Suggest Edits
Connectors
.Configure Connector
to open the “New Connector” modal.fraud_connector
).
ii. Choose your data source:
ORGNAME-ACCOUNT_NAME
. Find your account details.USAGE
privileges. If you followed Step 0, it will be KUMO_DB
.USAGE
privileges.USAGE
and SELECT
privileges, and CREATE TABLE
for writing back predictions. If you followed Step 0, it will be FRAUD
.s3://kumo-public-datasets/credit_card_fraud/
.Validate
button to see all files within the directory.Done
to save the connector.
Tables
.Add Table
.fraud_connector
).CC_NUM
with Type = ID
MERCHANT
with Type = ID
CC_NUM
and MERCHANT
to ID
, because they are foreign keys into other tables. Set TRANS_NUM
to be the Primary Key, with Type = ID
as well. Set TRANS_DATE_TRANS_TIME
as the Create Date.
TRANS_NUM
to ID because it is a foreign key into the TRANSACTIONS
table. Set REPORT_TIME
as the Create Date.
Save
to save each table.Graphs
.Create Graph
in the top right-hand corner.
ii. Provide Graph Details:
fraud_graph
).TRANSACTIONS
, CUSTOMERS
, FRAUD_REPORTS
, and MERCHANTS
tables by checking the respective boxes.Next
button on the top right-hand corner.CC_NUM
in CUSTOMERS
is linked to CC_NUM
in TRANSACTIONS
.MERCHANT
in MERCHANTS
is linked to MERCHANT
in TRANSACTIONS
.TRANS_NUM
in FRAUD_REPORTS
is linked to TRANS_NUM
in TRANSACTIONS
.Confirm Group
button for both column groups.Complete Graph Creation
button on the top right-hand corner.Write Predictive Query
in the top right-hand corner.cc_fraud
).
ii. Select the graph you created earlier from the drop-down menu.
iii. Specify PQuery:
Next
to specify the Model Planner.
100
and tune_metric to auprc
.
Save and Train
.
Inspecting the holdout set either via the Download button or via the shown SQL command within Snowflake for SPCS deployments .