WIP: fixed main issue but tests still failing

Author: CloseChoice

pandas/_libs/groupby.pyx

@@ -517,6 +517,7 @@ def group_add(add_t[:, ::1] out,
     N, K = (<object>values).shape
 
     if add_t is object:
+        print('IN GROUPADD: Val')
         # NB: this does not use 'compensation' like the non-object track does.
         for i in range(N):
             lab = labels[i]
@@ -546,30 +547,46 @@ def group_add(add_t[:, ::1] out,
                 else:
                     out[i, j] = sumx[i, j]
     else:
-        with nogil:
-            for i in range(N):
-                lab = labels[i]
-                if lab < 0:
-                    continue
+        # print('IN GROUPADD wihtout gil: Val. THIS IS N ' + str(N))
+        for i in range(N):
+            lab = labels[i]
+            # print('IN GROUPADD without gil: lab ' + str(lab) + ' WITH MINCOUNT ' + str(min_count))
+            if lab < 0:
+                continue
 
-                counts[lab] += 1
-                for j in range(K):
-                    val = values[i, j]
+            counts[lab] += 1
+            for j in range(K):
+                val = values[i, j]
 
-                    # not nan
-                    if val == val:
-                        nobs[lab, j] += 1
-                        y = val - compensation[lab, j]
-                        t = sumx[lab, j] + y
-                        compensation[lab, j] = t - sumx[lab, j] - y
-                        sumx[lab, j] = t
+                # not nan
+                # print('this is val ' + str(val))
+                # print('this is val == val ' + str(val == val))
+                if np.isinf(val):
+                    # print('val is INF or nan')
+                    sumx[lab, j] = val
+                    break
+                elif val == val:
+                    nobs[lab, j] += 1
+                    # print('before adding val ' + str(val))
+                    y = val - compensation[lab, j]
+                    t = sumx[lab, j] + y
+                    compensation[lab, j] = t - sumx[lab, j] - y
+                    sumx[lab, j] = t
+                    # print('after adding val ' + str(sumx[lab, j]))
+                # val is nan
+                else:
+                    sumx[lab, j] = val
 
-            for i in range(ncounts):
-                for j in range(K):
-                    if nobs[i, j] < min_count:
-                        out[i, j] = NAN
-                    else:
-                        out[i, j] = sumx[i, j]
+        # print('ncounts ' + str(ncounts))
+        for i in range(ncounts):
+            for j in range(K):
+                if nobs[i, j] < min_count:
+                    # print('CATCH CASE WHERE nan is given, MIN_COUNT: ' + str(min_count) + ' nobs[i, j] ' + str(nobs[i, j]))
+                    out[i, j] = NAN
+                else:
+                    # print('THIS IS OUT in ELSE CASE ' + str(sumx[i, j]))
+                    out[i, j] = sumx[i, j]
+                # print('THIS IS OUT ' + str(out[i, j]))
 
 
 @cython.wraparound(False)

pandas/core/groupby/groupby.py

@@ -1490,6 +1490,7 @@ def _agg_general(
 
         with self._group_selection_context():
             # try a cython aggregation if we can
+            # #import pdb; pdb.set_trace()
             result = self._cython_agg_general(
                 how=alias,
                 alt=npfunc,

pandas/core/groupby/ops.py

@@ -514,6 +514,7 @@ def _call_cython_op(
                 result_mask = result_mask.T
 
         out_shape = self._get_output_shape(ngroups, values)
+        #import pdb; pdb.set_trace()
         func, values = self.get_cython_func_and_vals(values, is_numeric)
         out_dtype = self.get_out_dtype(values.dtype)
 
@@ -925,6 +926,7 @@ def _cython_operation(
 
         ids, _, _ = self.group_info
         ngroups = self.ngroups
+        #import pdb; pdb.set_trace()
         return cy_op.cython_operation(
             values=values,
             axis=axis,

pandas/core/internals/managers.py

@@ -1259,6 +1259,7 @@ def grouped_reduce(self: T, func: Callable, ignore_failures: bool = False) -> T:
         dropped_any = False
 
         for blk in self.blocks:
+            #import pdb; pdb.set_trace()
             if blk.is_object:
                 # split on object-dtype blocks bc some columns may raise
                 #  while others do not.

pandas/tests/groupby/test_function.py

@@ -58,6 +58,7 @@ def test_intercept_builtin_sum():
     result = grouped.agg(builtins.sum)
     result2 = grouped.apply(builtins.sum)
     expected = grouped.sum()
+    import pdb; pdb.set_trace()
     tm.assert_series_equal(result, expected)
     tm.assert_series_equal(result2, expected)