Fix data transform issue, spark log_loss metric compute error and json dumps TypeError (Sync Fabric till 3c545e67) (#1371)

* Merged PR 1444697: Fix json dumps TypeError

Fix json dumps TypeError

----
Bug fix to address a `TypeError` in `json.dumps`.

This pull request fixes a `TypeError` encountered when using `json.dumps` on `automl._automl_user_configurations` by introducing a safe JSON serialization function.
- Added `safe_json_dumps` function in `flaml/fabric/mlflow.py` to handle non-serializable objects.
- Updated `MLflowIntegration` class in `flaml/fabric/mlflow.py` to use `safe_json_dumps` for JSON serialization.
- Modified `test/automl/test_multiclass.py` to test the new `safe_json_dumps` function.

Related work items: #3439408

* Fix data transform issue and spark log_loss metric compute error

flaml/automl/data.py

@@ -293,7 +293,7 @@ class DataTransformer:
                     y = y.rename(TS_VALUE_COL)
             for column in X.columns:
                 # sklearn\utils\validation.py needs int/float values
-                if X[column].dtype.name in ("object", "category"):
+                if X[column].dtype.name in ("object", "category", "string"):
                     if X[column].nunique() == 1 or X[column].nunique(dropna=True) == n - X[column].isnull().sum():
                         X.drop(columns=column, inplace=True)
                         drop = True

flaml/automl/spark/metrics.py

@@ -1,3 +1,4 @@
+import json
 from typing import Union
 
 import numpy as np
@@ -9,7 +10,7 @@ from pyspark.ml.evaluation import (
     RegressionEvaluator,
 )
 
-from flaml.automl.spark import F, psSeries
+from flaml.automl.spark import F, T, psDataFrame, psSeries, sparkDataFrame
 
 
 def ps_group_counts(groups: Union[psSeries, np.ndarray]) -> np.ndarray:
@@ -36,6 +37,16 @@ def _compute_label_from_probability(df, probability_col, prediction_col):
     return df
 
 
+def string_to_array(s):
+    try:
+        return json.loads(s)
+    except json.JSONDecodeError:
+        return []
+
+
+string_to_array_udf = F.udf(string_to_array, T.ArrayType(T.DoubleType()))
+
+
 def spark_metric_loss_score(
     metric_name: str,
     y_predict: psSeries,
@@ -135,6 +146,11 @@ def spark_metric_loss_score(
         )
     elif metric_name == "log_loss":
         # For log_loss, prediction_col should be probability, and we need to convert it to label
+        # handle data like "{'type': '1', 'values': '[1, 2, 3]'}"
+        # Fix cannot resolve "array_max(prediction)" due to data type mismatch: Parameter 1 requires the "ARRAY" type,
+        # however "prediction" has the type "STRUCT<type: TINYINT, size: INT, indices: ARRAY<INT>, values: ARRAY<DOUBLE>>"
+        df = df.withColumn(prediction_col, df[prediction_col].cast(T.StringType()))
+        df = df.withColumn(prediction_col, string_to_array_udf(df[prediction_col]))
         df = _compute_label_from_probability(df, prediction_col, prediction_col + "_label")
         evaluator = MulticlassClassificationEvaluator(
             metricName="logLoss",

flaml/automl/time_series/ts_data.py

@@ -393,7 +393,7 @@ class DataTransformerTS:
 
         for column in X.columns:
             # sklearn/utils/validation.py needs int/float values
-            if X[column].dtype.name in ("object", "category"):
+            if X[column].dtype.name in ("object", "category", "string"):
                 if (
                     # drop columns where all values are the same
                     X[column].nunique() == 1

flaml/fabric/mlflow.py

@@ -127,6 +127,13 @@ def _get_notebook_name():
     return None
 
 
+def safe_json_dumps(obj):
+    def default(o):
+        return str(o)
+
+    return json.dumps(obj, default=default)
+
+
 class MLflowIntegration:
     def __init__(self, experiment_type="automl", mlflow_exp_name=None, extra_tag=None):
         try:
@@ -438,7 +445,7 @@ class MLflowIntegration:
                 "flaml.meric": automl_metric_name,
                 "flaml.run_source": "flaml-automl",
                 "flaml.log_type": self.log_type,
-                "flaml.automl_user_configurations": json.dumps(automl._automl_user_configurations),
+                "flaml.automl_user_configurations": safe_json_dumps(automl._automl_user_configurations),
             },
             "params": {
                 "sample_size": search_state.sample_size,

test/automl/test_multiclass.py

@@ -187,7 +187,6 @@ class TestMultiClass(unittest.TestCase):
     def test_custom_metric(self):
         df, y = load_iris(return_X_y=True, as_frame=True)
         df["label"] = y
-        automl = AutoML()
         settings = {
             "dataframe": df,
             "label": "label",
@@ -204,7 +203,8 @@ class TestMultiClass(unittest.TestCase):
             "pred_time_limit": 1e-5,
             "ensemble": True,
         }
-        automl.fit(**settings)
+        automl = AutoML(**settings)  # test safe_json_dumps
+        automl.fit(dataframe=df, label="label")
         print(automl.classes_)
         print(automl.model)
         print(automl.config_history)