WIP: Implementing suggested changes

Author: AaronCritchley

pandas/io/parsers.py

@@ -1065,6 +1065,20 @@ def _evaluate_usecols(usecols, names):
     return usecols
 
 
+def _validate_usecols(usecols, names):
+    """
+    Validates that all usecols are present in a given
+    list of names, if not, raise a ValueError that
+    shows what usecols are missing.
+    """
+    missing = [c for c in usecols if c not in names]
+    if len(missing) > 0:
+        raise ValueError(
+            "Usecols do not match columns, "
+            "columns expected but not found: {missing}".format(missing=missing)
+        )
+
+
 def _validate_skipfooter_arg(skipfooter):
     """
     Validate the 'skipfooter' parameter.
@@ -1662,22 +1676,14 @@ def __init__(self, src, **kwds):
             # GH 14671
             if (self.usecols_dtype == 'string' and
                     not set(usecols).issubset(self.orig_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: {}".format(missing)
-                )
+                _validate_usecols(usecols, self.orig_names)
 
             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):
-                missing = [c for c in usecols if c not in self.names]
-                raise ValueError(
-                    "Usecols do not match columns, "
-                    "columns expected but not found: {}".format(missing)
-                )
+                _validate_usecols(usecols, self.names)
 
         self._set_noconvert_columns()
 
@@ -2451,16 +2457,12 @@ def _handle_usecols(self, columns, usecols_key):
                                      "be integers.")
                 col_indices = []
 
-                missing = [c for c in self.usecols if c not in usecols_key]
-                if len(missing) > 0:
-                    raise ValueError(
-                        "Usecols do not match columns, "
-                        "columns expected but not found: {}".format(missing)
-                    )
-
                 for col in self.usecols:
                     if isinstance(col, string_types):
-                        col_indices.append(usecols_key.index(col))
+                        try:
+                            col_indices.append(usecols_key.index(col))
+                        except ValueError:
+                            _validate_usecols(self.usecols, usecols_key)
                     else:
                         col_indices.append(col)
             else:

pandas/tests/io/parser/usecols.py

@@ -482,7 +482,7 @@ def test_raise_on_usecols_names_mismatch(self):
 
         msg = (
             "Usecols do not match columns, "
-            "columns expected but not found: {}"
+            "columns expected but not found: {missing}"
         )
 
         usecols = ['a', 'b', 'c', 'd']
@@ -492,11 +492,11 @@ def test_raise_on_usecols_names_mismatch(self):
         tm.assert_frame_equal(df, expected)
 
         usecols = ['a', 'b', 'c', 'f']
-        with tm.assert_raises_regex(ValueError, msg.format(['f'])):
+        with tm.assert_raises_regex(ValueError, msg.format(missing=['f'])):
             self.read_csv(StringIO(data), usecols=usecols)
 
         usecols = ['a', 'b', 'f']
-        with tm.assert_raises_regex(ValueError, msg.format(['f'])):
+        with tm.assert_raises_regex(ValueError, msg.format(missing=['f'])):
             self.read_csv(StringIO(data), usecols=usecols)
 
         names = ['A', 'B', 'C', 'D']
@@ -520,9 +520,9 @@ def test_raise_on_usecols_names_mismatch(self):
         # tm.assert_frame_equal(df, expected)
 
         usecols = ['A', 'B', 'C', 'f']
-        with tm.assert_ra(ValueError, msg.format(['f'])):
+        with tm.assert_ra(ValueError, msg.format(missing=['f'])):
             self.read_csv(StringIO(data), header=0, names=names,
                           usecols=usecols)
         usecols = ['A', 'B', 'f']
-        with tm.assert_raises_regex(ValueError, msg.format(['f'])):
+        with tm.assert_raises_regex(ValueError, msg.format(missing=['f'])):
             self.read_csv(StringIO(data), names=names, usecols=usecols)