官术网_书友最值得收藏!

Running the application

To run the application the process is nearly identical to Chapter 2's sample application. To iterate more quickly, the debug configuration automatically passes in the included sampledata.csv file as a command-line parameter:

Going forward, due to the increasing complexity of the applications, all sample applications will have this preset:

  1. To run the training on the command line as we did in Chapter 1, Getting Started with Machine Learning and ML.NET, simply pass in the following command (assuming you are using the included sample dataset):
PS chapter03\bin\Debug\netcoreapp3.0> .\chapter03.exe train ..\..\..\Data\sampledata.csv 
Loss Function: 324.71
Mean Absolute Error: 12.68
Mean Squared Error: 324.71
RSquared: 0.14
Root Mean Squared Error: 18.02

Note the expanded output to include several metric data pointswe will go through what each one of these means at the end of this chapter.

  1. After training the model, build a sample JSON file and save it as input.json:
{
"durationInMonths": 0.0,
"isMarried": 0,
"bsDegree": 1,
"msDegree": 1,
"yearsExperience": 2,
"ageAtHire": 29,
"hasKids": 0,
"withinMonthOfVesting": 0,
"deskDecorations": 1,
"longCommute": 1
}
  1. To run the model with this file, simply pass in the filename to the built application and the predicted output will show:
PS chapter03\bin\Debug\netcoreapp3.0> .\chapter03.exe predict input.json 
Based on input json:
{
"durationInMonths": 0.0,
"isMarried": 0,
"bsDegree": 1,
"msDegree": 1,
"yearsExperience": 2,
"ageAtHire": 29,
"hasKids": 0,
"withinMonthOfVesting": 0,
"deskDecorations": 1,
"longCommute": 1
}

The employee is predicted to work 22.82 months

Feel free to modify the values and see how the prediction changes based on the dataset that the model was trained on.  A few areas of experimentation from this point might be to do the following:

  • Add some additional features based on your own experience.
  • Modify sampledata.csv to include your team's experience.
  • Modify the sample application to have a GUI to make running predicts easier.
主站蜘蛛池模板: 冕宁县| 丰台区| 凤台县| 美姑县| 周口市| 梅河口市| 颍上县| 彩票| 若尔盖县| 满洲里市| 万山特区| 芜湖市| 巨鹿县| 饶平县| 娄烦县| 屏南县| 乃东县| 通化市| 白河县| 周宁县| 东乡| 枝江市| 林周县| 舟山市| 城口县| 阿克苏市| 多伦县| 大城县| 饶河县| 扬中市| 宁波市| 双江| 吐鲁番市| 凤翔县| 普兰县| 博罗县| 桓台县| 句容市| 万全县| 镇宁| 日土县|