0

加载镶木地板文件并收到以下错误。

我的 parquet 文件包含 5,128,680 行,它仅加载 5,100,000 行,而不加载 28,680 条记录和代码,如下所示:

错误 :

Response 
{
  "errorMessage": "Length mismatch: Expected axis has 28680 elements, new values have 100000 elements",
  "errorType": "ValueError",


import json 
import os
import pg8000
import boto3
import awswrangler as wr
import pandas as pd
import numpy as np
import pyarrow as pa

def lambda_handler(event, context):
    
    ## connect to RDS-ODS
    con = pg8000.connect(user=credential['username'], password=credential['password'], host=credential['host'], database=credential['dbname'])
    cursor = con.cursor()    
    dfs=wr.s3.read_parquet(path='s3://demobucket/sample_data_output_50lacks.parquet',chunked=100000)
    for wrdfs in dfs:
        wr.postgresql.to_sql(df=wrdfs,table="demo_test",schema="public",con=con)
    con.close()
    
    return {
        'statusCode': 200,
        'body': json.dumps('Parquet file reading')
    } 
4

0 回答 0