Knowledge Base

Data exploration

Next >>

<< Prev

Data exploration tutorial transcript

Welcome to the data exploration using Analytics Canvas tutorial.

This tutorial aims to give you an overview of data exploration features in Analytics Canvas.

Analytics Canvas offers the following data profiling features:

  • Data Viewer: Data preview of the raw data.
  • Data Profiler: Data structure and selection of statistics.
  • Data Chart: Graphical representation of the time series data.

Data Viewer
At the bottom of the screen, you will be able to see a preview of the data that you loaded in. You can also open Data Viewer by clicking on the input or output stub of a block, or on a connector line between blocks.

data viewer

There are many things available to you in Data Viewer. If you want to sort the data in a column, in ascending or descending order, you can click on the little triangles in the right corner next to the column names. You can explore the data by right-clicking and selecting “Show Data Type by Color”. Dates will be highlighted in light blue and numbers in brown.

Data Profiler
Data Profiler allows you to quickly evaluate the quality of your data. To access the Data Profiler, click on the input or output stub of a block, or on a connector line between blocks. Then select the “Data Profiler” tab at the lower left of the screen, or in the toolbar buttons above the Main Canvas.

Using_Data_Profiler

If your dataset is too large, you may be prompted to select which columns you wish to profile; otherwise all columns are provided.

data profiler

For each column that is profiled, the following metrics are calculated:

  • Column Name – the name of the column being profiled.
  • Data Type – the declared data type for the column.
  • Null rows – the count of rows that contain the Null value.
  • Missing rows – for string types the count of rows containing the empty string.
  • Populated rows – the count of rows that are not Null or missing.
  • Completeness – the percentage of rows that are Populated.
  • Cardinality – the number of unique values contained in the row.
  • Uniqueness – the cardinality divided by the number of populated rows.
  • Minimum – the minimum value within the column for numeric columns, the earliest date for date columns.
  • Maximum – the maximum value within the column for numeric columns, the latest date for date columns.
  • Average – the average of all values for numeric columns.

You can drill down into the rows by clicking on the bar in the column category count graphs.

Data Chart

Data Chart
The Data Chart tab is used to visualize the dataset. The Data Chart displays variables as a time series chart, and it can be used to examine changes in data over time. You can zoom in and out by clicking on the data and selecting the time frame that you are interested in.

Contents:

  • Data Viewer
  • Data Profiler
  • Data Profiler metrics
  • Data Chart

Related Materials:

Transcript – Data exploration

Other resources:

Tutorial – Data Profiler Block
Documentation

Length:

2:50

You can download a free trial of Analytics Canvas to follow along with the video.

Back to more Support    |   Try Analytics Canvas for Free

Was this article helpful?

Related Tutorials/Video

Need Support?

If you need any further help, don't hesitate to send a support request to our support team.

Contact Support