Merge pull request pandas-dev#3730 from cpcloud/parse-exceptions

ENH/CLN: give all AssertionErrors and nose.SkipTest raises an informative message

Author: cpcloud

pandas/core/panel.py

@@ -528,9 +528,14 @@ def get_value(self, *args):
         -------
         value : scalar value
         """
+        nargs = len(args)
+        nreq = self._AXIS_LEN
+
         # require an arg for each axis
-        if not ((len(args) == self._AXIS_LEN)):
-            raise AssertionError()
+        if nargs != nreq:
+            raise TypeError('There must be an argument for each axis, you gave'
+                            ' {0} args, but {1} are required'.format(nargs,
+                                                                     nreq))
 
         # hm, two layers to the onion
         frame = self._get_item_cache(args[0])
@@ -554,8 +559,13 @@ def set_value(self, *args):
             otherwise a new object
         """
         # require an arg for each axis and the value
-        if not ((len(args) == self._AXIS_LEN + 1)):
-            raise AssertionError()
+        nargs = len(args)
+        nreq = self._AXIS_LEN + 1
+
+        if nargs != nreq:
+            raise TypeError('There must be an argument for each axis plus the '
+                            'value provided, you gave {0} args, but {1} are '
+                            'required'.format(nargs, nreq))
 
         try:
             frame = self._get_item_cache(args[0])
@@ -592,8 +602,10 @@ def __setitem__(self, key, value):
                 **self._construct_axes_dict_for_slice(self._AXIS_ORDERS[1:]))
             mat = value.values
         elif isinstance(value, np.ndarray):
-            if not ((value.shape == shape[1:])):
-                raise AssertionError()
+            if value.shape != shape[1:]:
+                raise ValueError('shape of value must be {0}, shape of given '
+                                 'object was {1}'.format(shape[1:],
+                                                         value.shape))
             mat = np.asarray(value)
         elif np.isscalar(value):
             dtype, value = _infer_dtype_from_scalar(value)
@@ -1144,8 +1156,9 @@ def _extract_axes(self, data, axes, **kwargs):
     @staticmethod
     def _extract_axes_for_slice(self, axes):
         """ return the slice dictionary for these axes """
-        return dict([(self._AXIS_SLICEMAP[i], a) for i, a
-                     in zip(self._AXIS_ORDERS[self._AXIS_LEN - len(axes):], axes)])
+        return dict([(self._AXIS_SLICEMAP[i], a)
+                     for i, a in zip(self._AXIS_ORDERS[self._AXIS_LEN -
+                                                       len(axes):], axes)])
 
     @staticmethod
     def _prep_ndarray(self, values, copy=True):
@@ -1157,8 +1170,11 @@ def _prep_ndarray(self, values, copy=True):
         else:
             if copy:
                 values = values.copy()
-        if not ((values.ndim == self._AXIS_LEN)):
-            raise AssertionError()
+        if values.ndim != self._AXIS_LEN:
+            raise ValueError("The number of dimensions required is {0}, "
+                             "but the number of dimensions of the "
+                             "ndarray given was {1}".format(self._AXIS_LEN,
+                                                            values.ndim))
         return values
 
     @staticmethod

pandas/core/series.py

@@ -1299,9 +1299,6 @@ def __unicode__(self):
                                     dtype=True)
         else:
             result = u('Series([], dtype: %s)') % self.dtype
-
-        if not (isinstance(result, compat.text_type)):
-            raise AssertionError()
         return result
 
     def _tidy_repr(self, max_vals=20):
@@ -1377,7 +1374,9 @@ def to_string(self, buf=None, na_rep='NaN', float_format=None,
 
         # catch contract violations
         if not isinstance(the_repr, compat.text_type):
-            raise AssertionError("expected unicode string")
+            raise AssertionError("result must be of type unicode, type"
+                                 " of result is {0!r}"
+                                 "".format(the_repr.__class__.__name__))
 
         if buf is None:
             return the_repr
@@ -1397,11 +1396,16 @@ def _get_repr(
         """
 
         formatter = fmt.SeriesFormatter(self, name=name, header=print_header,
-                                        length=length, dtype=dtype, na_rep=na_rep,
+                                        length=length, dtype=dtype,
+                                        na_rep=na_rep,
                                         float_format=float_format)
         result = formatter.to_string()
-        if not (isinstance(result, compat.text_type)):
-            raise AssertionError()
+
+        # TODO: following check prob. not neces.
+        if not isinstance(result, compat.text_type):
+            raise AssertionError("result must be of type unicode, type"
+                                 " of result is {0!r}"
+                                 "".format(result.__class__.__name__))
         return result
 
     def __iter__(self):

pandas/io/date_converters.py

@@ -1,5 +1,5 @@
 """This module is designed for community supported date conversion functions"""
-from pandas.compat import range
+from pandas.compat import range, map
 import numpy as np
 import pandas.lib as lib
 
@@ -47,12 +47,16 @@ def _maybe_cast(arr):
 
 
 def _check_columns(cols):
-    if not ((len(cols) > 0)):
-        raise AssertionError()
+    if not len(cols):
+        raise AssertionError("There must be at least 1 column")
 
-    N = len(cols[0])
-    for c in cols[1:]:
-        if not ((len(c) == N)):
-            raise AssertionError()
+    head, tail = cols[0], cols[1:]
+
+    N = len(head)
+
+    for i, n in enumerate(map(len, tail)):
+        if n != N:
+            raise AssertionError('All columns must have the same length: {0}; '
+                                 'column {1} has length {2}'.format(N, i, n))
 
     return N

pandas/io/parsers.py

@@ -552,8 +552,10 @@ def _clean_options(self, options, engine):
 
         # type conversion-related
         if converters is not None:
-            if not (isinstance(converters, dict)):
-                raise AssertionError()
+            if not isinstance(converters, dict):
+                raise TypeError('Type converters must be a dict or'
+                                ' subclass, input was '
+                                'a {0!r}'.format(type(converters).__name__))
         else:
             converters = {}
 
@@ -631,6 +633,7 @@ def get_chunk(self, size=None):
             size = self.chunksize
         return self.read(nrows=size)
 
+
 def _is_index_col(col):
     return col is not None and col is not False
 
@@ -1174,6 +1177,7 @@ def TextParser(*args, **kwds):
     kwds['engine'] = 'python'
     return TextFileReader(*args, **kwds)
 
+
 # delimiter=None, dialect=None, names=None, header=0,
 # index_col=None,
 # na_values=None,
@@ -1653,8 +1657,8 @@ def _rows_to_cols(self, content):
         if self._implicit_index:
             col_len += len(self.index_col)
 
-        if not ((self.skip_footer >= 0)):
-            raise AssertionError()
+        if self.skip_footer < 0:
+            raise ValueError('skip footer cannot be negative')
 
         if col_len != zip_len and self.index_col is not False:
             i = 0
@@ -1883,6 +1887,7 @@ def _clean_na_values(na_values, keep_default_na=True):
 
     return na_values, na_fvalues
 
+
 def _clean_index_names(columns, index_col):
     if not _is_index_col(index_col):
         return None, columns, index_col
@@ -1941,6 +1946,7 @@ def _floatify_na_values(na_values):
             pass
     return result
 
+
 def _stringify_na_values(na_values):
     """ return a stringified and numeric for these values """
     result = []
@@ -1965,6 +1971,7 @@ def _stringify_na_values(na_values):
             pass
     return set(result)
 
+
 def _get_na_values(col, na_values, na_fvalues):
     if isinstance(na_values, dict):
         if col in na_values:
@@ -2014,15 +2021,17 @@ def __init__(self, f, colspecs, filler, thousands=None, encoding=None):
             encoding = get_option('display.encoding')
         self.encoding = encoding
 
-        if not ( isinstance(colspecs, (tuple, list))):
-            raise AssertionError()
+        if not isinstance(colspecs, (tuple, list)):
+            raise TypeError("column specifications must be a list or tuple, "
+                            "input was a %r" % type(colspecs).__name__)
 
         for colspec in colspecs:
-            if not ( isinstance(colspec, (tuple, list)) and
-                       len(colspec) == 2 and
-                       isinstance(colspec[0], int) and
-                       isinstance(colspec[1], int) ):
-                raise AssertionError()
+            if not (isinstance(colspec, (tuple, list)) and
+                    len(colspec) == 2 and
+                    isinstance(colspec[0], int) and
+                    isinstance(colspec[1], int)):
+                raise TypeError('Each column specification must be '
+                                '2 element tuple or list of integers')
 
     def next(self):
         line = next(self.f)

pandas/io/tests/test_data.py

@@ -16,6 +16,13 @@
 from numpy.testing import assert_array_equal
 
 
+def _skip_if_no_lxml():
+    try:
+        import lxml
+    except ImportError:
+        raise nose.SkipTest("no lxml")
+
+
 def assert_n_failed_equals_n_null_columns(wngs, obj, cls=SymbolWarning):
     all_nan_cols = pd.Series(dict((k, pd.isnull(v).all()) for k, v in
                                   compat.iteritems(obj)))
@@ -88,10 +95,7 @@ def test_get_multi2(self):
 class TestYahoo(unittest.TestCase):
     @classmethod
     def setUpClass(cls):
-        try:
-            import lxml
-        except ImportError:
-            raise nose.SkipTest
+        _skip_if_no_lxml()
 
     @network
     def test_yahoo(self):
@@ -210,10 +214,7 @@ def test_get_date_ret_index(self):
 class TestYahooOptions(unittest.TestCase):
     @classmethod
     def setUpClass(cls):
-        try:
-            import lxml
-        except ImportError:
-            raise nose.SkipTest
+        _skip_if_no_lxml()
 
         # aapl has monthlies
         cls.aapl = web.Options('aapl', 'yahoo')
@@ -272,10 +273,7 @@ def test_get_put_data(self):
 class TestOptionsWarnings(unittest.TestCase):
     @classmethod
     def setUpClass(cls):
-        try:
-            import lxml
-        except ImportError:
-            raise nose.SkipTest
+        _skip_if_no_lxml()
 
         with assert_produces_warning(FutureWarning):
             cls.aapl = web.Options('aapl')

pandas/io/tests/test_ga.py

@@ -14,7 +14,7 @@
     from pandas.io.auth import AuthenticationConfigError, reset_token_store
     from pandas.io import auth
 except ImportError:
-    raise nose.SkipTest
+    raise nose.SkipTest("need httplib2 and auth libs")
 
 class TestGoogle(unittest.TestCase):
 
@@ -68,7 +68,7 @@ def test_getdata(self):
             assert_frame_equal(df, df2)
 
         except AuthenticationConfigError:
-            raise nose.SkipTest
+            raise nose.SkipTest("authentication error")
 
     @slow
     @with_connectivity_check("http://www.google.com")
@@ -96,7 +96,7 @@ def test_iterator(self):
             assert (df2.index > df1.index).all()
 
         except AuthenticationConfigError:
-            raise nose.SkipTest
+            raise nose.SkipTest("authentication error")
 
     @slow
     @with_connectivity_check("http://www.google.com")
@@ -150,7 +150,8 @@ def test_segment(self):
             assert 'pageviewsPerVisit' in df
 
         except AuthenticationConfigError:
-            raise nose.SkipTest
+            raise nose.SkipTest("authentication error")
+
 
 if __name__ == '__main__':
     nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],

pandas/io/tests/test_json/test_pandas.py

@@ -567,17 +567,11 @@ def test_round_trip_exception_(self):
         assert_frame_equal(result.reindex(index=df.index,columns=df.columns),df)
 
     @network
-    @slow
     def test_url(self):
-        try:
-
-            url = 'https://api.github.com/repos/pydata/pandas/issues?per_page=5'
-            result = read_json(url,convert_dates=True)
-            for c in ['created_at','closed_at','updated_at']:
-                self.assert_(result[c].dtype == 'datetime64[ns]')
-
-            url = 'http://search.twitter.com/search.json?q=pandas%20python'
-            result = read_json(url)
+        url = 'https://api.github.com/repos/pydata/pandas/issues?per_page=5'
+        result = read_json(url,convert_dates=True)
+        for c in ['created_at','closed_at','updated_at']:
+            self.assert_(result[c].dtype == 'datetime64[ns]')
 
-        except URLError:
-            raise nose.SkipTest
+        url = 'http://search.twitter.com/search.json?q=pandas%20python'
+        result = read_json(url)

pandas/io/tests/test_json/test_ujson.py

@@ -29,7 +29,7 @@
 def _skip_if_python_ver(skip_major, skip_minor=None):
     major, minor = sys.version_info[:2]
     if major == skip_major and (skip_minor is None or minor == skip_minor):
-        raise nose.SkipTest
+        raise nose.SkipTest("skipping Python version %d.%d" % (major, minor))
 
 json_unicode = (json.dumps if sys.version_info[0] >= 3
                 else partial(json.dumps, encoding="utf-8"))
@@ -363,7 +363,8 @@ def test_nat(self):
     def test_npy_nat(self):
         from distutils.version import LooseVersion
         if LooseVersion(np.__version__) < '1.7.0':
-            raise nose.SkipTest
+            raise nose.SkipTest("numpy version < 1.7.0, is "
+                                "{0}".format(np.__version__))
 
         input = np.datetime64('NaT')
         assert ujson.encode(input) == 'null', "Expected null"