wrangl

gistfile1.txt

import awswrangler as wr
import pandas as pd

df = pd.DataFrame({"id": [1, 2], "value": ["foo1", "boo1"]})
print(df)
bucketPath = 's3://press0-test/awswrangler/'
database="awswrangler"
table="awswrangler_table1"

# Storing data on Data Lake
wr.s3.to_parquet(
    df=df,
    path=bucketPath,
    dataset=True,
    database=database,
    table=table
)

# Retrieving the data directly from Amazon S3
df = wr.s3.read_parquet(bucketPath, dataset=True)
print(df)

# Retrieving the data from Amazon Athena
df = wr.athena.read_sql_query("SELECT * FROM " + table, database=database)
print(df)