upgini 1.1.292__tar.gz → 1.1.294__tar.gz

{upgini-1.1.292 → upgini-1.1.294}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.292
+Version: 1.1.294
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

upgini-1.1.294/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.294"

upgini-1.1.294/src/upgini/__init__.py

@@ -0,0 +1,7 @@
+from .lazy_import import LazyImport
+
+FeaturesEnricher = LazyImport('upgini.features_enricher', 'FeaturesEnricher')
+SearchKey = LazyImport('upgini.metadata', 'SearchKey')
+RuntimeParameters = LazyImport('upgini.metadata', 'RuntimeParameters')
+CVType = LazyImport('upgini.metadata', 'CVType')
+ModelTaskType = LazyImport('upgini.metadata', 'ModelTaskType')

{upgini-1.1.292 → upgini-1.1.294}/src/upgini/data_source/data_source_publisher.py

@@ -95,6 +95,11 @@ class DataSourcePublisher:
                         "With MSISDN and DATE keys one of the snapshot_frequency_days or"
                         " join_date_abs_limit_days parameters is required"
                     )
+                if (
+                    set(search_keys.values()) == {SearchKey.PHONE, SearchKey.DATE}
+                    or set(search_keys.values()) == {SearchKey.HEM, SearchKey.DATE}
+                ) and not date_format:
+                    raise ValidationError("date_format argument is required for PHONE+DATE and HEM+DATE search keys")
 
                 request = {
                     "dataTableUri": data_table_uri,

upgini-1.1.294/src/upgini/lazy_import.py

@@ -0,0 +1,22 @@
+import importlib
+
+
+class LazyImport:
+    def __init__(self, module_name, class_name):
+        self.module_name = module_name
+        self.class_name = class_name
+        self._module = None
+        self._class = None
+
+    def _load(self):
+        if self._module is None:
+            self._module = importlib.import_module(self.module_name)
+            self._class = getattr(self._module, self.class_name)
+
+    def __call__(self, *args, **kwargs):
+        self._load()
+        return self._class(*args, **kwargs)
+
+    def __getattr__(self, name):
+        self._load()
+        return getattr(self._class, name)

upgini-1.1.292/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.292"

upgini-1.1.292/src/upgini/__init__.py

@@ -1,21 +0,0 @@
-from typing import List
-
-from .dataset import Dataset
-from .features_enricher import FeaturesEnricher  # noqa: F401
-from .metadata import (  # noqa: F401
-    FileColumnMeaningType,
-    FileMetrics,
-    ModelTaskType,
-    SearchKey,
-)
-from .search_task import SearchTask
-
-
-def search_history() -> List[SearchTask]:
-    # TODO
-    return []
-
-
-def datasets_history() -> List[Dataset]:
-    # TODO
-    return []

{upgini-1.1.292 → upgini-1.1.294}/src/upgini/features_enricher.py

@@ -2557,9 +2557,6 @@ class FeaturesEnricher(TransformerMixin):
         return [c for c, v in search_keys_with_autodetection.items() if v.value.value in keys]
 
     def _validate_X(self, X, is_transform=False) -> pd.DataFrame:
-        if _num_samples(X) == 0:
-            raise ValidationError(self.bundle.get("x_is_empty"))
-
         if isinstance(X, pd.DataFrame):
             if isinstance(X.columns, pd.MultiIndex) or isinstance(X.index, pd.MultiIndex):
                 raise ValidationError(self.bundle.get("x_multiindex_unsupported"))
@@ -2573,6 +2570,9 @@ class FeaturesEnricher(TransformerMixin):
         else:
             raise ValidationError(self.bundle.get("unsupported_x_type").format(type(X)))
 
+        if _num_samples(X) == 0:
+            raise ValidationError(self.bundle.get("x_is_empty"))
+
         if len(set(validated_X.columns)) != len(validated_X.columns):
             raise ValidationError(self.bundle.get("x_contains_dup_columns"))
         if not is_transform and not validated_X.index.is_unique: