Seeing Through the Numbers
0 likes212 views
This document provides tips and best practices for working with data including regular expressions, using wildcards, coding dichotomous variables, paying attention to case and formatting, dealing with outliers, and communicating findings from data exploration. It suggests learning regular expressions and find/replace tools, using online references, cleaning data by trimming fields and watching for "invisible baddies", being aware of differences between float and integer values, and considering outliers and context when analyzing data. The overall goal is to effectively communicate insights gained from exploring new data.
1 of 23
![^d{5}(?:[-s]d{4})?$
^
d{5}
(?:…)
[-s]
hyphen
d{4}
…?
condition 1)
$](https://image.slidesharecdn.com/data-130603091210-phpapp01/85/Seeing-Through-the-Numbers-12-320.jpg)
![/^([a-z0-9_.-]+)@([da-z.-]+).([a-](https://image.slidesharecdn.com/data-130603091210-phpapp01/85/Seeing-Through-the-Numbers-13-320.jpg)
Seeing Through the Numbers
- 2. 1. What story are you trying to tell?
- 3. 2. What actions do you expect people to take?
- 4. 3. What route are you taking?
- 5. 4. What is the difference?
- 6. 5. Where is your data coming from?
- 7. 6. What tools are available?
- 8. 7. What are best practices?
- 9. 8. Data?
- 10. Learn regular expressions and MS find/replace language.
- 11. Learn how to use wildcards!
- 16. Code dichotomous variables to 1 and 0
- 17. Pay attention to case
- 18. Watch for invisible “baddies”! ltrim(rtrim(Field))
- 19. Mind your floats and integers 1.0 is not always equal to 1
- 20. Watch for outliers 99/100 cases fall within 0-10 and the 100th is 86
- 21. BEWARE of the acceptable leading 0
- 22. 9. What is the context?
- 23. 10. What comes next? Communicate the story and guide the exploration of new data.