BUG: Fixed typo-related bug to resolve #9266

Fixed typo in _convert_to_ndarrays

Added tests for typo fix

Author: captainsafia

doc/source/whatsnew/v0.17.0.txt

@@ -376,6 +376,7 @@ Bug Fixes
 - Bug in `Series.from_csv` with ``header`` kwarg not setting the ``Series.name`` or the ``Series.index.name`` (:issue:`10483`)
 - Bug in `groupby.var` which caused variance to be inaccurate for small float values (:issue:`10448`)
 - Bug in ``Series.plot(kind='hist')`` Y Label not informative (:issue:`10485`)
+- Bug in ``read_csv`` when using a converter which generates a ``uint8`` type (:issue:`9266`)
 
 
 

pandas/io/parsers.py

@@ -995,7 +995,7 @@ def _convert_to_ndarrays(self, dct, na_values, na_fvalues, verbose=False,
                 try:
                     values = lib.map_infer(values, conv_f)
                 except ValueError:
-                    mask = lib.ismember(values, na_values).view(np.uin8)
+                    mask = lib.ismember(values, na_values).view(np.uint8)
                     values = lib.map_infer_mask(values, conv_f, mask)
                 coerce_type = False
 

pandas/io/tests/test_parsers.py

@@ -2654,6 +2654,25 @@ def test_fwf_regression(self):
             res = df.loc[:,c]
             self.assertTrue(len(res))
 
+    def test_fwf_for_uint8(self):
+        data = """1421302965.213420    PRI=3 PGN=0xef00      DST=0x17 SRC=0x28    04 154 00 00 00 00 00 127
+1421302964.226776    PRI=6 PGN=0xf002               SRC=0x47    243 00 00 255 247 00 00 71"""
+        df = read_fwf(StringIO(data),
+                colspecs=[(0,17),(25,26),(33,37),(49,51),(58,62),(63,1000)],
+                names=['time','pri','pgn','dst','src','data'],
+                converters={
+                        'pgn':lambda x: int(x,16),
+                        'src':lambda x: int(x,16),
+                        'dst':lambda x: int(x,16),
+                        'data':lambda x: len(x.split(' '))})
+
+        expected = DataFrame([[1421302965.213420,3,61184,23,40,8],
+                [1421302964.226776,6,61442,None, 71,8]],
+                columns = ["time", "pri", "pgn", "dst", "src","data"])
+        expected["dst"] = expected["dst"].astype(object)
+
+        tm.assert_frame_equal(df, expected)
+
     def test_fwf_compression(self):
         try:
             import gzip
@@ -3594,7 +3613,7 @@ def test_empty_with_dup_column_pass_dtype_by_indexes(self):
 
         data = 'one,one'
         result = self.read_csv(StringIO(data), mangle_dupe_cols=False, dtype={0: 'u1', 1: 'f'})
-        expected = pd.concat([Series([], name='one', dtype='u1'), 
+        expected = pd.concat([Series([], name='one', dtype='u1'),
                               Series([], name='one', dtype='f')], axis=1)
         tm.assert_frame_equal(result, expected)