(count):
                 if dtindex[i] == NPY_NAT:
@@ -374,9 +372,11 @@ def get_start_end_field(int64_t[:] dtindex, object field,
 
                 if (dts.month == end_month) and (ldom == doy):
                     out[i] = 1
-            return out.view(bool)
 
-    raise ValueError("Field %s not supported" % field)
+    else:
+        raise ValueError("Field {field} not supported".format(field=field))
+
+    return out.view(bool)
 
 
 @cython.wraparound(False)

pandas/_libs/tslibs/offsets.pyx

@@ -816,7 +816,8 @@ def shift_months(int64_t[:] dtindex, int months, object day=None):
     return np.asarray(out)
 
 
-cpdef datetime shift_month(datetime stamp, int months, object day_opt=None):
+def shift_month(stamp: datetime, months: int,
+                day_opt: object=None) -> datetime:
     """
     Given a datetime (or Timestamp) `stamp`, an integer `months` and an
     option `day_opt`, return a new datetimelike that many months later,
@@ -946,8 +947,8 @@ cpdef int roll_convention(int other, int n, int compare) nogil:
     return n
 
 
-cpdef int roll_qtrday(datetime other, int n, int month, object day_opt,
-                      int modby=3) except? -1:
+def roll_qtrday(other: datetime, n: int, month: int,
+                day_opt: object, modby: int=3) -> int:
     """
     Possibly increment or decrement the number of periods to shift
     based on rollforward/rollbackward conventions.

pandas/_libs/tslibs/timedeltas.pyx

@@ -6,6 +6,7 @@ import warnings
 import sys
 cdef bint PY3 = (sys.version_info[0] >= 3)
 
+import cython
 from cython import Py_ssize_t
 
 from cpython cimport Py_NE, Py_EQ, PyObject_RichCompare
@@ -82,6 +83,8 @@ _no_input = object()
 # ----------------------------------------------------------------------
 # API
 
+@cython.boundscheck(False)
+@cython.wraparound(False)
 def ints_to_pytimedelta(int64_t[:] arr, box=False):
     """
     convert an i8 repr to an ndarray of timedelta or Timedelta (if box ==
@@ -198,6 +201,8 @@ cpdef convert_to_timedelta64(object ts, object unit):
     return ts.astype('timedelta64[ns]')
 
 
+@cython.boundscheck(False)
+@cython.wraparound(False)
 def array_to_timedelta64(object[:] values, unit='ns', errors='raise'):
     """
     Convert an ndarray to an array of timedeltas. If errors == 'coerce',