BUG: regression of read_excel with squeeze=True

closes #12184
closes #12157

Author: chris-b1

doc/source/whatsnew/v0.18.0.txt

@@ -565,7 +565,7 @@ Bug Fixes
 
 - Bug in ``.plot`` potentially modifying the ``colors`` input when the number of columns didn't match the number of series provided (:issue:`12039`).
 
-
+- Bug in ``read_excel`` failing to read data with one column when ``squeeze=True`` (:issue:`12157`)
 - Bug in ``.groupby`` where a ``KeyError`` was not raised for a wrong column if there was only one row in the dataframe (:issue:`11741`)
 - Bug in ``.read_csv`` with dtype specified on empty data producing an error (:issue:`12048`)
 - Bug in building *pandas* with debugging symbols (:issue:`12123`)

pandas/io/excel.py

@@ -76,7 +76,7 @@ def read_excel(io, sheetname=0, header=0, skiprows=None, skip_footer=0,
                index_col=None, names=None, parse_cols=None, parse_dates=False,
                date_parser=None, na_values=None, thousands=None,
                convert_float=True, has_index_names=None, converters=None,
-               engine=None, **kwds):
+               engine=None, squeeze=False, **kwds):
     """
     Read an Excel table into a pandas DataFrame
 
@@ -133,6 +133,8 @@ def read_excel(io, sheetname=0, header=0, skiprows=None, skip_footer=0,
         * If list of ints then indicates list of column numbers to be parsed
         * If string then indicates comma separated list of column names and
           column ranges (e.g. "A:E" or "A,C,E:F")
+    squeeze : boolean, default False
+        If the parsed data only contains one column then return a Series
     na_values : list-like, default None
         List of additional strings to recognize as NA/NaN
     thousands : str, default None
@@ -171,7 +173,8 @@ def read_excel(io, sheetname=0, header=0, skiprows=None, skip_footer=0,
         index_col=index_col, parse_cols=parse_cols, parse_dates=parse_dates,
         date_parser=date_parser, na_values=na_values, thousands=thousands,
         convert_float=convert_float, has_index_names=has_index_names,
-        skip_footer=skip_footer, converters=converters, **kwds)
+        skip_footer=skip_footer, converters=converters,
+        squeeze=squeeze, **kwds)
 
 
 class ExcelFile(object):
@@ -227,7 +230,7 @@ def parse(self, sheetname=0, header=0, skiprows=None, skip_footer=0,
               index_col=None, parse_cols=None, parse_dates=False,
               date_parser=None, na_values=None, thousands=None,
               convert_float=True, has_index_names=None,
-              converters=None, **kwds):
+              converters=None, squeeze=False, **kwds):
         """
         Parse specified sheet(s) into a DataFrame
 
@@ -246,6 +249,7 @@ def parse(self, sheetname=0, header=0, skiprows=None, skip_footer=0,
                                  skip_footer=skip_footer,
                                  convert_float=convert_float,
                                  converters=converters,
+                                 squeeze=squeeze,
                                  **kwds)
 
     def _should_parse(self, i, parse_cols):
@@ -285,7 +289,7 @@ def _parse_excel(self, sheetname=0, header=0, skiprows=None, skip_footer=0,
                      index_col=None, has_index_names=None, parse_cols=None,
                      parse_dates=False, date_parser=None, na_values=None,
                      thousands=None, convert_float=True,
-                     verbose=False, **kwds):
+                     verbose=False, squeeze=False, **kwds):
 
         skipfooter = kwds.pop('skipfooter', None)
         if skipfooter is not None:
@@ -452,11 +456,13 @@ def _parse_cell(cell_contents, cell_typ):
                                 date_parser=date_parser,
                                 skiprows=skiprows,
                                 skip_footer=skip_footer,
+                                squeeze=squeeze,
                                 **kwds)
 
             output[asheetname] = parser.read()
-            output[asheetname].columns = output[
-                asheetname].columns.set_names(header_names)
+            if not squeeze or isinstance(output[asheetname], DataFrame):
+                output[asheetname].columns = output[
+                    asheetname].columns.set_names(header_names)
 
         if ret_dict:
             return output

pandas/io/tests/data/test_squeeze.xls

@@ -741,6 +741,24 @@ def test_read_excel_skiprows_list(self):
                                'skiprows_list', skiprows=np.array([0, 2]))
         tm.assert_frame_equal(actual, expected)
 
+    def test_read_excel_squeeze(self):
+        # GH 12157
+        f = os.path.join(self.dirpath, 'test_squeeze' + self.ext)
+
+        actual = pd.read_excel(f, 'two_columns', index_col=0, squeeze=True)
+        expected = pd.Series([2, 3, 4], [4, 5, 6], name='b')
+        expected.index.name = 'a'
+        tm.assert_series_equal(actual, expected)
+
+        actual = pd.read_excel(f, 'two_columns', squeeze=True)
+        expected = pd.DataFrame({'a': [4, 5, 6],
+                                 'b': [2, 3, 4]})
+        tm.assert_frame_equal(actual, expected)
+
+        actual = pd.read_excel(f, 'one_column', squeeze=True)
+        expected = pd.Series([1, 2, 3], name='a')
+        tm.assert_series_equal(actual, expected)
+
 
 class XlsReaderTests(XlrdTests, tm.TestCase):
     ext = '.xls'