fix: Box Plot Chart throws an error when the average (AVG) / SUM is b…

…eing calculated on the Metrics (#20235)

* fix: Box Plot Chart throws an error when the average (AVG) / SUM is being calculated on the Metrics

* add test

(cherry picked from commit 8638f59)

superset/utils/pandas_postprocessing/boxplot.py

@@ -18,7 +18,7 @@
 
 import numpy as np
 from flask_babel import gettext as _
-from pandas import DataFrame, Series
+from pandas import DataFrame, Series, to_numeric
 
 from superset.exceptions import InvalidPostProcessingError
 from superset.utils.core import PostProcessingBoxplotWhiskerType
@@ -122,4 +122,11 @@ def outliers(series: Series) -> Set[float]:
  for operator_name, operator in operators.items()
  for metric in metrics
  }
+
+ # nanpercentile needs numeric values, otherwise the isnan function
+ # that's used in the underlying function will fail
+ for column in metrics:
+ if df.dtypes[column] == np.object:
+ df[column] = to_numeric(df[column], errors="coerce")
+
  return aggregate(df, groupby=groupby, aggregates=aggregates)

tests/unit_tests/pandas_postprocessing/test_boxplot.py

@@ -124,3 +124,28 @@ def test_boxplot_percentile_incorrect_params():
  metrics=["cars"],
  percentiles=[10, 90, 10],
  )
+
+
+def test_boxplot_type_coercion():
+ df = names_df
+ df["cars"] = df["cars"].astype(str)
+ df = boxplot(
+ df=df,
+ groupby=["region"],
+ whisker_type=PostProcessingBoxplotWhiskerType.TUKEY,
+ metrics=["cars"],
+ )
+
+ columns = {column for column in df.columns}
+ assert columns == {
+ "cars__mean",
+ "cars__median",
+ "cars__q1",
+ "cars__q3",
+ "cars__max",
+ "cars__min",
+ "cars__count",
+ "cars__outliers",
+ "region",
+ }
+ assert len(df) == 4