Example sample transform on ISO 4217 Currency Codes

examples

Files Size Format Created Updated License Source
1 79kB csv odc-pddl SIX Interbank Clearing Ltd (on behalf of ISO)
This is an example Data Package to demonstrate how data transforms works. In this example, we explain how getting a sample from a dataset can be done before data package gets rendered in showcase page. It assumes publisher is already familiar with Data Packages and views specifications (views read more
Download

Data Files

codes-all  

Field information

Field Name Order Type (Format) Description
Entity 1 string Country or region name
Currency 2 string Name of the currency
AlphabeticCode 3 string 3 digit alphabetic code for the currency
NumericCode 4 number 3 digit numeric code
MinorUnit 5 string
WithdrawalDate 6 string Date currency withdrawn (values can be ranges or months

Read me

This is an example Data Package to demonstrate how data transforms works. In this example, we explain how getting a sample from a dataset can be done before data package gets rendered in showcase page. It assumes publisher is already familiar with Data Packages and views specifications (views property in Data Package specifications).

Getting sample data

On the top of this page, you can find a table that displays filtered data. Raw data is displayed in preview section. As you can see we are getting sample of 15 rows from the initial data. This is described in the second view object of views property:

  • "specType": "table" - this way we define the view as a table (other options are "simple" (renders a graph and accepts Plotly spec) and "vega" (renders a graph and accepts Vega spec)).
  • "resources" property is an array of objects in this case, where publishers can define data transforms they want to apply.
  • "name" - name of the resource as a reference.
  • "transform" - array of transforms. Each transform is an object, which properties vary depending on transform type. Only common property is "type" that is used to specify transform type.

Transform properties for "sample":

  • "type": "sample" - this way we define the transform to be a sample.
  • "size" - any integer that will be used as a size of a sample data.
{
  "contributors": [
    {
      "email": "[email protected]",
      "name": "rufus_pollock"
    },
    {
      "email": "[email protected]",
      "name": "kristofer_d._kusano"
    }
  ],
  "datahub": {
    "findability": "published",
    "hash": "4d924e3de5e5bd9b724c157d1111ebd3",
    "modified": "2017-08-08T17:37:48.763111",
    "owner": "examples",
    "ownerid": "examples",
    "stats": {
      "bytes": 80900,
      "rowcount": 874
    }
  },
  "homepage": "http://www.iso.org/iso/currency_codes",
  "id": "examples/example-sample-transform-on-currency-codes",
  "keywords": [
    "iso",
    "iso-4217",
    "currency",
    "codes"
  ],
  "licenses": [
    {
      "id": "odc-pddl",
      "label": "Open Data Commons Public Domain Dedication and Licence (PDDL)",
      "url": "http://opendatacommons.org/licenses/pddl/"
    }
  ],
  "maintainer": [
    {
      "email": "[email protected]",
      "name": "Rufus Pollock"
    }
  ],
  "name": "example-sample-transform-on-currency-codes",
  "readme": "This is an example Data Package to demonstrate how data transforms works. In this example, we explain how getting a sample from a dataset can be done before data package gets rendered in showcase page. It assumes publisher is already familiar with Data Packages and views specifications (`views` property in Data Package specifications).\n\n### Getting sample data\n\nOn the top of this page, you can find a table that displays filtered data. Raw data is displayed in preview section. As you can see we are getting sample of 15 rows from the initial data. This is described in the second view object of `views` property:\n\n* `\"specType\": \"table\"` - this way we define the view as a table (other options are `\"simple\"` (renders a graph and accepts Plotly spec) and `\"vega\"` (renders a graph and accepts Vega spec)).\n* `\"resources\"` property is an array of objects in this case, where publishers can define data transforms they want to apply.\n* `\"name\"` - name of the resource as a reference.\n* `\"transform\"` - array of transforms. Each transform is an object, which properties vary depending on transform type. Only common property is `\"type\"` that is used to specify transform type.\n\nTransform properties for \"sample\":\n\n* `\"type\": \"sample\"` - this way we define the transform to be a sample.\n* `\"size\"` - any integer that will be used as a size of a sample data.\n\n{{ dp.json }}\n",
  "resources": [
    {
      "bytes": 17660,
      "datahub": {
        "derivedFrom": [
          "codes-all"
        ],
        "type": "derived/csv"
      },
      "dialect": {
        "delimiter": ",",
        "doubleQuote": true,
        "lineTerminator": "\r\n",
        "quoteChar": "\"",
        "skipInitialSpace": false
      },
      "encoding": "utf-8",
      "format": "csv",
      "hash": "4a6bc82668aaa4e86f13a7a35d7e11b4",
      "mimetype": "text/csv",
      "name": "codes-all",
      "path": "data/csv/data/codes-all.csv",
      "rowcount": 437,
      "schema": {
        "fields": [
          {
            "description": "Country or region name",
            "name": "Entity",
            "type": "string"
          },
          {
            "description": "Name of the currency",
            "name": "Currency",
            "type": "string"
          },
          {
            "description": "3 digit alphabetic code for the currency",
            "name": "AlphabeticCode",
            "title": "Alphabetic Code",
            "type": "string"
          },
          {
            "decimalChar": ".",
            "description": "3 digit numeric code",
            "groupChar": "",
            "name": "NumericCode",
            "title": "Numeric Code",
            "type": "number"
          },
          {
            "description": "",
            "name": "MinorUnit",
            "title": "Minor Unit",
            "type": "string"
          },
          {
            "description": "Date currency withdrawn (values can be ranges or months",
            "name": "WithdrawalDate",
            "title": "Withdrawal Date",
            "type": "string"
          }
        ]
      },
      "size": "16863",
      "title": "",
      "description": "",
      "alternates": [
        {
          "datahub": {
            "type": "source/tabular"
          },
          "mimetype": "text/csv",
          "name": "codes-all",
          "schema": {
            "fields": [
              {
                "description": "Country or region name",
                "name": "Entity",
                "type": "string"
              },
              {
                "description": "Name of the currency",
                "name": "Currency",
                "type": "string"
              },
              {
                "description": "3 digit alphabetic code for the currency",
                "name": "AlphabeticCode",
                "title": "Alphabetic Code",
                "type": "string"
              },
              {
                "description": "3 digit numeric code",
                "name": "NumericCode",
                "title": "Numeric Code",
                "type": "number"
              },
              {
                "description": "",
                "name": "MinorUnit",
                "title": "Minor Unit",
                "type": "string"
              },
              {
                "description": "Date currency withdrawn (values can be ranges or months",
                "name": "WithdrawalDate",
                "title": "Withdrawal Date",
                "type": "string"
              }
            ]
          },
          "size": "16863",
          "url": "https://s3.amazonaws.com/rawstore.datahub.io/75f677233d68c15e9b74ffbf38334885"
        },
        {
          "bytes": 63240,
          "datahub": {
            "derivedFrom": [
              "codes-all"
            ],
            "type": "derived/json"
          },
          "encoding": "utf-8",
          "format": "json",
          "hash": "a9ba9b60fcb079f5f44f252dfb7c9446",
          "mimetype": "text/csv",
          "name": "codes-all_json",
          "path": "data/json/data/codes-all.json",
          "rowcount": 437,
          "schema": {
            "fields": [
              {
                "description": "Country or region name",
                "name": "Entity",
                "type": "string"
              },
              {
                "description": "Name of the currency",
                "name": "Currency",
                "type": "string"
              },
              {
                "description": "3 digit alphabetic code for the currency",
                "name": "AlphabeticCode",
                "title": "Alphabetic Code",
                "type": "string"
              },
              {
                "description": "3 digit numeric code",
                "name": "NumericCode",
                "title": "Numeric Code",
                "type": "number"
              },
              {
                "description": "",
                "name": "MinorUnit",
                "title": "Minor Unit",
                "type": "string"
              },
              {
                "description": "Date currency withdrawn (values can be ranges or months",
                "name": "WithdrawalDate",
                "title": "Withdrawal Date",
                "type": "string"
              }
            ]
          },
          "size": "16863"
        }
      ]
    }
  ],
  "sources": [
    {
      "email": "[email protected]",
      "name": "SIX Interbank Clearing Ltd (on behalf of ISO)",
      "title": "SIX Interbank Clearing Ltd (on behalf of ISO)"
    }
  ],
  "title": "Example sample transform on ISO 4217 Currency Codes",
  "views": [
    {
      "name": "sample-view",
      "resources": [
        {
          "name": "codes-all",
          "transform": [
            {
              "size": 15,
              "type": "sample"
            }
          ]
        }
      ],
      "specType": "table"
    }
  ]
}

Import into your tool

In order to use Data Package in R follow instructions below:

install.packages("devtools")
library(devtools)
install_github("hadley/readr")
install_github("ropenscilabs/jsonvalidate")
install_github("ropenscilabs/datapkg")

#Load client
library(datapkg)

#Get Data Package
datapackage <- datapkg_read("https://pkgstore.datahub.io/examples/example-sample-transform-on-currency-codes/latest")

#Package info
print(datapackage)

#Open actual data in RStudio Viewer
View(datapackage$data$"codes-all")

Tested with Python 3.5.2

To generate Pandas data frames based on JSON Table Schema descriptors we have to install jsontableschema-pandas plugin. To load resources from a data package as Pandas data frames use datapackage.push_datapackage function. Storage works as a container for Pandas data frames.

In order to work with Data Packages in Pandas you need to install our packages:

$ pip install datapackage
$ pip install jsontableschema-pandas

To get Data Package run following code:

import datapackage

data_url = "https://pkgstore.datahub.io/examples/example-sample-transform-on-currency-codes/latest/datapackage.json"

# to load Data Package into storage
storage = datapackage.push_datapackage(data_url, 'pandas')

# to see datasets in this package
storage.buckets

# you can access datasets inside storage, e.g. the first one:
storage[storage.buckets[0]]

In order to work with Data Packages in Python you need to install our packages:

$ pip install datapackage

To get Data Package into your Python environment, run following code:

import datapackage

dp = datapackage.DataPackage('https://pkgstore.datahub.io/examples/example-sample-transform-on-currency-codes/latest/datapackage.json')

# see metadata
print(dp.descriptor)

# get list of csv files
csvList = [dp.resources[x].descriptor['name'] for x in range(0,len(dp.resources))]
print(csvList) # ["resource name", ...]

# access csv file by the index starting 0
print(dp.resources[0].data)

To use this Data Package in JavaScript, please, follow instructions below:

Install datapackage using npm:

$ npm install [email protected]

Once the package is installed, use code snippet below


const Datapackage = require('datapackage').Datapackage

async function fetchDataPackageAndData(dataPackageIdentifier) {
  const dp = await new Datapackage(dataPackageIdentifier)
  await Promise.all(dp.resources.map(async (resource) => {
    if (resource.descriptor.format === 'geojson') {
      const baseUrl = resource._basePath.replace('/datapackage.json', '')
      const resourceUrl = `${baseUrl}/${resource._descriptor.path}`
      const response = await fetch(resourceUrl)
      resource.descriptor._values = await response.json()
    } else {
      // we assume resource is tabular for now ...
      const table = await resource.table
      // rows are simple arrays -- we can convert to objects elsewhere as needed
      const rowsAsObjects = false
      resource.descriptor._values = await table.read(rowsAsObjects)
    }
  }))

  // see the data package object
  console.dir(dp)

  // data itself is stored in Resource object, e.g. to access first resource:
  console.log(dp.resources[0]._values)

  return dp
}


fetchDataPackageAndData('https://pkgstore.datahub.io/examples/example-sample-transform-on-currency-codes/latest/datapackage.json');

Our JavaScript is written using ES6 features. We are using node.js v7.4.0 and passing --harmony option to enable ES6:

$ node --harmony index.js

In order to work with Data Packages in SQL you need to install our packages:

$ pip install datapackage
$ pip install jsontableschema-sql
$ pip install sqlalchemy

To import Data Package to your SQLite Database, run following code:

import datapackage
from sqlalchemy import create_engine

data_url = 'https://pkgstore.datahub.io/examples/example-sample-transform-on-currency-codes/latest/datapackage.json'
engine = create_engine('sqlite:///:memory:')

# to load Data Package into storage
storage = datapackage.push_datapackage(data_url, 'sql', engine=engine)

# to see datasets in this package
storage.buckets

# to execute sql command (assuming data is in "data" folder, name of resource is data and file name is data.csv)
storage._Storage__connection.execute('select * from data__data___data limit 1;').fetchall()

# description of the table columns
storage.describe('data__data___data')