Series.add / Series.lt with fill_value (#655)

Author: 1e-to

buildscripts/autogen_sources.py

@@ -77,6 +77,7 @@
 
 arithmetic_binops_symbols = {
     'add': '+',
+    'div': '/',
     'sub': '-',
     'mul': '*',
     'truediv': '/',
@@ -117,9 +118,11 @@
     import_section_text = ''.join(module_text_lines[imports_start_line: import_end_line + 1])
 
     # read function templates for arithmetic and comparison operators from templates module
-    template_series_arithmetic_binop = inspect.getsource(templates_module.sdc_pandas_series_operator_binop)
-    template_series_comparison_binop = inspect.getsource(templates_module.sdc_pandas_series_operator_comp_binop)
-    template_str_arr_comparison_binop = inspect.getsource(templates_module.sdc_str_arr_operator_comp_binop)
+    template_series_binop = inspect.getsource(templates_module.sdc_pandas_series_binop)
+    template_series_comp_binop = inspect.getsource(templates_module.sdc_pandas_series_comp_binop)
+    template_series_operator = inspect.getsource(templates_module.sdc_pandas_series_operator_binop)
+    template_series_comp_operator = inspect.getsource(templates_module.sdc_pandas_series_operator_comp_binop)
+    template_str_arr_comp_binop = inspect.getsource(templates_module.sdc_str_arr_operator_comp_binop)
 
     exit_status = -1
     try:
@@ -133,19 +136,32 @@
             # certaing modifications are needed to be applied for templates, so
             # verify correctness of produced code manually
             for name in arithmetic_binops_symbols:
-                func_text = template_series_arithmetic_binop.replace('binop', name)
+                func_text = template_series_binop.replace('binop', name)
                 func_text = func_text.replace(' + ', f' {arithmetic_binops_symbols[name]} ')
-                func_text = func_text.replace('def ', f'@sdc_overload(operator.{name})\ndef ', 1)
+                func_text = func_text.replace('def ', f"@sdc_overload_method(SeriesType, '{name}')\ndef ", 1)
                 file.write(f'\n\n{func_text}')
 
             for name in comparison_binops_symbols:
-                func_text = template_series_comparison_binop.replace('comp_binop', name)
+                func_text = template_series_comp_binop.replace('comp_binop', name)
+                func_text = func_text.replace(' < ', f' {comparison_binops_symbols[name]} ')
+                func_text = func_text.replace('def ', f"@sdc_overload_method(SeriesType, '{name}')\ndef ", 1)
+                file.write(f'\n\n{func_text}')
+
+            for name in arithmetic_binops_symbols:
+                if name != "div":
+                    func_text = template_series_operator.replace('binop', name)
+                    func_text = func_text.replace(' + ', f' {arithmetic_binops_symbols[name]} ')
+                    func_text = func_text.replace('def ', f'@sdc_overload(operator.{name})\ndef ', 1)
+                    file.write(f'\n\n{func_text}')
+
+            for name in comparison_binops_symbols:
+                func_text = template_series_comp_operator.replace('comp_binop', name)
                 func_text = func_text.replace(' < ', f' {comparison_binops_symbols[name]} ')
                 func_text = func_text.replace('def ', f'@sdc_overload(operator.{name})\ndef ', 1)
                 file.write(f'\n\n{func_text}')
 
             for name in comparison_binops_symbols:
-                func_text = template_str_arr_comparison_binop.replace('comp_binop', name)
+                func_text = template_str_arr_comp_binop.replace('comp_binop', name)
                 func_text = func_text.replace(' < ', f' {comparison_binops_symbols[name]} ')
                 if name == 'ne':
                     func_text = func_text.replace('and not', 'or')

sdc/datatypes/common_functions.py

@@ -228,9 +228,21 @@ def sdc_join_series_indexes_impl(left, right):
                 ridx = numpy.empty(est_total_size, numpy.int64)
                 joined = numpy.empty(est_total_size, numba_common_dtype)
 
+                left_nan = []
+                right_nan = []
+                for i in range(lsize):
+                    if numpy.isnan(left[i]):
+                        left_nan.append(i)
+                for i in range(rsize):
+                    if numpy.isnan(right[i]):
+                        right_nan.append(i)
+
                 # sort arrays saving the old positions
                 sorted_left = numpy.argsort(left, kind='mergesort')
                 sorted_right = numpy.argsort(right, kind='mergesort')
+                # put the position of the nans in an increasing sequence
+                sorted_left[lsize-len(left_nan):] = left_nan
+                sorted_right[rsize-len(right_nan):] = right_nan
 
                 i, j, k = 0, 0, 0
                 while (i < lsize and j < rsize):
@@ -241,13 +253,13 @@ def sdc_join_series_indexes_impl(left, right):
                     left_index = left[sorted_left[i]]
                     right_index = right[sorted_right[j]]
 
-                    if (left_index < right_index):
+                    if (left_index < right_index) or numpy.isnan(right_index):
                         joined[k] = left_index
                         lidx[k] = sorted_left[i]
                         ridx[k] = -1
                         i += 1
                         k += 1
-                    elif (left_index > right_index):
+                    elif (left_index > right_index) or numpy.isnan(left_index):
                         joined[k] = right_index
                         lidx[k] = -1
                         ridx[k] = sorted_right[j]