soumilshah1995 commented on issue #10725:
URL: https://github.com/apache/hudi/issues/10725#issuecomment-1958213121
Full code
```
try:
import os
import sys
import uuid
import pyspark
import datetime
from pyspark.sql import SparkSession
from pyspark import SparkConf, SparkContext
from faker import Faker
import datetime
from datetime import datetime
import random
import pandas as pd # Import Pandas library for pretty printing
print("Imports loaded ")
except Exception as e:
print("error", e)
os.environ['JAVA_HOME'] =
'/opt/homebrew/Cellar/openjdk@11/11.0.22/libexec/openjdk.jdk/Contents/Home'
HUDI_VERSION = '0.14.0'
SPARK_VERSION = '3.4'
SUBMIT_ARGS = f"--packages
org.apache.hudi:hudi-spark{SPARK_VERSION}-bundle_2.12:{HUDI_VERSION}
pyspark-shell"
os.environ["PYSPARK_SUBMIT_ARGS"] = SUBMIT_ARGS
os.environ['PYSPARK_PYTHON'] = sys.executable
spark = SparkSession.builder \
.config('spark.executor.memory', '4g') \
.config('spark.driver.memory', '4g') \
.config('spark.serializer',
'org.apache.spark.serializer.KryoSerializer') \
.config('spark.sql.extensions',
'org.apache.spark.sql.hudi.HoodieSparkSessionExtension') \
.config('className', 'org.apache.hudi') \
.config('spark.sql.hive.convertMetastoreParquet', 'false') \
.getOrCreate()
df = spark.read.parquet("user_behavior_sample_data.parquet")
df.show()
def write_to_hudi(spark_df,
table_name,
db_name,
method='upsert',
table_type='COPY_ON_WRITE',
recordkey='',
precombine='',
partition_fields='',
metadata_column_stats=""
):
path =
f"file:///Users/soumilshah/IdeaProjects/SparkProject/tem/{db_name}/{table_name}"
hudi_options = {
'hoodie.table.name': table_name,
'hoodie.datasource.write.table.type': table_type,
'hoodie.datasource.write.table.name': table_name,
'hoodie.datasource.write.operation': method,
'hoodie.datasource.write.recordkey.field': recordkey,
'hoodie.datasource.write.precombine.field': precombine,
"hoodie.datasource.write.partitionpath.field": partition_fields,
}
print("\n")
print(path)
print("\n")
spark_df.write.format("hudi"). \
options(**hudi_options). \
mode("append"). \
save(path)
write_to_hudi(
spark_df=df,
db_name="hudidb",
table_name="clicks",
recordkey="UserID,ItemID",
precombine="Timestamp",
partition_fields="",
)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
