Dataset: 6 Nations Rugby Files

About this Dataset

6 Nations Rugby Files

6 Nations Predictor
So, this is the first notebook I have done and given that I am not a data scientist, there is probably going to be a tonne of mistakes. Even so, as a rugby fan I thought it would be interesting to try and predict the score of the upcoming 6 nations tournament using a few of the things I have learnt on here.

Background
For those who are interested but don't know much about the 6 nations...

The 6 nations is an annual rugby union tournament held in February and March. It consists of 6 teams: England, Wales, Ireland, Scotland, France and Italy. All teams play each other once - 3 at home and 2 away alternating each year. If you win all five games its called the Grand Slam and if you lose all 5 then you win the dreaded wooden spoon. You don't get a wooden spoon - but it's a term that started years ago in Cambridge apparently that just meant you were the loser.

It is worth mentioning that it was the 5 nations until Italy joined in 2000. Since joining however, Italy have not fared quite as well and have been one of the weakest teams. Of the other nations, most have had periods of success but in the last 20 years (my data set runs from 2003) Scotland ranks second in terms of weaker performances while France have tended to be fairly inconsistent. Wales have enjoyed the most successes, winning the most grand slams in this period with Ireland and England enjoying spells of success too. I'm English and I’m sure some people will strongly disagree with what I have just said so I look forward to the comments……

Apart from Italy and possibly Scotland, home advantage is huge in the 6 nations. Later in the data worksheet you can see this clearly as in some years the model only predicts Scotland and Italy home losses.

Tables

Homedata

@kaggle.danieljorna_6_nations_rugby_files.homedata

5.87 KB
255 rows
5 columns


CREATE TABLE homedata (
  "team" VARCHAR,
  "diff" BIGINT,
  "opposition" VARCHAR,
  "ground" VARCHAR,
  "match_date" VARCHAR
);

Home Matches With Weather

@kaggle.danieljorna_6_nations_rugby_files.home_matches_with_weather

13.04 KB
255 rows
12 columns


CREATE TABLE home_matches_with_weather (
  "team" VARCHAR,
  "diff" BIGINT,
  "opposition" VARCHAR,
  "ground" VARCHAR,
  "match_date" TIMESTAMP,
  "year" BIGINT,
  "opponnents" VARCHAR,
  "home_standing" DOUBLE,
  "away_standing" DOUBLE,
  "temp" BIGINT,
  "pressure" BIGINT,
  "wind" BIGINT
);

Rugbystats

@kaggle.danieljorna_6_nations_rugby_files.rugbystats

14.02 KB
6 rows
20 columns


CREATE TABLE rugbystats (
  "member_union" VARCHAR,
  "tier" BIGINT,
  "n_2003" VARCHAR,
  "n_2004" DOUBLE,
  "n_2005" DOUBLE,
  "n_2006" DOUBLE,
  "n_2007" DOUBLE,
  "n_2008" DOUBLE,
  "n_2009" DOUBLE,
  "n_2010" DOUBLE,
  "n_2011" DOUBLE,
  "n_2012" DOUBLE,
  "n_2013" DOUBLE,
  "n_2014" DOUBLE,
  "n_2015" DOUBLE,
  "n_2016" DOUBLE,
  "n_2017" DOUBLE,
  "n_2018" DOUBLE,
  "n_2019" DOUBLE,
  "n_2020" DOUBLE
);

Target

@kaggle.danieljorna_6_nations_rugby_files.target

4.8 KB
15 rows
6 columns


CREATE TABLE target (
  "team" VARCHAR,
  "opponnents" VARCHAR,
  "home_standing" DOUBLE,
  "away_standing" DOUBLE,
  "home_prev" VARCHAR,
  "away_prev" VARCHAR
);