From 6aaab71e430c87deee18ee103b2135ac19f6dc17 Mon Sep 17 00:00:00 2001
From: Maxime Beauchemin <maximebeauchemin@gmail.com>
Date: Fri, 6 Apr 2018 01:04:12 +0000
Subject: [PATCH 1/2] [druid] fix 'Unorderable types' when col has nuls

Error "unorderable types: str() < int()" occurs when grouping by a
numerical Druid colummn that contains null values.

* druid/pydruid returns strings in the datafram with NAs for nulls
* Superset has custom logic around get_fillna_for_col that fills in the
NULLs based on declared column type (FLOAT here), so now we have a mixed
bag of type in the series
* pandas chokes on pivot_table or groupby operations as it cannot sorts
mixed types

The approach here is to stringify and fillna('<NULL>') to get a
consistent series.
---
 superset/connectors/druid/models.py | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/superset/connectors/druid/models.py b/superset/connectors/druid/models.py
index 25c68acae1283..b9263129f2a94 100644
--- a/superset/connectors/druid/models.py
+++ b/superset/connectors/druid/models.py
@@ -1277,6 +1277,21 @@ def run_query(  # noqa / druid
             client.query_builder.last_query.query_dict, indent=2)
         return query_str
 
+    @staticmethod
+    def homogenize_types(df, groupby_cols):
+        """Converting all GROUPBY columns to strings
+
+        When grouping by a numeric (say FLOAT) column, pydruid returns
+        strings in the dataframe. This creates issues downstream related
+        to having mixed types in the dataframe
+
+        Here we replace None with <NULL> and make the whole series a
+        str instead of an object.
+        """
+        for col in groupby_cols:
+            df[col] = df[col].fillna('<NULL>').astype(str)
+        return df
+
     def query(self, query_obj):
         qry_start_dttm = datetime.now()
         client = self.cluster.get_pydruid_client()
@@ -1284,6 +1299,8 @@ def query(self, query_obj):
             client=client, query_obj=query_obj, phase=2)
         df = client.export_pandas()
 
+        df = self.homogenize_types(df, query_obj.get('groupby', []))
+
         if df is None or df.size == 0:
             raise Exception(_('No data was returned.'))
         df.columns = [

From 5e4888af0a65cb725bca642a8903bd98d9dc3206 Mon Sep 17 00:00:00 2001
From: Maxime Beauchemin <maximebeauchemin@gmail.com>
Date: Fri, 6 Apr 2018 04:58:02 +0000
Subject: [PATCH 2/2] typo

---
 tests/druid_tests.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tests/druid_tests.py b/tests/druid_tests.py
index b0d9caff76b70..868cd5e2d51f8 100644
--- a/tests/druid_tests.py
+++ b/tests/druid_tests.py
@@ -61,6 +61,7 @@ def __reduce__(self):
         'timestamp': '2012-01-01T00:00:00.000Z',
         'event': {
             'dim1': 'Canada',
+            'dim2': 'boy',
             'metric1': 12345678,
         },
     },
@@ -69,6 +70,7 @@ def __reduce__(self):
         'timestamp': '2012-01-01T00:00:00.000Z',
         'event': {
             'dim1': 'USA',
+            'dim2': 'girl',
             'metric1': 12345678 / 2,
         },
     },
@@ -165,7 +167,7 @@ def test_client(self, PyDruid):
             'row_limit': 5000,
             'include_search': 'false',
             'metrics': ['count'],
-            'groupby': ['dim1', 'dim2d'],
+            'groupby': ['dim1', 'dim2'],
             'force': 'true',
         }
         # two groupby