Data Science For Process Analysts

Data Analysis for
Process Analysts team

Sajad Ghashami

4/12/2021

What is data science?

Goal

• Inference:

Use the model to learn about the data generation process.

• Prediction:

Use the model to predict the outcomes for new data points.

Steps

A nice image.

Process Analyst position

Visualization

Chart Types

A nice image.

Example

Gapminder dataset

• Country: Name of country.
• Continent: Which of the five continents the country is part of. Note that “Americas” includes - - countries in both North and South America and that Antarctica is excluded.
• Life Expectancy: Life expectancy in years.
• Population: Number of people living in the country.
• GDP per Capita: Gross domestic product (in US dollars).

Count continent frequency

Summary

	country	continent	year	lifeExp	pop	gdpPercap
	Afghanistan: 12	Africa :624	Min. :1952	Min. :23.60	Min. :6.001e+04	Min. : 241.2
	Albania : 12	Americas:300	1st Qu.:1966	1st Qu.:48.20	1st Qu.:2.794e+06	1st Qu.: 1202.1
	Algeria : 12	Asia :396	Median :1980	Median :60.71	Median :7.024e+06	Median : 3531.8
	Angola : 12	Europe :360	Mean :1980	Mean :59.47	Mean :2.960e+07	Mean : 7215.3
	Argentina : 12	Oceania : 24	3rd Qu.:1993	3rd Qu.:70.85	3rd Qu.:1.959e+07	3rd Qu.: 9325.5
	Australia : 12	NA	Max. :2007	Max. :82.60	Max. :1.319e+09	Max. :113523.1
	(Other) :1632	NA	NA	NA	NA	NA

Freq Table

continent	count	percent
Africa	52	37%
Americas	25	18%
Asia	33	23%
Europe	30	21%
Oceania	2	1%

Bar Chart

Pros & cons of bar chart

Pros

• Simple and Quick

cons

• Not good for many categories
• One dimensional
• Can be completely wrong (more advanced stuff)

Population per 1 million

Pop Table

continent	average.population
Africa	10
Americas	25
Asia	77
Europe	17
Oceania	9

Bar Chart(Mean)

Advantages and Problems of bar chart

Pros:

• Again Simple and Quick

Cons

• Outliers: China and India in Asia than can not be seen here but changed the results
• You can not see how each country is distributed if group
• One dimensional
• Can be completely wrong (more advanced stuff)
• It does not show the trends of population in continents

Mean vs Median

A nice image.

Consider we have these duration for completing a task(In hour) in a process: 1, 2, 3, 4, 5, 6, 7, 8, 100 then the mean is 15 but the median is 5.

Which one is a better answer?

Solve outlier (with median)

Boxplot desc

Boxplot of population

Remove China and India as outliers.

Pros and cons boxplot

Pros:

• Good to show how data is distributed

Cons:

• Bad to compare groups

Ridgeline plot

Still only show 1 variable and can not show the trend.

Solve the trend (No good)

Solve the trend (Good)

Process Mining