DEPS: bump xlrd min version to 1.0.0 (#23774)

Author: jreback

ci/deps/azure-27-compat.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytz=2013b
   - scipy=0.18.1
   - sqlalchemy=0.7.8
-  - xlrd=0.9.2
+  - xlrd=1.0.0
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal

ci/deps/travis-27-locale.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytz=2013b
   - scipy
   - sqlalchemy=0.8.1
-  - xlrd=0.9.2
+  - xlrd=1.0.0
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal

ci/deps/travis-27.yaml

@@ -35,7 +35,7 @@ dependencies:
   - scipy
   - sqlalchemy=0.9.6
   - xarray=0.9.6
-  - xlrd=0.9.2
+  - xlrd=1.0.0
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal

doc/source/install.rst

@@ -269,7 +269,7 @@ Optional Dependencies
 * `matplotlib <http://matplotlib.org/>`__: for plotting, Version 2.0.0 or higher.
 * For Excel I/O:
 
-    * `xlrd/xlwt <http://www.python-excel.org/>`__: Excel reading (xlrd) and writing (xlwt)
+    * `xlrd/xlwt <http://www.python-excel.org/>`__: Excel reading (xlrd), version 1.0.0 or higher required, and writing (xlwt)
     * `openpyxl <https://openpyxl.readthedocs.io/en/stable/>`__: openpyxl version 2.4.0
       for writing .xlsx files (xlrd >= 0.9.0)
     * `XlsxWriter <https://pypi.org/project/XlsxWriter>`__: Alternative Excel writer

doc/source/whatsnew/v0.24.0.rst

@@ -307,7 +307,7 @@ Backwards incompatible API changes
 Dependencies have increased minimum versions
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-We have updated our minimum supported versions of dependencies (:issue:`21242`, `18742`).
+We have updated our minimum supported versions of dependencies (:issue:`21242`, :issue:`18742`, :issue:`23774`).
 If installed, we now require:
 
 +-----------------+-----------------+----------+
@@ -331,6 +331,8 @@ If installed, we now require:
 +-----------------+-----------------+----------+
 | scipy           | 0.18.1          |          |
 +-----------------+-----------------+----------+
+| xlrd            | 1.0.0           |          |
++-----------------+-----------------+----------+
 
 Additionally we no longer depend on `feather-format` for feather based storage
 and replaced it with references to `pyarrow` (:issue:`21639` and :issue:`23053`).

pandas/_libs/algos_rank_helper.pxi.in

@@ -126,7 +126,7 @@ def rank_1d_{{dtype}}(object in_arr, ties_method='average',
 
     sorted_data = values.take(_as)
     sorted_mask = mask.take(_as)
-    _indices = np.diff(sorted_mask).nonzero()[0]
+    _indices = np.diff(sorted_mask.astype(int)).nonzero()[0]
     non_na_idx = _indices[0] if len(_indices) > 0 else -1
     argsorted = _as.astype('i8')
 

pandas/_libs/index.pyx

@@ -113,6 +113,8 @@ cdef class IndexEngine:
             if not self.is_unique:
                 return self._get_loc_duplicates(val)
             values = self._get_index_values()
+
+            self._check_type(val)
             loc = _bin_search(values, val)  # .searchsorted(val, side='left')
             if loc >= len(values):
                 raise KeyError(val)

pandas/_libs/index_class_helper.pxi.in

@@ -51,6 +51,8 @@ cdef class {{name}}Engine(IndexEngine):
             raise KeyError(val)
         elif util.is_float_object(val):
             raise KeyError(val)
+        elif not util.is_integer_object(val):
+            raise KeyError(val)
     {{endif}}
 
     {{if name != 'Object'}}

pandas/core/indexes/period.py

@@ -33,6 +33,7 @@
 from pandas.core.arrays.period import PeriodArray, period_array
 from pandas.core.base import _shared_docs
 from pandas.core.indexes.base import _index_shared_docs, ensure_index
+from pandas.core.missing import isna
 
 from pandas import compat
 from pandas.util._decorators import (
@@ -652,7 +653,8 @@ def get_value(self, series, key):
             except TypeError:
                 pass
 
-            key = Period(key, self.freq).ordinal
+            period = Period(key, self.freq)
+            key = period.value if isna(period) else period.ordinal
             return com.maybe_box(self, self._engine.get_value(s, key),
                                  series, key)
 

pandas/io/excel.py

@@ -5,7 +5,7 @@
 # ---------------------------------------------------------------------
 # ExcelFile class
 import abc
-from datetime import MINYEAR, date, datetime, time, timedelta
+from datetime import date, datetime, time, timedelta
 from distutils.version import LooseVersion
 from io import UnsupportedOperation
 import os
@@ -375,15 +375,14 @@ class ExcelFile(object):
 
     def __init__(self, io, **kwds):
 
-        err_msg = "Install xlrd >= 0.9.0 for Excel support"
+        err_msg = "Install xlrd >= 1.0.0 for Excel support"
 
         try:
             import xlrd
         except ImportError:
             raise ImportError(err_msg)
         else:
-            ver = tuple(map(int, xlrd.__VERSION__.split(".")[:2]))
-            if ver < (0, 9):  # pragma: no cover
+            if xlrd.__VERSION__ < LooseVersion("1.0.0"):
                 raise ImportError(err_msg +
                                   ". Current version " + xlrd.__VERSION__)
 
@@ -515,7 +514,6 @@ def _parse_excel(self,
             raise NotImplementedError("chunksize keyword of read_excel "
                                       "is not implemented")
 
-        import xlrd
         from xlrd import (xldate, XL_CELL_DATE,
                           XL_CELL_ERROR, XL_CELL_BOOLEAN,
                           XL_CELL_NUMBER)
@@ -528,36 +526,23 @@ def _parse_cell(cell_contents, cell_typ):
 
             if cell_typ == XL_CELL_DATE:
 
-                if xlrd_0_9_3:
-                    # Use the newer xlrd datetime handling.
-                    try:
-                        cell_contents = \
-                            xldate.xldate_as_datetime(cell_contents,
-                                                      epoch1904)
-                    except OverflowError:
-                        return cell_contents
-                    # Excel doesn't distinguish between dates and time,
-                    # so we treat dates on the epoch as times only.
-                    # Also, Excel supports 1900 and 1904 epochs.
-                    year = (cell_contents.timetuple())[0:3]
-                    if ((not epoch1904 and year == (1899, 12, 31)) or
-                            (epoch1904 and year == (1904, 1, 1))):
-                        cell_contents = time(cell_contents.hour,
-                                             cell_contents.minute,
-                                             cell_contents.second,
-                                             cell_contents.microsecond)
-                else:
-                    # Use the xlrd <= 0.9.2 date handling.
-                    try:
-                        dt = xldate.xldate_as_tuple(cell_contents, epoch1904)
-
-                    except xldate.XLDateTooLarge:
-                        return cell_contents
-
-                    if dt[0] < MINYEAR:
-                        cell_contents = time(*dt[3:])
-                    else:
-                        cell_contents = datetime(*dt)
+                # Use the newer xlrd datetime handling.
+                try:
+                    cell_contents = xldate.xldate_as_datetime(
+                        cell_contents, epoch1904)
+                except OverflowError:
+                    return cell_contents
+
+                # Excel doesn't distinguish between dates and time,
+                # so we treat dates on the epoch as times only.
+                # Also, Excel supports 1900 and 1904 epochs.
+                year = (cell_contents.timetuple())[0:3]
+                if ((not epoch1904 and year == (1899, 12, 31)) or
+                        (epoch1904 and year == (1904, 1, 1))):
+                    cell_contents = time(cell_contents.hour,
+                                         cell_contents.minute,
+                                         cell_contents.second,
+                                         cell_contents.microsecond)
 
             elif cell_typ == XL_CELL_ERROR:
                 cell_contents = np.nan
@@ -571,12 +556,6 @@ def _parse_cell(cell_contents, cell_typ):
                     cell_contents = val
             return cell_contents
 
-        # xlrd >= 0.9.3 can return datetime objects directly.
-        if LooseVersion(xlrd.__VERSION__) >= LooseVersion("0.9.3"):
-            xlrd_0_9_3 = True
-        else:
-            xlrd_0_9_3 = False
-
         ret_dict = False
 
         # Keep sheetname to maintain backwards compatibility.

pandas/tests/io/test_excel.py

@@ -36,7 +36,7 @@
 _mixed_frame['foo'] = 'bar'
 
 
-@td.skip_if_no('xlrd', '0.9')
+@td.skip_if_no('xlrd', '1.0.0')
 class SharedItems(object):
 
     @pytest.fixture(autouse=True)
@@ -796,35 +796,19 @@ def tdf(col_sheet_name):
                 tm.assert_frame_equal(dfs[s], dfs_returned[s])
 
     def test_reader_seconds(self, ext):
-        import xlrd
 
         # Test reading times with and without milliseconds. GH5945.
-        if LooseVersion(xlrd.__VERSION__) >= LooseVersion("0.9.3"):
-            # Xlrd >= 0.9.3 can handle Excel milliseconds.
-            expected = DataFrame.from_dict({"Time": [time(1, 2, 3),
-                                            time(2, 45, 56, 100000),
-                                            time(4, 29, 49, 200000),
-                                            time(6, 13, 42, 300000),
-                                            time(7, 57, 35, 400000),
-                                            time(9, 41, 28, 500000),
-                                            time(11, 25, 21, 600000),
-                                            time(13, 9, 14, 700000),
-                                            time(14, 53, 7, 800000),
-                                            time(16, 37, 0, 900000),
-                                            time(18, 20, 54)]})
-        else:
-            # Xlrd < 0.9.3 rounds Excel milliseconds.
-            expected = DataFrame.from_dict({"Time": [time(1, 2, 3),
-                                            time(2, 45, 56),
-                                            time(4, 29, 49),
-                                            time(6, 13, 42),
-                                            time(7, 57, 35),
-                                            time(9, 41, 29),
-                                            time(11, 25, 22),
-                                            time(13, 9, 15),
-                                            time(14, 53, 8),
-                                            time(16, 37, 1),
-                                            time(18, 20, 54)]})
+        expected = DataFrame.from_dict({"Time": [time(1, 2, 3),
+                                                 time(2, 45, 56, 100000),
+                                                 time(4, 29, 49, 200000),
+                                                 time(6, 13, 42, 300000),
+                                                 time(7, 57, 35, 400000),
+                                                 time(9, 41, 28, 500000),
+                                                 time(11, 25, 21, 600000),
+                                                 time(13, 9, 14, 700000),
+                                                 time(14, 53, 7, 800000),
+                                                 time(16, 37, 0, 900000),
+                                                 time(18, 20, 54)]})
 
         actual = self.get_exceldf('times_1900', ext, 'Sheet1')
         tm.assert_frame_equal(actual, expected)