spells-mtg 0.7.0__tar.gz → 0.7.1__tar.gz

{spells_mtg-0.7.0 → spells_mtg-0.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spells-mtg
-Version: 0.7.0
+Version: 0.7.1
 Summary: analaysis of 17Lands.com public datasets
 Author-Email: Joel Barnes <oelarnes@gmail.com>
 License: MIT
@@ -75,6 +75,7 @@ Spells is not affiliated with 17Lands. Please review the [Usage Guidelines](http
 - Caches aggregate DataFrames in the local file system automatically for instantaneous reproduction of previous analysis
 - Manages grouping and filtering by built-in and custom columns at the row level
 - Provides 124 explicitly specified, enumerated, documented column definitions
+- Can aggregate over multiple sets at once, even all of them, if you want.
 - Supports "Deck Color Data" aggregations with built-in column definitions.
 - Lets you feed card metrics back in to column definitions to support scientific workflows like MLE
 - Provides a CLI tool `spells [add|refresh|clean|remove|info] [SET]` to download and manage external files

{spells_mtg-0.7.0 → spells_mtg-0.7.1}/README.md

@@ -64,6 +64,7 @@ Spells is not affiliated with 17Lands. Please review the [Usage Guidelines](http
 - Caches aggregate DataFrames in the local file system automatically for instantaneous reproduction of previous analysis
 - Manages grouping and filtering by built-in and custom columns at the row level
 - Provides 124 explicitly specified, enumerated, documented column definitions
+- Can aggregate over multiple sets at once, even all of them, if you want.
 - Supports "Deck Color Data" aggregations with built-in column definitions.
 - Lets you feed card metrics back in to column definitions to support scientific workflows like MLE
 - Provides a CLI tool `spells [add|refresh|clean|remove|info] [SET]` to download and manage external files

{spells_mtg-0.7.0 → spells_mtg-0.7.1}/pyproject.toml

@@ -11,7 +11,7 @@ dependencies = [
 ]
 requires-python = ">=3.11"
 readme = "README.md"
-version = "0.7.0"
+version = "0.7.1"
 
 [project.license]
 text = "MIT"

{spells_mtg-0.7.0 → spells_mtg-0.7.1}/spells/external.py

@@ -15,6 +15,7 @@ from enum import StrEnum
 
 import wget
 import polars as pl
+from polars.exceptions import ComputeError
 
 from spells import cards
 from spells import cache
@@ -231,7 +232,15 @@ def _process_zipped_file(gzip_path, target_path):
 
     os.remove(gzip_path)
     df = pl.scan_csv(csv_path, schema=schema(csv_path))
-    df.sink_parquet(target_path)
+    try:
+        df.sink_parquet(target_path)
+    except ComputeError:
+        df = pl.scan_csv(csv_path)
+        cache.spells_print('error', 'Bad schema found, loading dataset into memory'\
+        + ' and attempting to cast to correct schema')
+        select = [pl.col(name).cast(dtype) for name, dtype in schema(csv_path).items()]
+        cast_df = df.select(select).collect()
+        cast_df.write_parquet(target_path)
 
     os.remove(csv_path)
 

{spells_mtg-0.7.0 → spells_mtg-0.7.1}/spells/schema.py

@@ -136,16 +136,14 @@ COLUMN_TYPES = (
     (re.compile(r"^oppo_total_cards_drawn_or_tutored$"), pl.Int8),
 )
 
-
 def schema(
     filename: str, print_missing: bool = False
-) -> Dict[str, pl.datatypes.DataType] | None:
+) -> Dict[str, pl.datatypes.DataType]:
     dtypes: Dict[str, pl.datatypes.DataType] = {}
     with open(filename, encoding="utf-8") as f:
         columns = csv.DictReader(f).fieldnames
     if columns is None:
-        print(f"Could not read fieldnames from {filename}")
-        return None
+        raise ValueError(f"Could not read fieldnames from {filename}")
     for column in columns:
         for regex, column_type in COLUMN_TYPES:
             if regex.match(column):