Review comments

Author: TomAugspurger

doc/source/whatsnew/v0.20.2.txt

@@ -53,6 +53,7 @@ Indexing
 I/O
 ^^^
 
+- Bug in :func:`read_csv` not raising an exception with nonexistent columns in ``usecols`` when it had the correct length (:issue:`14671`)
 - Bug that would force importing of the clipboard routines unnecessarily, potentially causing an import error on startup (:issue:`16288`)
 
 

pandas/io/parsers.py

@@ -1621,10 +1621,10 @@ def __init__(self, src, **kwds):
         if self.usecols:
             usecols = _evaluate_usecols(self.usecols, self.orig_names)
 
-            #gh-14671
-            if  (self.usecols_dtype == 'string') and \
-                (not set(usecols).issubset(self.orig_names)):
-               raise ValueError("Usecols do not match names.")
+            # GH 14671
+            if (self.usecols_dtype == 'string' and
+                    not set(usecols).issubset(self.orig_names)):
+                raise ValueError("Usecols do not match names.")
 
             if len(self.names) > len(usecols):
                 self.names = [n for i, n in enumerate(self.names)

pandas/tests/io/parser/usecols.py

@@ -9,7 +9,6 @@
 
 import numpy as np
 import pandas.util.testing as tm
-import re
 
 from pandas import DataFrame, Index
 from pandas._libs.lib import Timestamp
@@ -478,44 +477,52 @@ def test_uneven_length_cols(self):
         tm.assert_frame_equal(df, expected)
 
     def test_raise_on_usecols_names_mismatch(self):
-        ## see gh-14671
+        # GH 14671
         data = 'a,b,c,d\n1,2,3,4\n5,6,7,8'
-        msg = 'Usecols do not match names'  ## from parsers.py CParserWrapper()
-        msg2 = 'is not in list' ## from parser.py _handle_usecols()
 
-        usecols = ['a','b','c','d']
+        if self.engine == 'c':
+            msg = 'Usecols do not match names'
+        else:
+            msg = 'is not in list'
+
+        usecols = ['a', 'b', 'c', 'd']
         df = self.read_csv(StringIO(data), usecols=usecols)
-        expected = DataFrame({'a': [1,5], 'b': [2,6], 'c': [3,7], 'd': [4,8]})
+        expected = DataFrame({'a': [1, 5], 'b': [2, 6], 'c': [3, 7],
+                              'd': [4, 8]})
         tm.assert_frame_equal(df, expected)
 
-        usecols = ['a','b','c','f']
-        with tm.assert_raises_regex(ValueError, re.compile("'" + msg + '||' + msg2 + "'")):
+        usecols = ['a', 'b', 'c', 'f']
+        with tm.assert_raises_regex(ValueError, msg):
             self.read_csv(StringIO(data), usecols=usecols)
 
-        usecols = ['a','b','f']
-        with tm.assert_raises_regex(ValueError, re.compile("'" + msg + '||' + msg2 + "'")):
+        usecols = ['a', 'b', 'f']
+        with tm.assert_raises_regex(ValueError, msg):
             self.read_csv(StringIO(data), usecols=usecols)
 
         names = ['A', 'B', 'C', 'D']
 
         df = self.read_csv(StringIO(data), header=0, names=names)
-        expected = DataFrame({'A': [1,5], 'B': [2,6], 'C': [3,7], 'D': [4,8]})
+        expected = DataFrame({'A': [1, 5], 'B': [2, 6], 'C': [3, 7],
+                              'D': [4, 8]})
         tm.assert_frame_equal(df, expected)
 
+        # TODO: https://github.com/pandas-dev/pandas/issues/16469
         # usecols = ['A','C']
-        # df = self.read_csv(StringIO(data), header=0, names=names, usecols=usecols)
+        # df = self.read_csv(StringIO(data), header=0, names=names,
+        #                    usecols=usecols)
         # expected = DataFrame({'A': [1,5], 'C': [3,7]})
         # tm.assert_frame_equal(df, expected)
         #
         # usecols = [0,2]
-        # df = self.read_csv(StringIO(data), header=0, names=names, usecols=usecols)
+        # df = self.read_csv(StringIO(data), header=0, names=names,
+        #                    usecols=usecols)
         # expected = DataFrame({'A': [1,5], 'C': [3,7]})
         # tm.assert_frame_equal(df, expected)
 
-
-        usecols = ['A','B','C','f']
-        with tm.assert_raises_regex(ValueError, re.compile("'" + msg + '||' + msg2 + "'")):
-            self.read_csv(StringIO(data), header=0, names=names, usecols=usecols)
-        usecols = ['A','B','f']
-        with tm.assert_raises_regex(ValueError, re.compile("'" + msg + '||' + msg2 + "'")):
+        usecols = ['A', 'B', 'C', 'f']
+        with tm.assert_raises_regex(ValueError, msg):
+            self.read_csv(StringIO(data), header=0, names=names,
+                          usecols=usecols)
+        usecols = ['A', 'B', 'f']
+        with tm.assert_raises_regex(ValueError, msg):
             self.read_csv(StringIO(data), names=names, usecols=usecols)