cdiscbuilder 1.2.2__tar.gz → 1.2.3__tar.gz

{cdiscbuilder-1.2.2/src/cdiscbuilder.egg-info → cdiscbuilder-1.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cdiscbuilder
-Version: 1.2.2
+Version: 1.2.3
 Summary: A package to convert ODM XML to SDTM/ADaM Datasets
 Author-email: Ming-Chun Chen <hellomingchun@gmail.com>
 Requires-Python: >=3.9
@@ -10,7 +10,6 @@ Requires-Dist: pandas
 Requires-Dist: pyyaml
 Requires-Dist: polars>=0.20.0
 Requires-Dist: reactable>=0.1.6
-Requires-Dist: pyarrow
 Dynamic: license-file
 
 # CDISC Builder

{cdiscbuilder-1.2.2 → cdiscbuilder-1.2.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cdiscbuilder"
-version = "1.2.2"
+version = "1.2.3"
 description = "A package to convert ODM XML to SDTM/ADaM Datasets"
 readme = "README.md"
 authors = [{name = "Ming-Chun Chen", email = "hellomingchun@gmail.com"}]
@@ -12,8 +12,7 @@ dependencies = [
     "pandas",
     "pyyaml",
     "polars>=0.20.0",
-    "reactable>=0.1.6",
-    "pyarrow"
+    "reactable>=0.1.6"
 ]
 requires-python = ">=3.9"
 

{cdiscbuilder-1.2.2 → cdiscbuilder-1.2.3}/src/cdiscbuilder/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "1.2.1"
+__version__ = "1.2.3"
 
 from . import adam as adam
 from . import tlf as tlf

{cdiscbuilder-1.2.2 → cdiscbuilder-1.2.3}/src/cdiscbuilder/sdtm/engine/classes/general.py

@@ -168,6 +168,9 @@ class GeneralProcessor:
                         temp_df = final_df[group_cols].copy()
 
                         sort_keys = group_cols[:]  # Always sort by group first
+                        ascending_list = [True] * len(group_cols)
+                        
+                        order_cfg = col_config.get("order")
 
                         if sort_cols:
                             if not isinstance(sort_cols, list):
@@ -184,12 +187,26 @@ class GeneralProcessor:
                                 for c in sort_cols:
                                     temp_df[c] = final_df[c]
                                 sort_keys.extend(sort_cols)
+                                
+                                # Apply custom order if provided
+                                if order_cfg:
+                                    if not isinstance(order_cfg, list):
+                                        order_cfg = [order_cfg]
+                                    
+                                    # Map "asc"/"desc" to True/False for the sort_cols
+                                    for o in order_cfg:
+                                        if str(o).lower() in ["desc", "descending", "false"]:
+                                            ascending_list.append(False)
+                                        else:
+                                            ascending_list.append(True)
+                                else:
+                                    ascending_list.extend([True] * len(sort_cols))
 
                         # Sort
-                        temp_df = temp_df.sort_values(by=sort_keys)
+                        temp_df = temp_df.sort_values(by=sort_keys, ascending=ascending_list)
 
                         # Calculate Cumcount + 1
-                        seq_series = temp_df.groupby(group_cols).cumcount() + 1
+                        seq_series = temp_df.groupby(group_cols, sort=False).cumcount() + 1
 
                         # Map back to original index
                         series = seq_series.sort_index()

{cdiscbuilder-1.2.2 → cdiscbuilder-1.2.3}/src/cdiscbuilder/sdtm/engine/processor.py

@@ -86,6 +86,8 @@ def process_domain(domain_name, sources, df_long, default_keys, output_dir, cust
         group_cols = col_config.get("group")
         sort_cols = col_config.get("sort_by")
 
+        order_cfg = col_config.get("order")
+
         if not isinstance(group_cols, list):
             group_cols = [group_cols]
 
@@ -99,6 +101,9 @@ def process_domain(domain_name, sources, df_long, default_keys, output_dir, cust
         # Create sort view
         temp_df = combined_df[group_cols].copy()
         sort_keys = group_cols[:]
+        
+        # Determine sorting order (ascending by default)
+        ascending_list = [True] * len(group_cols)
 
         if sort_cols:
             if not isinstance(sort_cols, list):
@@ -108,11 +113,25 @@ def process_domain(domain_name, sources, df_long, default_keys, output_dir, cust
                 for c in sort_cols:
                     temp_df[c] = combined_df[c]
                 sort_keys.extend(sort_cols)
+                
+                # Apply custom order if provided
+                if order_cfg:
+                    if not isinstance(order_cfg, list):
+                        order_cfg = [order_cfg]
+                    
+                    # Map "asc"/"desc" to True/False for the sort_cols
+                    for o in order_cfg:
+                        if str(o).lower() in ["desc", "descending", "false"]:
+                            ascending_list.append(False)
+                        else:
+                            ascending_list.append(True)
+                else:
+                    ascending_list.extend([True] * len(sort_cols))
 
         # Sort
-        temp_df = temp_df.sort_values(by=sort_keys)
+        temp_df = temp_df.sort_values(by=sort_keys, ascending=ascending_list)
         # Cumcount + 1
-        seq_series = temp_df.groupby(group_cols).cumcount() + 1
+        seq_series = temp_df.groupby(group_cols, sort=False).cumcount() + 1
         # Re-align to combined_df index
         combined_df[target_col] = seq_series.sort_index()
 

{cdiscbuilder-1.2.2 → cdiscbuilder-1.2.3}/src/cdiscbuilder/sdtm/engine/tests/test_boundary_standardization.py

@@ -125,7 +125,7 @@ def test_create_sdtm_datasets_boundary_standardization(tmp_path):
     create_sdtm_datasets(str(spec_dir), str(input_csv), str(output_dir))
 
     # Verify dataset exists
-    out_file = output_dir / "AE.parquet"
+    out_file = output_dir / "ae.parquet"
     assert out_file.exists()
 
     res_df = pd.read_parquet(out_file)

{cdiscbuilder-1.2.2 → cdiscbuilder-1.2.3}/src/cdiscbuilder/sdtm/engine/tests/test_processor.py

@@ -90,7 +90,7 @@ def test_process_domain_append_real(tmp_path):
         out_dir = tmp_path / "sdtm_out"
         process_domain("DM", sources, pd.DataFrame(), ["Subj"], str(out_dir))
 
-        out_file = out_dir / "DM.parquet"
+        out_file = out_dir / "dm.parquet"
         assert out_file.exists()
 
         res_df = pd.read_parquet(out_file)
@@ -114,7 +114,7 @@ def test_process_domain_merge_blocks(tmp_path):
         out_dir = tmp_path / "sdtm_out"
         process_domain("DM", sources, pd.DataFrame(), ["Subj"], str(out_dir))
 
-        res_df = pd.read_parquet(out_dir / "DM.parquet")
+        res_df = pd.read_parquet(out_dir / "dm.parquet")
         assert len(res_df) == 2
         assert "AGE" in res_df.columns
         assert "SEX" in res_df.columns
@@ -140,7 +140,7 @@ def test_process_domain_merge_blocks_missing_keys(tmp_path, capsys):
         out, err = capsys.readouterr()
         assert "missing keys: ['USUBJID']" in out
 
-        res_df = pd.read_parquet(out_dir / "DM.parquet")
+        res_df = pd.read_parquet(out_dir / "dm.parquet")
         # Appended instead of merged
         assert len(res_df) == 2
         assert "SEX" in res_df.columns
@@ -174,6 +174,6 @@ def test_process_domain_global_sequence(tmp_path):
         out_dir = tmp_path / "sdtm_out"
         process_domain("DM", sources, pd.DataFrame(), ["Subj"], str(out_dir))
 
-        res_df = pd.read_parquet(out_dir / "DM.parquet")
+        res_df = pd.read_parquet(out_dir / "dm.parquet")
         assert "SEQ" in res_df.columns
         assert list(res_df["SEQ"]) == [1, 2, 1, 2]

{cdiscbuilder-1.2.2 → cdiscbuilder-1.2.3/src/cdiscbuilder.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cdiscbuilder
-Version: 1.2.2
+Version: 1.2.3
 Summary: A package to convert ODM XML to SDTM/ADaM Datasets
 Author-email: Ming-Chun Chen <hellomingchun@gmail.com>
 Requires-Python: >=3.9
@@ -10,7 +10,6 @@ Requires-Dist: pandas
 Requires-Dist: pyyaml
 Requires-Dist: polars>=0.20.0
 Requires-Dist: reactable>=0.1.6
-Requires-Dist: pyarrow
 Dynamic: license-file
 
 # CDISC Builder

{cdiscbuilder-1.2.2 → cdiscbuilder-1.2.3}/src/cdiscbuilder.egg-info/requires.txt

@@ -2,4 +2,3 @@ pandas
 pyyaml
 polars>=0.20.0
 reactable>=0.1.6
-pyarrow