Scale Corr

sdc/datatypes/hpat_pandas_series_functions.py

@@ -2196,40 +2196,7 @@ def hpat_pandas_series_corr(self, other, method='pearson', min_periods=None):
         ty_checker.raise_exc(min_periods, 'int64', 'min_periods')
 
     def hpat_pandas_series_corr_impl(self, other, method='pearson', min_periods=None):
-        if method not in ('pearson', ''):
-            raise ValueError("Method corr(). Unsupported parameter. Given method != 'pearson'")
-
-        if min_periods is None:
-            min_periods = 1
-
-        if len(self._data) == 0 or len(other._data) == 0:
-            return numpy.nan
-
-        self_arr = self._data[:min(len(self._data), len(other._data))]
-        other_arr = other._data[:min(len(self._data), len(other._data))]
-
-        invalid = numpy.isnan(self_arr) | numpy.isnan(other_arr)
-        if invalid.any():
-            self_arr = self_arr[~invalid]
-            other_arr = other_arr[~invalid]
-
-        if len(self_arr) < min_periods:
-            return numpy.nan
-
-        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 numpy_like.corr(self, other, method, min_periods)
 
     return hpat_pandas_series_corr_impl
 

sdc/functions/numpy_like.py

@@ -727,6 +727,54 @@ def nanmean_impl(a):
     return nanmean_impl
 
 
+def corr(self, other, method='pearson', min_periods=None):
+    pass
+
+
+@sdc_overload(corr)
+def corr_overload(self, other, method='pearson', min_periods=None):
+    def corr_impl(self, other, method='pearson', min_periods=None):
+        if method not in ('pearson', ''):
+            raise ValueError("Method corr(). Unsupported parameter. Given method != 'pearson'")
+
+        if min_periods is None or min_periods < 1:
+            min_periods = 1
+
+        min_len = min(len(self._data), len(other._data))
+
+        if min_len == 0:
+            return numpy.nan
+
+        sum_y = 0.
+        sum_x = 0.
+        sum_xy = 0.
+        sum_xx = 0.
+        sum_yy = 0.
+        total_count = 0
+        for i in prange(min_len):
+            x = self._data[i]
+            y = other._data[i]
+            if not (numpy.isnan(x) or numpy.isnan(y)):
+                sum_x += x
+                sum_y += y
+                sum_xy += x * y
+                sum_xx += x * x
+                sum_yy += y * y
+                total_count += 1
+
+        if total_count < min_periods:
+            return numpy.nan
+
+        cov_xy = (sum_xy - sum_x * sum_y / total_count)
+        var_x = (sum_xx - sum_x * sum_x / total_count)
+        var_y = (sum_yy - sum_y * sum_y / total_count)
+        corr_xy = cov_xy / numpy.sqrt(var_x * var_y)
+
+        return corr_xy
+
+    return corr_impl
+
+
 def nanvar(a):
     pass