predict_crnn

This document has been machine translated.

Apply a trained CRNN model to perform prediction.

The execution method uses JSON-RPC v2.0.

Example request

To execute prediction by CRNN model, specify predict_crnn as method in the parameter of prov.process of the Provenance API.

An example request for JSON-RPC is as follows

{
  "jsonrpc": "2.0",
  "method": "prov.process",
  "params": {
    "method": "predict_crnn",
    "params": {
      "output_ddc": "ddc:result",
      "model_ddc": "ddc:model",
      "input_ddc": "ddc:test_data",
      "start_datetime": "2020-07-20 00:00:00+09",
      "end_datetime": "2020-07-24 23:59:59+09",
      "train_period": "1 days",
      "crnn_param_json": "{}",
      "no_exec": true
    },
  },
  "id": "occurrence_jsonrpc_id"
}

Parameters

The following parameters can be specified for train_crnn.

Parameter name	Data type	Contents	Default value
output_ddc	string	output ddc name	mandatory
output_mode	string	output mode (overwrite, append, or error)	error
model_ddc	string	model ddc name	mandatory
input_ddc	string	input ddc name	mandatory
start_datetime	string	prediction start date and time	mandatory
end_datetime	string	prediciton end date and time	mandatory
train_period	string	data period used for prediction	mandatory
crnn_param_json	string	CRNN parameters	mandatory
no_exec	boolean	execute asynchronously	false

Set crnn_param_json to the same value you specified when training the model.

Input data

The ddc specified in model_ddc should have the following schema: ## Input data Normally this should be the same ddc output by CRNN model training (train_crnn).

column name	contents	remarks
data_table	name of training data table	real table name will be recorded instead of ddc
meshcode	measurement point id
target_column	name of column for prediction
prediction_time	time to predict
crnn_param_json	CRNN parameters
cnn_model_path	CNN model file name
lstm_model_path	LSTM model file name

The ddc specified in input_ddc must have the following schema.

column name	contents	remarks
start_datetime	start time	required column for event table
end_datetime	end time	required column in event table
(measurement point id)	id representing the measurement point
(attribute 1)	any attribute value (numeric type)
(attribute 2)	any attribute value (numeric type)
(...)	any attribute value (numeric type)

Output data

The schema of ddc to be output to output_ddc is as follows.

column name	content	remarks
start_datetime	start time
end_datetime	end time
location	location information
value	prediction result	for classification prediction it will be a number between 0, 1, ...

Return value

Output ddc information