docs: add possibility to specify timestamp column

Author: bednar

influxdb_client/client/write/dataframe_serializer.py

@@ -44,6 +44,7 @@ def __init__(self, data_frame, point_settings, precision=DEFAULT_WRITE_PRECISION
         :key data_frame_timestamp_column: name of DataFrame column which contains a timestamp. The column can be defined as a :class:`~str` value
                                           formatted as `2018-10-26`, `2018-10-26 12:00`, `2018-10-26 12:00:00-05:00`
                                           or other formats and types supported by `pandas.to_datetime <https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.to_datetime.html#pandas.to_datetime>`_ - ``DataFrame``
+        :key data_frame_timestamp_timezone: name of the timezone which is used for timestamp column - ``DataFrame``
         """  # noqa: E501
         # This function is hard to understand but for good reason:
         # the approach used here is considerably more efficient
@@ -96,6 +97,7 @@ def __init__(self, data_frame, point_settings, precision=DEFAULT_WRITE_PRECISION
             raise TypeError('"data_frame_measurement_name" is a Required Argument')
 
         timestamp_column = kwargs.get('data_frame_timestamp_column', None)
+        timestamp_timezone = kwargs.get('data_frame_timestamp_timezone', None)
         data_frame = data_frame.copy(deep=False)
         data_frame_timestamp = data_frame.index if timestamp_column is None else data_frame[timestamp_column]
         if isinstance(data_frame_timestamp, pd.PeriodIndex):
@@ -108,6 +110,12 @@ def __init__(self, data_frame, point_settings, precision=DEFAULT_WRITE_PRECISION
             # enabled.
             data_frame_timestamp = pd.to_datetime(data_frame_timestamp, unit=precision)
 
+        if timestamp_timezone:
+            if isinstance(data_frame_timestamp, pd.DatetimeIndex):
+                data_frame_timestamp = data_frame_timestamp.tz_localize(timestamp_timezone)
+            else:
+                data_frame_timestamp = data_frame_timestamp.dt.tz_localize(timestamp_timezone)
+
         if hasattr(data_frame_timestamp, 'tzinfo') and data_frame_timestamp.tzinfo is None:
             data_frame_timestamp = data_frame_timestamp.tz_localize('UTC')
         if timestamp_column is None:
@@ -284,5 +292,6 @@ def data_frame_to_list_of_points(data_frame, point_settings, precision=DEFAULT_W
     :key data_frame_timestamp_column: name of DataFrame column which contains a timestamp. The column can be defined as a :class:`~str` value
                                       formatted as `2018-10-26`, `2018-10-26 12:00`, `2018-10-26 12:00:00-05:00`
                                       or other formats and types supported by `pandas.to_datetime <https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.to_datetime.html#pandas.to_datetime>`_ - ``DataFrame``
+    :key data_frame_timestamp_timezone: name of the timezone which is used for timestamp column - ``DataFrame``
     """  # noqa: E501
     return DataframeSerializer(data_frame, point_settings, precision, **kwargs).serialize()

influxdb_client/client/write_api.py

@@ -297,6 +297,7 @@ def write(self, bucket: str, org: str = None,
         :key data_frame_timestamp_column: name of DataFrame column which contains a timestamp. The column can be defined as a :class:`~str` value
                                           formatted as `2018-10-26`, `2018-10-26 12:00`, `2018-10-26 12:00:00-05:00`
                                           or other formats and types supported by `pandas.to_datetime <https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.to_datetime.html#pandas.to_datetime>`_ - ``DataFrame``
+        :key data_frame_timestamp_timezone: name of the timezone which is used for timestamp column - ``DataFrame``
         :key record_measurement_key: key of record with specified measurement -
                                      ``dictionary``, ``NamedTuple``, ``dataclass``
         :key record_measurement_name: static measurement name - ``dictionary``, ``NamedTuple``, ``dataclass``

influxdb_client/client/write_api_async.py

@@ -61,6 +61,7 @@ async def write(self, bucket: str, org: str = None,
         :key data_frame_timestamp_column: name of DataFrame column which contains a timestamp. The column can be defined as a :class:`~str` value
                                           formatted as `2018-10-26`, `2018-10-26 12:00`, `2018-10-26 12:00:00-05:00`
                                           or other formats and types supported by `pandas.to_datetime <https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.to_datetime.html#pandas.to_datetime>`_ - ``DataFrame``
+        :key data_frame_timestamp_timezone: name of the timezone which is used for timestamp column - ``DataFrame``
         :key record_measurement_key: key of record with specified measurement -
                                      ``dictionary``, ``NamedTuple``, ``dataclass``
         :key record_measurement_name: static measurement name - ``dictionary``, ``NamedTuple``, ``dataclass``

tests/test_WriteApiDataFrame.py

@@ -459,6 +459,58 @@ def test_str_format_for_timestamp(self):
             self.assertEqual(1, len(points))
             self.assertEqual(time_format[1], points[0])
 
+    def test_specify_timezone(self):
+        from influxdb_client.extras import pd
+        data_frame = pd.DataFrame(data={
+            'column_time': ['2020-05-24 10:00', '2020-05-24 01:00'],
+            'value1': [10, 20],
+            'value2': [30, 40],
+        }, index=['A', 'B'])
+
+        points = data_frame_to_list_of_points(data_frame=data_frame,
+                                              data_frame_measurement_name="test",
+                                              data_frame_timestamp_column="column_time",
+                                              data_frame_timestamp_timezone="Europe/Berlin",
+                                              point_settings=PointSettings())
+
+        self.assertEqual(2, len(points))
+        self.assertEqual('test value1=10i,value2=30i 1590307200000000000', points[0])
+        self.assertEqual('test value1=20i,value2=40i 1590274800000000000', points[1])
+
+    def test_specify_timezone_date_time_index(self):
+        from influxdb_client.extras import pd
+        data_frame = pd.DataFrame(data={
+            'value1': [10, 20],
+            'value2': [30, 40],
+        }, index=[pd.Timestamp('2020-05-24 10:00'), pd.Timestamp('2020-05-24 01:00')])
+
+        points = data_frame_to_list_of_points(data_frame=data_frame,
+                                              data_frame_measurement_name="test",
+                                              data_frame_timestamp_timezone="Europe/Berlin",
+                                              point_settings=PointSettings())
+
+        self.assertEqual(2, len(points))
+        self.assertEqual('test value1=10i,value2=30i 1590307200000000000', points[0])
+        self.assertEqual('test value1=20i,value2=40i 1590274800000000000', points[1])
+
+    def test_specify_timezone_period_time_index(self):
+        from influxdb_client.extras import pd
+        data_frame = pd.DataFrame(data={
+            'value1': [10, 20],
+            'value2': [30, 40],
+        }, index=pd.period_range(start='2020-05-24 10:00', freq='H', periods=2))
+
+        print(data_frame.to_string())
+
+        points = data_frame_to_list_of_points(data_frame=data_frame,
+                                              data_frame_measurement_name="test",
+                                              data_frame_timestamp_timezone="Europe/Berlin",
+                                              point_settings=PointSettings())
+
+        self.assertEqual(2, len(points))
+        self.assertEqual('test value1=10i,value2=30i 1590307200000000000', points[0])
+        self.assertEqual('test value1=20i,value2=40i 1590310800000000000', points[1])
+
 
 class DataSerializerChunksTest(unittest.TestCase):
     def test_chunks(self):