-
Notifications
You must be signed in to change notification settings - Fork 0
/
wrangle_data.Rmd
192 lines (155 loc) · 6.88 KB
/
wrangle_data.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
---
title: "Read and wrangle Football.co.uk data"
output:
pdf_document: default
toc: true
toc_depth: 3
---
# Summary
This R-notebook takes as input the raw match data files (one for each season) downloaded from Football.co.uk.
It merges them into one dataset, adds a few derived variables, and adds information on which matches were played on artificial turf.
Finally, the complete enriched dataset is saved as a R object, ready for analysis.
# Load packages
```{r}
rm(list=ls())
library(data.table)
```
# Read data Eredivisie 2000/2001 - 2017/2018 (up to 2017/12/11)
```{r}
source("code/addTeamIds.R")
# stand 11 december 2017
NL17 <- read.table("data\\N1.csv", header=T, quote="\"", sep=",")
NL16 <- read.table(unz("data\\data16.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL15 <- read.table(unz("data\\data15.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL14 <- read.table(unz("data\\data14.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL13 <- read.table(unz("data\\data13.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL12 <- read.table(unz("data\\data12.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL11 <- read.table(unz("data\\data11.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL10 <- read.table(unz("data\\data10.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL9 <- read.table(unz("data\\data9.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL8 <- read.table(unz("data\\data8.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL7 <- read.table(unz("data\\data7.zip", "N1.csv"), header=T, quote="\"", sep=",", fill = TRUE)
NL6 <- read.table(unz("data\\data6.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL5 <- read.table(unz("data\\data5.zip", "N1.csv"), header=T, quote="\"", sep=",")
NL4 <- read.table(unz("data\\data4.zip", "N1.csv"), header=T, quote="\"", sep=",", fill = TRUE)
NL3 <- read.table(unz("data\\data3.zip", "N1.csv"), header=T, quote="\"", sep=",", fill = TRUE)
NL2 <- read.table(unz("data\\data2.zip", "N1.csv"), header=T, quote="\"", sep=",", fill = TRUE)
NL1 <- read.table(unz("data\\data1.zip", "N1.csv"), header=T, quote="\"", sep=",", fill = TRUE)
NL0 <- read.table(unz("data\\data0.zip", "N1.csv"), header=T, quote="\"", sep=",", fill = TRUE)
select_cols <- c("Div" , "Date" , "HomeTeam" , "AwayTeam" , "FTHG" ,
"FTAG" , "FTR" , "WHH", "WHD", "WHA")
NL <- rbind(NL17[, select_cols],
NL16[, select_cols],
NL15[, select_cols],
NL14[, select_cols],
NL13[, select_cols],
NL12[, select_cols],
NL11[, select_cols],
NL10[, select_cols],
NL9[, select_cols],
NL8[, select_cols],
NL7[, select_cols],
NL6[, select_cols],
NL5[, select_cols],
NL4[, select_cols],
NL3[, select_cols],
NL2[, select_cols],
NL1[, select_cols],
NL0[, select_cols])
NL <- data.table(NL)
```
# Variable descriptives
Key to results data:
* Div = League Division
* Date = Match Date (dd/mm/yy)
* HomeTeam = Home Team
* AwayTeam = Away Team
* FTHG and HG = Full Time Home Team Goals
* FTAG and AG = Full Time Away Team Goals
* FTR and Res = Full Time Result (H=Home Win, D=Draw, A=Away Win)
* WHH = William Hill home win odds
* WHD = William Hill draw odds
* WHA = William Hill away win odds
# Enrich data DPL
```{r}
NL <- NL[, WinningTeam := "Draw"]
NL <- NL[FTR == "H", WinningTeam := HomeTeam]
NL <- NL[FTR == "A", WinningTeam := AwayTeam]
# add year
NL <- NL[, Year := as.integer(paste("20", substr(Date, 7,8), sep = ''))]
# drop empty records
NL <- NL[Year != 20,]
# trim whitespace
NL <- NL[, HomeTeam := trimws(HomeTeam, "r")]
# fix team names
NL <- NL[HomeTeam == "Sparta Rotterdam", HomeTeam := "Sparta"]
NL <- NL[AwayTeam == "Sparta Rotterdam", AwayTeam := "Sparta"]
NL <- NL[HomeTeam == "Roda", HomeTeam := "Roda JC"]
NL <- NL[AwayTeam == "Roda", AwayTeam := "Roda JC"]
# add goal difference for each match
NL <- NL[, goal_difference := FTHG - FTAG]
NL <- addTeamIds(NL)
# Eyeball teams in time
#res <- NL[, .N, .(HomeTeam, Year)]
#res <- NL[, .N, .(AwayTeam, Year)]
```
# Add Artificial turf data
Teams with Artificial turf in the DPL:
* Heracles (2003)
* Excelsior (from 2010),
* PEC Zwolle (from 2012)
* SC Cambuur (2013)
* ADO Den Haag (okt 2013, first four games on natural turf)
* Roda JC (2014)
* FC Dordrecht (2014)
* Sparta (from 2014/2015)
* VVV-Venlo (from 2013 in jupiler, 2017)
```{r}
NL <- NL[, Date := as.Date(Date, "%d/%m/%y")]
NL <- NL[, art_turf := 0]
NL <- NL[, art_turf_away := 0]
# * Heracles (2003)
NL <- NL[HomeTeam == "Heracles" & Date > as.Date("2003-06-01"), art_turf := 1]
NL <- NL[AwayTeam == "Heracles" & Date > as.Date("2003-06-01"), art_turf_away := 1]
# * Excelsior (from 2010),
NL <- NL[HomeTeam == "Excelsior" & Date > as.Date("2010-06-01"), art_turf := 1]
NL <- NL[AwayTeam == "Excelsior" & Date > as.Date("2010-06-01"), art_turf_away := 1]
# * PEC Zwolle (from 2012)
NL <- NL[HomeTeam == "Zwolle" & Date > as.Date("2012-06-01"), art_turf := 1]
NL <- NL[AwayTeam == "Zwolle" & Date > as.Date("2012-06-01"), art_turf_away := 1]
# * SC Cambuur (2013)
NL <- NL[HomeTeam == "Cambuur" & Date > as.Date("2013-06-01"), art_turf := 1]
NL <- NL[AwayTeam == "Cambuur" & Date > as.Date("2013-06-01"), art_turf_away := 1]
# * ADO Den Haag (okt 2013, first four games on natural turf)
NL <- NL[HomeTeam == "Den Haag" & Date > as.Date("2013-10-01"), art_turf := 1]
NL <- NL[AwayTeam == "Den Haag" & Date > as.Date("2013-10-01"), art_turf_away := 1]
# * Roda JC (2014)
NL <- NL[HomeTeam == "Roda JC" & Date > as.Date("2014-6-01"), art_turf := 1]
NL <- NL[AwayTeam == "Roda JC" & Date > as.Date("2014-6-01"), art_turf_away := 1]
# * FC Dordrecht (2014)
NL <- NL[HomeTeam == "Dordrecht" & Date > as.Date("2014-6-01"), art_turf := 1]
NL <- NL[AwayTeam == "Dordrecht" & Date > as.Date("2014-6-01"), art_turf_away := 1]
# * Sparta (from 2014/2015)
NL <- NL[HomeTeam == "Sparta" & Date > as.Date("2014-6-01"), art_turf := 1]
NL <- NL[AwayTeam == "Sparta" & Date > as.Date("2014-6-01"), art_turf_away := 1]
# * VVV-Venlo (from 2013 in jupiler, 2017)
NL <- NL[HomeTeam == "VVV Venlo" & Date > as.Date("2013-6-01"), art_turf := 1]
NL <- NL[AwayTeam == "VVV Venlo" & Date > as.Date("2013-6-01"), art_turf_away := 1]
NL <- NL[, art_turf_advantage := 0]
NL <- NL[art_turf == 1 & art_turf_away == 0, art_turf_advantage := 1]
# Vars van Ours & Teijl
NL <- NL[, nat2 := 0]
NL <- NL[art_turf == 0 & art_turf_away == 0, nat2 := 1]
NL <- NL[, natkun := 0]
NL <- NL[art_turf == 0 & art_turf_away == 1, natkun := 1]
NL <- NL[, kunnat := 0]
NL <- NL[art_turf == 1 & art_turf_away == 0, kunnat := 1]
NL <- NL[, kun2 := 0]
NL <- NL[art_turf == 1 & art_turf_away == 1, kun2 := 1]
NL <- NL[, match_type := "Nat-Nat"]
NL <- NL[natkun == 1, match_type := "Nat-Kun"]
NL <- NL[kunnat == 1, match_type := "Kun-Nat"]
NL <- NL[kun2 == 1, match_type := "Kun-Kun"]
saveRDS(NL, "data\\NL Eredivisie 2000-2018.rds")
```