Misc cleanups, test parametrization (#21690)

Author: jbrockmendel

pandas/_libs/src/inference.pyx

@@ -1225,7 +1225,7 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
         ndarray[int64_t] idatetimes
         ndarray[int64_t] itimedeltas
         Seen seen = Seen()
-        object val, onan
+        object val
         float64_t fval, fnan
 
     n = len(objects)
@@ -1244,7 +1244,6 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=0,
         timedeltas = np.empty(n, dtype='m8[ns]')
         itimedeltas = timedeltas.view(np.int64)
 
-    onan = np.nan
     fnan = np.nan
 
     for i from 0 <= i < n:

pandas/_libs/tslibs/conversion.pyx

@@ -1002,7 +1002,7 @@ cdef inline bisect_right_i8(int64_t *data, int64_t val, Py_ssize_t n):
 
 cdef inline str _render_tstamp(int64_t val):
     """ Helper function to render exception messages"""
-    from pandas._libs.tslib import Timestamp
+    from timestamps import Timestamp
     return str(Timestamp(val))
 
 

pandas/_libs/tslibs/period.pyx

@@ -15,8 +15,6 @@ from libc.stdlib cimport free, malloc
 from libc.time cimport strftime, tm
 from libc.string cimport strlen, memset
 
-from pandas.compat import PY2
-
 cimport cython
 
 from cpython.datetime cimport (PyDateTime_Check, PyDelta_Check,
@@ -59,6 +57,8 @@ from offsets cimport to_offset
 
 from pandas.tseries import offsets
 
+cdef bint PY2 = str == bytes
+
 
 cdef extern from "period_helper.h":
     int FR_ANN

pandas/_libs/tslibs/resolution.pyx

@@ -26,9 +26,9 @@ from conversion import tz_convert
 from conversion cimport tz_convert_utc_to_tzlocal
 from ccalendar import MONTH_ALIASES, int_to_weekday
 from ccalendar cimport get_days_in_month
+from timestamps import Timestamp
 
 from pandas._libs.properties import cache_readonly
-from pandas._libs.tslib import Timestamp
 
 from pandas.core.algorithms import unique  # TODO: Avoid this non-cython import
 

pandas/tests/indexes/datetimes/test_tools.py

@@ -7,7 +7,7 @@
 import dateutil
 import numpy as np
 from dateutil.parser import parse
-from datetime import datetime, date, time
+from datetime import datetime, time
 from distutils.version import LooseVersion
 
 import pandas as pd
@@ -1251,92 +1251,90 @@ def test_day_not_in_month_ignore(self, cache):
 
 class TestDatetimeParsingWrappers(object):
 
+    @pytest.mark.parametrize('date_str,expected', list({
+        '2011-01-01': datetime(2011, 1, 1),
+        '2Q2005': datetime(2005, 4, 1),
+        '2Q05': datetime(2005, 4, 1),
+        '2005Q1': datetime(2005, 1, 1),
+        '05Q1': datetime(2005, 1, 1),
+        '2011Q3': datetime(2011, 7, 1),
+        '11Q3': datetime(2011, 7, 1),
+        '3Q2011': datetime(2011, 7, 1),
+        '3Q11': datetime(2011, 7, 1),
+
+        # quarterly without space
+        '2000Q4': datetime(2000, 10, 1),
+        '00Q4': datetime(2000, 10, 1),
+        '4Q2000': datetime(2000, 10, 1),
+        '4Q00': datetime(2000, 10, 1),
+        '2000q4': datetime(2000, 10, 1),
+        '2000-Q4': datetime(2000, 10, 1),
+        '00-Q4': datetime(2000, 10, 1),
+        '4Q-2000': datetime(2000, 10, 1),
+        '4Q-00': datetime(2000, 10, 1),
+        '00q4': datetime(2000, 10, 1),
+        '2005': datetime(2005, 1, 1),
+        '2005-11': datetime(2005, 11, 1),
+        '2005 11': datetime(2005, 11, 1),
+        '11-2005': datetime(2005, 11, 1),
+        '11 2005': datetime(2005, 11, 1),
+        '200511': datetime(2020, 5, 11),
+        '20051109': datetime(2005, 11, 9),
+        '20051109 10:15': datetime(2005, 11, 9, 10, 15),
+        '20051109 08H': datetime(2005, 11, 9, 8, 0),
+        '2005-11-09 10:15': datetime(2005, 11, 9, 10, 15),
+        '2005-11-09 08H': datetime(2005, 11, 9, 8, 0),
+        '2005/11/09 10:15': datetime(2005, 11, 9, 10, 15),
+        '2005/11/09 08H': datetime(2005, 11, 9, 8, 0),
+        "Thu Sep 25 10:36:28 2003": datetime(2003, 9, 25, 10, 36, 28),
+        "Thu Sep 25 2003": datetime(2003, 9, 25),
+        "Sep 25 2003": datetime(2003, 9, 25),
+        "January 1 2014": datetime(2014, 1, 1),
+
+        # GHE10537
+        '2014-06': datetime(2014, 6, 1),
+        '06-2014': datetime(2014, 6, 1),
+        '2014-6': datetime(2014, 6, 1),
+        '6-2014': datetime(2014, 6, 1),
+
+        '20010101 12': datetime(2001, 1, 1, 12),
+        '20010101 1234': datetime(2001, 1, 1, 12, 34),
+        '20010101 123456': datetime(2001, 1, 1, 12, 34, 56)}.items()))
     @pytest.mark.parametrize('cache', [True, False])
-    def test_parsers(self, cache):
+    def test_parsers(self, date_str, expected, cache):
 
         # dateutil >= 2.5.0 defaults to yearfirst=True
         # https://github.com/dateutil/dateutil/issues/217
         yearfirst = True
 
-        cases = {'2011-01-01': datetime(2011, 1, 1),
-                 '2Q2005': datetime(2005, 4, 1),
-                 '2Q05': datetime(2005, 4, 1),
-                 '2005Q1': datetime(2005, 1, 1),
-                 '05Q1': datetime(2005, 1, 1),
-                 '2011Q3': datetime(2011, 7, 1),
-                 '11Q3': datetime(2011, 7, 1),
-                 '3Q2011': datetime(2011, 7, 1),
-                 '3Q11': datetime(2011, 7, 1),
-
-                 # quarterly without space
-                 '2000Q4': datetime(2000, 10, 1),
-                 '00Q4': datetime(2000, 10, 1),
-                 '4Q2000': datetime(2000, 10, 1),
-                 '4Q00': datetime(2000, 10, 1),
-                 '2000q4': datetime(2000, 10, 1),
-                 '2000-Q4': datetime(2000, 10, 1),
-                 '00-Q4': datetime(2000, 10, 1),
-                 '4Q-2000': datetime(2000, 10, 1),
-                 '4Q-00': datetime(2000, 10, 1),
-                 '00q4': datetime(2000, 10, 1),
-                 '2005': datetime(2005, 1, 1),
-                 '2005-11': datetime(2005, 11, 1),
-                 '2005 11': datetime(2005, 11, 1),
-                 '11-2005': datetime(2005, 11, 1),
-                 '11 2005': datetime(2005, 11, 1),
-                 '200511': datetime(2020, 5, 11),
-                 '20051109': datetime(2005, 11, 9),
-                 '20051109 10:15': datetime(2005, 11, 9, 10, 15),
-                 '20051109 08H': datetime(2005, 11, 9, 8, 0),
-                 '2005-11-09 10:15': datetime(2005, 11, 9, 10, 15),
-                 '2005-11-09 08H': datetime(2005, 11, 9, 8, 0),
-                 '2005/11/09 10:15': datetime(2005, 11, 9, 10, 15),
-                 '2005/11/09 08H': datetime(2005, 11, 9, 8, 0),
-                 "Thu Sep 25 10:36:28 2003": datetime(2003, 9, 25, 10,
-                                                      36, 28),
-                 "Thu Sep 25 2003": datetime(2003, 9, 25),
-                 "Sep 25 2003": datetime(2003, 9, 25),
-                 "January 1 2014": datetime(2014, 1, 1),
-
-                 # GH 10537
-                 '2014-06': datetime(2014, 6, 1),
-                 '06-2014': datetime(2014, 6, 1),
-                 '2014-6': datetime(2014, 6, 1),
-                 '6-2014': datetime(2014, 6, 1),
-
-                 '20010101 12': datetime(2001, 1, 1, 12),
-                 '20010101 1234': datetime(2001, 1, 1, 12, 34),
-                 '20010101 123456': datetime(2001, 1, 1, 12, 34, 56),
-                 }
-
-        for date_str, expected in compat.iteritems(cases):
-            result1, _, _ = parsing.parse_time_string(date_str,
-                                                      yearfirst=yearfirst)
-            result2 = to_datetime(date_str, yearfirst=yearfirst)
-            result3 = to_datetime([date_str], yearfirst=yearfirst)
-            # result5 is used below
-            result4 = to_datetime(np.array([date_str], dtype=object),
-                                  yearfirst=yearfirst, cache=cache)
-            result6 = DatetimeIndex([date_str], yearfirst=yearfirst)
-            # result7 is used below
-            result8 = DatetimeIndex(Index([date_str]), yearfirst=yearfirst)
-            result9 = DatetimeIndex(Series([date_str]), yearfirst=yearfirst)
-
-            for res in [result1, result2]:
-                assert res == expected
-            for res in [result3, result4, result6, result8, result9]:
-                exp = DatetimeIndex([pd.Timestamp(expected)])
-                tm.assert_index_equal(res, exp)
-
-            # these really need to have yearfirst, but we don't support
-            if not yearfirst:
-                result5 = Timestamp(date_str)
-                assert result5 == expected
-                result7 = date_range(date_str, freq='S', periods=1,
-                                     yearfirst=yearfirst)
-                assert result7 == expected
-
-        # NaT
+        result1, _, _ = parsing.parse_time_string(date_str,
+                                                  yearfirst=yearfirst)
+        result2 = to_datetime(date_str, yearfirst=yearfirst)
+        result3 = to_datetime([date_str], yearfirst=yearfirst)
+        # result5 is used below
+        result4 = to_datetime(np.array([date_str], dtype=object),
+                              yearfirst=yearfirst, cache=cache)
+        result6 = DatetimeIndex([date_str], yearfirst=yearfirst)
+        # result7 is used below
+        result8 = DatetimeIndex(Index([date_str]), yearfirst=yearfirst)
+        result9 = DatetimeIndex(Series([date_str]), yearfirst=yearfirst)
+
+        for res in [result1, result2]:
+            assert res == expected
+        for res in [result3, result4, result6, result8, result9]:
+            exp = DatetimeIndex([pd.Timestamp(expected)])
+            tm.assert_index_equal(res, exp)
+
+        # these really need to have yearfirst, but we don't support
+        if not yearfirst:
+            result5 = Timestamp(date_str)
+            assert result5 == expected
+            result7 = date_range(date_str, freq='S', periods=1,
+                                 yearfirst=yearfirst)
+            assert result7 == expected
+
+    def test_parsers_nat(self):
+        # Test that each of several string-accepting methods return pd.NaT
         result1, _, _ = parsing.parse_time_string('NaT')
         result2 = to_datetime('NaT')
         result3 = Timestamp('NaT')
@@ -1516,18 +1514,6 @@ def test_parsers_timezone_minute_offsets_roundtrip(self, cache):
             assert dt_string_repr == repr(converted_time)
 
 
-def test_normalize_date():
-    value = date(2012, 9, 7)
-
-    result = tslib.normalize_date(value)
-    assert (result == datetime(2012, 9, 7))
-
-    value = datetime(2012, 9, 7, 12)
-
-    result = tslib.normalize_date(value)
-    assert (result == datetime(2012, 9, 7))
-
-
 @pytest.fixture(params=['D', 's', 'ms', 'us', 'ns'])
 def units(request):
     return request.param

pandas/tests/tslibs/test_tslib.py

@@ -0,0 +1,18 @@
+# -*- coding: utf-8 -*-
+"""Tests for functions from pandas._libs.tslibs"""
+
+from datetime import datetime, date
+
+from pandas._libs import tslib
+
+
+def test_normalize_date():
+    value = date(2012, 9, 7)
+
+    result = tslib.normalize_date(value)
+    assert (result == datetime(2012, 9, 7))
+
+    value = datetime(2012, 9, 7, 12)
+
+    result = tslib.normalize_date(value)
+    assert (result == datetime(2012, 9, 7))