Data Processing
| Industry | 2009 | 2010 | 2011 | 2012 | 2013 | 2014 | 2015 | 2016 | 2017 | 2018 |
|---|---|---|---|---|---|---|---|---|---|---|
| Agriculture | 37,700 | 38,200 | 36,100 | 36,100 | 36,800 | 42,700 | 40,700 | 43,200 | 40,200 | 41,100 |
| Production | 156,700 | 149,800 | 158,600 | 154,400 | 164,200 | 173,300 | 172,300 | 162,500 | 165,100 | 165,700 |
| Construction | 8,900 | 93,200 | 90,000 | 91,300 | 89,300 | 97,000 | 92,600 | 102,700 | 90,800 | 101,800 |
| Retail | 345,400 | 344,500 | 343,100 | 347,300 | 345,100 | 337,300 | 357,700 | 360,200 | 333,500 | 347,600 |
| ICT | 27,800 | 27,900 | 26,400 | 27,200 | 26,900 | 35,700 | 24,000 | 34,400 | 58,900 | 31,500 |
| Finance | 33,800 | 29,800 | 33,200 | 31,100 | 32,400 | 32,400 | 30,800 | 31,000 | 32,100 | 35,500 |
| Real Estate | 13,500 | 14,600 | 17,600 | 18,800 | 18,000 | 22,200 | 19,100 | 22,700 | 18,200 | 25,200 |
| Professional Service | 144,800 | 145,800 | 143,600 | 137,300 | 149,900 | 152,900 | 166,200 | 161,200 | 176,400 | 187,100 |
| Public Administration | 415,600 | 418,600 | 425,600 | 421,000 | 427,000 | 427,600 | 423,200 | 418,500 | 424,500 | 434,900 |
| Other Services | 64,200 | 68,000 | 72,400 | 72,800 | 75,500 | 73,300 | 77,200 | 72,400 | 83,200 | 81,800 |
| Total | 1,248,400 | 1,330,400 | 1,346,600 | 1,337,300 | 1,365,100 | 1,394,400 | 1,403,800 | 1,408,800 | 1,422,900 | 1,452,200 |
Following is the dataset provided by the Wales Government official site. The dataset contains the years 2009–2018.
Data Analysis
Which industry employed the highest and lowest workers over the period?
The industry with the lowest number of employees over the period is ICT. In 2009, ICT recorded
27,800, which is the lowest value in the dataset for 2009–2018. The industry with the highest
employment is Public Administration, reaching 434,900 (2018) and remaining the highest
employer across all years compared to the other industries.
Which industry has the highest and lowest overall growth over the period?
Construction has the highest overall growth over the period, increasing by 92,900
(from 8,900 in 2009 to 101,800 in 2018). The lowest overall growth is Finance, increasing by
1,700 (from 33,800 in 2009 to 35,500 in 2018).
Which years are the best and worst performing year in relation to total employment?
The worst performing year is 2009, with the lowest total employment of 1,248,400.
The best performing year is 2018, with the highest total employment of 1,452,200.
PCA/Correlation
The correlation table of the dataset given above is below:
| Pearson’s r | 2009 | 2010 | 2011 | 2012 | 2013 | 2014 | 2015 | 2016 | 2017 | 2018 |
|---|---|---|---|---|---|---|---|---|---|---|
| 2009 | 0.983 | 0.985 | 0.984 | 0.985 | 0.983 | 0.985 | 0.981 | 0.984 | 0.981 | |
| 2010 | 0.983 | 1.000 | 1.000 | 0.999 | 0.999 | 0.998 | 0.999 | 0.995 | 0.997 | |
| 2011 | 0.985 | 1.000 | 1.000 | 1.000 | 0.999 | 0.998 | 0.998 | 0.995 | 0.997 | |
| 2012 | 0.984 | 1.000 | 1.000 | 0.999 | 0.998 | 0.998 | 0.998 | 0.994 | 0.995 | |
| 2013 | 0.985 | 0.999 | 1.000 | 0.999 | 0.999 | 0.999 | 0.998 | 0.996 | 0.997 | |
| 2014 | 0.983 | 0.999 | 0.999 | 0.998 | 0.999 | 0.998 | 0.998 | 0.996 | 0.997 | |
| 2015 | 0.985 | 0.998 | 0.998 | 0.998 | 0.999 | 0.998 | 0.999 | 0.996 | 0.998 | |
| 2016 | 0.981 | 0.999 | 0.998 | 0.998 | 0.998 | 0.998 | 0.999 | 0.995 | 0.997 | |
| 2017 | 0.984 | 0.995 | 0.995 | 0.994 | 0.996 | 0.996 | 0.996 | 0.995 | 0.997 | |
| 2018 | 0.981 | 0.997 | 0.997 | 0.995 | 0.997 | 0.997 | 0.998 | 0.997 | 0.997 |
The individual cluster correlation diagram of the years with respect to the industry is given below. The Excel sheet with all the calculations performed on it is also attached.
Clustering
Cluster analysis (clustering) is the task of grouping a set of objects so that objects in the same group are more similar
to each other than to those in other groups.
Discussion
The dataset provided for analysis covers Wales employment by industry for each year and compares performance over time.
The conclusions below are based strictly on the provided data and the machine learning tasks performed.
Starting with Agriculture, it is not among the largest sectors, but it improves over the period.
Production remains a mid-sized sector with limited change. Construction shows the most
noticeable change, rising sharply from a low base in 2009. Retail, ICT, and
Finance remain relatively stable overall with positive movement across the timeline.
Real Estate, Professional Service, Public Administration, and
Other Services also show positive performance.
Public Administration is consistently the largest employer in the dataset, providing the highest
employment counts each year compared to the other listed industries.
