upgini 1.2.157a4196.dev2__tar.gz → 1.2.157a4196.dev3__tar.gz

{upgini-1.2.157a4196.dev2 → upgini-1.2.157a4196.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.157a4196.dev2
+Version: 1.2.157a4196.dev3
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -203,10 +203,10 @@ Run [Simple sales prediction for retail stores](https://github.com/upgini/upgini
 
 ### 1. Install from PyPI
 ```python
-%pip install -U 'pyarrow>=23.0.1,<24' upgini
+%pip install upgini
 ```
 
-In Colab or Jupyter, **restart the runtime after install** before importing upgini. Otherwise pyarrow may fail with a binary incompatibility error.
+In Colab, it is recommended to **restart the runtime after install** before importing upgini. Otherwise pyarrow may fail with a binary incompatibility error.
 <details>
 	<summary>
 	🐳 <b>Docker-way</b>

{upgini-1.2.157a4196.dev2 → upgini-1.2.157a4196.dev3}/README.md

@@ -158,10 +158,10 @@ Run [Simple sales prediction for retail stores](https://github.com/upgini/upgini
 
 ### 1. Install from PyPI
 ```python
-%pip install -U 'pyarrow>=23.0.1,<24' upgini
+%pip install upgini
 ```
 
-In Colab or Jupyter, **restart the runtime after install** before importing upgini. Otherwise pyarrow may fail with a binary incompatibility error.
+In Colab, it is recommended to **restart the runtime after install** before importing upgini. Otherwise pyarrow may fail with a binary incompatibility error.
 <details>
 	<summary>
 	🐳 <b>Docker-way</b>

upgini-1.2.157a4196.dev3/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.157.a4196.dev3"

{upgini-1.2.157a4196.dev2 → upgini-1.2.157a4196.dev3}/src/upgini/dataset.py

@@ -490,17 +490,8 @@ class Dataset:
             parquet_file_path = f"{tmp_dir}/{self.dataset_name}.parquet"
 
             # calculate deterministic digest for any environment
-            try:
-                import pyarrow as pa
-                import pyarrow.parquet as pq
-            except ValueError as exc:
-                if "binary incompatibility" in str(exc) or "size changed" in str(exc):
-                    raise ImportError(
-                        "pyarrow was upgraded but the runtime still has an older version loaded. "
-                        "Restart the runtime after installing upgini (Runtime -> Restart session in Colab), "
-                        "then import upgini again."
-                    ) from exc
-                raise
+            import pyarrow as pa
+            import pyarrow.parquet as pq
 
             table = pa.Table.from_pandas(df_without_fake_date, preserve_index=False)
             table = table.replace_schema_metadata({})  # remove all metadata

{upgini-1.2.157a4196.dev2 → upgini-1.2.157a4196.dev3}/src/upgini/features_enricher.py

@@ -105,6 +105,7 @@ from upgini.utils.feature_info import FeatureInfo, _round_shap_value
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.format import Format
 from upgini.utils.hash_utils import file_hash, hash_input
+from upgini.utils.pyarrow_utils import import_pyarrow_modules
 from upgini.utils.ip_utils import IpSearchKeyConverter
 from upgini.utils.phone_utils import PhoneSearchKeyDetector
 from upgini.utils.postal_code_utils import PostalCodeSearchKeyDetector
@@ -508,6 +509,7 @@ class FeaturesEnricher(TransformerMixin):
         stability_agg_func: str, optional (default="max")
             Function to aggregate stability values. Can be "max", "min", "mean".
         """
+        self._ensure_pyarrow_available()
         trace_id = self._get_trace_id()
         if self.print_trace_id:
             print(f"https://app.datadoghq.eu/logs?query=%40correlation_id%3A{trace_id}")
@@ -793,6 +795,7 @@ class FeaturesEnricher(TransformerMixin):
         X_new: pandas.DataFrame of shape (n_samples, n_features_new)
             Transformed dataframe, enriched with valuable features.
         """
+        self._ensure_pyarrow_available()
         self.warning_counter.reset()
         search_progress = SearchProgress(0.0, ProgressStage.START_TRANSFORM)
         if progress_callback is not None:
@@ -922,6 +925,7 @@ class FeaturesEnricher(TransformerMixin):
             Dataframe with metrics calculated on train and validation datasets.
         """
 
+        self._ensure_pyarrow_available()
         trace_id = self._get_trace_id()
         start_time = time.time()
         search_id = self.search_id or (self._search_task.search_task_id if self._search_task is not None else None)
@@ -1320,6 +1324,10 @@ class FeaturesEnricher(TransformerMixin):
             finally:
                 self.logger.info(f"Calculating metrics elapsed time: {time.time() - start_time}")
 
+    @staticmethod
+    def _ensure_pyarrow_available() -> None:
+        import_pyarrow_modules()
+
     def _get_trace_id(self):
         if get_mdc_fields().get("correlation_id") is not None:
             return get_mdc_fields().get("correlation_id")

upgini-1.2.157a4196.dev3/src/upgini/utils/pyarrow_utils.py

@@ -0,0 +1,28 @@
+import warnings
+
+PYARROW_RUNTIME_RESTART_MESSAGE = (
+    "pyarrow was upgraded but the runtime still has an older version loaded. "
+    "Restart the runtime after installing upgini (Runtime -> Restart session in Colab), "
+    "then import upgini again."
+)
+
+
+def is_pyarrow_binary_incompatibility(exc: BaseException) -> bool:
+    msg = str(exc).lower()
+    return "binary incompatibility" in msg or "size changed" in msg or "ipcreadoptions" in msg
+
+
+def raise_pyarrow_runtime_error(exc: BaseException) -> None:
+    warnings.warn(PYARROW_RUNTIME_RESTART_MESSAGE, UserWarning, stacklevel=3)
+    raise ImportError(PYARROW_RUNTIME_RESTART_MESSAGE) from exc
+
+
+def import_pyarrow_modules():
+    try:
+        import pyarrow as pa
+        import pyarrow.parquet as pq
+    except (ValueError, ImportError) as exc:
+        if is_pyarrow_binary_incompatibility(exc):
+            raise_pyarrow_runtime_error(exc)
+        raise
+    return pa, pq

upgini-1.2.157a4196.dev2/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.157.a4196.dev2"