sfirke

final_blank <- read_csv("data/kaggle/SampleSubmission.csv") %>%
  separate(Id, into = c("year", "lower_team", "higher_team"), sep = "_", convert = TRUE, remove = FALSE) %>%
  dplyr::select(-Pred)

final_blank_with_data <- final_blank %>%
  add_kp_data %>%
  create_vars_for_prediction %>%
  mutate(lower_team_court_adv = as.factor("N")) %>%
  dplyr::select(contains("diff"), lower_team_court_adv, contains("rank")) %>%
  dplyr::select(-lower_pre_seas_rank_all, -higher_pre_seas_rank_all)

sfirke

library(pacman)
p_load(fuzzyjoin, dplyr)
# returns clusters of records that almost match
get_fuzzy_dupes <- function(x, max_dist = 2){
  result <- stringdist_inner_join(x, x, max_dist = max_dist, distance_col = "distance")
  result <- result[result[[1]] != result[[2]], ] # remove actual 100% accurate duplicates
  result <- t(apply(result, 1, sort)) # these two lines treat A, B as a duplicate of B, A and remove it.  From http://stackoverflow.com/a/9028416
  result <- result[!duplicated(result), ]
  as_data_frame(result) %>%

sfirke

library(stringr)

get_part_before_dot <- function(email){
  x <- str_split(email, "[.]")
  lapply(x, `[[`, 1) %>%
    unlist
}


dat <- data.frame(email = c("robert.rosen@tntp.org", "Sam.firke@tntp.org"))

sfirke

## Date to SY function
## Year of 2nd argument does not matter
## Turns 2015-10-02 into "2015-16", and 2016-04-05 into "2015-16", with cutoff day = 2010-07-01
date_to_sy <- function(date_var, last_day_of_sy){
  if(!(is.Date(date_var) & is.Date(last_day_of_sy))){stop("`date_var` and `last_day_of_sy` must both be class Date")}
  cutoff_day <- day(last_day_of_sy)
  cutoff_month <- month(last_day_of_sy)
  case_when(
    is.na(date_var) ~ as.character(NA),
    month(date_var) > cutoff_month ~ paste0(year(date_var), " - ", year(date_var) + 1), # if past cutoff, X - X+!

sfirke

clean_names <- function(dat){
  # Takes a data.frame, returns the same data frame with cleaned names
  old_names <- names(dat)
  new_names <- old_names %>%
    gsub("%", "percent", .) %>%
    make.names(.) %>%
    gsub("[.]+", "_", .) %>%
    tolower(.) %>%
    gsub("_$", "", .)
  setNames(dat, new_names)

sfirke

SELECT Id, Body, Tags
FROM Posts
WHERE Body LIKE '%set.seed(%' AND Tags LIKE '%r%'