daanalytics

SELECT GET_DLL( 'SCHEMA','"<Database Name>"."<Schema"Name>');

daanalytics

CREATE  OR REPLACE STAGE <stage name> URL = 's3://<bucket_name>/path/' CREDENTIALS=(AWS_KEY_ID='xxxxxxx'AWS_SECRET_KEY='xxxxxxxxxxxxxx');

daanalytics

LIST @<Stage Name>
;

daanalytics

CREATE OR REPLACE FILE FORMAT <Database>.<Schema>.<File Format Name> 
TYPE = 'CSV' 
COMPRESSION = 'AUTO' 
FIELD_DELIMITER = '|' 
RECORD_DELIMITER = '\n' 
SKIP_HEADER = 1 
FIELD_OPTIONALLY_ENCLOSED_BY = '\042' 
TRIM_SPACE = FALSE 
ERROR_ON_COLUMN_COUNT_MISMATCH = TRUE 
ESCAPE = 'NONE' 

daanalytics

COPY INTO <Table Name> FROM @<Stage Name>
FILES = ( '<File Name>' )
FILE_FORMAT = ( FORMAT_NAME = <Format Name> )
;

daanalytics

COPY INTO <Table Name> 
FROM (
SELECT t.$1
,      t.$2
,      t.$3      
,      TO_NUMBER(REPLACE(t.$4,',','.'),8,2)
,      t.$5
,      TO_DATE(t.$6, 'DD-MM-YY') 
,      t.$7
FROM @<Stage Name>/<File Name> t)

daanalytics

{"username":"<user_name>","key":"<API token>"}

daanalytics

{"secrets":
       {
        "account"   : "<account",
        "user"      : "<user>",
        "warehouse" : "<warehouse>",
        "role"      : "<role>",
        "database"  : "<database>",
        "schema"    : "<schema>",
        "password"  : "<password>"
      },

daanalytics

# Setting the environment
import os
from kaggle.api.kaggle_api_extended import KaggleApi

# Setting the variabeles
os.environ['KAGGLE_USERNAME'] = "<kaggle-username>"
os.environ['KAGGLE_KEY'] = "<kaggle-API-token>"

# Connecting to Kaggle
api = KaggleApi()

daanalytics

# Setting up connection to Kaggle and Snowflake 
conn_location = '<location Credential file>'

connect = json.loads(open(str(conn_location+'/<Credential file>')).read())

#Kaggle variables referencing kaggle in the Credential file
os.environ['KAGGLE_USERNAME']   = connect['kaggle']['kaggle-username']
os.environ['KAGGLE_KEY']        = connect['kaggle']['kaggle-API-token']

# Connect to Kaggle