GH14671 - ERR: Raise ValueError if usecol doesn't exist with same len

- Updated tests
- Updated whatsnew 0.19.2 note
- Added new parameter file_header for CParserWrapper to contain
the original header read from the file for comparison

Author: GGordonGordon

doc/source/whatsnew/v0.19.2.txt

@@ -32,6 +32,7 @@ Bug Fixes
 
 
 
+- Bug in pd.read_csv - catch missing columns if usecols and header lengths match (:issue:`14671`)
 
 
 

pandas/io/parsers.py

@@ -1425,12 +1425,14 @@ def __init__(self, src, **kwds):
         self.orig_names = self.names[:]
 
         if self.usecols:
-            if len(self.names) > len(self.usecols):
-                self.names = [n for i, n in enumerate(self.names)
-                              if (i in self.usecols or n in self.usecols)]
-
-            if len(self.names) < len(self.usecols):
-                raise ValueError("Usecols do not match names.")
+            if self._reader.file_header is not None:
+                h = self._reader.file_header[0]
+                usecol_len = len(set(self.usecols) - set(h))
+                usecoli_len = len(set(self.usecols) - set(range(0, len(h))))
+                if usecol_len > 0 and usecoli_len > 0:
+                    raise ValueError("Usecols do not match names.")
+
+            self.names = self._filter_usecols(self.names)
 
         self._set_noconvert_columns()
 

pandas/io/tests/parser/usecols.py

@@ -54,6 +54,10 @@ def test_usecols(self):
         expected.columns = ['foo', 'bar']
         tm.assert_frame_equal(result, expected)
 
+        # same length but usecols column doesn't exist - see gh-14671
+        self.assertRaises(ValueError, self.read_csv, StringIO(data),
+                          usecols=['a', 'b', 'z'])
+
         data = """\
 1,2,3
 4,5,6

pandas/parser.pyx

@@ -290,7 +290,7 @@ cdef class TextReader:
         object na_values
         object memory_map
         object as_recarray
-        object header, orig_header, names, header_start, header_end
+        object header, orig_header, names, header_start, header_end, file_header
         object index_col
         object low_memory
         object skiprows
@@ -775,6 +775,12 @@ cdef class TextReader:
                 data_line = hr + 1
                 header.append(this_header)
 
+            self.file_header = header[:]
+
+            #if self.usecols is not None:
+            #    if len(set(self.usecols) - set(header[0])) > 0 and len(set(self.usecols) - set(range(0,field_count))) > 0:
+            #        raise ValueError("Usecols do not match names.")
+
             if self.names is not None:
                 header = [ self.names ]