MindSphere CLI: mdsp trend-prediction Command


mdsp trend-prediction


mdsp trend-prediction --help

Alternative form:

mc trend-prediction

(The CLI was using mc as default command name in older versions)


perform trend prediction (linear/polynomial) @


Parameter list:

Usage: mc trend-prediction|tp [options]

perform trend prediction (linear/polynomial) @

  -f, --file                                       timeseries file (default: "timeseries-sample.mdsp.json")
  -m, --mode [train|predict|trainandpredict|list|read|delete]  mode see @ Additional Documentation (default: "list")
  -o, --output                                         output variables
  -i, --input                                           input variables (comma separated)
  -e, --modelid                                       modelid of the stored model for prediction
  -r, --predict                                       regression parameters for prediction (comma separated)
  -c, --predictfile                               regression parameters for prediction as timeseries
  -d, --degree [degree]                                        degree for linear / polynomial regression  (default: "1")
  -y, --retry                                          retry attempts before giving up (default: "3")
  -p, --passkey                                       passkey
  -v, --verbose                                                verbose output
  -h, --help                                                   display help for command


Here are some examples of how to use the mdsp trend-prediction command:


    mdsp trend-prediction --mode list 				 lists all trend prediction models
    mdsp trend-prediction --mode get --modelid 12345..ef 		 retrieves the trend prediction model from the mindsphere
    mdsp trend-prediction --mode delete --modelid 12345..ef 	 deletes the trend prediction model from the mindsphere
    mdsp tp --mode trendandpredict 				 training and prediction in one single step (see parameters below)

    mdsp tp --mode train -f data.json -i "temp,vibration" -o "quality" -d 2 		   trains quadratic fit function for f(temp, vibration) = quality 
    mdsp tp --mode predict --modelid 12345..ef -i "temp,vibration" -o "quality" -p "30,0.01" predict the quality with temp=30, vibration=0.01 using trained model

  Additional Documentation:


See MindSphere API documentation for more information about MindSphere APIs.

The content of the community tools and libraries documentation pages is licensed under the MIT License.
Siemens API Notice applies.
Back to top