tidytuesday VS data

TidyTuesday is a weekly data cleaning project where a new, interesting data source is linked to each week: https://github.com/rfordatascience/tidytuesday

For R, I don't have specific resources, but I remember I started out with doing tidytuesdays challenge (https://github.com/rfordatascience/tidytuesday).

Tidy Tuesday has data and links to more data. The nice thing about those data sets is that you can search for what other people did with the data on social media (e.g. Twitter).

Dataset: https://github.com/rfordatascience/tidytuesday/tree/master/data/2022/2022-11-01

What you're describing is contributing to open source. Some things I'd suggest doing: - learn some git first - create GitHub account and create at least a practice repo - look at learning community-related repos, like Tidy Tuesday - follow R "power" users, people associated with RStudio, and similar folks on social media. Those folks will sometimes mention projects aimed at beginners.

Data: TidyTuesday April 4

The Tidy Tuesday git repo has a lot of example datasets to work with.

I mostly use ggplot2 in R for visualisations which means that The R Graph Gallery is my starting point for inspiration. The best thing to do is start with a simple idea that tells a story, and one of the best guys out there that does this is Cedric Scherer. He is involved a bit with the TidyTuesday project which I wish I had more time to play around with, and is a great starting point for developing a library of vis techniques.

FiveThirtyEight Datasets: Datasets related to articles and investigations published by FiveThirtyEight. FiveThirtyEight Datasets

You of course already know this answer, but just to put it into more perspective. Here are the SPI ranking equivalents to what he did with these 11 goals in Scotland and Switzerland.

To answer these questions I decided to look at 538’s RAPTOR ratings. RAPTOR uses player tracking data to estimate how much each player contributes on the offensive and defensive ends. The total RAPTOR score should be something like the “number of points a player contributes to his team’s offense and defense per 100 possessions, relative to a league-average player.” Higher is better, best during the regular season has been Nikola Jokic at +14. You can read more about it here or play with an interactive tool on their website here. I don’t really care about the details of why it’s a good statistic, but it seems pretty helpful and most importantly for my purposes you can download the data here for free.

EDIT: I came to this data from this repository which has a nice csv collection for machine training.

Looks like we may actually be collectively underrating our guys now. That's an interesting change. Based on SPI (rating = 72.4) we would be:

Before Disney/ABC get any -ideas-, might be a good chance to get our hands on at least their data[0]!

[0]: https://data.fivethirtyeight.com/

Most young women expect words to be involved when their partner seeks their consent. 43% of young men actually ask for verbal confirmation of consent. Overall, verbal indicators of consent or nonconsent are more common than nonverbal indicators. More open communication also increases the likelihood of orgasm for women.

DHM does not use an equity sample. Of all polling operations they rank 250 out of 517. Id like to see another pollster https://github.com/fivethirtyeight/data/blob/master/pollster-ratings/pollster-ratings.csv