Regression performance
by Ferran Garcia Pagans, Neeraj Kharpate, Philip Hand, James Richardson, Dr. Henric
Qlik Sense: Advanced Data Visualization for Your Organization
- Qlik Sense: Advanced Data Visualization for Your Organization
- Table of Contents
- Qlik Sense: Advanced Data Visualization for Your Organization
- Credits
- Preface
- 1. Module 1
- 1. Qlik Sense® and Data Discovery
- 2. Overview of a Qlik Sense® Application's Life Cycle
- 3. Empowering Next Generation Data Discovery Consumers
- 4. Contributing to Data Discovery
- 5. Authoring Engaging Applications
- 6. Building Qlik Sense® Data Models
- 7. Qlik Sense® Apps in the Cloud
- 8. Extending the Qlik® Analytic Platform
- 9. Administering Qlik Sense®
- 10. Sales Discovery
- 11. Human Resource Discovery
- 12. Travel Expense Discovery
- 13. Demographic Data Discovery
- 2. Module 2
- 1. Getting Started with the Data
- Introduction
- Extracting data from databases and data files
- Extracting data from Web Files
- Activating the Legacy Mode in Qlik Sense® desktop
- Extracting data from custom databases
- Invoking help while in the data load editor or the expression editor
- Previewing data in the Data model viewer
- Creating a Master Library from the Data model viewer
- Using a Master Library in the Edit mode
- 2. Visualizations
- Introduction
- Creating Snapshots
- Creating and adding content to a story
- Adding embedded sheets to the story
- Highlighting the performance measure in a bar chart
- Associating persistent colors to field values
- Using the ColorMix1 function
- Composition
- Relationships
- Comparison
- Distribution
- Structuring visualizations
- 3. Scripting
- Introduction
- Structuring the script
- Efficiently debugging the script
- Packaging the code in script files
- How to use sub routines in Qlik Sense®
- Optimizing the UI calculation speed
- Optimizing the reload time of the application
- Using a For Each loop to load data from multiple files
- Using the Concat function to store multiple field values in a single cell
- 4. Managing Apps and User Interface
- Introduction
- Publishing a Qlik Sense® application created in Qlik Sense® desktop
- Creating private, approved, and community sheets
- Publishing a Qlik Sense® application to Qlik Sense® cloud
- Creating geo maps in Qlik Sense®
- Reference lines in Sales versus Target gauge chart
- Effectively using the KPI object in Qlik Sense®
- Creating Tree Maps
- Creating dimensionless bar charts in Qlik Sense®
- Adding Reference Lines to trendline charts
- Creating text and images
- Applying limitations to charts
- Adding thumbnails – a clear environment
- Navigating many data points in a scatter chart
- 5. Useful Functions
- Introduction
- Using an extended interval match to handle Slowly Changing Dimensions
- Using the Previous() function to identify the latest record for a dimensional value
- Using the NetworkDays() function to calculate the working days in a calendar month
- Using the Concat() function to display a string of field values as a dimension
- Using the Minstring() function to calculate the age of the oldest case in a queue
- Using the Rangesum() function to plot cumulative figures in trendline charts
- Using the Fractile() function to generate quartiles
- Using the FirstSortedValue() function to identify the median in a quartile range
- Using the Declare and Derive functions to generate Calendar fields
- Setting up a moving annual total figure
- Using the For Each loop to extract files from a folder
- Using the Peek() function to create a currency Exchange Rate Calendar
- Using the Peek() function to create a Trial Balance sheet
- 6. Set Analysis
- Introduction
- Cracking the syntax for Set Analysis
- Using flags in Set Analysis
- Using the = sign with variables in Set Analysis
- Point in time using Set Analysis
- Using comparison sets in Set Analysis
- Using embedded functions in Set Analysis
- Creating a multi-measure expression in Set Analysis
- Using search strings inside a set modifier
- Capturing a list of field values using a concat() function in Set Analysis
- Using the element functions P() and E() in Set Analysis
- 7. Extensions in Qlik Sense®
- 8. What's New in Version 2.1.1?
- Introduction
- Using the visual exploration capability in Qlik Sense® 2.1.1
- Defining variables in Qlik Sense®
- Exporting stories to MS PowerPoint
- Using the Qlik Dev Hub in Qlik Sense® 2.1.1
- Using Extension editor in Qlik Dev Hub
- Using Qlik Dev Hub to generate mashups
- Embedding Qlik Sense® application on a website using a single configurator
- Using the Qlik DataMarket
- Creating dynamic charts in Qlik Sense®
- Using Smart Search
- Using smart data load profiling
- Conclusion
- A. Appendix
- 1. Getting Started with the Data
- 3. Module 3
- 1. Getting Ready with Predictive Analytics
- 2. Preparing Your Data
- 3. Exploring and Understanding Your Data
- 4. Creating Your First Qlik Sense Application
- 5. Clustering and Other Unsupervised Learning Methods
- 6. Decision Trees and Other Supervised Learning Methods
- 7. Model Evaluation
- 8. Visualizations, Data Applications, Dashboards, and Data Storytelling
- 9. Developing a Complete Application
- A. Bibliography
- Index
To measure the performance of a regression, the distance between the predicted outputs and the actual outputs, is a good model performance measure.
Rattle offers us a good way to see predicted values versus the actual value—the Predicted versus Observed plot. To test this plot, you need to create a regression model. You can download a sample dataset from the UCI Machine Learning Repository (http://archive.ics.uci.edu/ml; Irvine, CA: University of California, School of Information and Computer Science), or from Kaggle (http://www.kaggle.com/). On some websites, such as the UCI Machine Learning Repository, the datasets are classified by the task you want to perform with the dataset.
Imagine we have to create a model to predict the price of a house. Click on the Evaluate tab:
Rattle's Evaluate tab offers us two good options for a regression model as shown in the preceding screenshot:
- Predicted versus Observed Plot: We will use this option to compare predicted values versus actual values.
- Score: As we've seen before, this option creates predictions for the selected dataset:
After creating the model, go to the Evaluate tab, select your Model, the Validation dataset, the Pr v Ob option, press Execute, and Rattle will build a Predicted vs. Observed plot for you, as shown here:
This plot shows a set of points; each point is an observation in the y axes, where we can see the predicted value, and in the x axes, we can see the actual value. We can also see a dotted line; this line represents a perfect prediction, when predicted values are the same as the actual values. The last line is a linear fit to points.
Finally, Pseudo R-square is an approach to R-square. This measures the variance explained by the model. R-square is a number from 0 to 1; an R-square close to 1 means that the model has strong predictive power. When the model doesn't provide a good prediction, R-square is close to 0. In the same way, a Pseudo R-square close to 1 is good; a measure close to 0 means low performance.
-
No Comment