-
Notifications
You must be signed in to change notification settings - Fork 0
/
Chess_Analysis.Rmd
143 lines (123 loc) · 5.32 KB
/
Chess_Analysis.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
---
title: "Chess Master Pairings"
output: html_notebook
---
```{r Load Libraries, echo=F}
library(dplyr); library(rvest); library(stringr); library(ggplot2)
library(forcats); library(tidyr)
```
### Scrape data from chess-results.com
```{r Get Masters Data: 1}
page <- "http://www.chess-results.com/tnr257693.aspx?lan=1&art=0&wi=821&zeilen=99999"
page_html <- read_html(page)
masters <- page_html %>% html_nodes("#_ctl0_F7 > div:nth-child(2) > table") %>% html_table() %>% .[[1]]
names(masters) <- masters[1,]
names(masters)[2] <- "rating_category"
masters <- masters %>% slice(-1) %>%
mutate(player_id = `No.`, name = Name, fide_id = FideID,
country = FED, rating = as.integer(Rtg)) %>%
select(player_id, fide_id, name, country, rating_category, rating)
FideID_links <- page_html %>% html_nodes("td:nth-child(4) a") %>% html_attr("href")
masters$fideid_links <- FideID_links
```
### Get gender data from each player's page
```{r Get Masters Data: 2}
get_gender <- function(player_page){
player_page_html <- read_html(player_page)
gender <- player_page_html %>%
html_nodes(".contentpaneopen table td:nth-child(1) tr:nth-child(7) td:nth-child(2)") %>%
html_text() %>% str_trim()
if(length(gender) != 1){
return(NA)
} else
{
return(gender)
}
}
gender_list <- vector(mode = "list", length = nrow(masters))
for(i in seq_along(gender_list)){
print(paste0("Getting # ", i))
print(paste0("Link: ", masters$fideid_links[i]))
gender_list[[i]] <- get_gender(masters$fideid_links[i])
}
masters$gender <- gender_list %>% unlist()
```
### Clean & Summarize Masters Data
```{r Get Masters Data: 3}
masters_gender_manual <-
tribble(
~fide_id, ~gender,
"24614386", "Male",
"1400231", "Male",
"24165514", "Male",
"14105870", "Female",
"405256", "Male",
"8500150", "Male",
"620165", "Male",
"9100075", "Male"
)
masters <-
left_join(masters, masters_gender_manual, by = "fide_id") %>%
mutate(gender = ifelse(is.na(gender.x), gender.y, gender.x)) %>%
select(-gender.x, -gender.y, player_id:name, gender, country:fideid_links)
#Display & Summarise Masters data
masters
masters %>% group_by(rating_category) %>% summarise(count = n())
masters_gender_summary <-
masters %>% group_by(gender) %>%
summarise(count = n())
masters_country_gender_summary <-
masters %>% group_by(country, gender) %>%
summarise(count = n()) %>% ungroup() %>%
spread(gender, count) %>%
mutate(Female = ifelse(is.na(Female), 0, Female),
Male = ifelse(is.na(Male), 0, Male),
Female_pct = 100 * round(Female / (Female + Male), 2)) %>%
arrange(desc(Female))
masters_country_gender_summary
ggplot(masters_country_gender_summary %>% gather(gender, count, Female:Male) %>% mutate(country = factor(country))) +
geom_bar(aes(fct_reorder(country, -count), count, fill = gender), stat = "identity", position = "stack") +
theme(axis.text.x = element_text(angle = 90, size = 6, vjust = .5)) +
ggtitle("Chess Masters by Country & Gender") + xlab("") + ylab("# Players")
```
### Get Pairing Data
```{r Get Pairing Data}
pairing_list <- vector(mode = "list", length = 10)
pairing_page <- function(i) paste0("http://www.chess-results.com/tnr257693.aspx?lan=1&art=2&rd=", i, "&turdet=YES&wi=821")
for(i in 1:10){
page_html <- read_html(pairing_page(i))
pairing <- page_html %>% html_nodes(".CRs1") %>% html_table() %>% .[[1]]
names(pairing) <- pairing[1,]
names(pairing)[1] <- "board_id"
names(pairing)[c(2:4,10,11,14)] <- c("player1_id", "X1", "player1_name",
"X2", "player2_name", "player2_id")
pairing <- pairing[c(1,2,4,14,11)] %>% slice(-1) %>% mutate(round = i)
pairing_list[[i]] <- pairing
}
pairing <- bind_rows(pairing_list)
pairing <-
pairing %>%
left_join(masters %>% select(player_id, gender), by = c("player1_id" = "player_id")) %>%
rename(player1_gender = gender) %>%
left_join(masters %>% select(player_id, gender), by = c("player2_id" = "player_id")) %>%
rename(player2_gender = gender) %>%
mutate(game_type = ifelse(is.na(player2_gender), "unmatched",
ifelse(player1_gender == "Female" & player2_gender == "Female", "F-F",
ifelse(player1_gender == "Male" & player2_gender == "Male", "M-M",
ifelse(player1_gender != player2_gender, "mixed", "weird")))))
```
### Summarize pairing data
```{r Summarize pairing data}
pairing %>% group_by(game_type) %>% summarise(num_games = n()) %>% arrange(desc(num_games))
pairing %>%
filter(game_type == "F-F") %>%
select(player1_name, player2_name) %>%
gather(player_num, player_name) %>%
group_by(player_name) %>% summarise(num_Female_Female_Matches = n()) %>%
arrange(desc(num_Female_Female_Matches)) %>%
ggplot(aes(fct_reorder(player_name, num_Female_Female_Matches), num_Female_Female_Matches)) + geom_bar(stat = "identity") +
coord_flip() + scale_y_continuous(breaks = 0:7) +
xlab("") + ylab("") +
ggtitle("2017 Tradewise Gibraltar Chess Tournament", subtitle = "Number of Female-Female Matches") +
theme(axis.text.y = element_text(vjust = .3))
```