I am downloading 2 csv files from my Azure Data Lake storage(gen 2). Then merging them together and uploading it in parquet format to the same storage account, but to different folder. I want to upload the summary dataframe in parquet format to my storage account using a FuctionApp in VS Code. The code runs perfectly locally, but the functionapp gives me '500-internal server error'. There is an issue with the Pyarrow engine that I use for the to_parquet method.Azure does not seem to support this engine.
import pandas as pd
from azure.storage.filedatalake import DataLakeServiceClient
import azure.functions as func
from io import StringIO
def main(req: func.HttpRequest) -> func.HttpResponse:
STORAGEACCOUNTURL= 'https://storage_acc_name.dfs.core.windows.net/'
STORAGEACCOUNTKEY= 'Key'
LOCALFILENAME= ['file1', 'file2']
file1 = pd.DataFrame()
file2 = pd.DataFrame()
service_client = DataLakeServiceClient(account_url=STORAGEACCOUNTURL, credential=STORAGEACCOUNTKEY)
adl_client_instance = service_client.get_file_system_client(file_system="raw")
directory_client = adl_client_instance.get_directory_client("raw")
for i in LOCALFILENAME:
if i == 'file1.csv':
file_client = adl_client_instance.get_file_client(i)
adl_data = file_client.download_file()
byte1 = adl_data.readall()
s=str(byte1,'utf-8')
file1 = pd.read_csv(StringIO(s))
if i == 'file2.csv':
file_client = adl_client_instance.get_file_client(i)
adl_data = file_client.download_file()
byte2 = adl_data.readall()
s=str(byte2,'utf-8')
file2 = pd.read_csv(StringIO(s))
summary = pd.merge(left=file1, right=file2, on='key', how='inner')
service_client = DataLakeServiceClient(account_url=STORAGEACCOUNTURL, credential=STORAGEACCOUNTKEY)
file_system_client = service_client.get_file_system_client(file_system="output")
directory_client = file_system_client.get_directory_client("output")
file_client = directory_client.create_file("output.parquet")
file_contents = pd.DataFrame(summary).to_parquet()
file_client.append_data(data=file_contents, offset=0, length=len(file_contents))
file_client.flush_data(len(file_contents))
return("This HTTP triggered function executed successfully.")
if __name__ == '__main__':
main("name")
maybe you can use pyspark
df_MF=spark_session.createDataFrame(df)
# now you get spark df,you can save it use spark save it
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.