petersen-poul

{
    "name": "Lat/Long Distance between a pair of points",
    "description": "Extends a dataset with the distance in meters between pairs of lat/long fields.",
    "inputs": [
        {
            "name": "dataset-in",
            "type": "dataset-id",
            "description": "Dataset for extending with distance calculation."
        },
        {

petersen-poul

{
  "name": "Apply Date Format by Field Name",
  "description": "Allows applying a custom date format to a source by matching field names",
  "inputs": [
    { 
      "name": "source",
      "description": "Source to update",
      "type": "source-id"
    }
  ],

petersen-poul

{
  "name": "One Click Cluster Labels",
  "description": "Given a cluster as input, assigns the cluster label to every instance in the dataset used to train the cluster.",
  "inputs": [
    { 
      "name": "cluster",
      "description": "Cluster to use for labeling",
      "type": "cluster-id"
    }
  ],

petersen-poul

{
  "name": "Assign Field Types by Field Name",
  "description": "Sometimes, the automatic field detection does not assign field types correctly. This is especially a problem with fields that have a lot of missing values since the detection process only takes a peek at the data to determine if a field should be numeric, categorical, etc. This script allows you to alter the field types for a source based on the name of each field. Just put a partial match for the name in the list for the type you want to assign, and it will change all the fields whose name contain that string.",
  "inputs": [
    { 
      "name": "source",
      "description": "Source to update.",
      "type": "source-id"
    },
    {

petersen-poul

{
    "name": "1-Click Dataset Prefer-it-All",
    "description": "Given a source, creates a 1-click dataset and then marks all non-preferred field as preferred.",
    "inputs": [
        {
            "name": "source",
            "type": "source-id",
            "description": "Source to process."
        }
    ],

petersen-poul

{
    "name": "Minimum Scale for Cluster Class Purity",
    "description": "Given a dataset and a categorical field, finds the minimum scale required to create class purity in the cluster with k = number of classes.",
    "inputs": [
        {
            "name": "dataset",
            "type": "dataset-id",
            "description": "Dataset to analyze."
        },
        {

petersen-poul

{
    "name": "Simple JSON key/val extraction",
    "description": "Given a dataset field containing JSON documents and a key, this WhizzML script creates a new feature with the JSON values. This is a hack and *NOT* a valid JSON parser",
    "inputs": [
        {
            "name": "dataset-in",
            "type": "dataset-id",
            "description": "Dataset to transform by extracting JSON values."
        },
        {

petersen-poul

{
    "name": "JSON key/val extraction",
    "description": "Given a dataset field containing JSON documents and a key, this WhizzML script creates a new feature with the JSON values. This is a hack and *NOT* a valid JSON parser",
    "inputs": [
        {
            "name": "dataset-in",
            "type": "dataset-id",
            "description": "Dataset to transform by extracting JSON values."
        },
        {

petersen-poul

{
    "name": "Redfin Deals",
    "description": "Given a source of sold homes and listed homes, builds a model to predict the price and then shows possible deals.",
    "inputs": [
        {
            "name": "redfin-sold-source",
            "type": "source-id",
            "description": "Source of sold homes from Redfin."
        },
        {

petersen-poul

{
    "name": "Lat/Long Distance from a reference point",
    "description": "Extends a dataset with the distance in meters between lat/long fields and a reference point.",
    "inputs": [
        {
            "name": "dataset-in",
            "type": "dataset-id",
            "description": "Dataset for extending with distance calculation."
        },
        {