soumilshah1995 commented on issue #10110:
URL: https://github.com/apache/hudi/issues/10110#issuecomment-1814400817
Here is Full code for references
```
from pyspark.sql import SparkSession
from pyspark.sql.types import StructType, StructField, StringType,
TimestampType, FloatType
from datetime import datetime
HUDI_VERSION = '1.0.0-beta1'
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 session
spark = SparkSession.builder \
.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()
data = [
[datetime.strptime('2023-09-20 03:58:59', '%Y-%m-%d %H:%M:%S'),
'334e26e9-8355-45cc-97c6-c31daf0df330', 'rider-A', 'driver-K', 19.10,
'san_francisco'],
[datetime.strptime('2023-09-19 08:46:34', '%Y-%m-%d %H:%M:%S'),
'e96c4396-3fad-413a-a942-4cb36106d721', 'rider-C', 'driver-M', 27.70,
'san_francisco'],
[datetime.strptime('2023-09-18 17:45:31', '%Y-%m-%d %H:%M:%S'),
'9909a8b1-2d15-4d3d-8ec9-efc48c536a00', 'rider-D', 'driver-L', 33.90,
'san_francisco'],
[datetime.strptime('2023-09-22 13:12:56', '%Y-%m-%d %H:%M:%S'),
'1dced545-862b-4ceb-8b43-d2a568f6616b', 'rider-E', 'driver-O', 93.50,
'san_francisco'],
[datetime.strptime('2023-09-24 06:15:45', '%Y-%m-%d %H:%M:%S'),
'e3cf430c-889d-4015-bc98-59bdce1e530c', 'rider-F', 'driver-P', 34.15,
'sao_paulo'],
[datetime.strptime('2023-09-22 15:21:36', '%Y-%m-%d %H:%M:%S'),
'7a84095f-737f-40bc-b62f-6b69664712d2', 'rider-G', 'driver-Q', 43.40,
'sao_paulo'],
[datetime.strptime('2023-09-20 12:35:45', '%Y-%m-%d %H:%M:%S'),
'3eeb61f7-c2b0-4636-99bd-5d7a5a1d2c04', 'rider-I', 'driver-S', 41.06,
'chennai'],
[datetime.strptime('2023-09-19 05:34:56', '%Y-%m-%d %H:%M:%S'),
'c8abbe79-8d89-47ea-b4ce-4d224bae5bfa', 'rider-J', 'driver-T', 17.85, 'chennai']
]
# Define schema for the DataFrame
schema = StructType([
StructField("ts", TimestampType(), True),
StructField("transaction_id", StringType(), True),
StructField("rider", StringType(), True),
StructField("driver", StringType(), True),
StructField("price", FloatType(), True),
StructField("location", StringType(), True),
])
# Create Spark DataFrame
df = spark.createDataFrame(data, schema=schema)
# Show the DataFrame
df.show()
db_name = "hudidb"
table_name = "hudi_table_func_index"
path = f"file:///Users/soumilnitinshah/Downloads/{db_name}/{table_name}" #
Updated path
method = 'upsert'
table_type = "COPY_ON_WRITE"
recordkey = "transaction_id"
precombine = "ts"
partition_fields = "location"
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.table.metadata.enable": "true",
"hoodie.datasource.write.partitionpath.field": partition_fields
}
df.write.format("hudi"). \
options(**hudi_options). \
mode("append"). \
save(path)
# path =
'file:///Users/soumilnitinshah/Downloads/hudidb/hudi_table_func_index'
#
spark.read.format("hudi").load(path).createOrReplaceTempView("hudi_table_func_index")
functional_index_sql = """
CREATE INDEX IF NOT EXISTS ts_hour
ON hudi_table_func_index
USING column_stats(ts)
"""
spark.sql(functional_index_sql)
```
--
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]
