394 lines
13 KiB
Python
394 lines
13 KiB
Python
|
|
__generated_with = "0.13.15"
|
|
|
|
# %%
|
|
|
|
import sys
|
|
import time
|
|
from pyspark.sql.utils import AnalysisException
|
|
sys.path.append('/opt/spark/work-dir/')
|
|
from workflow_templates.spark.udf_manager import bootstrap_udfs
|
|
from util import get_logger, observe_metrics, collect_metrics, log_info, log_error, forgiving_serializer
|
|
from pyspark.sql.functions import udf
|
|
from pyspark.sql.functions import count, expr, lit, input_file_name
|
|
from pyspark.sql.types import StringType, IntegerType, MapType, StructType,StructField
|
|
from postal.parser import parse_address
|
|
import uuid
|
|
from pathlib import Path
|
|
from pyspark import SparkConf, Row
|
|
from pyspark.sql import SparkSession
|
|
from pyspark.sql.observation import Observation
|
|
from pyspark import StorageLevel
|
|
import os
|
|
import pandas as pd
|
|
import polars as pl
|
|
import pyarrow as pa
|
|
from pyspark.sql.functions import approx_count_distinct, avg, collect_list, collect_set, corr, count, countDistinct, covar_pop, covar_samp, first, kurtosis, last, max, mean, min, skewness, stddev, stddev_pop, stddev_samp, sum, var_pop, var_samp, variance,expr,to_json,struct, date_format, col, lit, when, regexp_replace, ltrim, lpad, format_number
|
|
from functools import reduce
|
|
from handle_structs_or_arrays import preprocess_then_expand
|
|
import requests
|
|
from requests.adapters import HTTPAdapter
|
|
from urllib3.util.retry import Retry
|
|
from jinja2 import Template
|
|
import json
|
|
import orjson
|
|
|
|
from ocular_ai_sdk import OcularClient
|
|
from ocular_ai_sdk.exceptions import (
|
|
OcularSDKException,
|
|
AuthenticationError,
|
|
ResourceNotFoundError
|
|
)
|
|
|
|
|
|
from secrets_manager import SecretsManager
|
|
|
|
from WorkflowManager import WorkflowDSL, WorkflowManager
|
|
from KnowledgebaseManager import KnowledgebaseManager
|
|
from gitea_client import GiteaClient, WorkspaceVersionedContent
|
|
from FilesystemManager import FilesystemManager, SupportedFilesystemType
|
|
from Materialization import Materialization
|
|
|
|
import ssl
|
|
from urllib.request import Request, urlopen
|
|
from urllib.parse import urlencode
|
|
from urllib.error import HTTPError
|
|
|
|
init_start_time=time.time()
|
|
|
|
LOGGER = get_logger()
|
|
alias_str='abcdefghijklmnopqrstuvwxyz'
|
|
workspace = os.getenv('WORKSPACE') or 'exp360-cus-uat'
|
|
workflow = 'service_request_metrics'
|
|
execution_environment = os.getenv('EXECUTION_ENVIRONMENT') or 'CLUSTER'
|
|
|
|
job_id = os.getenv("EXECUTION_ID") or str(uuid.uuid4())
|
|
retry_job_id = os.getenv("RETRY_EXECUTION_ID") or ''
|
|
|
|
log_info(LOGGER, f"Workspace: '{workspace}', Workflow: '{workflow}', Execution Environment: '{execution_environment}', Job Id: '{job_id}', Retry Job Id: '{retry_job_id}'")
|
|
|
|
sm = SecretsManager(os.getenv('SECRET_MANAGER_URL'), os.getenv('SECRET_MANAGER_NAMESPACE'), os.getenv('SECRET_MANAGER_ENV'), os.getenv('SECRET_MANAGER_TOKEN'))
|
|
secrets = sm.list_secrets(workspace)
|
|
|
|
gitea_client=GiteaClient(os.getenv('GITEA_HOST'), os.getenv('GITEA_TOKEN'), os.getenv('GITEA_OWNER') or 'gitea_admin', os.getenv('GITEA_REPO') or 'tenant1')
|
|
workspaceVersionedContent=WorkspaceVersionedContent(gitea_client)
|
|
|
|
client = OcularClient(
|
|
pat_token=secrets.get('OCULAR_AI_PAT_TOKEN')
|
|
)
|
|
|
|
if 'AZURE_SERVICE_PRINCIPAL' in secrets:
|
|
_storage_options=orjson.loads(secrets['AZURE_SERVICE_PRINCIPAL'])
|
|
else:
|
|
_storage_options = {
|
|
'key': secrets.get('S3_ACCESS_KEY'),
|
|
'secret': secrets.get('S3_SECRET_KEY'),
|
|
'region': secrets.get('S3_REGION')
|
|
}
|
|
|
|
filesystemManager = FilesystemManager.create(secrets.get('LAKEHOUSE_BUCKET'), storage_options=_storage_options)
|
|
if retry_job_id:
|
|
logs = Materialization.get_execution_history_by_job_id(filesystemManager, secrets.get('LAKEHOUSE_BUCKET'), workspace, workflow, retry_job_id, selected_components=['finalize']).to_dicts()
|
|
if len(logs) == 1 and logs[0].get('metrics').get('execute_status') == 'SUCCESS':
|
|
log_info(LOGGER, f"Workspace: '{workspace}', Workflow: '{workflow}', Execution Environment: '{execution_environment}', Job Id: '{job_id}' - Retry Job Id: '{retry_job_id}' was already successful. Hence exiting to forward processing to next in chain.")
|
|
sys.exit(0)
|
|
|
|
_conf = SparkConf()
|
|
_params = {
|
|
"spark.jars.ivy": "/opt/spark/.ivy2/",
|
|
"spark.hadoop.fs.s3a.access.key": secrets.get('S3_ACCESS_KEY'),
|
|
"spark.hadoop.fs.s3a.secret.key": secrets.get('S3_SECRET_KEY'),
|
|
"spark.hadoop.fs.s3a.aws.region": secrets.get("S3_REGION") or "us-west-1",
|
|
"spark.sql.catalog.dremio.warehouse" : secrets.get('LAKEHOUSE_BUCKET'),
|
|
"spark.hadoop.fs.s3a.aws.credentials.provider": "com.amazonaws.auth.DefaultAWSCredentialsProviderChain",
|
|
"spark.hadoop.fs.s3.aws.credentials.provider": "com.amazonaws.auth.DefaultAWSCredentialsProviderChain",
|
|
"spark.sql.catalog.dremio" : "org.apache.iceberg.spark.SparkCatalog",
|
|
"spark.sql.catalog.dremio.type" : "hadoop",
|
|
"spark.hadoop.fs.s3a.impl": "org.apache.hadoop.fs.s3a.S3AFileSystem",
|
|
"spark.hadoop.fs.s3.impl": "org.apache.hadoop.fs.s3a.S3AFileSystem",
|
|
"spark.hadoop.fs.gs.impl": "com.google.cloud.hadoop.fs.gcs.GoogleHadoopFileSystem",
|
|
"spark.sql.extensions": "org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions",
|
|
"spark.driver.extraJavaOptions": "--add-opens=java.base/java.nio=ALL-UNNAMED",
|
|
"spark.executor.extraJavaOptions": "--add-opens=java.base/java.nio=ALL-UNNAMED"
|
|
}
|
|
|
|
if filesystemManager.storage_type == SupportedFilesystemType.AZUREBLOB:
|
|
_params[f"fs.azure.account.auth.type.{_storage_options['account_name']}.dfs.core.windows.net"] = "OAuth"
|
|
_params[f"fs.azure.account.oauth.provider.type.{_storage_options['account_name']}.dfs.core.windows.net"] = "org.apache.hadoop.fs.azurebfs.oauth2.ClientCredsTokenProvider"
|
|
_params[f"fs.azure.account.oauth2.client.id.{_storage_options['account_name']}.dfs.core.windows.net"] = _storage_options['client_id']
|
|
_params[f"fs.azure.account.oauth2.client.secret.{_storage_options['account_name']}.dfs.core.windows.net"] = _storage_options['client_secret']
|
|
_params[f"fs.azure.account.oauth2.client.endpoint.{_storage_options['account_name']}.dfs.core.windows.net"] = f"https://login.microsoftonline.com/{_storage_options['tenant_id']}/oauth2/v2.0/token"
|
|
|
|
|
|
|
|
_conf.setAll(list(_params.items()))
|
|
|
|
spark = SparkSession.builder.appName(workspace).config(conf=_conf).getOrCreate()
|
|
bootstrap_udfs(spark)
|
|
|
|
materialization = Materialization(spark, secrets.get('LAKEHOUSE_BUCKET'), workspace, workflow, job_id, retry_job_id, execution_environment, LOGGER)
|
|
|
|
init_dependency_key="init"
|
|
|
|
|
|
init_end_time=time.time()
|
|
|
|
# %%
|
|
|
|
|
|
ActionsAuditData_start_time=time.time()
|
|
|
|
ActionsAuditData_fail_on_error=""
|
|
try:
|
|
_ActionsAuditData_options = {
|
|
'jdbc':{
|
|
'dbtable': """actionsaudit""",
|
|
'url':secrets.get(''),
|
|
'driver':''
|
|
},
|
|
'kafka' : {
|
|
'kafka.bootstrap.servers' : secrets.get('OCULAR_KAFKA_BOOTSTRAP_SERVERS'),
|
|
'subscribe' : '',
|
|
'startingOffsets' : 'earliest'
|
|
},
|
|
'cobol' : {
|
|
'copybook' : '',
|
|
'encoding' : '',
|
|
'is_text': False,
|
|
'schema_retention_policy' : 'collapse_root'
|
|
}
|
|
}
|
|
|
|
|
|
|
|
_ActionsAuditData_reader = spark.read.format('iceberg')
|
|
|
|
|
|
|
|
|
|
ActionsAuditData_df = _ActionsAuditData_reader.load('dremio.actionsaudit')
|
|
|
|
|
|
ActionsAuditData_df, ActionsAuditData_observer = observe_metrics("ActionsAuditData_df", ActionsAuditData_df)
|
|
|
|
|
|
|
|
ActionsAuditData_df.createOrReplaceTempView('ActionsAuditData_df')
|
|
|
|
|
|
ActionsAuditData_dependency_key="ActionsAuditData"
|
|
|
|
ActionsAuditData_execute_status="SUCCESS"
|
|
except Exception as e:
|
|
ActionsAuditData_error = e
|
|
log_error(LOGGER, f"Component ActionsAuditData Failed", e)
|
|
ActionsAuditData_execute_status="ERROR"
|
|
|
|
raise e
|
|
|
|
finally:
|
|
ActionsAuditData_end_time=time.time()
|
|
|
|
# %%
|
|
|
|
|
|
data_mapper__1_start_time=time.time()
|
|
|
|
data_mapper__1_fail_on_error=""
|
|
try:
|
|
|
|
|
|
|
|
_data_mapper__1_select_clause=ActionsAuditData_df.columns if False else []
|
|
|
|
_data_mapper__1_select_clause.append('''DATE(action_date) AS action_date''')
|
|
|
|
_data_mapper__1_select_clause.append('''sub_category AS service_type''')
|
|
|
|
_data_mapper__1_select_clause.append('''action_count AS action_count''')
|
|
|
|
try:
|
|
data_mapper__1_df=spark.sql(("SELECT " + ', '.join(_data_mapper__1_select_clause) + " FROM ActionsAuditData_df").replace("{job_id}",f"'{job_id}'"))
|
|
except Exception as e:
|
|
data_mapper__1_df = ActionsAuditData_df.limit(0)
|
|
log_info(LOGGER, f"error while mapping the data :{e} " )
|
|
data_mapper__1_df, data_mapper__1_observer = observe_metrics("data_mapper__1_df", data_mapper__1_df)
|
|
|
|
|
|
|
|
data_mapper__1_df.createOrReplaceTempView("data_mapper__1_df")
|
|
|
|
data_mapper__1_dependency_key="data_mapper__1"
|
|
|
|
print(ActionsAuditData_dependency_key)
|
|
|
|
data_mapper__1_execute_status="SUCCESS"
|
|
except Exception as e:
|
|
data_mapper__1_error = e
|
|
log_error(LOGGER, f"Component data_mapper__1 Failed", e)
|
|
data_mapper__1_execute_status="ERROR"
|
|
|
|
raise e
|
|
|
|
finally:
|
|
data_mapper__1_end_time=time.time()
|
|
|
|
# %%
|
|
|
|
|
|
LatestServiceRequests_start_time=time.time()
|
|
|
|
print(data_mapper__1_df.columns)
|
|
LatestServiceRequests_fail_on_error=""
|
|
try:
|
|
try:
|
|
LatestServiceRequests_df = spark.sql("select * from data_mapper__1_df where action_date >= COALESCE((SELECT MAX(DATE(action_date)) FROM dremio.servicemetrics), (SELECT MIN(action_date) FROM data_mapper__1_df))")
|
|
except AnalysisException as e:
|
|
log_info(LOGGER, f"error while filtering data : {e}")
|
|
LatestServiceRequests_df = data_mapper__1_df.limit(0)
|
|
except Exception as e:
|
|
log_info(LOGGER, f"Unexpected error: {e}")
|
|
LatestServiceRequests_df = data_mapper__1_df.limit(0)
|
|
LatestServiceRequests_df, LatestServiceRequests_observer = observe_metrics("LatestServiceRequests_df", LatestServiceRequests_df)
|
|
|
|
|
|
|
|
LatestServiceRequests_df.createOrReplaceTempView('LatestServiceRequests_df')
|
|
|
|
LatestServiceRequests_dependency_key="LatestServiceRequests"
|
|
|
|
LatestServiceRequests_execute_status="SUCCESS"
|
|
except Exception as e:
|
|
LatestServiceRequests_error = e
|
|
log_error(LOGGER, f"Component LatestServiceRequests Failed", e)
|
|
LatestServiceRequests_execute_status="ERROR"
|
|
|
|
raise e
|
|
|
|
finally:
|
|
LatestServiceRequests_end_time=time.time()
|
|
|
|
# %%
|
|
|
|
|
|
aggregate__3_start_time=time.time()
|
|
|
|
aggregate__3_fail_on_error="True"
|
|
try:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
aggregate__3_df = LatestServiceRequests_df.groupBy(
|
|
|
|
"action_date",
|
|
|
|
"service_type"
|
|
).agg(
|
|
|
|
sum('action_count').alias("service_count")
|
|
|
|
)
|
|
aggregate__3_df, aggregate__3_observer = observe_metrics("aggregate__3_df", aggregate__3_df)
|
|
|
|
|
|
|
|
aggregate__3_df.createOrReplaceTempView('aggregate__3_df')
|
|
|
|
aggregate__3_dependency_key="aggregate__3"
|
|
|
|
print(LatestServiceRequests_dependency_key)
|
|
|
|
aggregate__3_execute_status="SUCCESS"
|
|
except Exception as e:
|
|
aggregate__3_error = e
|
|
log_error(LOGGER, f"Component aggregate__3 Failed", e)
|
|
aggregate__3_execute_status="ERROR"
|
|
|
|
raise e
|
|
|
|
finally:
|
|
aggregate__3_end_time=time.time()
|
|
|
|
# %%
|
|
|
|
CheckpointOutput_start_time=time.time()
|
|
|
|
CheckpointOutput_df = aggregate__3_df.localCheckpoint()
|
|
# aggregate__3_df.persist()
|
|
CheckpointOutput_df.createOrReplaceTempView("CheckpointOutput_df")
|
|
|
|
CheckpointOutput_end_time=time.time()
|
|
|
|
CheckpointOutput_dependency_key="CheckpointOutput"
|
|
|
|
print(aggregate__3_dependency_key)
|
|
|
|
|
|
# %%
|
|
|
|
|
|
ServiceRequestMetricsWriter_start_time=time.time()
|
|
|
|
ServiceRequestMetricsWriter_fail_on_error=""
|
|
try:
|
|
|
|
|
|
_ServiceRequestMetricsWriter_options = {
|
|
'jdbc':{
|
|
'dbtable': 'servicemetrics',
|
|
'url':secrets.get(''),
|
|
'driver':'',
|
|
'stringtype': 'unspecified'
|
|
},
|
|
'kafka' : {
|
|
'kafka.bootstrap.servers' : secrets.get('OCULAR_KAFKA_BOOTSTRAP_SERVERS'),
|
|
'topic' : ''
|
|
}
|
|
|
|
|
|
}
|
|
|
|
_CheckpointOutput_df = CheckpointOutput_df
|
|
|
|
_ServiceRequestMetricsWriter_writer = _CheckpointOutput_df.write.format('iceberg').mode('append')
|
|
|
|
|
|
_ServiceRequestMetricsWriter_writer.save('dremio.servicemetrics')
|
|
|
|
|
|
ServiceRequestMetricsWriter_dependency_key="ServiceRequestMetricsWriter"
|
|
|
|
print(CheckpointOutput_dependency_key)
|
|
|
|
ServiceRequestMetricsWriter_execute_status="SUCCESS"
|
|
except Exception as e:
|
|
ServiceRequestMetricsWriter_error = e
|
|
log_error(LOGGER, f"Component ServiceRequestMetricsWriter Failed", e)
|
|
ServiceRequestMetricsWriter_execute_status="ERROR"
|
|
|
|
raise e
|
|
|
|
finally:
|
|
ServiceRequestMetricsWriter_end_time=time.time()
|
|
|
|
# %%
|
|
|
|
finalize_start_time=time.time()
|
|
|
|
metrics = {
|
|
'data': collect_metrics(locals()),
|
|
}
|
|
materialization.materialized_execution_history({'finalize': {'execute_status': 'SUCCESS', 'fail_on_error': 'False', 'execution_order': os.environ.get('EXECUTION_ORDER')}, **metrics['data']})
|
|
log_info(LOGGER, f"Workflow Data metrics: {metrics['data']}")
|
|
|
|
finalize_end_time=time.time()
|
|
|
|
if os.getenv('EXECUTION_ENVIRONMENT'):
|
|
spark.stop() |