fix: serialization of dataframes with NaN values and columns starting with digits (#486)

Author: fdorssers

CHANGELOG.md

@@ -5,6 +5,7 @@
 ### Bug Fixes
 1. [#483](https://github.com/influxdata/influxdb-client-python/pull/483): Querying data if the `debug` is enabled
 1. [#477](https://github.com/influxdata/influxdb-client-python/pull/477): Parsing date fails due to thread race
+1. [#486](https://github.com/influxdata/influxdb-client-python/pull/486): Fix bug when serializing DataFrames that might occur if you're inserting NaN values and have columns starting with digits.
 
 ### Dependencies
 1. [#472](https://github.com/influxdata/influxdb-client-python/pull/472): Update `RxPY` to `4.0.4`

influxdb_client/client/write/dataframe_serializer.py

@@ -265,7 +265,7 @@ def serialize(self, chunk_idx: int = None):
         if self.first_field_maybe_null:
             # When the first field is null (None/NaN), we'll have
             # a spurious leading comma which needs to be removed.
-            lp = (re.sub('^(( |[^ ])* ),([a-zA-Z])(.*)', '\\1\\3\\4', self.f(p))
+            lp = (re.sub('^(( |[^ ])* ),([a-zA-Z0-9])(.*)', '\\1\\3\\4', self.f(p))
                   for p in filter(lambda x: _any_not_nan(x, self.field_indexes), _itertuples(chunk)))
             return list(lp)
         else:

tests/test_WriteApiDataFrame.py

@@ -511,6 +511,39 @@ def test_specify_timezone_period_time_index(self):
         self.assertEqual('test value1=10i,value2=30i 1590307200000000000', points[0])
         self.assertEqual('test value1=20i,value2=40i 1590310800000000000', points[1])
 
+    def test_serialization_for_nan_in_columns_starting_with_digits(self):
+        from influxdb_client.extras import pd
+        from influxdb_client.extras import np
+        data_frame = pd.DataFrame(data={
+            '1value': [np.nan, 30.0, np.nan, 30.0, np.nan],
+            '2value': [30.0, np.nan, np.nan, np.nan, np.nan],
+            '3value': [30.0, 30.0, 30.0, np.nan, np.nan],
+            'avalue': [30.0, 30.0, 30.0, 30.0, 30.0]
+        }, index=pd.period_range('2020-05-24 10:00', freq='H', periods=5))
+
+        points = data_frame_to_list_of_points(data_frame,
+                                              PointSettings(),
+                                              data_frame_measurement_name='test')
+
+        self.assertEqual(5, len(points))
+        self.assertEqual('test 2value=30.0,3value=30.0,avalue=30.0 1590314400000000000', points[0])
+        self.assertEqual('test 1value=30.0,3value=30.0,avalue=30.0 1590318000000000000', points[1])
+        self.assertEqual('test 3value=30.0,avalue=30.0 1590321600000000000', points[2])
+        self.assertEqual('test 1value=30.0,avalue=30.0 1590325200000000000', points[3])
+        self.assertEqual('test avalue=30.0 1590328800000000000', points[4])
+
+        data_frame = pd.DataFrame(data={
+            '1value': [np.nan],
+            'avalue': [30.0],
+            'bvalue': [30.0]
+        }, index=pd.period_range('2020-05-24 10:00', freq='H', periods=1))
+
+        points = data_frame_to_list_of_points(data_frame,
+                                              PointSettings(),
+                                              data_frame_measurement_name='test')
+        self.assertEqual(1, len(points))
+        self.assertEqual('test avalue=30.0,bvalue=30.0 1590314400000000000', points[0])
+
 
 class DataSerializerChunksTest(unittest.TestCase):
     def test_chunks(self):