mindsdb/mindsdb:lightwood
Docker image. Learn more here.AI Table
or a predictor
. By querying the model, we’ll predict the
probability of churn for new customers of a telecoms company.
Install MindsDB locally via Docker or Docker Desktop.
Let’s get started.
example_db.demo_data.customer_churn
table).files.churn
file as a table. Make sure you replace it with
example_db.demo_data.customer_churn
if you connect the data as a database.files.churn
table.
Column | Description | Data Type | Usage |
---|---|---|---|
CustomerId | The identification number of a customer. | character varying | Feature |
Gender | The gender of a customer. | character varying | Feature |
SeniorCitizen | It indicates whether the customer is a senior citizen (1 ) or not (0 ). | integer | Feature |
Partner | It indicates whether the customer has a partner (Yes ) or not (No ). | character varying | Feature |
Dependents | It indicates whether the customer has dependents (Yes ) or not (No ). | character varying | Feature |
Tenure | Number of months the customer has been staying with the company. | integer | Feature |
PhoneService | It indicates whether the customer has a phone service (Yes ) or not (No ). | character varying | Feature |
MultipleLines | It indicates whether the customer has multiple lines (Yes ) or not (No , No phone service ). | character varying | Feature |
InternetService | Customer’s internet service provider (DSL , Fiber optic , No ). | character varying | Feature |
OnlineSecurity | It indicates whether the customer has online security (Yes ) or not (No , No internet service ). | character varying | Feature |
OnlineBackup | It indicates whether the customer has online backup (Yes ) or not (No , No internet service ). | character varying | Feature |
DeviceProtection | It indicates whether the customer has device protection (Yes ) or not (No , No internet service ). | character varying | Feature |
TechSupport | It indicates whether the customer has tech support (Yes ) or not (No , No internet service ). | character varying | Feature |
StreamingTv | It indicates whether the customer has streaming TV (Yes ) or not (No , No internet service ). | character varying | Feature |
StreamingMovies | It indicates whether the customer has streaming movies (Yes ) or not (No , No internet service ). | character varying | Feature |
Contract | The contract term of the customer (Month-to-month , One year , Two year ). | character varying | Feature |
PaperlessBilling | It indicates whether the customer has paperless billing (Yes ) or not (No ). | character varying | Feature |
PaymentMethod | Customer’s payment method (Electronic check , Mailed check , Bank transfer (automatic) , Credit card (automatic) ). | character varying | Feature |
MonthlyCharges | The monthly charge amount. | money | Feature |
TotalCharges | The total amount charged to the customer. | money | Feature |
Churn | It indicates whether the customer churned (Yes ) or not (No ). | character varying | Label |
CREATE MODEL
statement and specify the
input columns used to train FROM
(features) and what we want to
PREDICT
(labels).
Churn
column, whose
values will be predicted.
complete
, we can start making
predictions!
SELECT
statement lets you make predictions for the label
based on the chosen features.
WHERE
clause. Let’s run another query.
JOIN
.