ENH: better error message if usecols doesn't match

GH17301: Improving the error message given when usecols
doesn't match with the columns provided.

Signed-off-by: Aaron Critchley <[email protected]>

Author: AaronCritchley

pandas/io/parsers.py

@@ -1662,14 +1662,22 @@ def __init__(self, src, **kwds):
             # GH 14671
             if (self.usecols_dtype == 'string' and
                     not set(usecols).issubset(self.orig_names)):
-                raise ValueError("Usecols do not match names.")
+                missing = [c for c in usecols if c not in self.orig_names]
+                raise ValueError(
+                    "Usecols do not match columns, "
+                    "columns expected but not found: %s" % missing
+                )
 
             if len(self.names) > len(usecols):
                 self.names = [n for i, n in enumerate(self.names)
                               if (i in usecols or n in usecols)]
 
             if len(self.names) < len(usecols):
-                raise ValueError("Usecols do not match names.")
+                missing = [c for c in usecols if c not in self.orig_names]
+                raise ValueError(
+                    "Usecols do not match columns, "
+                    "columns expected but not found: %s" % missing
+                )
 
         self._set_noconvert_columns()
 

pandas/tests/io/parser/usecols.py

@@ -481,7 +481,7 @@ def test_raise_on_usecols_names_mismatch(self):
         data = 'a,b,c,d\n1,2,3,4\n5,6,7,8'
 
         if self.engine == 'c':
-            msg = 'Usecols do not match names'
+            msg = "do not match columns, columns expected but not found"
         else:
             msg = 'is not in list'