rebuid and retest

Author: JohnMount

build/lib/data_algebra/pandas_base.py

@@ -322,14 +322,14 @@ def _populate_impl_map(self) -> Dict[str, Callable]:
             "as_int64": lambda x: x.astype("int64").copy(),
             "as_str": lambda x: x.astype("str").copy(),
             "trimstr": lambda x, start, stop: x.str.slice(start=start, stop=stop),
-            "datetime_to_date": lambda x: x.dt.date.copy(),
+            "datetime_to_date": lambda x: self.pd.to_datetime(x).dt.date.copy(),
             "parse_datetime": lambda x, format: self.pd.to_datetime(
                 x, format=format
             ),
             "parse_date": lambda x, format: self.pd.to_datetime(
                 x, format=format
             ).dt.date.copy(),
-            "format_datetime": lambda x, format: x.dt.strftime(date_format=format),
+            "format_datetime": lambda x, format: self.pd.to_datetime(x).dt.strftime(date_format=format),
             "format_date": lambda x, format: self.pd.to_datetime(
                 x
             ).dt.strftime(date_format=format),
@@ -343,22 +343,12 @@ def _populate_impl_map(self) -> Dict[str, Callable]:
                 )
                 % 7
             ),
-            "dayofyear": lambda x: self.pd.to_datetime(x)
-            .dt.dayofyear.astype("int64")
-            .copy(),
+            "dayofyear": lambda x: self.pd.to_datetime(x).dt.dayofyear.astype("int64").copy(),
             "weekofyear": lambda x: self._calc_week_of_Year(x),
-            "dayofmonth": lambda x: self.pd.to_datetime(x)
-            .dt.day.astype("int64")
-            .copy(),
-            "month": lambda x: self.pd.to_datetime(x)
-            .dt.month.astype("int64")
-            .copy(),
-            "quarter": lambda x: self.pd.to_datetime(x)
-            .dt.quarter.astype("int64")
-            .copy(),
-            "year": lambda x: self.pd.to_datetime(x)
-            .dt.year.astype("int64")
-            .copy(),
+            "dayofmonth": lambda x: self.pd.to_datetime(x).dt.day.astype("int64").copy(),
+            "month": lambda x: self.pd.to_datetime(x).dt.month.astype("int64").copy(),
+            "quarter": lambda x: self.pd.to_datetime(x).dt.quarter.astype("int64").copy(),
+            "year": lambda x: self.pd.to_datetime(x).dt.year.astype("int64").copy(),
             "timestamp_diff": lambda c1, c2: [
                 self.pd.Timedelta(c1[i] - c2[i]).total_seconds()
                 for i in range(len(c1))

build/lib/data_algebra/polars_model.py

@@ -637,7 +637,7 @@ def get_cell(self, *, d, row: int, colname: str):
 
     def set_col(self, *, d, colname: str, values):
         """set column, return ref"""
-        d2 = d.with_column(pl.Series(values=values).alias(colname))
+        d2 = d.with_columns([pl.Series(values=values).alias(colname)])
         return d2
 
     def table_is_keyed_by_columns(self, table, *, column_names: Iterable[str]) -> bool:
@@ -667,7 +667,7 @@ def table_is_keyed_by_columns(self, table, *, column_names: Iterable[str]) -> bo
         mx = (
             table
                 .select(column_names)
-                .with_column(pl.lit(1, pl.Int64).alias("_da_count_tmp"))
+                .with_columns([pl.lit(1, pl.Int64).alias("_da_count_tmp")])
                 .groupby(column_names)
                 .sum()["_da_count_tmp"]
                 .max()
@@ -720,8 +720,8 @@ def _concat_rows_step(self, op: data_algebra.data_ops_types.OperatorPlatform, *,
         assert len(inputs) == 2
         inputs = [input_i.select(common_columns) for input_i in inputs]  # get columns in same order
         if op.id_column is not None:
-            inputs[0] = inputs[0].with_column(_build_lit(op.a_name).alias(op.id_column))
-            inputs[1] = inputs[1].with_column(_build_lit(op.b_name).alias(op.id_column))
+            inputs[0] = inputs[0].with_columns([_build_lit(op.a_name).alias(op.id_column)])
+            inputs[1] = inputs[1].with_columns([_build_lit(op.b_name).alias(op.id_column)])
         res = pl.concat(inputs, how="vertical")
         return res
 
@@ -799,7 +799,7 @@ def _extend_step(self, op: data_algebra.data_ops_types.OperatorPlatform, *, data
                 if c not in partition_set:
                     order_cols.append(c)
             reversed_cols = [True if ci in set(op.reverse) else False for ci in op.order_by]
-            res = res.sort(by=op.order_by, reverse=reversed_cols)
+            res = res.sort(by=op.order_by, descending=reversed_cols)
         res = res.with_columns(produced_columns)
         if len(temp_v_columns) > 0:
             res = res.select(op.columns_produced())
@@ -865,7 +865,7 @@ def _project_step(self, op: data_algebra.data_ops_types.OperatorPlatform, *, dat
                 res = res.collect()
             if res.shape[0] <= 0:
                 # make an all None frame
-                res = pl.DataFrame({c: [None] for c in res.columns}, columns=[(res.columns[j], res.dtypes[j]) for j in range(res.shape[1])])
+                res = pl.DataFrame({c: [None] for c in res.columns}, schema=[(res.columns[j], res.dtypes[j]) for j in range(res.shape[1])])
         # see if we need to convert to lazy type
         if self.use_lazy_eval and isinstance(res, pl.DataFrame):
             res = res.lazy()
@@ -952,7 +952,7 @@ def _order_rows_step(self, op: data_algebra.data_ops_types.OperatorPlatform, *,
             )
         res = self._compose_polars_ops(op.sources[0], data_map=data_map)
         reversed_cols = [True if ci in set(op.reverse) else False for ci in op.order_columns]
-        res = res.sort(by=op.order_columns, reverse=reversed_cols)
+        res = res.sort(by=op.order_columns, descending=reversed_cols)
         if op.limit is not None:
             res = res.head(op.limit)
         return res

coverage.txt

@@ -1,7 +1,7 @@
 ============================= test session starts ==============================
-platform darwin -- Python 3.10.8, pytest-7.1.2, pluggy-1.0.0
+platform darwin -- Python 3.10.10, pytest-7.1.2, pluggy-1.0.0
 rootdir: /Users/johnmount/Documents/work/data_algebra
-plugins: anyio-3.5.0, cov-3.0.0
+plugins: anyio-3.5.0, cov-4.0.0
 collected 377 items
 
 tests/test_OrderedSet.py ......                                          [  1%]
@@ -131,7 +131,7 @@ tests/test_window_fns.py .....                                           [ 98%]
 tests/test_with.py ..                                                    [ 99%]
 tests/test_xicor.py ..                                                   [100%]
 
----------- coverage: platform darwin, python 3.10.8-final-0 ----------
+--------- coverage: platform darwin, python 3.10.10-final-0 ----------
 Name                                   Stmts   Miss  Cover   Missing
 --------------------------------------------------------------------
 data_algebra/BigQuery.py                 126     67    47%   22-23, 27, 131-135, 139, 153-160, 169-178, 183-201, 215-244, 248-261, 272-287
@@ -159,7 +159,7 @@ data_algebra/expression_walker.py         11      0   100%
 data_algebra/flow_text.py                 17      0   100%
 data_algebra/near_sql.py                 237      3    99%   41, 256-257
 data_algebra/op_catalog.py                 3      0   100%
-data_algebra/pandas_base.py              696     68    90%   54, 68, 77, 87, 92, 101, 223, 225, 239, 242, 247, 252, 427, 467, 478, 503, 506, 511, 514, 516, 528, 534-541, 548, 582-587, 617, 621, 624, 626, 663, 717, 758, 775, 795, 813, 823, 838, 886, 894, 902, 917, 928, 940, 959, 974, 1002, 1017, 1054, 1071, 1074, 1085, 1113, 1145, 1154, 1181, 1198, 1210, 1265, 1279-1281
+data_algebra/pandas_base.py              696     68    90%   54, 68, 77, 87, 92, 101, 223, 225, 239, 242, 247, 252, 417, 457, 468, 493, 496, 501, 504, 506, 518, 524-531, 538, 572-577, 607, 611, 614, 616, 653, 707, 748, 765, 785, 803, 813, 828, 876, 884, 892, 907, 918, 930, 949, 964, 992, 1007, 1044, 1061, 1064, 1075, 1103, 1135, 1144, 1171, 1188, 1200, 1255, 1269-1271
 data_algebra/pandas_model.py              19      2    89%   32-33
 data_algebra/parse_by_lark.py            164     24    85%   71, 93, 108, 129-130, 137, 161, 171, 185-186, 188, 200, 206, 213-217, 245, 253, 263-266
 data_algebra/polars_model.py             597     74    88%   180, 189, 203, 446-452, 458-465, 483-484, 486, 570, 586, 596, 603, 616-620, 628, 630, 655, 658, 663, 666, 715, 733, 749, 816, 832-834, 879, 922, 941, 950, 965, 983, 1001, 1021, 1033-1035, 1038, 1045, 1047, 1054-1066, 1073, 1078, 1109, 1138, 1147, 1175, 1190, 1202
@@ -173,4 +173,4 @@ data_algebra/util.py                     127     28    78%   26, 59-60, 63-64, 6
 TOTAL                                   6737    912    86%
 
 
-======================= 377 passed in 857.38s (0:14:17) ========================
+======================= 377 passed in 793.00s (0:13:12) ========================