CREATE ML_ENGINE
statement:
CREATE MODEL
statement to create the NeuralForecast model in MindsDB.
USING
clause at the end.
The frequency
parameter informs the model about the expected time difference between each measurement (supported values here). And the train_time
parameter defines the training time - it defaults to 1, and lower values will reduce trainig time linearly by reducing the number of searches allowed for the best configuration by AutoNHITS. You can also define exogenous_vars
as a parameter in the USING
clause - these are complementary variables in the table that may improve forecast accuracy.
historical_expenditures
table stores monthly expenditure data for various categories, such as food
, clothing
, industry
, and more.
Let’s create a model table to predict the expenditures:
CREATE MODEL
statement creates, trains, and deploys the model. Here, we predict the expenditure
column values. As it is a time series model, we order the data by the month
column. Additionally, we group data by the category
column - the predictions are made for each group independently (here, for each category).
Next, we define the WINDOW
and HORIZON
clauses. The WINDOW
clause specifies the number of rows we look back at (here, we look back at sets of 12 rows). And the HORIZON
clause defines for how many rows the predictions are made (here, for the next 3 rows).
CREATE MODEL
statement to learn more.ENGINE
parameter in the USING
clause specifies the ML engine used to make predictions.
We can check the training status with the following query:
complete
, the behavior is the same as with any other AI table – you can query for batch predictions by joining it with a data table:
historical_expenditures
table is used to make batch predictions. Upon joining the quarterly_expenditure_forecaster
model with the historical_expenditures
table, we get predictions for the next quarter as defined by the HORIZON 3
clause.
Please note that the output month
column contains both the date and timestamp. This format is used by default, as the timestamp is required when dealing with the hourly frequency of data.
MindsDB provides the LATEST
keyword that marks the latest training data point. In the WHERE
clause, we specify the month > LATEST
condition to ensure the predictions are made for data after the latest training data point.
Let’s consider our quarterly_expenditure_forecaster
model. We train the model using data until the third quarter of 2017, and the predictions come for the fourth quarter of 2017 (as defined by HORIZON 3
).
food
rises in October 2017, it may be more likely that spending on cafes
also rises in October 2017. Hierarchical reconciliation can account for this shared information.
Here is how we can create a model: