Abstract
This is an exercise in data mining that scrapes data from the Bamako Data Science Meetup website, wrangles the messy data into tidy data and performs some exploratory analysis. Just for fun, interactive plots are created with Plotly, animated images (GIF) are introduced and we aven added a Wordcloud. And finlally, we even sprinkled some emojis throughout the report.
macOS Catalina 10.15.3
R version 3.6.2 (2019-12-12) – “Dark and Stormy Night”
RStudio Version 1.1.463
Click Here“Bamako Data Science”
Click Here“Lubridate Cheat Sheet”
Click Here“Basic Regular Expressions in R”
Click Here“Ggplot2 Visualiztons”
Click Here“Lollipop Plot”
Click Here“Emojis”
Click Here“More Emojis”
Click Here“GIFS”
Click Here“R Brewer Color Palettes”
“The Bamako Data Science Meetup is open to everyone who wants to contribute to building a Data Science community in Mali. It is meant to be a place for you to share what you do and to find people you can learn from or with.”
What can we learn from the website?
It was founded on July 2, 2018 by Fousseyenou Ba. Mariam B. became an event organizer on September 24, 2019.
As of January 12, 2021, there are 268 members.
The most recent event was on October 23, 2020. No upcoming events are scheduled.
To explore data about members, we have scraped the website and downloaded a dataset. This exercise uses R, RStudio and RMarkdown on a Mac computer.
After musch trial, error, and perserverance, I succeded in getting data into Excel, thanks to Outwit Hub software.
Click Here“Outwit Hub”
Steps taken:
There are almost 17,000 packages for can be used to augment the power of basic R. We will use over a dozen of them.
There is an R package for that (fields).
The distance, as the jet flies, between Bamako and Peaks Island is approximately 6818 kilometers.
## Freq Name
## 1 7 Mamadou
## 2 9 Amadou
## 3 7 Mohamed
## 4 8 Mahamadou
## 5 1 Hamadoun
## 6 1 Mamadi
## 7 4 Adama
Do we see six variations of a common name?
What is the probability that an Adama is male?
Top 20 names.
## Names Frequency
## 1 oumar 9
## 2 amadou 8
## 3 mahamadou 8
## 4 mohamed 7
## 5 mamadou 6
## 6 moussa 5
## 7 abdoulaye 4
## 8 adama 4
## 9 mariam 4
## 10 abdoul 3
## 11 aly 3
## 12 brehima 3
## 13 cheikh 3
## 14 fatoumata 3
## 15 modibo 3
## 16 traore 3
## 17 yacouba 3
## 18 abdallah 2
## 19 ahmadou 2
## 20 allahsera 2
## # A tibble: 2 x 3
## Name Joined row
## <chr> <chr> <dbl>
## 1 Allahsera Auguste T. Joined Thu Jan 07 2021 09:52:02 6
## 2 Allahsera Auguste T. Joined Fri Oct 09 2020 13:08:47 26
## [1] 12 2
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.00 8.50 13.00 22.25 37.50 55.00
## Mean = 22.25
## Median = 13
## Range = 2 55
Over 85 weeks since its creation, the Bamako DS Meetup has added an average of just over 3 members a week. 29 people joined in the first week. The second highest week was 16 new members in week 66 (on or about June 6, 2020).
What happened to cause this jump in membership?
Comments
Tis analysis has provided some interesting insights in to the dynamics of the evolution of the Bamako DS Meetup. Do we have any idea about how many of the members are still potentially active?