Table of contents

Quick Start

importawswrangleraswrimportpandasaspdfromdatetimeimportdatetimedf=pd.DataFrame({"id": [1,2],"value": ["foo","boo"]})# Storing data on Data Lakewr.s3.to_parquet(df=df,path="s3://bucket/dataset/",dataset=True,database="my_db",table="my_table")# Retrieving the data directly from Amazon S3df=wr.s3.read_parquet("s3://bucket/dataset/",dataset=True)# Retrieving the data from Amazon Athenadf=wr.athena.read_sql_query("SELECT * FROM my_table",database="my_db")# Get a Redshift connection from Glue Catalog and retrieving data from Redshift Spectrumcon=wr.redshift.connect("my-glue-connection")df=wr.redshift.read_sql_query("SELECT * FROM external_schema.my_table",con=con)con.close()# Amazon Timestream Writedf=pd.DataFrame({"time": [datetime.now(),datetime.now()],"my_dimension": ["foo","boo"],"measure": [1.0,1.1],})rejected_records=wr.timestream.write(df,database="sampleDB",table="sampleTable",time_col="time",measure_col="measure",dimensions_cols=["my_dimension"],)# Amazon Timestream Querywr.timestream.query("""SELECT time, measure_value::double, my_dimensionFROM "sampleDB"."sampleTable" ORDER BY time DESC LIMIT 3""")

At scale

Read The Docs

Getting Help

Logging

importlogginglogging.basicConfig(level=logging.INFO,format="[%(name)s][%(funcName)s] %(message)s")logging.getLogger("awswrangler").setLevel(logging.DEBUG)logging.getLogger("botocore.credentials").setLevel(logging.CRITICAL)

importlogginglogging.getLogger("awswrangler").setLevel(logging.DEBUG)