SNOW-1690711: support for cortex sentiment, classify_text with apply

Signed-off-by: Labanya Mukhopadhyay <labanya.mukhopadhyay@snowflake.com>

src/snowflake/snowpark/functions.py

@@ -10149,3 +10149,35 @@ def snowflake_cortex_summarize(text: ColumnOrLiteralStr):
     sql_func_name = "snowflake.cortex.summarize"
     text_col = _to_col_if_lit(text, sql_func_name)
     return builtin(sql_func_name)(text_col)
+
+
+def snowflake_cortex_classify_text(input: ColumnOrLiteralStr, list_of_categories):
+    """
+    Classifies free-form text into categories that you provide.
+    Args:
+        input: A string containing the English text from which a summary should be generated.
+        list_of_categories: Array that represents the categories. Must contain at least two and at most 100 unique
+            categories. Categories are case sensitive. If these requirements are not met, the function returns an error.
+    Returns:
+        Returns a string that contains a JSON object. The JSON object contains the category that the input prompt was
+        classified as. If invalid arguments are given, an error is returned.
+    """
+    sql_func_name = "snowflake.cortex.classify_text"
+    input_col = _to_col_if_lit(input, sql_func_name)
+    return builtin(sql_func_name)(input_col, list_of_categories)
+
+
+def snowflake_cortex_sentiment(text: ColumnOrLiteralStr):
+    """
+    A string containing the text for which a sentiment score should be calculated.
+
+    Args:
+        text: A string containing the English text from which a summary should be generated.
+
+    Returns:
+        A floating-point number from -1 to 1 (inclusive) indicating the level of negative or positive sentiment in the
+        text. Values around 0 indicate neutral sentiment.
+    """
+    sql_func_name = "snowflake.cortex.sentiment"
+    text_col = _to_col_if_lit(text, sql_func_name)
+    return builtin(sql_func_name)(text_col)

src/snowflake/snowpark/modin/plugin/_internal/apply_utils.py

@@ -35,7 +35,9 @@
     _log2,
     _log10,
     sin,
+    snowflake_cortex_sentiment,
     snowflake_cortex_summarize,
+    snowflake_cortex_classify_text,
     udf,
     to_variant,
     when,
@@ -110,7 +112,9 @@
     floor,
     trunc,
     sqrt,
+    snowflake_cortex_sentiment,
     snowflake_cortex_summarize,
+    snowflake_cortex_classify_text,
 }
 
 

tests/integ/modin/test_apply_snowpark_python_functions.py

@@ -89,3 +89,13 @@ def test_apply_snowflake_cortex_summarize():
     summary = s.apply(snowflake_cortex_summarize).iloc[0]
     # this length check is to get around the fact that this function may not be deterministic
     assert 0 < len(summary) < len(content)
+
+
+@sql_count_checker(query_count=1)
+def test_apply_snowflake_cortex_sentiment():
+    from snowflake.snowpark.functions import snowflake_cortex_sentiment
+
+    content = "A very very bad review!"
+    s = pd.Series([content])
+    sentiment = s.apply(snowflake_cortex_sentiment).iloc[0]
+    assert -1 <= sentiment <= 1