TST: fixed cython doctests (pandas-dev#43768)

ci/code_checks.sh

@@ -84,6 +84,10 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
       pandas/tseries/
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Cython Doctests' ; echo $MSG
+    python -m pytest --doctest-cython pandas/_libs
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
 fi
 
 ### DOCSTRINGS ###

environment.yml

@@ -122,3 +122,4 @@ dependencies:
     - types-PyMySQL
     - types-pytz
     - types-setuptools
+    - pytest-cython

pandas/_libs/hashtable.pyx

@@ -98,7 +98,8 @@ cdef class ObjectFactorizer(Factorizer):
         --------
         Factorize values with nans replaced by na_sentinel
 
-        >>> factorize(np.array([1,2,np.nan], dtype='O'), na_sentinel=20)
+        >>> fac = ObjectFactorizer(3)
+        >>> fac.factorize(np.array([1,2,np.nan], dtype='O'), na_sentinel=20)
         array([ 0,  1, 20])
         """
         cdef:
@@ -142,8 +143,9 @@ cdef class Int64Factorizer(Factorizer):
         --------
         Factorize values with nans replaced by na_sentinel
 
-        >>> factorize(np.array([1,2,np.nan], dtype='O'), na_sentinel=20)
-        array([ 0,  1, 20])
+        >>> fac = Int64Factorizer(3)
+        >>> fac.factorize(np.array([1,2,3]), na_sentinel=20)
+        array([0, 1, 2])
         """
         cdef:
             ndarray[intp_t] labels

pandas/_libs/lib.pyx

@@ -175,6 +175,7 @@ def is_scalar(val: object) -> bool:
 
     Examples
     --------
+    >>> import datetime
     >>> dt = datetime.datetime(2018, 10, 3)
     >>> pd.api.types.is_scalar(dt)
     True
@@ -256,11 +257,12 @@ def is_iterator(obj: object) -> bool:
 
     Examples
     --------
+    >>> import datetime
     >>> is_iterator((x for x in []))
     True
     >>> is_iterator([1, 2, 3])
     False
-    >>> is_iterator(datetime(2017, 1, 1))
+    >>> is_iterator(datetime.datetime(2017, 1, 1))
     False
     >>> is_iterator("foo")
     False
@@ -1076,11 +1078,12 @@ def is_list_like(obj: object, allow_sets: bool = True) -> bool:
 
     Examples
     --------
+    >>> import datetime
     >>> is_list_like([1, 2, 3])
     True
     >>> is_list_like({1, 2, 3})
     True
-    >>> is_list_like(datetime(2017, 1, 1))
+    >>> is_list_like(datetime.datetime(2017, 1, 1))
     False
     >>> is_list_like("foo")
     False
@@ -1355,6 +1358,7 @@ def infer_dtype(value: object, skipna: bool = True) -> str:
 
     Examples
     --------
+    >>> import datetime
     >>> infer_dtype(['foo', 'bar'])
     'string'
 

pandas/_libs/tslibs/dtypes.pyx

@@ -227,7 +227,7 @@ class Resolution(Enum):
         Examples
         --------
         >>> Resolution.from_attrname('second')
-        2
+        <Resolution.RESO_SEC: 3>
 
         >>> Resolution.from_attrname('second') == Resolution.RESO_SEC
         True
@@ -244,7 +244,7 @@ class Resolution(Enum):
         Examples
         --------
         >>> Resolution.get_reso_from_freq('H')
-        4
+        <Resolution.RESO_HR: 5>
 
         >>> Resolution.get_reso_from_freq('H') == Resolution.RESO_HR
         True

pandas/_libs/tslibs/nattype.pyx

@@ -581,7 +581,7 @@ class NaTType(_NaT):
 
         Examples
         --------
-        >>> pd.Timestamp.utcnow()
+        >>> pd.Timestamp.utcnow()   # doctest: +SKIP
         Timestamp('2020-11-16 22:50:18.092888+0000', tz='UTC')
         """,
     )
@@ -705,7 +705,7 @@ class NaTType(_NaT):
 
         Examples
         --------
-        >>> pd.Timestamp.now()
+        >>> pd.Timestamp.now()  # doctest: +SKIP
         Timestamp('2020-11-16 22:06:16.378782')
 
         Analogous for ``pd.NaT``:
@@ -730,7 +730,7 @@ class NaTType(_NaT):
 
         Examples
         --------
-        >>> pd.Timestamp.today()
+        >>> pd.Timestamp.today()    # doctest: +SKIP
         Timestamp('2020-11-16 22:37:39.969883')
 
         Analogous for ``pd.NaT``:

pandas/_libs/tslibs/period.pyx

@@ -2375,7 +2375,7 @@ cdef class _Period(PeriodMixin):
         >>>
         >>> a = Period(freq='D', year=2001, month=1, day=1)
         >>> a.strftime('%d-%b-%Y')
-        '01-Jan-2006'
+        '01-Jan-2001'
         >>> a.strftime('%b. %d, %Y was a %A')
         'Jan. 01, 2001 was a Monday'
         """

pandas/_libs/tslibs/timestamps.pyx

@@ -909,16 +909,20 @@ cdef class _Timestamp(ABCTimestamp):
         Examples
         --------
         >>> ts = pd.Timestamp('2020-03-14T15:32:52.192548651')
-        >>> ts.to_period(freq='Y) # Year end frequency
-        numpy.datetime64('2020-03-14T15:32:52.192548651')
+        >>> # Year end frequency
+        >>> ts.to_period(freq='Y')
+        Period('2020', 'A-DEC')
 
-        >>> ts.to_period(freq='M') # Month end frequency
+        >>> # Month end frequency
+        >>> ts.to_period(freq='M')
         Period('2020-03', 'M')
 
-        >>> ts.to_period(freq='W') # Weekly frequency
+        >>> # Weekly frequency
+        >>> ts.to_period(freq='W')
         Period('2020-03-09/2020-03-15', 'W-SUN')
 
-        >>> ts.to_period(freq='Q') # Quarter end frequency
+        >>> # Quarter end frequency
+        >>> ts.to_period(freq='Q')
         Period('2020Q1', 'Q-DEC')
         """
         from pandas import Period
@@ -1059,7 +1063,7 @@ class Timestamp(_Timestamp):
 
         Examples
         --------
-        >>> pd.Timestamp.now()
+        >>> pd.Timestamp.now()  # doctest: +SKIP
         Timestamp('2020-11-16 22:06:16.378782')
 
         Analogous for ``pd.NaT``:
@@ -1087,7 +1091,7 @@ class Timestamp(_Timestamp):
 
         Examples
         --------
-        >>> pd.Timestamp.today()
+        >>> pd.Timestamp.today()    # doctest: +SKIP
         Timestamp('2020-11-16 22:37:39.969883')
 
         Analogous for ``pd.NaT``:
@@ -1106,7 +1110,7 @@ class Timestamp(_Timestamp):
 
         Examples
         --------
-        >>> pd.Timestamp.utcnow()
+        >>> pd.Timestamp.utcnow()   # doctest: +SKIP
         Timestamp('2020-11-16 22:50:18.092888+0000', tz='UTC')
         """
         return cls.now(UTC)

pandas/_libs/tslibs/timezones.pyx

@@ -385,25 +385,23 @@ def tz_standardize(tz: tzinfo) -> tzinfo:
     -------
     tzinfo
 
-    Examples:
+    Examples
     --------
+    >>> from datetime import datetime
+    >>> from pytz import timezone
+    >>> tz = timezone('US/Pacific').normalize(
+    ...     datetime(2014, 1, 1, tzinfo=pytz.utc)
+    ... ).tzinfo
     >>> tz
     <DstTzInfo 'US/Pacific' PST-1 day, 16:00:00 STD>
-
     >>> tz_standardize(tz)
     <DstTzInfo 'US/Pacific' LMT-1 day, 16:07:00 STD>
 
+    >>> tz = timezone('US/Pacific')
     >>> tz
     <DstTzInfo 'US/Pacific' LMT-1 day, 16:07:00 STD>
-
     >>> tz_standardize(tz)
     <DstTzInfo 'US/Pacific' LMT-1 day, 16:07:00 STD>
-
-    >>> tz
-    dateutil.tz.tz.tzutc
-
-    >>> tz_standardize(tz)
-    dateutil.tz.tz.tzutc
     """
     if treat_tz_as_pytz(tz):
         return pytz.timezone(str(tz))

requirements-dev.txt

@@ -85,4 +85,5 @@ types-python-dateutil
 types-PyMySQL
 types-pytz
 types-setuptools
+pytest-cython
 setuptools>=51.0.0