fix: Add handling for spark DecimalType

src/ydata_profiling/model/spark/describe_counts_spark.py

@@ -5,7 +5,7 @@
 
 import pandas as pd
 from pyspark.sql import DataFrame
-from pyspark.sql import functions as F
+from pyspark.sql import functions as F, types as T
 
 from ydata_profiling.config import Settings
 from ydata_profiling.model.summary_algorithms import describe_counts
@@ -25,6 +25,9 @@ def describe_counts_spark(
     Returns:
         Updated settings, input series, and summary dictionary.
     """
+    # Cast Decimal Type s
+    if isinstance(series.schema.fields[0].dataType, T.DecimalType):
+        series = series.select(F.col(series.columns[0]).cast(T.DoubleType()).alias(series.columns[0]))
 
     # Count occurrences of each value
     value_counts = series.groupBy(series.columns[0]).count()

src/ydata_profiling/model/spark/summary_spark.py

@@ -43,6 +43,8 @@ def spark_describe_1d(
 
         if str(series.schema[0].dataType).startswith("ArrayType"):
             dtype = "ArrayType"
+        elif str(series.schema[0].dataType).startswith("Decimal"):
+            dtype = "decimal"
         else:
             dtype = series.schema[0].dataType.simpleString()
 
@@ -56,6 +58,7 @@ def spark_describe_1d(
             "boolean": "Boolean",
             "date": "DateTime",
             "timestamp": "DateTime",
+            "decimal": "Numeric",
         }[dtype]
 
     return summarizer.summarize(config, series, dtype=vtype)

tests/issues/test_issue1602.py

@@ -0,0 +1,36 @@
+"""
+Test for issue 1602:
+https://github.com/ydataai/ydata-profiling/issues/1602
+"""
+
+from ydata_profiling import ProfileReport
+from pyspark.sql import types as T
+
+def test_spark_handles_decimal_type(test_output_dir, spark_session):
+    from decimal import Decimal
+    spark = spark_session
+
+    schema = T.StructType(
+        [
+            T.StructField("number", T.StringType(), True),
+            T.StructField("decimal", T.DecimalType(10, 2), True)
+        ]
+    )
+
+    data = [
+        (f"test_{num + 1}", Decimal(num + 1)) for num in range(205)
+    ]
+
+    data.extend(
+        [
+            ("test_1", Decimal("1.05")) for _ in range(205)
+        ]
+    )
+
+    test_df = spark.createDataFrame(data, schema=schema)
+
+    profile = ProfileReport(test_df, title="decimal_handling", explorative=True)
+    output_file = test_output_dir / "decimal_handling.html"
+    profile.to_file(output_file)
+
+    assert output_file.exists()