```{r}
library(lsa)
nearest <- function(df, word) {
  wEmbedding <- df[which(df$word==word),]$fastrpEmbedding %>% unlist
  
  res <- df %>% rowwise() %>% mutate(sim = cosine(unlist(fastrpEmbedding), wEmbedding)) %>% arrange(-sim) %>% select(-fastrpEmbedding)
  res[-1,]
}

deduped_words %>% nearest("mi")
```

```{r}
analogue <- function(df, a, b, c) {
  embA <- unlist(words[which(words$word==a),]$fastrpEmbedding)
  embB <- unlist(words[which(words$word==b),]$fastrpEmbedding)
  embC <- unlist(words[which(words$word==c),]$fastrpEmbedding)
  
  embD <- embA - embB + embC
  
  res <- df %>% rowwise() %>% mutate(sim = cosine(unlist(fastrpEmbedding), embD)) %>% arrange(-sim) %>% select(-fastrpEmbedding)
  res[-1,]
}
deduped_words %>% analogue("ŝi", "virino", "viro")
```