{"id":660,"date":"2018-04-27T03:49:45","date_gmt":"2018-04-27T03:49:45","guid":{"rendered":"http:\/\/kusuaks7\/?p=265"},"modified":"2025-06-30T11:30:27","modified_gmt":"2025-06-30T11:30:27","slug":"the-journey-of-a-machine-learning-model-from-building-to-retraining","status":"publish","type":"post","link":"https:\/\/www.experfy.com\/blog\/ai-ml\/the-journey-of-a-machine-learning-model-from-building-to-retraining\/","title":{"rendered":"The Journey of a Machine Learning model from Building to Retraining"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tReady to learn Machine Learning? Browse courses<\/a>\u00a0like\u00a0Machine Learning Foundations: Supervised Learning<\/a> developed by industry thought leaders and Experfy in Harvard Innovation Lab.<\/em><\/strong>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Update:\u00a0<\/em><\/strong>IBM Data Science Experience is now<\/em>\u00a0IBM Watson Studio.\u00a0<\/em><\/strong>This post is an excerpt from our\u00a0solution tutorial\u00a0that walks you through the process of building a predictive machine learning model, deploying it as an API to be used in applications, testing the model and retraining the model with feedback data. All of this happening in an integrated and unified self-service experience on IBM Cloud.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

In this post, the famous\u00a0Iris flower data set<\/strong>\u00a0is used for creating a machine learning model to classify species of flowers.<\/p>\n

In the terminology of machine learning, classification is considered an instance of supervised learning, i.e. learning where a training set of correctly identified observations is available.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Import data to a\u00a0project<\/strong><\/h3><\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

A project is how you organize your resources to achieve a particular goal within Watson Data Platform. Your project resources can include data, collaborators, and analytic tools like Jupyter notebooks and machine learning models.<\/p>\n

You can create a project to add data and open a data asset in the data refiner for cleansing and shaping your data.<\/p>\n

Create a project:<\/strong><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
    \n \t
  1. Go to the\u00a0IBM\u00ae Cloud catalog<\/a>\u00a0and select\u00a0Watson Studio<\/a>\u00a0under the\u00a0Watson section.\u00a0Create<\/strong>\u00a0the service. Click on the\u00a0Get Started<\/strong>\u00a0button to launch the\u00a0Watson Studio\u00a0<\/strong>dashboard.<\/li>\n<\/ol>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t

    2. Create a\u00a0New Project<\/strong>\u00a0> Select\u00a0Complete<\/strong>. Click\u00a0OK<\/strong>. Add a name say\u00a0iris_project<\/code>\u00a0and optional description for the project.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t

    3. Leave the\u00a0Restrict who can be a collaborator<\/strong>\u00a0checkbox unchecked as there\u2019s no confidential data.<\/p>\n

    4. Under\u00a0Define Storage<\/strong>, Click on\u00a0Add<\/strong>\u00a0and choose an existing object storage service or create a new one (Select\u00a0Lite<\/strong>\u00a0plan > Create). Hit\u00a0Refresh<\/strong>\u00a0to see the created service.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t

    5. Click\u00a0Create<\/strong>. Your new project opens and you can start adding resources to it.<\/p>\n

    Import data:<\/strong><\/p>\n

    As mentioned earlier, you will be using the\u00a0Iris data set<\/strong>. The Iris dataset was used in R.A. Fisher\u2019s classic 1936 paper,\u00a0The Use of Multiple Measurements in Taxonomic Problems, and can also be found on the\u00a0UCI Machine Learning Repository<\/a>. This small dataset is often used for testing out machine learning algorithms and visualizations. The aim is to classify Iris flowers among three species (Setosa, Versicolor or Virginica) from measurements of length and width of sepals and petals. The iris data set contains 3 classes of 50 instances each, where each class refers to a type of iris plant.<\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t

    Download<\/strong>\u00a0iris_initial.csv<\/a>\u00a0which consists of 40 instances of each class. You will use the rest 10 instances of each class to re-train your model.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t
      \n \t
    1. Under\u00a0Assets<\/strong>\u00a0in your project, click the\u00a0Find and Add Data<\/strong>\u00a0icon<\/li>\n<\/ol>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t\t\t\t\t

      2. Under\u00a0Load<\/strong>, click on\u00a0browse<\/strong>\u00a0and upload the downloaded\u00a0iris_initial.csv<\/code>.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

      \n\t\t\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t\t\t\t\t

      3. Once added, you should see\u00a0iris_initial.csv<\/code>\u00a0in the\u00a0Data assets<\/strong>\u00a0section of the project. Click on the name to see the contents of the data set.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

      \n\t\t\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t

      Build a machine learning\u00a0model<\/strong><\/h3>\n<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t\t
      \n\t\t\t
      \n\t\t\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t\t\t\t\t
        \n \t
      1. Back in the\u00a0Assets<\/strong>\u00a0overview, under\u00a0Models<\/strong>\u00a0click on\u00a0New model<\/strong>. In the dialog, add\u00a0iris-model<\/strong>\u00a0as name and an optional description.<\/li>\n \t
      2. Under\u00a0Machine Learning Service<\/strong>\u00a0section, click on\u00a0Associate a Machine Learning service instance<\/strong>\u00a0to bind a machine learning service (Lite<\/strong>\u00a0plan) to your project. Click\u00a0Reload<\/strong>.<\/li>\n<\/ol>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
        \n\t\t\t\t\t\t
        \n\t\t\t\t\t
        \n\t\t\t
        \n\t\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
        \n\t\t\t\t\t\t
        \n\t\t\t\t\t
        \n\t\t\t
        \n\t\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t\t\t

        3.Under\u00a0Spark Service<\/strong>\u00a0section, click on\u00a0Associate an IBM Analytics for Apache Spark instance<\/strong>\u00a0to bind a Apache Spark service (Lite<\/strong>\u00a0plan) to your project. Click\u00a0Reload<\/strong>.<\/p>\n

        4. Select\u00a0Model builder<\/strong>\u00a0as your model type and\u00a0Manual<\/strong>\u00a0to manually create a model. Click\u00a0Create<\/strong>.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

        \n\t\t\t\t\t\t
        \n\t\t\t\t\t
        \n\t\t\t
        \n\t\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t\t\t

        For the automatic method, you rely on automatic data preparation (ADP) completely. For the manual method, in addition to some functions that are handled by the ADP transformer, you can add and configure your own estimators, which are the algorithms used in the analysis.<\/p>\n

        5. On the next page, select\u00a0iris_initial.csv<\/code>\u00a0as your data set and click\u00a0Next<\/strong>.<\/p>\n

        6. On the\u00a0Select a technique<\/strong>\u00a0page, based on the data set added, Label columns and feature columns are pre-populated. Select\u00a0species (String)<\/strong>\u00a0as your\u00a0Label Col<\/strong>\u00a0and\u00a0petal_length (Decimal)<\/strong>\u00a0and\u00a0petal_width (Decimal)<\/strong>\u00a0as your\u00a0Feature columns<\/strong>.<\/p>\n

        7. Choose\u00a0Multiclass Classification<\/strong>\u00a0as your suggested technique.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

        \n\t\t\t\t\t\t
        \n\t\t\t\t\t
        \n\t\t\t
        \n\t\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
        \n\t\t\t\t\t\t
        \n\t\t\t\t\t
        \n\t\t\t
        \n\t\t\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t\t\t

        8. For\u00a0Validation Split<\/strong>\u00a0configure the following setting:<\/p>\n\n