debate_data.Rmd

---
title: "Debate"
author: "Chris Hua"
date: "February 13, 2017"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = FALSE)
library(googlesheets)
library(magrittr)
library(dplyr)
library(tidyr)
```

# Data import

May need to do this to authenticate...

```{r, eval = F}
gs_ls()
```

Main sheet has links to all tournaments Google docs. If `ws=1` then this is 2016-17 data, `ws=2` is 2015-16, `ws=1` is 2014-15. Remove the camp/lab tournaments and fix tournament names.

```{r contents}
main_sheet <- gs_url("https://docs.google.com/spreadsheets/d/1zHl8n2_ORg3daWUCDK07Bt-5jjYddQ_TltWncD06434/")
main_data <- gs_read_csv(main_sheet, ws = 2) 
names(main_data) <- c("tournament", "link")
main_data %<>%
  filter(!(tournament %in% 
             c("Pronouns Doc-", "BEFJR In-Lab -", "GASM In-Lab -",
               "DDI Camp -", "GDI Camp -", "NDI Camp -", "UMich Camp -", 
               "Pre-2014 Archives -")))
main_data$tournament %<>%
  stringr::str_replace("-", "") %>%
  stringr::str_trim()
```

Example with 2016 TOC

```{r}
toc <- gs_url("https://docs.google.com/spreadsheets/d/1aVnIxUYmuVrlfHR4NRyuYsFhiCIhs9vNv1IFKVC4bCc/")
toc_data <- gs_read_csv(toc, ws = 1)
```

```{r}
toc_rounds <- 7
toc_round_max <- sprintf("Round %s", toc_rounds)

toc_opp <- toc_data %>%
  dplyr::select(1, 3:9) %>% 
  gather_(key = "round", value = "opponent", paste("Round", 1:toc_rounds))
  
toc_results <- toc_data %>%
  select(1, 10:16) %>% 
  tidyr::gather(key = "round", value = "win", `Round 1 Result` : `Round 7 Result`)

toc_results$round %<>%
  stringr::str_replace(" Result", "")

toc_tidy <- left_join(toc_opp, toc_results, by = c("Team", "round"))
toc_tidy %<>% rename(team = Team)

toc_tidy %>% head
```

```{r}
# read_tournament_data(url, rounds)
```

```{r}
# ndca_doc <- gs_read_csv(toc, ws = 2)
ss <- gs_url("https://docs.google.com/spreadsheets/d/1aVnIxUYmuVrlfHR4NRyuYsFhiCIhs9vNv1IFKVC4bCc/")
tidy_debate <- function(ss, ws_num, rounds = 6, sleep = T) {
  if(sleep) Sys.sleep(6)
  doc <- gs_read_csv(ss, ws = ws_num)
  names(doc)[1] <- "Team"
  toc_opp <- doc %>%
    select(1, 3:(2 + rounds)) %>% 
    tidyr::gather_(key = "round", value = "opponent", 
                   gather_cols = paste("Round", 1:rounds))
  toc_results <- doc %>%
    select(1, (3+rounds):(2+rounds*2)) %>% 
    tidyr::gather_(key = "round", value = "win", 
                   sprintf("Round %s Result", 1:rounds))
  toc_results$round %<>%
    stringr::str_replace(" Result", "")
  toc_tidy <- left_join(toc_opp, toc_results, by = c("Team", "round"))
  names(toc_tidy)[1] <- "team"
  toc_tidy
}
```

Read tournaments

```{r}
ndca_tidy <- tidy_debate(ss, ws_num = 2)
toc_tidy <- tidy_debate(ss, ws_num = 1, rounds = 7)
berk_tidy <- tidy_debate(ss, ws_num = 3)
alta_tidy <- tidy_debate(ss, ws_num = 4)
asu_tidy <- tidy_debate(ss, ws_num = 5)
blake_tidy <- tidy_debate(ss, ws_num = 6, rounds = 7)
emery_tidy <- tidy_debate(ss, ws_num = 7)
fullerton_tidy <- tidy_debate(ss, ws_num = 8)
georgetown_tidy <- tidy_debate(ss, ws_num = 9)
glenbrooks_tidy <- tidy_debate(ss, ws_num = 10, rounds = 7)
goldendesert_tidy <- tidy_debate(ss, ws_num = 11)
gonzaga_tidy <- tidy_debate(ss, ws_num = 12)
```

Save data

```{r}
write.csv(berk_tidy, "berk2016.csv", row.names = F)
write.csv(ndca_tidy, "ndca2016.csv", row.names = F)
write.csv(toc_tidy, "toc2016.csv", row.names = F)
write.csv(alta_tidy, "alta2016.csv", row.names = F)
write.csv(asu_tidy, "asu2016.csv", row.names = F)
write.csv(blake_tidy, "blake2016.csv", row.names = F)
write.csv(emery_tidy, "emery2016.csv", row.names = F)
write.csv(fullerton_tidy, "fullerton2016.csv", row.names = F)
write.csv(georgetown_tidy, "georgetown2016.csv", row.names = F)
write.csv(glenbrooks_tidy, "glenbrooks2016.csv", row.names = F)
write.csv(goldendesert_tidy, "goldendesert2016.csv", row.names = F)
write.csv(gonzaga_tidy, "gonzaga2016.csv", row.names = F)
```