Process

Chapter 2, Good Data Science, mentioned the requirement for governance in data science to ensure the outcomes of projects are sound. The process of creating value from data follows an iterative workflow that works from raw data to a finished project. (Wickham, H., & Grolemund, G. (2016). R for data science: Import, Tidy, Transform, Visualize, and Model Data Sebastopol, CA: O'Reilly. Available at—https://r4ds.had.co.nz/). The workflow starts with defining a problem that needs solving as shown in Figure 4.2. The next step involves loading and transforming the data into a format that is suitable for the required analysis. The data science workflow contains a loop that consists of exploration, modelling, and reflection, which is repeated until the problem is solved or is shown to be unsolvable.

Figure 4.2: Data science workflow

The workflow for a data project is independent of the aspect of the data science continuum under consideration. The same principles...

The Limitations of Data Science

The problems that data science can solve seem to be limitless when reading some of the articles on the web and in literature. There are, however, theoretical and practical limitations to what a computational analysis can achieve. Besides limits to what we can do, there are also ethical limits to what we should be doing. This final section reflects on some of the boundaries of data science.

The Limits of Computation

The limitations of computation relate to some complex and deeply philosophical issues concerning the limits of human knowledge. This short introduction to this problem looks at the restrictions of measuring physical and social processes, and the limitations of algorithms.

• Limitations of Measurement: The first limitation relates to the fact that our collection of data will always be an incomplete description of reality. In a physical system, choose which points to measure, at which frequency, by which method, and so on. We need to make a lot of...

Process

Chapter 2, Good Data Science, mentioned the requirement for governance in data science to ensure the outcomes of projects are sound. The process of creating value from data follows an iterative workflow that works from raw data to a finished project. (Wickham, H., & Grolemund, G. (2016). R for data science: Import, Tidy, Transform, Visualize, and Model Data Sebastopol, CA: O'Reilly. Available at—https://r4ds.had.co.nz/). The workflow starts with defining a problem that needs solving as shown in Figure 4.2. The next step involves loading and transforming the data into a format that is suitable for the required analysis. The data science workflow contains a loop that consists of exploration, modelling, and reflection, which is repeated until the problem is solved or is shown to be unsolvable.

Figure 4.2: Data science workflow

The workflow for a data project is independent of the aspect of the data science continuum under consideration. The same principles apply to every type of analysis...

The Limitations of Data Science

The problems that data science can solve seem to be limitless when reading some of the articles on the web and in literature. There are, however, theoretical and practical limitations to what a computational analysis can achieve. Besides limits to what we can do, there are also ethical limits to what we should be doing. This final section reflects on some of the boundaries of data science.

The Limits of Computation

The limitations of computation relate to some complex and deeply philosophical issues concerning the limits of human knowledge. This short introduction to this problem looks at the restrictions of measuring physical and social processes, and the limitations of algorithms.

• Limitations of Measurement: The first limitation relates to the fact that our collection of data will always be an incomplete description of reality. In a physical system, choose which points to measure, at which frequency, by which method, and so on. We need to make a lot of choices...

Process

Chapter 2, Good Data Science, mentioned the requirement for governance in data science to ensure the outcomes of projects are sound. The process of creating value from data follows an iterative workflow that works from raw data to a finished project. (Wickham, H., & Grolemund, G. (2016). R for data science: Import, Tidy, Transform, Visualize, and Model Data Sebastopol, CA: O'Reilly. Available at—https://r4ds.had.co.nz/). The workflow starts with defining a problem that needs solving as shown in Figure 4.2. The next step involves loading and transforming the data into a format that is suitable for the required analysis. The data science workflow contains a loop that consists of exploration, modelling, and reflection, which is repeated until the problem is solved or is shown to be unsolvable.

Figure 4.2: Data science workflow

The workflow for a data project is independent of the aspect of the data science continuum under consideration...

The Limitations of Data Science

The problems that data science can solve seem to be limitless when reading some of the articles on the web and in literature. There are, however, theoretical and practical limitations to what a computational analysis can achieve. Besides limits to what we can do, there are also ethical limits to what we should be doing. This final section reflects on some of the boundaries of data science.

The Limits of Computation

The limitations of computation relate to some complex and deeply philosophical issues concerning the limits of human knowledge. This short introduction to this problem looks at the restrictions of measuring physical and social processes, and the limitations of algorithms.

• Limitations of Measurement: The first limitation relates to the fact that our collection of data will always be an incomplete description of reality. In a physical system, choose which points to measure, at which frequency, by which method, and so on. We need...