Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Updates for PCDM to Delta #432

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 9, 2023
Merged

Updates for PCDM to Delta #432

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
126 changes: 66 additions & 60 deletions src/sdk/python/rtdip_sdk/pipelines/destinations/spark/pcdm_to_delta.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@ class ValueTypeConstants():
FLOAT_VALUE = "ValueType = 'float'"
STRING_VALUE = "ValueType = 'string'"


class SparkPCDMToDeltaDestination(DestinationInterface):
'''
The Process Control Data Model written to Delta
Expand Down Expand Up @@ -123,71 +122,78 @@ def _get_eventdate_string(self, df: DataFrame) -> str:
dates_list = list(dates_df.toPandas()["EventDate"])
return str(dates_list).replace('[','').replace(']','')

def _write_delta_batch(self, df: DataFrame, destination: str):
def _write_delta_merge(self, df: DataFrame, destination: str):
df = df.select("EventDate", "TagName", "EventTime", "Status", "Value", "ChangeType")
when_matched_update_list = [
DeltaMergeConditionValues(
condition="(source.ChangeType IN ('insert', 'update', 'upsert')) AND ((source.Status != target.Status) OR (source.Value != target.Value))",
values={
"EventDate": "source.EventDate",
"TagName": "source.TagName",
"EventTime": "source.EventTime",
"Status": "source.Status",
"Value": "source.Value"
}
)
]
when_matched_delete_list = [
DeltaMergeCondition(
condition="source.ChangeType = 'delete'"
)
]
when_not_matched_insert_list = [
DeltaMergeConditionValues(
condition="(source.ChangeType IN ('insert', 'update', 'upsert'))",
values={
"EventDate": "source.EventDate",
"TagName": "source.TagName",
"EventTime": "source.EventTime",
"Status": "source.Status",
"Value": "source.Value"
}
)
]

merge_condition = "source.EventDate = target.EventDate AND source.TagName = target.TagName AND source.EventTime = target.EventTime"

if self.merge == True:
df = df.select("EventDate", "TagName", "EventTime", "Status", "Value", "ChangeType")
when_matched_update_list = [
DeltaMergeConditionValues(
condition="(source.ChangeType IN ('insert', 'update', 'upsert')) AND ((source.Status != target.Status) OR (source.Value != target.Value))",
values={
"EventDate": "source.EventDate",
"TagName": "source.TagName",
"EventTime": "source.EventTime",
"Status": "source.Status",
"Value": "source.Value"
}
)
]
when_matched_delete_list = [
DeltaMergeCondition(
condition="source.ChangeType = 'delete'"
)
]
when_not_matched_insert_list = [
DeltaMergeConditionValues(
condition="(source.ChangeType IN ('insert', 'update', 'upsert'))",
values={
"EventDate": "source.EventDate",
"TagName": "source.TagName",
"EventTime": "source.EventTime",
"Status": "source.Status",
"Value": "source.Value"
}
)
]
perform_merge = True
if self.try_broadcast_join != True:
eventdate_string = self._get_eventdate_string(df)
if eventdate_string == None or eventdate_string == "":
perform_merge = False
else:
merge_condition = "target.EventDate in ({}) AND ".format(eventdate_string) + merge_condition

merge_condition = "source.EventDate = target.EventDate AND source.TagName = target.TagName AND source.EventTime = target.EventTime"

perform_merge = True
if self.try_broadcast_join != True:
eventdate_string = self._get_eventdate_string(df)
if eventdate_string == None or eventdate_string == "":
perform_merge = False
else:
merge_condition = "target.EventDate in ({}) AND ".format(eventdate_string) + merge_condition
if perform_merge == True:
SparkDeltaMergeDestination(
spark=self.spark,
data=df,
destination=destination,
options=self.options,
merge_condition=merge_condition,
when_matched_update_list=when_matched_update_list,
when_matched_delete_list=when_matched_delete_list,
when_not_matched_insert_list=when_not_matched_insert_list,
try_broadcast_join=self.try_broadcast_join,
trigger=self.trigger,
query_name=self.query_name
).write_batch()

if perform_merge == True:
delta = SparkDeltaMergeDestination(
spark=self.spark,
data=df,
destination=destination,
options=self.options,
merge_condition=merge_condition,
when_matched_update_list=when_matched_update_list,
when_matched_delete_list=when_matched_delete_list,
when_not_matched_insert_list=when_not_matched_insert_list,
try_broadcast_join=self.try_broadcast_join
)
def _write_delta_batch(self, df: DataFrame, destination: str):

if self.merge == True:
self._write_delta_merge(df.filter(col("ChangeType").isin('insert', 'update', 'upsert')), destination)
self._write_delta_merge(df.filter(col("ChangeType") == 'delete'), destination)
else:
df = df.select("TagName", "EventTime", "Status", "Value")
delta = SparkDeltaDestination(
SparkDeltaDestination(
data=df,
destination=destination,
options=self.options
)

delta.write_batch()
options=self.options,
mode=self.mode,
trigger=self.trigger,
query_name=self.query_name
).write_batch()

def _write_data_by_type(self, df: DataFrame):
if self.merge == True:
Expand All @@ -197,7 +203,7 @@ def _write_data_by_type(self, df: DataFrame):
df = df.withColumn("EventTime", (floor(col("EventTime").cast("double")*1000)/1000).cast("timestamp"))

if self.remove_duplicates == True:
df = df.drop_duplicates(["TagName", "EventTime"])
df = df.drop_duplicates(["TagName", "EventTime", "ChangeType"])

float_df = (
df
Expand Down