BUG: add sanity check to groupby agg function, outside main loop

Author: y-p

pandas/core/groupby.py

@@ -57,6 +57,8 @@ def _groupby_function(name, alias, npfunc, numeric_only=True,
     def f(self):
         try:
             return self._cython_agg_general(alias, numeric_only=numeric_only)
+        except AssertionError as e:
+            raise SpecificationError(str(e))
         except Exception:
             result = self.aggregate(lambda x: npfunc(x, axis=self.axis))
             if _convert:
@@ -348,7 +350,7 @@ def mean(self):
         """
         try:
             return self._cython_agg_general('mean')
-        except DataError:
+        except GroupByError:
             raise
         except Exception:  # pragma: no cover
             f = lambda x: x.mean(axis=self.axis)
@@ -362,7 +364,7 @@ def median(self):
         """
         try:
             return self._cython_agg_general('median')
-        except DataError:
+        except GroupByError:
             raise
         except Exception:  # pragma: no cover
             f = lambda x: x.median(axis=self.axis)
@@ -462,7 +464,10 @@ def _cython_agg_general(self, how, numeric_only=True):
             if numeric_only and not is_numeric:
                 continue
 
-            result, names = self.grouper.aggregate(obj.values, how)
+            try:
+                result, names = self.grouper.aggregate(obj.values, how)
+            except AssertionError as e:
+                raise GroupByError(str(e))
             output[name] = result
 
         if len(output) == 0:
@@ -1725,9 +1730,10 @@ def _aggregate_multiple_funcs(self, arg):
                                      grouper=self.grouper)
                 results.append(colg.aggregate(arg))
                 keys.append(col)
-            except (TypeError, DataError):
+            except (TypeError, DataError) :
                 pass
-
+            except SpecificationError:
+                raise
         result = concat(results, keys=keys, axis=1)
 
         return result

pandas/src/generate_code.py

@@ -628,6 +628,9 @@ def group_last_%(name)s(ndarray[%(dest_type2)s, ndim=2] out,
         ndarray[%(dest_type2)s, ndim=2] resx
         ndarray[int64_t, ndim=2] nobs
 
+    if not len(values) == len(labels):
+       raise AssertionError("len(index) != len(labels)")
+
     nobs = np.zeros((<object> out).shape, dtype=np.int64)
     resx = np.empty_like(out)
 
@@ -763,6 +766,9 @@ def group_nth_%(name)s(ndarray[%(dest_type2)s, ndim=2] out,
         ndarray[%(dest_type2)s, ndim=2] resx
         ndarray[int64_t, ndim=2] nobs
 
+    if not len(values) == len(labels):
+       raise AssertionError("len(index) != len(labels)")
+
     nobs = np.zeros((<object> out).shape, dtype=np.int64)
     resx = np.empty_like(out)
 
@@ -805,6 +811,9 @@ def group_add_%(name)s(ndarray[%(dest_type2)s, ndim=2] out,
         %(dest_type2)s val, count
         ndarray[%(dest_type2)s, ndim=2] sumx, nobs
 
+    if not len(values) == len(labels):
+       raise AssertionError("len(index) != len(labels)")
+
     nobs = np.zeros_like(out)
     sumx = np.zeros_like(out)
 
@@ -918,6 +927,9 @@ def group_prod_%(name)s(ndarray[%(dest_type2)s, ndim=2] out,
         %(dest_type2)s val, count
         ndarray[%(dest_type2)s, ndim=2] prodx, nobs
 
+    if not len(values) == len(labels):
+       raise AssertionError("len(index) != len(labels)")
+
     nobs = np.zeros_like(out)
     prodx = np.ones_like(out)
 
@@ -1028,6 +1040,9 @@ def group_var_%(name)s(ndarray[%(dest_type2)s, ndim=2] out,
         %(dest_type2)s val, ct
         ndarray[%(dest_type2)s, ndim=2] nobs, sumx, sumxx
 
+    if not len(values) == len(labels):
+       raise AssertionError("len(index) != len(labels)")
+
     nobs = np.zeros_like(out)
     sumx = np.zeros_like(out)
     sumxx = np.zeros_like(out)
@@ -1223,6 +1238,9 @@ def group_max_%(name)s(ndarray[%(dest_type2)s, ndim=2] out,
         %(dest_type2)s val, count
         ndarray[%(dest_type2)s, ndim=2] maxx, nobs
 
+    if not len(values) == len(labels):
+       raise AssertionError("len(index) != len(labels)")
+
     nobs = np.zeros_like(out)
 
     maxx = np.empty_like(out)
@@ -1345,6 +1363,9 @@ def group_min_%(name)s(ndarray[%(dest_type2)s, ndim=2] out,
         %(dest_type2)s val, count
         ndarray[%(dest_type2)s, ndim=2] minx, nobs
 
+    if not len(values) == len(labels):
+       raise AssertionError("len(index) != len(labels)")
+
     nobs = np.zeros_like(out)
 
     minx = np.empty_like(out)
@@ -1402,6 +1423,9 @@ def group_mean_%(name)s(ndarray[%(dest_type2)s, ndim=2] out,
         %(dest_type2)s val, count
         ndarray[%(dest_type2)s, ndim=2] sumx, nobs
 
+    if not len(values) == len(labels):
+       raise AssertionError("len(index) != len(labels)")
+
     nobs = np.zeros_like(out)
     sumx = np.zeros_like(out)