Merge branch 'master' into numpy_1.17

Author: Vyacheslav-Smirnov

sdc/datatypes/hpat_pandas_dataframe_pass.py

@@ -65,7 +65,8 @@ def run_pass(self, state):
                 out_nodes = [inst]
 
                 if isinstance(inst, ir.Assign):
-                    self.state.func_ir._definitions[inst.target.name].remove(inst.value)
+                    if inst.value in self.state.func_ir._definitions[inst.target.name]:
+                        self.state.func_ir._definitions[inst.target.name].remove(inst.value)
                     out_nodes = self._run_assign(inst)
 
                 if isinstance(out_nodes, list):

sdc/datatypes/hpat_pandas_series_functions.py

@@ -1178,7 +1178,7 @@ def hpat_pandas_series_corr(self, other, method='pearson', min_periods=None):
     if not isinstance(other.data.dtype, types.Number):
         ty_checker.raise_exc(other.data, 'number', 'other.data')
 
-    if not isinstance(min_periods, (types.Integer, types.Omitted, types.NoneType)):
+    if not isinstance(min_periods, (int, types.Integer, types.Omitted, types.NoneType)) and min_periods is not None:
         ty_checker.raise_exc(min_periods, 'int64', 'min_periods')
 
     def hpat_pandas_series_corr_impl(self, other, method='pearson', min_periods=None):
@@ -1200,7 +1200,20 @@ def hpat_pandas_series_corr_impl(self, other, method='pearson', min_periods=None
         if len(self_arr) < min_periods:
             return numpy.nan
 
-        return numpy.corrcoef(self_arr, other_arr)[0, 1]
+        new_self = pandas.Series(self_arr)
+        new_other = pandas.Series(other_arr)
+
+        n = new_self.count()
+        ma = new_self.sum()
+        mb = new_other.sum()
+        a = n * (self_arr * other_arr).sum() - ma * mb
+        b1 = n * (self_arr * self_arr).sum() - ma * ma
+        b2 = n * (other_arr * other_arr).sum() - mb * mb
+
+        if b1 == 0 or b2 == 0:
+            return numpy.nan
+
+        return a / numpy.sqrt(b1 * b2)
 
     return hpat_pandas_series_corr_impl
 

sdc/hiframes/dataframe_pass.py

@@ -76,6 +76,18 @@ def __init__(self, state):
         self.state = state
 
     def run_pass(self):
+        """
+        The function could return exxeption. It means that the IR transformation can not be completed.
+        This is acceptable behaviour.
+        """
+
+        try:
+            self.run_pass_throw()
+            return True
+        except ValueError:
+            return False
+
+    def run_pass_throw(self):
         blocks = self.state.func_ir.blocks
         # topo_order necessary so DataFrame data replacement optimization can
         # be performed in one pass
@@ -109,8 +121,7 @@ def run_pass(self):
                         # TODO: add this to dead_branch_prune pass
                         for inst in self.state.func_ir.blocks[dead_label].body:
                             if is_assign(inst):
-                                self.state.func_ir._definitions[inst.target.name].remove(
-                                    inst.value)
+                                self.state.func_ir._definitions[inst.target.name].remove(inst.value)
 
                         del self.state.func_ir.blocks[dead_label]
                     else:
@@ -124,9 +135,7 @@ def run_pass(self):
                         used_vars = set()
                         new_body = []
                         for inst in reversed(block.body):
-                            if (is_assign(inst)
-                                    and inst.target.name not in used_vars
-                                    and inst.target.name in jmp_defs):
+                            if (is_assign(inst) and inst.target.name not in used_vars and inst.target.name in jmp_defs):
                                 self.state.func_ir._definitions[inst.target.name].remove(inst.value)
                                 continue
                             used_vars.update(v.name for v in inst.list_vars())
@@ -140,7 +149,8 @@ def run_pass(self):
                 out_nodes = [inst]
 
                 if isinstance(inst, ir.Assign):
-                    self.state.func_ir._definitions[inst.target.name].remove(inst.value)
+                    if inst.value in self.state.func_ir._definitions[inst.target.name]:
+                        self.state.func_ir._definitions[inst.target.name].remove(inst.value)
                     out_nodes = self._run_assign(inst)
                 elif isinstance(inst, (ir.SetItem, ir.StaticSetItem)):
                     out_nodes = self._run_setitem(inst)

sdc/tests/test_series.py

@@ -623,7 +623,7 @@ def test_series_corr_impl(S1, S2, min_periods=None):
     @skip_sdc_jit('Series.corr() parameter "min_periods" unsupported')
     def test_series_corr_unsupported_period(self):
         def test_series_corr_impl(S1, S2, min_periods=None):
-            return S1.corr(S2, min_periods)
+            return S1.corr(S2, min_periods=min_periods)
 
         hpat_func = self.jit(test_series_corr_impl)
         S1 = pd.Series([.2, .0, .6, .2])