Created
July 18, 2017 02:23
-
-
Save lgallen/d768b529edd314e519de2bc466372758 to your computer and use it in GitHub Desktop.
A efficient implementation of cosine similarity created for a Shiny app about games.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
cosine_similarity_vec <- function(row_index, df){ | |
row <- df[row_index,] | |
mat <- df[-row_index,] | |
numerator <- rowSums(sweep(mat, MARGIN=2, row, "*")) | |
denominator <- sqrt(sum(row**2)) * sqrt(rowSums(mat**2)) | |
similarities <- numerator/denominator | |
game_numbers <- 1:dim(df)[1] | |
game_numbers <- game_numbers[! game_numbers %in% row_index] | |
df_similarity <- data.frame(game_numbers, similarities) | |
df_similarity <- df_similarity %>% arrange(desc(similarities)) | |
return(df_similarity) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment