Check for usecols mismatch with names

Closes pandas-devgh-14671.
forking-repos · May 24, 2017 · 4af9e45 · 4af9e45
1 parent 7271f50
commit 4af9e45
Show file tree

Hide file tree

Showing 2 changed files with 55 additions and 0 deletions.
diff --git a/pandas/io/parsers.py b/pandas/io/parsers.py
@@ -1626,6 +1626,12 @@ def __init__(self, src, **kwds):
 
         if self.usecols:
             usecols = _evaluate_usecols(self.usecols, self.orig_names)
+
+            # see 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)
                               if (i in usecols or n in usecols)]

diff --git a/pandas/tests/io/parser/usecols.py b/pandas/tests/io/parser/usecols.py
@@ -475,3 +475,52 @@ def test_uneven_length_cols(self):
                               'C': [3, 5, 4, 3, 3, 7]})
         df = self.read_csv(StringIO(data), usecols=usecols)
         tm.assert_frame_equal(df, expected)
+
+    def test_raise_on_usecols_names_mismatch(self):
+        # see gh-14671
+        msg = ('Usecols do not match names' if self.engine == 'c'
+               else 'is not in list')
+        data = 'a,b,c,d\n1,2,3,4\n5,6,7,8'
+
+        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]})
+        tm.assert_frame_equal(df, expected)
+
+        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, 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]})
+        tm.assert_frame_equal(df, expected)
+
+        # usecols = ['A', 'C']
+        # 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)
+        # 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, 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)