Project import generated by Copybara. (#104)

GitOrigin-RevId: a6c37eeb0694bccabb7e846f9ae08441d3fd437f

Co-authored-by: Snowflake Authors <[email protected]>

CHANGELOG.md

@@ -1,5 +1,17 @@
 # Release History
 
+## 1.5.2
+
+### Bug Fixes
+
+- Registry: Fix an issue that leads to unable to log model in store procedure.
+- Modeling: Quick fix `import snowflake.ml.modeling.parameters.enable_anonymous_sproc` cannot be imported due to package
+  dependency error.
+
+### Behavior Changes
+
+### New Features
+
 ## 1.5.1
 
 ### Bug Fixes

ci/conda_recipe/meta.yaml

@@ -17,7 +17,7 @@ build:
   noarch: python
 package:
   name: snowflake-ml-python
-  version: 1.5.1
+  version: 1.5.2
 requirements:
   build:
     - python

codegen/sklearn_wrapper_template.py_template

@@ -442,7 +442,14 @@ class {transform.original_class_name}(BaseTransformer):
     ) -> List[str]:
         # in case the inferred output column names dimension is different 
         # we use one line of snowpark dataframe and put it into sklearn estimator using pandas
-        output_df_pd = getattr(self, method)(dataset.limit(1).to_pandas(), output_cols_prefix)
+        sample_pd_df = dataset.select(self.input_cols).limit(1).to_pandas()
+
+        # Rename the pandas df column names to snowflake identifiers and reorder columns to match the order
+        # seen during the fit.
+        snowpark_column_names = dataset.select(self.input_cols).columns
+        sample_pd_df.columns = snowpark_column_names
+
+        output_df_pd = getattr(self, method)(sample_pd_df, output_cols_prefix)
         output_df_columns = list(output_df_pd.columns)
         output_df_columns_set: Set[str] = set(output_df_columns) - set(dataset.columns)
         if self.sample_weight_col:

snowflake/cortex/_sentiment.py

@@ -11,7 +11,7 @@
 )
 def Sentiment(
     text: Union[str, snowpark.Column], session: Optional[snowpark.Session] = None
-) -> Union[str, snowpark.Column]:
+) -> Union[float, snowpark.Column]:
     """Sentiment calls into the LLM inference service to perform sentiment analysis on the input text.
 
     Args:
@@ -21,11 +21,14 @@ def Sentiment(
     Returns:
         A column of floats. 1 represents positive sentiment, -1 represents negative sentiment.
     """
-
     return _sentiment_impl("snowflake.cortex.sentiment", text, session=session)
 
 
 def _sentiment_impl(
     function: str, text: Union[str, snowpark.Column], session: Optional[snowpark.Session] = None
-) -> Union[str, snowpark.Column]:
-    return call_sql_function(function, session, text)
+) -> Union[float, snowpark.Column]:
+
+    output = call_sql_function(function, session, text)
+    if isinstance(output, snowpark.Column):
+        return output
+    return float(output)

snowflake/cortex/sentiment_test.py

@@ -7,35 +7,36 @@
 
 
 class SentimentTest(absltest.TestCase):
-    prompt = "|prompt|"
+    sentiment = "0.53"
 
     @staticmethod
-    def sentiment_for_test(prompt: str) -> str:
-        return f"result: {prompt}"
+    def sentiment_for_test(sentiment: str) -> float:
+        return float(sentiment)
 
     def setUp(self) -> None:
         self._session = _test_util.create_test_session()
         functions.udf(
             self.sentiment_for_test,
             name="sentiment",
-            return_type=types.StringType(),
-            input_types=[types.StringType()],
+            session=self._session,
+            return_type=types.FloatType(),
+            input_types=[types.FloatType()],
             is_permanent=False,
         )
 
     def tearDown(self) -> None:
-        self._session.sql("drop function sentiment(string)").collect()
+        self._session.sql("drop function sentiment(float)").collect()
         self._session.close()
 
     def test_sentiment_str(self) -> None:
-        res = _sentiment._sentiment_impl("sentiment", self.prompt)
-        self.assertEqual(self.sentiment_for_test(self.prompt), res)
+        res = _sentiment._sentiment_impl("sentiment", self.sentiment, session=self._session)
+        self.assertEqual(self.sentiment_for_test(self.sentiment), res)
 
     def test_sentiment_column(self) -> None:
-        df_in = self._session.create_dataframe([snowpark.Row(prompt=self.prompt)])
+        df_in = self._session.create_dataframe([snowpark.Row(prompt=self.sentiment)])
         df_out = df_in.select(_sentiment._sentiment_impl("sentiment", functions.col("prompt")))
         res = df_out.collect()[0][0]
-        self.assertEqual(self.sentiment_for_test(self.prompt), res)
+        self.assertEqual(self.sentiment_for_test(self.sentiment), res)
 
 
 if __name__ == "__main__":

snowflake/ml/_internal/utils/temp_file_utils.py

@@ -8,14 +8,17 @@
 logger = logging.getLogger(__name__)
 
 
-def get_temp_file_path() -> str:
+def get_temp_file_path(prefix: str = "") -> str:
     """Returns a new random temp file path.
 
+    Args:
+        prefix: A prefix to the temp file path, this can help add stored file information. Defaults to None.
+
     Returns:
         A new temp file path.
     """
     # TODO(snandamuri): Use in-memory filesystem for temp files.
-    local_file = tempfile.NamedTemporaryFile(delete=True)
+    local_file = tempfile.NamedTemporaryFile(prefix=prefix, delete=True)
     local_file_name = local_file.name
     local_file.close()
     return local_file_name