Skip to content

Write Process Control Data Model Latest Values to Delta

SparkPCDMLatestToDeltaDestination

Bases: DestinationInterface

The Process Control Data Model Latest Values written to Delta.

Example

#PCDM Latest To Delta Destination for Streaming Queries

from rtdip_sdk.pipelines.destinations import SparkPCDMLatestToDeltaDestination

pcdm_latest_to_delta_destination = SparkPCDMLatestToDeltaDestination(
    data=df,
    options={
        "checkpointLocation": "{/CHECKPOINT-LOCATION/}"
    },
    destination="{DELTA_TABLE_PATH}",
    mode="append",
    trigger="10 seconds",
    query_name="PCDMLatestToDeltaDestination",
    query_wait_interval=None
)

pcdm_latest_to_delta_destination.write_stream()

#PCDM Latest To Delta Destination for Batch Queries

from rtdip_sdk.pipelines.destinations import SparkPCDMLatestToDeltaDestination

pcdm_latest_to_delta_destination = SparkPCDMLatestToDeltaDestination(
    data=df,
    options={
        "maxRecordsPerFile", "10000"
    },
    destination="{DELTA_TABLE_PATH}",
    mode="overwrite",
    trigger="10 seconds",
    query_name="PCDMLatestToDeltaDestination",
    query_wait_interval=None
)

pcdm_latest_to_delta_destination.write_batch()

Parameters:

Name Type Description Default
data DataFrame

Dataframe to be merged into a Delta Table

 required
options dict

Options that can be specified for a Delta Table read operation (See Attributes table below). Further information on the options is available for batch and streaming.

 required
destination str

Either the name of the Hive Metastore or Unity Catalog Delta Table or the path to the Delta table to store the latest values

 required
mode str

Method of writing to Delta Table - append/overwrite (batch), append/complete (stream)

 None
trigger optional str

Frequency of the write operation. Specify "availableNow" to execute a trigger once, otherwise specify a time period such as "30 seconds", "5 minutes". Set to "0 seconds" if you do not want to use a trigger. (stream) Default is 10 seconds

 '10 seconds'
query_name str

Unique name for the query in associated SparkSession

 'PCDMLatestToDeltaDestination'
query_wait_interval optional int

If set, waits for the streaming query to complete before returning. (stream) Default is None

 None

Attributes:

Name Type Description
checkpointLocation str

Path to checkpoint files. (Streaming)
Source code in src/sdk/python/rtdip_sdk/pipelines/destinations/spark/pcdm_latest_to_delta.py 
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
class SparkPCDMLatestToDeltaDestination(DestinationInterface):
    """
    The Process Control Data Model Latest Values written to Delta.

    Example
    --------
    ```python
    #PCDM Latest To Delta Destination for Streaming Queries

    from rtdip_sdk.pipelines.destinations import SparkPCDMLatestToDeltaDestination

    pcdm_latest_to_delta_destination = SparkPCDMLatestToDeltaDestination(
        data=df,
        options={
            "checkpointLocation": "{/CHECKPOINT-LOCATION/}"
        },
        destination="{DELTA_TABLE_PATH}",
        mode="append",
        trigger="10 seconds",
        query_name="PCDMLatestToDeltaDestination",
        query_wait_interval=None
    )

    pcdm_latest_to_delta_destination.write_stream()
    ```
    ```python
    #PCDM Latest To Delta Destination for Batch Queries

    from rtdip_sdk.pipelines.destinations import SparkPCDMLatestToDeltaDestination

    pcdm_latest_to_delta_destination = SparkPCDMLatestToDeltaDestination(
        data=df,
        options={
            "maxRecordsPerFile", "10000"
        },
        destination="{DELTA_TABLE_PATH}",
        mode="overwrite",
        trigger="10 seconds",
        query_name="PCDMLatestToDeltaDestination",
        query_wait_interval=None
    )

    pcdm_latest_to_delta_destination.write_batch()
    ```

    Parameters:
        data (DataFrame): Dataframe to be merged into a Delta Table
        options (dict): Options that can be specified for a Delta Table read operation (See Attributes table below). Further information on the options is available for [batch](https://docs.delta.io/latest/delta-batch.html#write-to-a-table){ target="_blank" } and [streaming](https://docs.delta.io/latest/delta-streaming.html#delta-table-as-a-sink){ target="_blank" }.
        destination (str): Either the name of the Hive Metastore or Unity Catalog Delta Table **or** the path to the Delta table to store the latest values
        mode (str): Method of writing to Delta Table - append/overwrite (batch), append/complete (stream)
        trigger (optional str): Frequency of the write operation. Specify "availableNow" to execute a trigger once, otherwise specify a time period such as "30 seconds", "5 minutes". Set to "0 seconds" if you do not want to use a trigger. (stream) Default is 10 seconds
        query_name (str): Unique name for the query in associated SparkSession
        query_wait_interval (optional int): If set, waits for the streaming query to complete before returning. (stream) Default is None

    Attributes:
        checkpointLocation (str): Path to checkpoint files. (Streaming)
    """

    spark: SparkSession
    data: DataFrame
    options: dict
    destination: str
    mode: str
    trigger: str
    query_name: str
    query_wait_interval: int

    def __init__(
        self,
        spark: SparkSession,
        data: DataFrame,
        options: dict,
        destination: str,
        mode: str = None,
        trigger="10 seconds",
        query_name: str = "PCDMLatestToDeltaDestination",
        query_wait_interval: int = None,
    ) -> None:
        self.spark = spark
        self.data = data
        self.destination = destination
        self.options = options
        self.mode = mode
        self.trigger = trigger
        self.query_name = query_name
        self.query_wait_interval = query_wait_interval

    @staticmethod
    def system_type():
        """
        Attributes:
            SystemType (Environment): Requires PYSPARK
        """
        return SystemType.PYSPARK

    @staticmethod
    def libraries():
        libraries = Libraries()
        libraries.add_maven_library(get_default_package("spark_delta_core"))
        return libraries

    @staticmethod
    def settings() -> dict:
        return {}

    def pre_write_validation(self):
        return True

    def post_write_validation(self):
        return True

    def _write_latest_to_delta(self, df: DataFrame, epoch_id=None):  # NOSONAR
        df.persist()

        latest_df = (
            df.withColumn(
                "Latest",
                max(struct("EventTime", "Status")).over(Window.partitionBy("TagName")),
            )
            .withColumn(
                "GoodLatest",
                when(
                    col("Latest.Status") == "Good",
                    struct(col("EventTime"), col("Value"), col("ValueType")),
                ).otherwise(
                    max(
                        when(
                            col("Status") == "Good",
                            struct("EventTime", "Value", "ValueType"),
                        )
                    ).over(Window.partitionBy("TagName"))
                ),
            )
            .filter(col("EventTime") == col("Latest.EventTime"))
            .drop("Latest")
            .dropDuplicates(["TagName"])
        )

        when_matched_update_list = [
            DeltaMergeConditionValues(
                condition="source.EventTime > target.EventTime AND (source.GoodLatest.EventTime IS NULL OR source.GoodLatest.EventTime <= target.GoodEventTime)",
                values={
                    "EventTime": "source.EventTime",
                    "Status": "source.Status",
                    "Value": "source.Value",
                    "ValueType": "source.ValueType",
                },
            ),
            DeltaMergeConditionValues(
                condition="source.EventTime > target.EventTime AND source.GoodLatest.EventTime IS NOT NULL AND source.GoodLatest.EventTime > target.GoodEventTime",
                values={
                    "EventTime": "source.EventTime",
                    "Status": "source.Status",
                    "Value": "source.Value",
                    "ValueType": "source.ValueType",
                    "GoodEventTime": "source.GoodLatest.EventTime",
                    "GoodValue": "source.GoodLatest.Value",
                    "GoodValueType": "source.GoodLatest.ValueType",
                },
            ),
            DeltaMergeConditionValues(
                condition="source.EventTime <= target.EventTime AND source.GoodLatest.EventTime IS NOT NULL AND source.GoodLatest.EventTime > target.GoodEventTime",
                values={
                    "GoodEventTime": "source.GoodLatest.EventTime",
                    "GoodValue": "source.GoodLatest.Value",
                    "GoodValueType": "source.GoodLatest.ValueType",
                },
            ),
        ]

        when_not_matched_insert_list = [
            DeltaMergeConditionValues(
                values={
                    "TagName": "source.TagName",
                    "EventTime": "source.EventTime",
                    "Status": "source.Status",
                    "Value": "source.Value",
                    "ValueType": "source.ValueType",
                    "GoodEventTime": "source.GoodLatest.EventTime",
                    "GoodValue": "source.GoodLatest.Value",
                    "GoodValueType": "source.GoodLatest.ValueType",
                },
            )
        ]

        merge_condition = "source.TagName = target.TagName"

        SparkDeltaMergeDestination(
            spark=self.spark,
            data=latest_df,
            destination=self.destination,
            options=self.options,
            merge_condition=merge_condition,
            when_matched_update_list=when_matched_update_list,
            when_not_matched_insert_list=when_not_matched_insert_list,
            trigger=self.trigger,
            query_name=self.query_name,
        ).write_batch()

        df.unpersist()

    def write_batch(self):
        """
        Writes Process Control Data Model data to Delta
        """
        try:
            self._write_latest_to_delta(self.data)

        except Py4JJavaError as e:
            logging.exception(e.errmsg)
            raise e
        except Exception as e:
            logging.exception(str(e))
            raise e

    def write_stream(self):
        """
        Writes streaming Process Control Data Model data to Delta using foreachBatch
        """
        try:
            TRIGGER_OPTION = (
                {"availableNow": True}
                if self.trigger == "availableNow"
                else {"processingTime": self.trigger}
            )

            query = (
                self.data.writeStream.trigger(**TRIGGER_OPTION)
                .format("delta")
                .foreachBatch(self._write_latest_to_delta)
                .queryName(self.query_name)
                .outputMode("append")
                .options(**self.options)
                .start()
            )

            if self.query_wait_interval:
                while query.isActive:
                    if query.lastProgress:
                        logging.info(query.lastProgress)
                    time.sleep(self.query_wait_interval)

        except Py4JJavaError as e:
            logging.exception(e.errmsg)
            raise e
        except Exception as e:
            logging.exception(str(e))
            raise e

system_type() staticmethod

Attributes:

Name Type Description
SystemType Environment

Requires PYSPARK
Source code in src/sdk/python/rtdip_sdk/pipelines/destinations/spark/pcdm_latest_to_delta.py 
126
127
128
129
130
131
132
@staticmethod
def system_type():
    """
    Attributes:
        SystemType (Environment): Requires PYSPARK
    """
    return SystemType.PYSPARK

write_batch()

Writes Process Control Data Model data to Delta

Source code in src/sdk/python/rtdip_sdk/pipelines/destinations/spark/pcdm_latest_to_delta.py 
240
241
242
243
244
245
246
247
248
249
250
251
252
def write_batch(self):
    """
    Writes Process Control Data Model data to Delta
    """
    try:
        self._write_latest_to_delta(self.data)

    except Py4JJavaError as e:
        logging.exception(e.errmsg)
        raise e
    except Exception as e:
        logging.exception(str(e))
        raise e

write_stream()

Writes streaming Process Control Data Model data to Delta using foreachBatch

Source code in src/sdk/python/rtdip_sdk/pipelines/destinations/spark/pcdm_latest_to_delta.py 
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
def write_stream(self):
    """
    Writes streaming Process Control Data Model data to Delta using foreachBatch
    """
    try:
        TRIGGER_OPTION = (
            {"availableNow": True}
            if self.trigger == "availableNow"
            else {"processingTime": self.trigger}
        )

        query = (
            self.data.writeStream.trigger(**TRIGGER_OPTION)
            .format("delta")
            .foreachBatch(self._write_latest_to_delta)
            .queryName(self.query_name)
            .outputMode("append")
            .options(**self.options)
            .start()
        )

        if self.query_wait_interval:
            while query.isActive:
                if query.lastProgress:
                    logging.info(query.lastProgress)
                time.sleep(self.query_wait_interval)

    except Py4JJavaError as e:
        logging.exception(e.errmsg)
        raise e
    except Exception as e:
        logging.exception(str(e))
        raise e