spacy_regression

Load saved CHILDES .csv corpus for a language (here French and Italian).

Rbind different corpora.

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.3     ✓ purrr   0.3.4
## ✓ tibble  3.1.0     ✓ dplyr   1.0.5
## ✓ tidyr   1.1.3     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(lme4)

## Loading required package: Matrix

## 
## Attaching package: 'Matrix'

## The following objects are masked from 'package:tidyr':
## 
##     expand, pack, unpack

library(ggeffects)
library(wordbankr)
library(psych)

## 
## Attaching package: 'psych'

## The following objects are masked from 'package:ggplot2':
## 
##     %+%, alpha

library(reshape2)

## 
## Attaching package: 'reshape2'

## The following object is masked from 'package:tidyr':
## 
##     smiths

library(ggpubr)

## Registered S3 methods overwritten by 'car':
##   method                          from
##   influence.merMod                lme4
##   cooks.distance.influence.merMod lme4
##   dfbeta.influence.merMod         lme4
##   dfbetas.influence.merMod        lme4

library(rstatix)

## 
## Attaching package: 'rstatix'

## The following object is masked from 'package:stats':
## 
##     filter

library(data.table)

## 
## Attaching package: 'data.table'

## The following objects are masked from 'package:reshape2':
## 
##     dcast, melt

## The following objects are masked from 'package:dplyr':
## 
##     between, first, last

## The following object is masked from 'package:purrr':
## 
##     transpose

library(gridExtra)

## 
## Attaching package: 'gridExtra'

## The following object is masked from 'package:dplyr':
## 
##     combine

library(here)

## here() starts at /Users/lscpuser/Documents/fyssen-project

library(langcog)

## 
## Attaching package: 'langcog'

## The following object is masked from 'package:base':
## 
##     scale

library(modelr)
#theme_set(theme_mikabr())
#font <- theme_mikabr()$text$family

source("get_wordbank.R")

Load data and clean CHILDES utterances by removing puctuation, incomplete sentences and target-child speech.

#add this function to aoa
clean_childes <- function(corpus_) {
  annot <- c("xxx", "yyy", "www", "-", "'") 
  annotUtt <- filter(corpus_, lemma %in% annot) 
  annotUttID<- unique(annotUtt$utterance_id) 
  corpus_ <- filter(corpus_, !(utterance_id  %in% annotUttID))  #remove utterances with annotations - incomplete info
  corpus_<-corpus_ %>% filter (speaker_code != "CHI") #remove target child utterances
  corpus_<-corpus_ %>% filter (pos != "PUNCT")  #remove punctuation 
  corpus_ %>% mutate(lemma = tolower(lemma))
}

load_data <- function(language_list) {
  for (lang in language_list){
    if (lang == "english")     { 
      english=read_csv(here("data/Providence_spacy.csv"))
      english=clean_childes(english)
      english <- english %>% 
            mutate(language = "english")
    }
    if (lang == "italian")     { 
      italian=read_csv(here("data/italian_1403.csv"))
      italian=clean_childes(italian)
      italian <- italian %>% 
            mutate(language = "italian")
    }
    if (lang == "french")     { 
      french=read_csv(here("data/french_1403.csv"))
      french=clean_childes(french)
      french <- french %>% 
            mutate(language = "french")
    }
  }
  return(list(english = data.table(english), italian = data.table(italian), french = data.table(french)))
  #return(list(english = data.table(english), italian = data.table(italian)))

  }

corpus<-load_data(language_list) 

## Warning: Missing column names filled in: 'X1' [1]

## Warning: Missing column names filled in: 'X1' [1]

#corpus <- lapply(corpus, clean_childes)

lapply(corpus, function(x) {
  summary(x)
})

## $english
##      text              lemma               lex                pos           
##  Length:601140      Length:601140      Length:601140      Length:601140     
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##      tag             dependency           morph               prefix         
##  Length:601140      Length:601140      Length:601140      Min.   :1.010e+02  
##  Class :character   Class :character   Class :character   1st Qu.:5.100e+18  
##  Mode  :character   Mode  :character   Mode  :character   Median :1.190e+19  
##                                                           Mean   :1.016e+19  
##                                                           3rd Qu.:1.540e+19  
##                                                           Max.   :1.800e+19  
##    prefix_              suffix            suffix_            sentiment
##  Length:601140      Min.   :1.010e+02   Length:601140      Min.   :0  
##  Class :character   1st Qu.:5.010e+18   Class :character   1st Qu.:0  
##  Mode  :character   Median :9.600e+18   Mode  :character   Median :0  
##                     Mean   :9.701e+18                      Mean   :0  
##                     3rd Qu.:1.490e+19                      3rd Qu.:0  
##                     Max.   :1.840e+19                      Max.   :0  
##   utterance_id      target_child_id speaker_code       corpus_name       
##  Min.   :16759250   Min.   :22704   Length:601140      Length:601140     
##  1st Qu.:16824040   1st Qu.:22704   Class :character   Class :character  
##  Median :16880697   Median :22720   Mode  :character   Mode  :character  
##  Mean   :16875975   Mean   :22719                                        
##  3rd Qu.:16929977   3rd Qu.:22728                                        
##  Max.   :16974451   Max.   :22728                                        
##  transcript_id     language        
##  Min.   :42204   Length:601140     
##  1st Qu.:42251   Class :character  
##  Median :42296   Mode  :character  
##  Mean   :42290                     
##  3rd Qu.:42329                     
##  Max.   :42374                     
## 
## $italian
##        X1             text              lemma               lex           
##  Min.   :     4   Length:191701      Length:191701      Length:191701     
##  1st Qu.:116248   Class :character   Class :character   Class :character  
##  Median :228267   Mode  :character   Mode  :character   Mode  :character  
##  Mean   :226863                                                           
##  3rd Qu.:338982                                                           
##  Max.   :437481                                                           
##      pos                tag             dependency           morph          
##  Length:191701      Length:191701      Length:191701      Length:191701     
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##      prefix            prefix_              suffix            suffix_         
##  Min.   :7.187e+15   Length:191701      Min.   :1.675e+16   Length:191701     
##  1st Qu.:3.209e+18   Class :character   1st Qu.:5.304e+18   Class :character  
##  Median :1.190e+19   Mode  :character   Median :9.840e+18   Mode  :character  
##  Mean   :1.023e+19                      Mean   :9.961e+18                     
##  3rd Qu.:1.560e+19                      3rd Qu.:1.405e+19                     
##  Max.   :1.800e+19                      Max.   :1.845e+19                     
##    sentiment  utterance_id     target_child_id speaker_code      
##  Min.   :0   Min.   :7388853   Min.   :14314   Length:191701     
##  1st Qu.:0   1st Qu.:7425645   1st Qu.:14341   Class :character  
##  Median :0   Median :7452333   Median :14377   Mode  :character  
##  Mean   :0   Mean   :7453658   Mean   :14374                     
##  3rd Qu.:0   3rd Qu.:7482842   3rd Qu.:14412                     
##  Max.   :0   Max.   :7514844   Max.   :14421                     
##  corpus_name        transcript_id     language        
##  Length:191701      Min.   :22462   Length:191701     
##  Class :character   1st Qu.:22497   Class :character  
##  Mode  :character   Median :22532   Mode  :character  
##                     Mean   :22539                     
##                     3rd Qu.:22584                     
##                     Max.   :22616                     
## 
## $french
##        X1              text              lemma               lex           
##  Min.   :     11   Length:1550282     Length:1550282     Length:1550282    
##  1st Qu.: 760646   Class :character   Class :character   Class :character  
##  Median :1456100   Mode  :character   Mode  :character   Mode  :character  
##  Mean   :1444290                                                           
##  3rd Qu.:2108927                                                           
##  Max.   :2970632                                                           
##      pos                tag             dependency           morph          
##  Length:1550282     Length:1550282     Length:1550282     Length:1550282    
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##      prefix            prefix_              suffix            suffix_         
##  Min.   :7.187e+15   Length:1550282     Min.   :4.050e+02   Length:1550282    
##  1st Qu.:2.985e+18   Class :character   1st Qu.:5.902e+18   Class :character  
##  Median :9.149e+18   Mode  :character   Median :1.126e+19   Mode  :character  
##  Mean   :9.195e+18                      Mean   :1.050e+19                     
##  3rd Qu.:1.537e+19                      3rd Qu.:1.462e+19                     
##  Max.   :1.800e+19                      Max.   :1.844e+19                     
##    sentiment  utterance_id      target_child_id speaker_code      
##  Min.   :0   Min.   :17476553   Min.   :23235   Length:1550282    
##  1st Qu.:0   1st Qu.:17655732   1st Qu.:23275   Class :character  
##  Median :0   Median :17800624   Median :23312   Mode  :character  
##  Mean   :0   Mean   :17788687   Mean   :23319                     
##  3rd Qu.:0   3rd Qu.:17922106   3rd Qu.:23381                     
##  Max.   :0   Max.   :18149594   Max.   :23412                     
##  corpus_name        transcript_id     language        
##  Length:1550282     Min.   :44628   Length:1550282    
##  Class :character   1st Qu.:44900   Class :character  
##  Mode  :character   Median :45108   Mode  :character  
##                     Mean   :45033                     
##                     3rd Qu.:45176                     
##                     Max.   :45263

Measure frequency

source("measure_frequency.R") # add interecept function to aoa-pipeline

frequencies <- lapply(corpus, frequency_model) %>%
  bind_rows()

## `summarise()` has grouped output by 'lemma', 'target_child_id'. You can override using the `.groups` argument.

## `summarise()` has grouped output by 'target_child_id'. You can override using the `.groups` argument.

## Joining, by = c("target_child_id", "language")

## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.

## Joining, by = c("lemma", "language")
## Joining, by = c("lemma", "language")

## `summarise()` has grouped output by 'lemma', 'target_child_id'. You can override using the `.groups` argument.

## `summarise()` has grouped output by 'target_child_id'. You can override using the `.groups` argument.

## Joining, by = c("target_child_id", "language")

## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.

## Joining, by = c("lemma", "language")
## Joining, by = c("lemma", "language")

## `summarise()` has grouped output by 'lemma', 'target_child_id'. You can override using the `.groups` argument.

## `summarise()` has grouped output by 'target_child_id'. You can override using the `.groups` argument.

## Joining, by = c("target_child_id", "language")

## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.

## Joining, by = c("lemma", "language")
## Joining, by = c("lemma", "language")

# TEST1 frequency metric:
#frequencies %>% 
 # group_by(target_child_id) %>% 
  #summarize (sum(rawFrequency)) #Test frequence: should be 1 for each child

# TEST2 frequency metric:   
#frequencies %>% 
 # arrange(desc(FrequencyLog))#: maximum values

Measure aoas

language_list_=c("Italian", "English (American)", "French (French)")  

aoas <- lapply(language_list_, load_wordbank) %>%
  bind_rows()

## Joining, by = c("num_item_id", "item_id", "type", "category", "lexical_category", "lexical_class", "uni_lemma", "complexity_category")
## Joining, by = c("num_item_id", "item_id", "type", "category", "lexical_category", "lexical_class", "uni_lemma", "complexity_category")
## Joining, by = c("num_item_id", "item_id", "type", "category", "lexical_category", "lexical_class", "uni_lemma", "complexity_category")

Merge all

d <- aoas %>%
  group_by(language, lemma, lexical_class) %>%
  summarise(aoa = aoa[1]) %>%
  filter(!is.na(aoa)) %>%
  mutate(language = ifelse(language == "French (French)", "french", language)) %>%
  mutate(language = ifelse(language == "English (American)", "english", language)) %>%
  mutate(language = ifelse(language == "Italian", "italian", language)) %>%
  left_join(frequencies %>% 
              group_by(language, lemma) %>%
              summarise(log_freq = FrequencyLogMean[1], 
                        intercept_freq = interceptmodel[1])   )

## `summarise()` has grouped output by 'language', 'lemma'. You can override using the `.groups` argument.

## `summarise()` has grouped output by 'language'. You can override using the `.groups` argument.

## Joining, by = c("language", "lemma")

Plot frequency and aoa using log frequency and model intercept frequency

d<-d %>% 
  filter(!is.na(log_freq)) 


plot_frequency1<-function(db, language){
  ggplot(db, 
         aes(log_freq, aoa, label=lemma)) + 
    geom_point()  +
    geom_smooth() + 
    geom_point(alpha=.1)+
    ggrepel::geom_label_repel()+
    geom_text(aes(label=lemma),hjust=0, vjust=0)  +
    xlim(0,0.6) + 
    facet_wrap(~lexical_class, nrow=2) +
    ggtitle(paste(language)) 
    
}

plot_frequency2<-function(db){
  ggplot(db, 
         aes(intercept_freq, aoa, label=lemma)) + 
    geom_point()  +
    geom_text(aes(label=lemma),hjust=0, vjust=0) + facet_wrap(~lexical_class, nrow=2)
}

plot_frequency3<-function(db){
  ggplot(db, 
         aes(x = intercept_freq, y = log_freq, label = lemma)) + 
    geom_point() + 
    geom_smooth(method = "lm") +   facet_wrap(~lexical_class, nrow=2)
}

plot_frequency1(filter(d, language == "english"), "english")

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

## Warning: Removed 15 rows containing non-finite values (stat_smooth).

## Warning: Removed 15 rows containing missing values (geom_point).

## Warning: Removed 15 rows containing missing values (geom_point).

## Warning: Removed 15 rows containing missing values (geom_label_repel).

## Warning: Removed 15 rows containing missing values (geom_text).

## Warning: ggrepel: 50 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 49 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 30 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 83 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 247 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

plot_frequency1(filter(d, language == "italian"), "italian")

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

## Warning: Removed 12 rows containing non-finite values (stat_smooth).

## Warning: Removed 12 rows containing missing values (geom_point).

## Warning: Removed 12 rows containing missing values (geom_point).

## Warning: Removed 12 rows containing missing values (geom_label_repel).

## Warning: Removed 12 rows containing missing values (geom_text).

## Warning: ggrepel: 50 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 37 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 25 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 88 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 196 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

plot_frequency1(filter(d, language == "french"), "french")

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

## Warning: Removed 13 rows containing non-finite values (stat_smooth).

## Warning: Removed 13 rows containing missing values (geom_point).

## Warning: Removed 13 rows containing missing values (geom_point).

## Warning: Removed 13 rows containing missing values (geom_label_repel).

## Warning: Removed 13 rows containing missing values (geom_text).

## Warning: ggrepel: 17 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 38 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 20 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 62 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

## Warning: ggrepel: 202 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps

ggplot(d, aes(x = log_freq, y = aoa, col = lexical_class)) + 
  geom_point(alpha = .1) + 
  geom_smooth(method = "lm") + 
  facet_grid(rows = vars(language)) +
 # facet_grid(language ~ lexical_class, scales = "free_x") + 
 # langcog::theme_mikabr() + 
 # langcog::scale_color_solarized() + 
  theme(legend.position = "bottom") + 
  xlab("Frequency (log)") + 
  ylab("Age of Acquisition (months)")

## `geom_smooth()` using formula 'y ~ x'

### Reliability_frequency: half-split and Spearman-Brown


```r
# add lemmas of the first half not existing at the second half, with 1 
same_size_df <- function(df1, df2) { 
  firstlistlemma<-(df1$name)
  secondlistlemma<-(df2$name)
  diff1<-setdiff(firstlistlemma,secondlistlemma) 
  df<-as.data.frame(diff1)
  df[,2] <- NA
  df[,3] <- 1
  colnames(df)<- c("lemma","pos","CountLemma")
  df$name = df$lemma
  secondhalf<- rbind(df2, df)
  return(secondhalf)
}


split_half_cor <-function(dataAoa, corpus){
  n<-nrow(corpus) #corpus size in word tokens
  
  wblemmas<-unique(dataAoa$lemma) #unique wordbank lemmas
  
  ind <- sample(c(TRUE, FALSE), n, replace=TRUE, prob=c(0.5, 0.5)) #randomly split word tokens
  firsthalf <- corpus[ind, ] #split in two
  secondhalf <- corpus[!ind, ]
  
  firsthalf <- firsthalf %>%  
    group_by(lemma, pos) %>% 
    summarize(CountLemma=n()) #group by lemma and pos and count raw frequency
  
  secondhalf <- secondhalf %>%  
    group_by(lemma, pos) %>% 
    summarize(CountLemma=n()) 
  
  secondhalf <- secondhalf[secondhalf$lemma %in% wblemmas, ] #keep only lemmas existing in wordbank
  firsthalf <- firsthalf[firsthalf$lemma %in% wblemmas, ]
  
  firsthalf$name <- paste(firsthalf$lemma, "-", firsthalf$pos) #merge lemma and pos to a new name, just in case
  secondhalf$name <- paste(secondhalf$lemma, "-", secondhalf$pos)
  
  firsthalf<-firsthalf[order(firsthalf$name),] #order vector alphabetically
  secondhalf<-secondhalf[order(secondhalf$name),]
  
  secondhalf<- same_size_df(firsthalf, secondhalf)
  firsthalf<-same_size_df(secondhalf, firsthalf)
  
  firsthalf<-firsthalf[order(firsthalf$name),] #order again
  secondhalf<-secondhalf[order(secondhalf$name),]
  
  r<-cor(firsthalf$CountLemma, secondhalf$CountLemma, method="kendall") #measure r
  return(r)
}

sbformula <- function(r){  #adjust with spearman-brown formula
  r1<-(2*r)/(1+r)
  return(r1)
}

Reliability_frequency: cronbach alpha

cronbach_alpha <-function(dataAoa, corpus_frequency_){
  corpus_frequency_reliability <- corpus_frequency_ %>% 
    ungroup() %>% 
    select(lemma, rawFrequency, target_child_id)
  
  wblemmas<-unique(dataAoa$lemma) #unique wordbank lemmas
  corpus_frequency_reliability  <- corpus_frequency_reliability [corpus_frequency_reliability $lemma %in% wblemmas, ] #keep only lemmas with corresponding items in wordbank
  
  lemma_<-corpus_frequency_reliability$lemma  #restructure dataframe
  target_child_id_<-corpus_frequency_reliability$target_child_id
  freq_<-corpus_frequency_reliability$rawFrequency
  
  df<-data.frame(lemma_, target_child_id_, freq_)
  corpus_frequency_reliability_<-tidyr::spread(df, target_child_id_, freq_)
  
  child_ids_<- unique(as.character(colnames(corpus_frequency_reliability_)[3:ncol(corpus_frequency_reliability_)]))
  
  child<-select(corpus_frequency_reliability_, child_ids_ )
  a<-alpha(child) 
#  return(a$raw_)
 return(a$total[1,1]) 
}

Measure reliabilities

reliabilities <- expand_grid(language = c( "english", "italian", "french"), 
                            word_class = c("all", "nouns","adjectives","verbs",
                                           "function_words","other")) %>% 
  rowwise %>%
  mutate(split_half_tau = ifelse(word_class == "all", 
                             split_half_cor(aoas, corpus[[language]]),
                             split_half_cor(filter(aoas, 
                                                   lexical_class == word_class),
                                            corpus[[language]])),
         split_half_tau_sb = sbformula(split_half_tau) )#,

## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.
## `summarise()` has grouped output by 'lemma'. You can override using the `.groups` argument.

    #  cronbach_alpha = ifelse(word_class == "all", 
     #             cronbach_alpha(aoas, 
      #                           filter(frequencies, 
       #                                 language == language)),
        #          cronbach_alpha(filter(aoas, 
         #                               lexical_class == word_class),
          #                       filter(frequencies, 
           #                             language == language))))

reliabilities %>%
  knitr::kable(digits = 2)

language	word_class	split_half_tau	split_half_tau_sb
english	all	0.90	0.95
english	nouns	0.87	0.93
english	adjectives	0.90	0.94
english	verbs	0.89	0.94
english	function_words	0.93	0.96
english	other	0.87	0.93
italian	all	0.81	0.90
italian	nouns	0.77	0.87
italian	adjectives	0.77	0.87
italian	verbs	0.84	0.91
italian	function_words	0.88	0.93
italian	other	0.83	0.91
french	all	0.89	0.94
french	nouns	0.89	0.94
french	adjectives	0.86	0.93
french	verbs	0.91	0.95
french	function_words	0.83	0.91
french	other	0.86	0.93

reliabilities <- reliabilities %>%
    mutate(language = sub("english", "English (American)", language)) %>%
    mutate(language = sub("italian", "Italian", language)) %>%
    mutate(language = sub("french", "French (French)", language))

Reliability_AoA

split_half_cor_aoa <-function(lang_, clas_){
  
  i<-get_item_data(language = lang_,form="WS")
  i<-i %>% filter(type=="word") #get item data and filter by lexical class
  if (clas_ != ""){
    i<-i %>% filter(lexical_class==clas_)  
    }
  if (lang_ == "French (French)") {
   i <- filter(i, item_id !="item_514")
   i <- filter(i, item_id !="item_628")
   i <- filter(i, item_id !="item_601")
   i <- filter(i, item_id !="item_627")
   i <- filter(i, item_id !="item_452")
   i <- filter(i, item_id !="item_599")
    }  
  ids<-unique(i$item_id)
  ids<-lapply(X = ids, FUN = function(t) gsub(pattern = "item_", replacement = "", x = t, fixed = TRUE))
  
  items<-get_instrument_data(language = lang_,form="WS", administrations = TRUE) #get instrument data and filter by item
  items<-items %>% filter(num_item_id %in% ids)
  
  admin<-as.data.frame(unique(items$data_id))
  n<-nrow(admin) #corpus size in word tokens
  ind <- sample(c(TRUE, FALSE), n, replace=TRUE, prob=c(0.5, 0.5)) #randomly split administrations
  
  adminfirstnum <- admin[ind, ]
  adminsecondnum <- admin[!ind, ] #create two groups of administrations
  
  adminfirst<-items %>% filter(data_id %in% adminfirstnum) #filter items in administrations
  adminsecond<-items %>% filter(data_id %in% adminsecondnum)
  
  aoafirst<- fit_aoa(adminfirst, method = "glmrob", proportion = 0.5) # get aoa for each group
  aoasecond<- fit_aoa(adminsecond, method = "glmrob", proportion = 0.5) # 
  
  r<-cor(aoafirst$aoa, aoasecond$aoa, use="complete.obs", method="kendall") #measure r
  return(r)
}

reliabilities_aoa <- expand_grid(language = c("French (French)","English (American)", "Italian"),
                            word_class = c("all", "nouns","adjectives","verbs",
                                           "function_words","other")) %>% 
  rowwise %>%
  mutate(split_half_aoa = ifelse(word_class == "all", 
                             split_half_cor_aoa(language, ""),
                             split_half_cor_aoa(language, word_class)),
         split_half_aoa_sb = sbformula(split_half_aoa))

## Warning in glmrobMqle(X = X, y = Y, weights = weights, start = start, offset =
## offset, : Algorithm did not converge

## Warning in glmrobMqle(X = X, y = Y, weights = weights, start = start, offset =
## offset, : fitted probabilities numerically 0 or 1 occurred

reliabilities_aoa %>%
  knitr::kable(digits = 2)

language	word_class	split_half_aoa	split_half_aoa_sb
French (French)	all	0.88	0.94
French (French)	nouns	0.90	0.95
French (French)	adjectives	0.88	0.94
French (French)	verbs	0.82	0.90
French (French)	function_words	0.73	0.84
French (French)	other	0.92	0.96
English (American)	all	0.97	0.98
English (American)	nouns	0.97	0.98
English (American)	adjectives	0.96	0.98
English (American)	verbs	0.94	0.97
English (American)	function_words	0.95	0.98
English (American)	other	0.97	0.99
Italian	all	0.93	0.96
Italian	nouns	0.92	0.96
Italian	adjectives	0.91	0.95
Italian	verbs	0.89	0.94
Italian	function_words	0.92	0.96
Italian	other	0.88	0.94

Regression

regression_option1<-function(db){
  db <- db[!is.na(db$log_freq),]
  option1<-lm(aoa~ log_freq, data=db) 
  return(summary(option1)$adj.r.squared)
}

r2 <- expand_grid(lang = c("english", "italian", "french"), 
                            class = c("all", "nouns","adjectives","verbs",
                                           "function_words","other")) %>% 
  rowwise %>%
   mutate(r2 = ifelse(class == "all", 
                             regression_option1(filter(d, 
                                                   language == lang)),
                             regression_option1(filter(d, 
                                                   language == lang, lexical_class == class)))) %>%
  rename( language = lang,lexical_class = class) %>%
  left_join(d)

## Joining, by = c("language", "lexical_class")

r2 %>%
  knitr::kable(digits = 2)

language	lexical_class	r2	lemma	aoa	log_freq	intercept_freq
english	all	0.00	NA	NA	NA	NA
english	nouns	0.35	airplane	20	0.01	0.00
english	nouns	0.35	alligator	25	0.01	0.00
english	nouns	0.35	animal	24	0.04	0.00
english	nouns	0.35	ankle	30	0.00	0.00
english	nouns	0.35	ant	25	0.01	0.00
english	nouns	0.35	apple	18	0.06	0.00
english	nouns	0.35	applesauce	25	0.00	0.00
english	nouns	0.35	arm	22	0.02	0.00
english	nouns	0.35	backyard	27	0.00	0.00
english	nouns	0.35	balloon	17	0.03	0.00
english	nouns	0.35	basket	25	0.01	0.00
english	nouns	0.35	bat	26	0.02	0.00
english	nouns	0.35	bathroom	23	0.01	0.00
english	nouns	0.35	bathtub	22	0.00	0.00
english	nouns	0.35	bear	19	0.10	0.00
english	nouns	0.35	bed	20	0.04	0.00
english	nouns	0.35	bedroom	25	0.00	0.00
english	nouns	0.35	bee	21	0.02	0.00
english	nouns	0.35	belt	26	0.00	0.00
english	nouns	0.35	bench	30	0.00	0.00
english	nouns	0.35	bib	24	0.00	0.00
english	nouns	0.35	bicycle	22	0.01	0.00
english	nouns	0.35	bird	17	0.06	0.00
english	nouns	0.35	blanket	21	0.01	0.00
english	nouns	0.35	block	22	0.06	0.00
english	nouns	0.35	boat	21	0.02	0.00
english	nouns	0.35	boots	22	0.00	0.00
english	nouns	0.35	bottle	19	0.03	0.00
english	nouns	0.35	bowl	23	0.03	0.00
english	nouns	0.35	box	22	0.07	0.00
english	nouns	0.35	bread	22	0.01	0.00
english	nouns	0.35	broom	24	0.00	0.00
english	nouns	0.35	brush	22	0.02	0.00
english	nouns	0.35	bucket	26	0.01	0.00
english	nouns	0.35	bug	21	0.01	0.00
english	nouns	0.35	bunny	20	0.04	0.00
english	nouns	0.35	bus	21	0.03	0.00
english	nouns	0.35	butter	24	0.01	0.00
english	nouns	0.35	butterfly	23	0.02	0.00
english	nouns	0.35	button	22	0.02	0.00
english	nouns	0.35	cake	22	0.02	0.00
english	nouns	0.35	camera	25	0.06	0.00
english	nouns	0.35	candy	22	0.01	0.00
english	nouns	0.35	car	18	0.13	0.00
english	nouns	0.35	cat	18	0.07	0.00
english	nouns	0.35	cereal	22	0.01	0.00
english	nouns	0.35	chair	21	0.05	0.00
english	nouns	0.35	chalk	27	0.00	0.00
english	nouns	0.35	cheek	23	0.00	0.00
english	nouns	0.35	cheerios	24	0.00	0.00
english	nouns	0.35	cheese	18	0.03	0.00
english	nouns	0.35	chin	24	0.01	0.00
english	nouns	0.35	chocolate	25	0.02	0.00
english	nouns	0.35	clock	23	0.01	0.00
english	nouns	0.35	closet	26	0.01	0.00
english	nouns	0.35	cloud	25	0.01	0.00
english	nouns	0.35	coat	23	0.01	0.00
english	nouns	0.35	coffee	25	0.01	0.00
english	nouns	0.35	coke	28	0.00	0.00
english	nouns	0.35	comb	25	0.00	0.00
english	nouns	0.35	cookie	18	0.04	0.00
english	nouns	0.35	corn	24	0.01	0.00
english	nouns	0.35	couch	24	0.01	0.00
english	nouns	0.35	cow	20	0.03	0.00
english	nouns	0.35	cracker	19	0.01	0.00
english	nouns	0.35	crayon	23	0.03	0.00
english	nouns	0.35	crib	25	0.01	0.00
english	nouns	0.35	cup	20	0.03	0.00
english	nouns	0.35	deer	26	0.00	0.00
english	nouns	0.35	diaper	19	0.01	0.00
english	nouns	0.35	dish	27	0.01	0.00
english	nouns	0.35	doll	22	0.01	0.00
english	nouns	0.35	donkey	28	0.00	0.00
english	nouns	0.35	donut	26	0.00	0.00
english	nouns	0.35	door	20	0.04	0.00
english	nouns	0.35	drawer	27	0.01	0.00
english	nouns	0.35	dryer	28	0.00	0.00
english	nouns	0.35	duck	17	0.03	0.00
english	nouns	0.35	ear	18	0.03	0.00
english	nouns	0.35	egg	22	0.05	0.00
english	nouns	0.35	elephant	23	0.03	0.00
english	nouns	0.35	eye	17	0.06	0.00
english	nouns	0.35	face	24	0.06	0.00
english	nouns	0.35	finger	22	0.03	0.00
english	nouns	0.35	firetruck	24	0.01	0.00
english	nouns	0.35	flag	26	0.00	0.00
english	nouns	0.35	flower	21	0.04	0.00
english	nouns	0.35	food	23	0.02	0.00
english	nouns	0.35	foot	21	0.04	0.00
english	nouns	0.35	fork	22	0.01	0.00
english	nouns	0.35	frog	22	0.03	0.00
english	nouns	0.35	game	26	0.02	0.00
english	nouns	0.35	garage	26	0.00	0.00
english	nouns	0.35	garbage	26	0.01	0.00
english	nouns	0.35	garden	29	0.01	0.00
english	nouns	0.35	giraffe	24	0.01	0.00
english	nouns	0.35	glass	25	0.02	0.00
english	nouns	0.35	glue	29	0.01	0.00
english	nouns	0.35	goose	27	0.01	0.00
english	nouns	0.35	grass	23	0.00	0.00
english	nouns	0.35	gum	27	0.00	0.00
english	nouns	0.35	hair	20	0.03	0.00
english	nouns	0.35	hamburger	25	0.00	0.00
english	nouns	0.35	hammer	26	0.02	0.00
english	nouns	0.35	hand	21	0.09	0.00
english	nouns	0.35	hat	19	0.08	0.00
english	nouns	0.35	head	22	0.06	0.00
english	nouns	0.35	helicopter	25	0.01	0.00
english	nouns	0.35	hen	29	0.00	0.00
english	nouns	0.35	horse	21	0.02	0.00
english	nouns	0.35	hose	27	0.00	0.00
english	nouns	0.35	ice	23	0.02	0.00
english	nouns	0.35	jacket	24	0.00	0.00
english	nouns	0.35	jar	29	0.00	0.00
english	nouns	0.35	jeans	27	0.00	0.00
english	nouns	0.35	jello	28	0.00	0.00
english	nouns	0.35	jelly	26	0.01	0.00
english	nouns	0.35	juice	17	0.03	0.00
english	nouns	0.35	kitchen	24	0.02	0.00
english	nouns	0.35	kitty	17	0.03	0.00
english	nouns	0.35	knee	22	0.01	0.00
english	nouns	0.35	knife	25	0.01	0.00
english	nouns	0.35	ladder	27	0.01	0.00
english	nouns	0.35	lamb	26	0.01	0.00
english	nouns	0.35	lamp	28	0.00	0.00
english	nouns	0.35	leg	23	0.02	0.00
english	nouns	0.35	light	20	0.04	0.00
english	nouns	0.35	lion	23	0.02	0.00
english	nouns	0.35	lollipop	27	0.00	0.00
english	nouns	0.35	meat	26	0.00	0.00
english	nouns	0.35	medicine	24	0.00	0.00
english	nouns	0.35	melon	28	0.00	0.00
english	nouns	0.35	milk	18	0.03	0.00
english	nouns	0.35	money	23	0.01	0.00
english	nouns	0.35	monkey	21	0.02	0.00
english	nouns	0.35	moon	21	0.04	0.00
english	nouns	0.35	moose	29	0.00	0.00
english	nouns	0.35	mop	29	0.00	0.00
english	nouns	0.35	motorcycle	25	0.00	0.00
english	nouns	0.35	mouse	23	0.03	0.00
english	nouns	0.35	mouth	20	0.05	0.00
english	nouns	0.35	muffin	26	0.00	0.00
english	nouns	0.35	nail	28	0.00	0.00
english	nouns	0.35	napkin	24	0.01	0.00
english	nouns	0.35	necklace	26	0.01	0.00
english	nouns	0.35	nose	17	0.05	0.00
english	nouns	0.35	nuts	27	0.00	0.00
english	nouns	0.35	oven	27	0.00	0.00
english	nouns	0.35	owl	24	0.01	0.00
english	nouns	0.35	pancake	24	0.00	0.00
english	nouns	0.35	paper	23	0.03	0.00
english	nouns	0.35	pen	24	0.02	0.00
english	nouns	0.35	pencil	25	0.01	0.00
english	nouns	0.35	penguin	27	0.00	0.00
english	nouns	0.35	penny	26	0.00	0.00
english	nouns	0.35	pickle	26	0.00	0.00
english	nouns	0.35	picture	24	0.07	0.00
english	nouns	0.35	pig	21	0.03	0.00
english	nouns	0.35	pillow	22	0.01	0.00
english	nouns	0.35	pizza	21	0.01	0.00
english	nouns	0.35	plant	26	0.01	0.00
english	nouns	0.35	plate	24	0.01	0.00
english	nouns	0.35	pony	28	0.00	0.00
english	nouns	0.35	pool	24	0.00	0.00
english	nouns	0.35	popcorn	24	0.01	0.00
english	nouns	0.35	popsicle	25	0.00	0.00
english	nouns	0.35	porch	30	0.00	0.00
english	nouns	0.35	potato	25	0.03	0.00
english	nouns	0.35	potty	21	0.03	0.00
english	nouns	0.35	present	25	0.01	0.00
english	nouns	0.35	pretzel	26	0.01	0.00
english	nouns	0.35	pudding	29	0.00	0.00
english	nouns	0.35	pumpkin	25	0.03	0.00
english	nouns	0.35	puppy	21	0.05	0.00
english	nouns	0.35	purse	25	0.00	0.00
english	nouns	0.35	puzzle	24	0.02	0.00
english	nouns	0.35	radio	27	0.00	0.00
english	nouns	0.35	rain	22	0.01	0.00
english	nouns	0.35	raisin	24	0.01	0.00
english	nouns	0.35	refrigerator	26	0.01	0.00
english	nouns	0.35	rock	22	0.03	0.00
english	nouns	0.35	roof	29	0.01	0.00
english	nouns	0.35	room	25	0.04	0.00
english	nouns	0.35	rooster	27	0.01	0.00
english	nouns	0.35	salt	28	0.00	0.00
english	nouns	0.35	sandbox	27	0.00	0.00
english	nouns	0.35	sandwich	25	0.00	0.00
english	nouns	0.35	sauce	28	0.00	0.00
english	nouns	0.35	sheep	23	0.02	0.00
english	nouns	0.35	shirt	22	0.04	0.00
english	nouns	0.35	shoulder	27	0.00	0.00
english	nouns	0.35	shovel	26	0.01	0.00
english	nouns	0.35	shower	24	0.00	0.00
english	nouns	0.35	sidewalk	27	0.00	0.00
english	nouns	0.35	sink	25	0.01	0.00
english	nouns	0.35	sky	24	0.02	0.00
english	nouns	0.35	sled	30	0.00	0.00
english	nouns	0.35	slipper	27	0.01	0.00
english	nouns	0.35	sneaker	29	0.00	0.00
english	nouns	0.35	snow	25	0.03	0.00
english	nouns	0.35	snowman	27	0.01	0.00
english	nouns	0.35	soap	22	0.00	0.00
english	nouns	0.35	sock	21	0.02	0.00
english	nouns	0.35	sofa	30	0.00	0.00
english	nouns	0.35	soup	25	0.01	0.00
english	nouns	0.35	spaghetti	24	0.00	0.00
english	nouns	0.35	spoon	20	0.03	0.00
english	nouns	0.35	sprinkler	29	0.00	0.00
english	nouns	0.35	squirrel	25	0.01	0.00
english	nouns	0.35	star	22	0.05	0.00
english	nouns	0.35	stick	24	0.06	0.00
english	nouns	0.35	stone	30	0.01	0.00
english	nouns	0.35	story	25	0.05	0.00
english	nouns	0.35	stove	26	0.00	0.00
english	nouns	0.35	strawberry	24	0.02	0.00
english	nouns	0.35	street	25	0.01	0.00
english	nouns	0.35	stroller	25	0.01	0.00
english	nouns	0.35	sun	23	0.03	0.00
english	nouns	0.35	sweater	24	0.01	0.00
english	nouns	0.35	table	23	0.03	0.00
english	nouns	0.35	tape	26	0.01	0.00
english	nouns	0.35	teddybear	23	0.00	0.00
english	nouns	0.35	telephone	21	0.00	0.00
english	nouns	0.35	tiger	24	0.01	0.00
english	nouns	0.35	toast	23	0.01	0.00
english	nouns	0.35	toe	21	0.03	0.00
english	nouns	0.35	tongue	23	0.01	0.00
english	nouns	0.35	tooth	22	0.02	0.00
english	nouns	0.35	toothbrush	22	0.01	0.00
english	nouns	0.35	towel	23	0.01	0.00
english	nouns	0.35	tractor	25	0.01	0.00
english	nouns	0.35	train	21	0.11	0.00
english	nouns	0.35	trash	24	0.01	0.00
english	nouns	0.35	tree	20	0.07	0.00
english	nouns	0.35	tricycle	29	0.00	0.00
english	nouns	0.35	truck	19	0.08	0.00
english	nouns	0.35	tummy	21	0.01	0.00
english	nouns	0.35	tuna	30	0.01	0.00
english	nouns	0.35	turkey	26	0.01	0.00
english	nouns	0.35	turtle	23	0.02	0.00
english	nouns	0.35	vacuum	24	0.00	0.00
english	nouns	0.35	wind	26	0.01	0.00
english	nouns	0.35	window	25	0.02	0.00
english	nouns	0.35	wolf	28	0.00	0.00
english	nouns	0.35	yogurt	23	0.00	0.00
english	nouns	0.35	zebra	25	0.01	0.00
english	nouns	0.35	zipper	25	0.01	0.00
english	adjectives	0.04	asleep	25	0.01	0.00
english	adjectives	0.04	awake	26	0.00	0.00
english	adjectives	0.04	bad	25	0.01	0.00
english	adjectives	0.04	big	22	0.21	0.00
english	adjectives	0.04	black	26	0.03	0.00
english	adjectives	0.04	blue	23	0.13	0.00
english	adjectives	0.04	broken	23	0.00	0.00
english	adjectives	0.04	brown	27	0.04	0.00
english	adjectives	0.04	careful	26	0.07	0.00
english	adjectives	0.04	cold	21	0.02	0.00
english	adjectives	0.04	cute	27	0.04	0.00
english	adjectives	0.04	dark	26	0.02	0.00
english	adjectives	0.04	dirty	22	0.04	0.00
english	adjectives	0.04	empty	26	0.01	0.00
english	adjectives	0.04	fast	26	0.04	0.00
english	adjectives	0.04	fine	30	0.01	0.00
english	adjectives	0.04	first	28	0.06	0.00
english	adjectives	0.04	full	27	0.01	0.00
english	adjectives	0.04	gentle	28	0.02	0.00
english	adjectives	0.04	good	24	0.30	0.00
english	adjectives	0.04	green	24	0.12	0.00
english	adjectives	0.04	happy	24	0.04	0.00
english	adjectives	0.04	hard	27	0.04	0.00
english	adjectives	0.04	heavy	25	0.01	0.00
english	adjectives	0.04	high	26	0.02	0.00
english	adjectives	0.04	hot	17	0.02	0.00
english	adjectives	0.04	hungry	24	0.02	0.00
english	adjectives	0.04	hurt	24	0.03	0.00
english	adjectives	0.04	long	29	0.04	0.00
english	adjectives	0.04	loud	26	0.01	0.00
english	adjectives	0.04	mad	28	0.00	0.00
english	adjectives	0.04	new	28	0.09	0.00
english	adjectives	0.04	nice	25	0.12	0.00
english	adjectives	0.04	noisy	28	0.00	0.00
english	adjectives	0.04	old	29	0.03	0.00
english	adjectives	0.04	pretty	25	0.05	0.00
english	adjectives	0.04	quiet	26	0.01	0.00
english	adjectives	0.04	red	24	0.11	0.00
english	adjectives	0.04	sad	26	0.02	0.00
english	adjectives	0.04	scared	26	0.01	0.00
english	adjectives	0.04	sick	26	0.01	0.00
english	adjectives	0.04	sleepy	25	0.02	0.00
english	adjectives	0.04	slow	28	0.01	0.00
english	adjectives	0.04	soft	26	0.01	0.00
english	adjectives	0.04	sticky	26	0.03	0.00
english	adjectives	0.04	stuck	26	0.03	0.00
english	adjectives	0.04	thirsty	26	0.01	0.00
english	adjectives	0.04	tiny	30	0.01	0.00
english	adjectives	0.04	tired	26	0.02	0.00
english	adjectives	0.04	wet	22	0.02	0.00
english	adjectives	0.04	white	27	0.05	0.00
english	adjectives	0.04	windy	27	0.00	0.00
english	adjectives	0.04	yellow	24	0.09	0.00
english	adjectives	0.04	yucky	22	0.01	0.00
english	verbs	0.03	bite	22	0.01	0.00
english	verbs	0.03	blow	24	0.02	0.00
english	verbs	0.03	break	25	0.06	0.00
english	verbs	0.03	bring	27	0.04	0.00
english	verbs	0.03	build	27	0.02	0.00
english	verbs	0.03	bump	26	0.03	0.00
english	verbs	0.03	buy	27	0.02	0.00
english	verbs	0.03	carry	25	0.02	0.00
english	verbs	0.03	catch	25	0.03	0.00
english	verbs	0.03	chase	28	0.00	0.00
english	verbs	0.03	clap	23	0.02	0.00
english	verbs	0.03	climb	25	0.02	0.00
english	verbs	0.03	close	24	0.04	0.00
english	verbs	0.03	cook	25	0.01	0.00
english	verbs	0.03	cover	27	0.01	0.00
english	verbs	0.03	cry	23	0.02	0.00
english	verbs	0.03	cut	26	0.02	0.00
english	verbs	0.03	dance	23	0.02	0.00
english	verbs	0.03	draw	25	0.04	0.00
english	verbs	0.03	drive	25	0.02	0.00
english	verbs	0.03	drop	26	0.02	0.00
english	verbs	0.03	dump	29	0.02	0.00
english	verbs	0.03	eat	20	0.12	0.00
english	verbs	0.03	fall	23	0.09	0.00
english	verbs	0.03	feed	26	0.01	0.00
english	verbs	0.03	find	25	0.14	0.00
english	verbs	0.03	finish	28	0.02	0.00
english	verbs	0.03	fit	28	0.02	0.00
english	verbs	0.03	fix	25	0.07	0.00
english	verbs	0.03	get	24	0.45	0.01
english	verbs	0.03	give	25	0.11	0.00
english	verbs	0.03	go	19	0.65	0.02
english	verbs	0.03	have	26	0.62	0.01
english	verbs	0.03	hear	27	0.04	0.00
english	verbs	0.03	help	23	0.11	0.00
english	verbs	0.03	hide	25	0.02	0.00
english	verbs	0.03	hit	24	0.02	0.00
english	verbs	0.03	hold	25	0.06	0.00
english	verbs	0.03	hug	22	0.02	0.00
english	verbs	0.03	hurry	27	0.01	0.00
english	verbs	0.03	jump	23	0.03	0.00
english	verbs	0.03	kick	24	0.01	0.00
english	verbs	0.03	kiss	21	0.06	0.00
english	verbs	0.03	knock	25	0.02	0.00
english	verbs	0.03	lick	27	0.00	0.00
english	verbs	0.03	like	26	0.52	0.01
english	verbs	0.03	listen	28	0.01	0.00
english	verbs	0.03	look	24	0.41	0.00
english	verbs	0.03	love	23	0.09	0.00
english	verbs	0.03	make	26	0.27	0.01
english	verbs	0.03	open	22	0.09	0.00
english	verbs	0.03	paint	26	0.03	0.00
english	verbs	0.03	pick	28	0.07	0.00
english	verbs	0.03	play	23	0.14	0.00
english	verbs	0.03	pour	28	0.01	0.00
english	verbs	0.03	pretend	30	0.02	0.00
english	verbs	0.03	pull	26	0.07	0.00
english	verbs	0.03	push	24	0.09	0.00
english	verbs	0.03	put	26	0.34	0.01
english	verbs	0.03	read	22	0.11	0.00
english	verbs	0.03	ride	24	0.03	0.00
english	verbs	0.03	rip	30	0.00	0.00
english	verbs	0.03	run	23	0.04	0.00
english	verbs	0.03	say	27	0.40	0.00
english	verbs	0.03	see	23	0.50	0.01
english	verbs	0.03	shake	27	0.05	0.00
english	verbs	0.03	share	26	0.01	0.00
english	verbs	0.03	show	27	0.08	0.00
english	verbs	0.03	sing	24	0.04	0.00
english	verbs	0.03	sit	22	0.11	0.00
english	verbs	0.03	skate	30	0.00	0.00
english	verbs	0.03	sleep	23	0.05	0.00
english	verbs	0.03	smile	27	0.01	0.00
english	verbs	0.03	spill	26	0.01	0.00
english	verbs	0.03	splash	25	0.01	0.00
english	verbs	0.03	stand	26	0.03	0.00
english	verbs	0.03	stay	26	0.06	0.00
english	verbs	0.03	stop	23	0.06	0.00
english	verbs	0.03	sweep	26	0.00	0.00
english	verbs	0.03	swim	24	0.02	0.00
english	verbs	0.03	take	27	0.16	0.00
english	verbs	0.03	talk	26	0.03	0.00
english	verbs	0.03	taste	28	0.01	0.00
english	verbs	0.03	tear	29	0.01	0.00
english	verbs	0.03	think	30	0.27	0.00
english	verbs	0.03	throw	24	0.06	0.00
english	verbs	0.03	tickle	23	0.05	0.00
english	verbs	0.03	touch	26	0.03	0.00
english	verbs	0.03	wait	26	0.09	0.00
english	verbs	0.03	wake	26	0.01	0.00
english	verbs	0.03	walk	22	0.06	0.00
english	verbs	0.03	wash	23	0.02	0.00
english	verbs	0.03	wipe	26	0.01	0.00
english	verbs	0.03	write	27	0.02	0.00
english	function_words	-0.01	a	27	1.27	0.02
english	function_words	-0.01	all	27	0.29	0.00
english	function_words	-0.01	and	27	0.97	0.00
english	function_words	-0.01	another	28	0.11	0.00
english	function_words	-0.01	any	29	0.05	0.00
english	function_words	-0.01	around	29	0.07	0.00
english	function_words	-0.01	at	28	0.25	0.00
english	function_words	-0.01	away	27	0.07	0.00
english	function_words	-0.01	back	26	0.17	0.00
english	function_words	-0.01	be	30	1.98	0.06
english	function_words	-0.01	because	30	0.11	0.00
english	function_words	-0.01	behind	29	0.02	0.00
english	function_words	-0.01	by	29	0.04	0.00
english	function_words	-0.01	do	25	1.04	0.02
english	function_words	-0.01	down	20	0.22	0.01
english	function_words	-0.01	for	28	0.34	0.00
english	function_words	-0.01	he	28	0.59	0.01
english	function_words	-0.01	her	29	0.10	0.00
english	function_words	-0.01	here	25	0.51	0.02
english	function_words	-0.01	his	30	0.21	0.00
english	function_words	-0.01	how	29	0.27	0.01
english	function_words	-0.01	is	28	0.00	0.00
english	function_words	-0.01	it	26	1.18	0.04
english	function_words	-0.01	mine	20	0.02	0.00
english	function_words	-0.01	more	20	0.16	0.00
english	function_words	-0.01	my	25	0.24	0.00
english	function_words	-0.01	myself	30	0.00	0.00
english	function_words	-0.01	not	27	0.26	0.01
english	function_words	-0.01	off	22	0.13	0.00
english	function_words	-0.01	on	22	0.59	0.01
english	function_words	-0.01	other	28	0.12	0.00
english	function_words	-0.01	out	22	0.24	0.00
english	function_words	-0.01	over	27	0.22	0.01
english	function_words	-0.01	same	30	0.03	0.00
english	function_words	-0.01	she	29	0.32	-0.01
english	function_words	-0.01	some	26	0.22	0.00
english	function_words	-0.01	that	24	1.20	0.02
english	function_words	-0.01	the	27	1.48	0.03
english	function_words	-0.01	there	26	0.62	0.01
english	function_words	-0.01	these	29	0.10	0.00
english	function_words	-0.01	they	30	0.44	0.00
english	function_words	-0.01	this	25	0.58	0.02
english	function_words	-0.01	those	30	0.11	0.00
english	function_words	-0.01	to	27	0.87	0.01
english	function_words	-0.01	too	26	0.21	0.00
english	function_words	-0.01	under	26	0.04	0.00
english	function_words	-0.01	up	19	0.39	0.01
english	function_words	-0.01	we	29	0.61	0.01
english	function_words	-0.01	what	24	0.90	0.02
english	function_words	-0.01	where	25	0.37	0.01
english	function_words	-0.01	who	28	0.24	0.00
english	function_words	-0.01	why	28	0.08	0.00
english	function_words	-0.01	will	30	0.09	0.00
english	function_words	-0.01	with	28	0.32	0.00
english	function_words	-0.01	you	24	1.58	0.05
english	function_words	-0.01	your	29	0.64	0.01
english	other	0.10	after	29	0.05	0.00
english	other	0.10	aunt	25	0.01	0.00
english	other	0.10	bath	18	0.01	0.00
english	other	0.10	beach	26	0.01	0.00
english	other	0.10	boy	23	0.09	0.00
english	other	0.10	breakfast	24	0.01	0.00
english	other	0.10	brother	27	0.01	0.00
english	other	0.10	circus	30	0.01	0.00
english	other	0.10	clown	27	0.01	0.00
english	other	0.10	cockadoodledoo	25	0.00	0.00
english	other	0.10	cowboy	30	0.00	0.00
english	other	0.10	day	28	0.06	0.00
english	other	0.10	dinner	24	0.01	0.00
english	other	0.10	doctor	25	0.01	0.00
english	other	0.10	farm	28	0.01	0.00
english	other	0.10	fireman	28	0.00	0.00
english	other	0.10	friend	27	0.04	0.00
english	other	0.10	girl	24	0.04	0.00
english	other	0.10	hello	18	0.08	0.00
english	other	0.10	home	22	0.04	0.00
english	other	0.10	house	23	0.07	0.00
english	other	0.10	lady	27	0.01	0.00
english	other	0.10	later	28	0.03	0.00
english	other	0.10	lunch	24	0.01	0.00
english	other	0.10	mailman	28	0.00	0.00
english	other	0.10	man	25	0.03	0.00
english	other	0.10	morning	27	0.03	0.00
english	other	0.10	movie	27	0.01	0.00
english	other	0.10	nap	23	0.01	0.00
english	other	0.10	night	24	0.04	0.00
english	other	0.10	now	25	0.24	0.01
english	other	0.10	ouch	17	0.01	0.00
english	other	0.10	outside	20	0.03	0.00
english	other	0.10	park	23	0.01	0.00
english	other	0.10	party	26	0.01	0.00
english	other	0.10	pattycake	25	0.00	0.00
english	other	0.10	peekaboo	19	0.01	0.00
english	other	0.10	people	27	0.03	0.00
english	other	0.10	picnic	28	0.01	0.00
english	other	0.10	playground	28	0.00	0.00
english	other	0.10	please	19	0.12	0.00
english	other	0.10	police	28	0.02	0.00
english	other	0.10	school	23	0.04	0.00
english	other	0.10	shopping	26	0.00	0.00
english	other	0.10	sister	27	0.01	0.00
english	other	0.10	snack	24	0.01	0.00
english	other	0.10	store	24	0.02	0.00
english	other	0.10	teacher	28	0.01	0.00
english	other	0.10	today	29	0.06	0.00
english	other	0.10	tomorrow	29	0.01	0.00
english	other	0.10	tonight	30	0.01	0.00
english	other	0.10	uncle	26	0.01	0.00
english	other	0.10	yard	27	0.00	0.00
english	other	0.10	yes	18	0.17	0.00
english	other	0.10	zoo	26	0.02	0.00
italian	all	0.00	NA	NA	NA	NA
italian	nouns	0.17	aereo	22	0.01	0.00
italian	nouns	0.17	agnello	36	0.01	0.00
italian	nouns	0.17	albero	23	0.03	0.00
italian	nouns	0.17	altalena	25	0.04	0.00
italian	nouns	0.17	animale	27	0.07	0.00
italian	nouns	0.17	ape	25	0.01	0.00
italian	nouns	0.17	armadio	27	0.01	0.00
italian	nouns	0.17	asciugamano	26	0.02	0.00
italian	nouns	0.17	asino	29	0.01	0.00
italian	nouns	0.17	automobile	24	0.00	0.00
italian	nouns	0.17	bagno	22	0.01	0.00
italian	nouns	0.17	bambola	22	0.10	0.00
italian	nouns	0.17	banana	20	0.01	0.00
italian	nouns	0.17	bandiera	30	0.00	0.00
italian	nouns	0.17	barca	24	0.02	0.00
italian	nouns	0.17	bavaglino	23	0.00	0.00
italian	nouns	0.17	benzina	30	0.01	0.00
italian	nouns	0.17	biberon	21	0.01	0.00
italian	nouns	0.17	bicchiere	22	0.05	0.00
italian	nouns	0.17	bicicletta	22	0.04	0.00
italian	nouns	0.17	bocca	20	0.06	0.00
italian	nouns	0.17	borsa	23	0.05	0.00
italian	nouns	0.17	bottiglia	24	0.01	0.00
italian	nouns	0.17	bottone	25	0.02	0.00
italian	nouns	0.17	braccio	24	0.04	0.00
italian	nouns	0.17	budino	33	0.01	0.00
italian	nouns	0.17	burro	30	0.00	0.00
italian	nouns	0.17	camera	25	0.03	0.00
italian	nouns	0.17	camicia	25	0.01	0.00
italian	nouns	0.17	camion	24	0.03	0.00
italian	nouns	0.17	camomilla	28	0.04	0.00
italian	nouns	0.17	cane	20	0.08	0.00
italian	nouns	0.17	cappello	22	0.02	0.00
italian	nouns	0.17	capra	30	0.02	0.00
italian	nouns	0.17	caramella	20	0.02	0.00
italian	nouns	0.17	carne	19	0.02	0.00
italian	nouns	0.17	casetta	24	0.02	0.00
italian	nouns	0.17	cassetto	26	0.01	0.00
italian	nouns	0.17	cavallo	21	0.12	0.00
italian	nouns	0.17	chiave	21	0.07	0.00
italian	nouns	0.17	cielo	24	0.02	0.00
italian	nouns	0.17	cioccolata	24	0.06	0.00
italian	nouns	0.17	coccodrillo	26	0.03	0.00
italian	nouns	0.17	collana	25	0.01	0.00
italian	nouns	0.17	coltello	23	0.02	0.00
italian	nouns	0.17	coniglio	26	0.02	0.00
italian	nouns	0.17	coperchio	29	0.03	0.00
italian	nouns	0.17	cracker	25	0.02	0.00
italian	nouns	0.17	cucchiaio	21	0.04	0.00
italian	nouns	0.17	cucciolo	29	0.04	0.00
italian	nouns	0.17	cuscino	24	0.01	0.00
italian	nouns	0.17	dentifricio	26	0.03	0.00
italian	nouns	0.17	disegno	27	0.02	0.00
italian	nouns	0.17	dito	21	0.05	0.00
italian	nouns	0.17	divano	25	0.03	0.00
italian	nouns	0.17	elefante	24	0.02	0.00
italian	nouns	0.17	elicottero	26	0.01	0.00
italian	nouns	0.17	erba	25	0.01	0.00
italian	nouns	0.17	faccia	25	0.00	0.00
italian	nouns	0.17	farfalla	24	0.01	0.00
italian	nouns	0.17	fazzoletto	26	0.01	0.00
italian	nouns	0.17	finestra	25	0.02	0.00
italian	nouns	0.17	fiore	22	0.03	0.00
italian	nouns	0.17	foca	29	0.01	0.00
italian	nouns	0.17	foglia	25	0.01	0.00
italian	nouns	0.17	fon	25	0.00	0.00
italian	nouns	0.17	forchetta	22	0.02	0.00
italian	nouns	0.17	formaggio	22	0.02	0.00
italian	nouns	0.17	forno	26	0.04	0.00
italian	nouns	0.17	fotografia	27	0.02	0.00
italian	nouns	0.17	fragola	27	0.02	0.00
italian	nouns	0.17	frigorifero	26	0.03	0.00
italian	nouns	0.17	fumo	26	0.01	0.00
italian	nouns	0.17	gallina	24	0.06	0.00
italian	nouns	0.17	gallo	25	0.01	0.00
italian	nouns	0.17	garage	29	0.01	0.00
italian	nouns	0.17	gatto	20	0.08	0.00
italian	nouns	0.17	giacca	26	0.00	0.00
italian	nouns	0.17	giocattolo	25	0.04	0.00
italian	nouns	0.17	giornale	26	0.03	0.00
italian	nouns	0.17	giraffa	26	0.04	0.00
italian	nouns	0.17	gola	27	0.02	-0.01
italian	nouns	0.17	grembiule	33	0.01	0.00
italian	nouns	0.17	gru	30	0.00	0.00
italian	nouns	0.17	ippopotamo	29	0.02	0.00
italian	nouns	0.17	lavandino	27	0.01	0.00
italian	nouns	0.17	lavatrice	26	0.00	0.00
italian	nouns	0.17	leone	24	0.05	0.00
italian	nouns	0.17	letto	21	0.00	0.00
italian	nouns	0.17	libro	22	0.02	0.00
italian	nouns	0.17	lingua	24	0.01	0.00
italian	nouns	0.17	luce	20	0.00	0.00
italian	nouns	0.17	lupo	23	0.06	0.00
italian	nouns	0.17	maglione	27	0.02	0.00
italian	nouns	0.17	maiale	26	0.03	0.00
italian	nouns	0.17	mano	19	0.11	0.00
italian	nouns	0.17	marmellata	28	0.04	0.00
italian	nouns	0.17	martello	27	0.00	0.00
italian	nouns	0.17	medicina	26	0.04	0.00
italian	nouns	0.17	mela	19	0.02	0.00
italian	nouns	0.17	melone	31	0.00	0.00
italian	nouns	0.17	miele	28	0.03	0.00
italian	nouns	0.17	mosca	25	0.04	0.00
italian	nouns	0.17	motocicletta	26	0.00	0.00
italian	nouns	0.17	mucca	22	0.09	0.00
italian	nouns	0.17	muro	26	0.01	0.00
italian	nouns	0.17	naso	20	0.03	0.00
italian	nouns	0.17	nebbia	34	0.00	0.00
italian	nouns	0.17	neve	26	0.04	0.00
italian	nouns	0.17	oca	27	0.02	0.00
italian	nouns	0.17	occhio	20	0.06	0.00
italian	nouns	0.17	ombrello	24	0.01	0.00
italian	nouns	0.17	orecchio	22	0.02	0.00
italian	nouns	0.17	orso	24	0.02	0.00
italian	nouns	0.17	paletta	25	0.01	0.00
italian	nouns	0.17	palloncino	25	0.06	0.00
italian	nouns	0.17	pancia	21	0.04	0.00
italian	nouns	0.17	panino	28	0.03	0.00
italian	nouns	0.17	panna	30	0.00	0.00
italian	nouns	0.17	pannolino	22	0.02	0.00
italian	nouns	0.17	papera	26	0.05	0.00
italian	nouns	0.17	pasta	21	0.02	0.00
italian	nouns	0.17	pecora	24	0.05	0.00
italian	nouns	0.17	pentola	27	0.04	0.00
italian	nouns	0.17	pera	21	0.01	0.00
italian	nouns	0.17	pesca	28	0.00	0.00
italian	nouns	0.17	pesciolino	22	0.03	0.00
italian	nouns	0.17	pettine	24	0.02	0.00
italian	nouns	0.17	piatto	22	0.07	0.00
italian	nouns	0.17	piede	20	0.07	0.00
italian	nouns	0.17	pigiama	24	0.02	0.00
italian	nouns	0.17	pinguino	30	0.01	0.00
italian	nouns	0.17	pioggia	24	0.05	0.00
italian	nouns	0.17	piscina	27	0.01	0.00
italian	nouns	0.17	pistola	27	0.03	0.00
italian	nouns	0.17	pizza	20	0.19	0.00
italian	nouns	0.17	pollo	22	0.01	0.00
italian	nouns	0.17	poltrona	30	0.02	0.00
italian	nouns	0.17	prato	28	0.01	0.00
italian	nouns	0.17	pulcino	26	0.02	0.00
italian	nouns	0.17	rana	26	0.02	0.00
italian	nouns	0.17	registratore	33	0.02	0.00
italian	nouns	0.17	sacchetto	32	0.02	0.00
italian	nouns	0.17	salotto	32	0.01	0.00
italian	nouns	0.17	sapone	23	0.03	0.00
italian	nouns	0.17	sasso	23	0.02	0.00
italian	nouns	0.17	scala	24	0.02	0.00
italian	nouns	0.17	scatola	27	0.01	0.00
italian	nouns	0.17	sciarpa	27	0.01	0.00
italian	nouns	0.17	scimmia	26	0.04	0.00
italian	nouns	0.17	scivolo	25	0.02	0.00
italian	nouns	0.17	scoiattolo	31	0.01	0.00
italian	nouns	0.17	secchiello	26	0.02	0.00
italian	nouns	0.17	secchio	28	0.01	0.00
italian	nouns	0.17	sederino	23	0.01	0.00
italian	nouns	0.17	sedia	22	0.02	0.00
italian	nouns	0.17	seggiolone	26	0.02	0.00
italian	nouns	0.17	seno	26	0.00	0.00
italian	nouns	0.17	shampoo	30	0.02	0.00
italian	nouns	0.17	spalla	29	0.01	0.00
italian	nouns	0.17	spinaci	31	0.00	0.00
italian	nouns	0.17	stella	24	0.00	0.00
italian	nouns	0.17	straccio	30	0.00	0.00
italian	nouns	0.17	strada	26	0.02	0.00
italian	nouns	0.17	sugo	27	0.00	0.00
italian	nouns	0.17	tacchino	32	0.01	0.00
italian	nouns	0.17	tappeto	28	0.03	0.00
italian	nouns	0.17	tappo	23	0.02	0.00
italian	nouns	0.17	tartaruga	25	0.03	0.00
italian	nouns	0.17	tavolo	24	0.04	0.00
italian	nouns	0.17	tazza	25	0.02	0.00
italian	nouns	0.17	telefono	22	0.02	0.00
italian	nouns	0.17	termometro	28	0.01	0.00
italian	nouns	0.17	termosifone	30	0.00	0.00
italian	nouns	0.17	terra	24	0.06	0.00
italian	nouns	0.17	testa	22	0.00	0.00
italian	nouns	0.17	tetto	28	0.01	0.00
italian	nouns	0.17	tigre	27	0.02	0.00
italian	nouns	0.17	topo	25	0.03	0.00
italian	nouns	0.17	torre	29	0.05	0.00
italian	nouns	0.17	trattore	26	0.03	0.00
italian	nouns	0.17	treno	22	0.09	0.00
italian	nouns	0.17	tromba	29	0.01	0.00
italian	nouns	0.17	trottola	30	0.01	0.00
italian	nouns	0.17	tubo	30	0.00	0.00
italian	nouns	0.17	tuta	25	0.02	0.00
italian	nouns	0.17	uccellino	24	0.02	0.00
italian	nouns	0.17	uovo	21	0.02	0.00
italian	nouns	0.17	uva	22	0.01	0.00
italian	nouns	0.17	vasino	26	0.01	0.00
italian	nouns	0.17	vento	25	0.02	0.00
italian	nouns	0.17	verdura	31	0.01	0.00
italian	nouns	0.17	vestito	26	0.02	0.00
italian	nouns	0.17	vino	24	0.02	0.00
italian	nouns	0.17	yogurt	24	0.01	0.00
italian	nouns	0.17	zanzara	26	0.01	0.00
italian	nouns	0.17	zebra	29	0.02	0.00
italian	adjectives	0.20	addormentato	29	0.01	0.00
italian	adjectives	0.20	alto	25	0.03	0.00
italian	adjectives	0.20	amaro	31	0.02	0.00
italian	adjectives	0.20	arancione	30	0.04	0.00
italian	adjectives	0.20	arrabbiato	27	0.01	0.00
italian	adjectives	0.20	asciutto	27	0.01	0.00
italian	adjectives	0.20	attento	29	0.06	0.00
italian	adjectives	0.20	bagnato	24	0.03	0.00
italian	adjectives	0.20	bello	20	0.22	0.00
italian	adjectives	0.20	bianco	26	0.05	0.00
italian	adjectives	0.20	blu	25	0.03	0.00
italian	adjectives	0.20	brutto	21	0.04	0.00
italian	adjectives	0.20	buio	22	0.02	0.00
italian	adjectives	0.20	buono	22	0.07	0.00
italian	adjectives	0.20	caldo	22	0.02	0.00
italian	adjectives	0.20	carino	31	0.01	0.00
italian	adjectives	0.20	cattivo	24	0.04	0.00
italian	adjectives	0.20	contento	32	0.02	0.00
italian	adjectives	0.20	corto	32	0.01	0.00
italian	adjectives	0.20	dolce	27	0.02	0.00
italian	adjectives	0.20	duro	28	0.01	0.00
italian	adjectives	0.20	felice	32	0.01	0.00
italian	adjectives	0.20	ferito	34	0.00	0.00
italian	adjectives	0.20	finito	26	0.03	0.00
italian	adjectives	0.20	forte	28	0.06	0.00
italian	adjectives	0.20	freddo	23	0.01	0.00
italian	adjectives	0.20	gentile	34	0.01	0.00
italian	adjectives	0.20	giallo	25	0.06	0.00
italian	adjectives	0.20	leggero	33	0.02	0.00
italian	adjectives	0.20	lungo	28	0.06	0.00
italian	adjectives	0.20	malato	28	0.03	0.00
italian	adjectives	0.20	marrone	31	0.03	0.00
italian	adjectives	0.20	morbido	30	0.03	0.00
italian	adjectives	0.20	nero	28	0.05	0.00
italian	adjectives	0.20	nuovo	28	0.05	0.00
italian	adjectives	0.20	piano	26	0.01	0.00
italian	adjectives	0.20	piccolo	23	0.08	0.00
italian	adjectives	0.20	pieno	29	0.02	0.00
italian	adjectives	0.20	povero	33	0.04	0.00
italian	adjectives	0.20	pulito	25	0.01	0.00
italian	adjectives	0.20	rosso	24	0.08	0.00
italian	adjectives	0.20	rotto	21	0.05	0.00
italian	adjectives	0.20	sbagliato	31	0.00	0.00
italian	adjectives	0.20	spaventato	33	0.01	0.00
italian	adjectives	0.20	sporco	22	0.02	0.00
italian	adjectives	0.20	stanco	26	0.02	0.00
italian	adjectives	0.20	sveglio	28	0.03	0.00
italian	adjectives	0.20	ultimo	34	0.00	0.00
italian	adjectives	0.20	vecchio	31	0.02	0.00
italian	adjectives	0.20	verde	26	0.04	0.00
italian	adjectives	0.20	vuoto	28	0.01	0.00
italian	verbs	0.06	abbracciare	27	0.01	0.00
italian	verbs	0.06	accendere	26	0.07	0.00
italian	verbs	0.06	acchiappare	31	0.01	0.00
italian	verbs	0.06	aggiustare	28	0.01	0.00
italian	verbs	0.06	aiutare	25	0.07	0.00
italian	verbs	0.06	alzarsi	26	0.02	0.00
italian	verbs	0.06	andare	23	0.56	0.01
italian	verbs	0.06	aprire	20	0.16	0.00
italian	verbs	0.06	arrampicarsi	33	0.00	0.00
italian	verbs	0.06	asciugare	25	0.02	0.00
italian	verbs	0.06	aspettare	25	0.13	0.00
italian	verbs	0.06	baciare	25	0.04	0.00
italian	verbs	0.06	ballare	25	0.02	0.00
italian	verbs	0.06	bere	22	0.07	0.00
italian	verbs	0.06	bussare	28	0.02	0.00
italian	verbs	0.06	buttare	25	0.05	0.00
italian	verbs	0.06	cadere	23	0.07	0.00
italian	verbs	0.06	camminare	26	0.03	0.00
italian	verbs	0.06	cantare	25	0.06	0.00
italian	verbs	0.06	cercare	28	0.07	0.00
italian	verbs	0.06	chiudere	23	0.09	0.00
italian	verbs	0.06	colorare	27	0.01	0.00
italian	verbs	0.06	comprare	27	0.05	0.00
italian	verbs	0.06	conoscere	32	0.05	0.00
italian	verbs	0.06	coprire	27	0.01	0.00
italian	verbs	0.06	correre	24	0.04	0.00
italian	verbs	0.06	costruire	30	0.02	0.00
italian	verbs	0.06	cucinare	28	0.02	0.00
italian	verbs	0.06	cullare	32	0.01	0.00
italian	verbs	0.06	dare	24	0.48	0.01
italian	verbs	0.06	dire	27	0.40	0.01
italian	verbs	0.06	disegnare	27	0.07	0.00
italian	verbs	0.06	dondolare	31	0.01	0.00
italian	verbs	0.06	dormire	24	0.07	0.00
italian	verbs	0.06	entrare	27	0.04	0.00
italian	verbs	0.06	fare	26	1.29	0.03
italian	verbs	0.06	fermarsi	29	0.00	0.00
italian	verbs	0.06	finire	28	0.07	0.00
italian	verbs	0.06	giocare	24	0.22	0.00
italian	verbs	0.06	girare	27	0.09	0.00
italian	verbs	0.06	guardare	26	0.74	0.01
italian	verbs	0.06	guidare	28	0.02	0.00
italian	verbs	0.06	lanciare	32	0.01	0.00
italian	verbs	0.06	lavare	24	0.08	0.00
italian	verbs	0.06	lavorare	27	0.04	0.00
italian	verbs	0.06	leccare	29	0.02	0.00
italian	verbs	0.06	leggere	25	0.09	0.00
italian	verbs	0.06	litigare	32	0.01	0.00
italian	verbs	0.06	mangiare	23	0.36	0.01
italian	verbs	0.06	mettere	26	0.56	0.01
italian	verbs	0.06	mordere	29	0.03	0.00
italian	verbs	0.06	nuotare	29	0.01	0.00
italian	verbs	0.06	parlare	27	0.06	0.00
italian	verbs	0.06	passeggiare	31	0.01	0.00
italian	verbs	0.06	pettinare	26	0.02	0.00
italian	verbs	0.06	piacere	30	0.15	0.00
italian	verbs	0.06	piangere	24	0.08	0.00
italian	verbs	0.06	portare	27	0.09	0.00
italian	verbs	0.06	prendere	25	0.26	0.00
italian	verbs	0.06	provare	32	0.05	0.00
italian	verbs	0.06	pulire	25	0.03	0.00
italian	verbs	0.06	raccontare	29	0.03	0.00
italian	verbs	0.06	regalare	29	0.03	0.00
italian	verbs	0.06	restare	32	0.01	0.00
italian	verbs	0.06	ridere	27	0.02	0.00
italian	verbs	0.06	rispondere	30	0.02	0.00
italian	verbs	0.06	rompere	26	0.12	0.00
italian	verbs	0.06	rovesciare	34	0.02	0.00
italian	verbs	0.06	saltare	26	0.03	0.00
italian	verbs	0.06	salutare	27	0.02	0.00
italian	verbs	0.06	scappare	29	0.06	0.00
italian	verbs	0.06	scendere	25	0.03	0.00
italian	verbs	0.06	scrivere	25	0.06	0.00
italian	verbs	0.06	sedersi	25	0.02	0.00
italian	verbs	0.06	sentire	28	0.22	0.00
italian	verbs	0.06	soffiare	27	0.03	0.00
italian	verbs	0.06	spazzare	32	0.02	0.00
italian	verbs	0.06	spegnere	26	0.01	0.00
italian	verbs	0.06	spingere	28	0.02	0.00
italian	verbs	0.06	sporcarsi	27	0.02	0.00
italian	verbs	0.06	sputare	30	0.02	0.00
italian	verbs	0.06	stare	29	0.44	0.01
italian	verbs	0.06	strappare	31	0.01	0.00
italian	verbs	0.06	svegliarsi	28	0.00	0.00
italian	verbs	0.06	tagliare	27	0.03	0.00
italian	verbs	0.06	telefonare	26	0.05	0.00
italian	verbs	0.06	tenere	28	0.17	0.00
italian	verbs	0.06	tirare	27	0.08	0.00
italian	verbs	0.06	toccare	27	0.04	0.00
italian	verbs	0.06	trovare	29	0.09	0.00
italian	verbs	0.06	uscire	25	0.04	0.00
italian	verbs	0.06	vedere	26	0.61	0.01
italian	verbs	0.06	venire	26	0.37	0.00
italian	verbs	0.06	versare	33	0.02	0.00
italian	verbs	0.06	volare	27	0.03	0.00
italian	function_words	-0.02	a	26	0.96	0.02
italian	function_words	-0.02	che	30	1.04	0.02
italian	function_words	-0.02	chi	27	0.53	0.01
italian	function_words	-0.02	ci	33	0.59	0.01
italian	function_words	-0.02	come	31	0.70	0.01
italian	function_words	-0.02	con	28	0.42	0.00
italian	function_words	-0.02	così	29	0.30	0.00
italian	function_words	-0.02	da	27	0.24	0.00
italian	function_words	-0.02	davanti	30	0.02	0.00
italian	function_words	-0.02	dentro	27	0.21	0.00
italian	function_words	-0.02	di	25	0.63	0.01
italian	function_words	-0.02	dietro	29	0.03	0.00
italian	function_words	-0.02	dove	27	0.47	0.01
italian	function_words	-0.02	e	26	1.11	0.02
italian	function_words	-0.02	ecco	23	0.30	0.00
italian	function_words	-0.02	fuori	25	0.10	0.00
italian	function_words	-0.02	giù	23	0.08	0.00
italian	function_words	-0.02	il	28	1.70	0.05
italian	function_words	-0.02	in	31	0.37	0.00
italian	function_words	-0.02	io	21	0.34	0.00
italian	function_words	-0.02	la	26	1.51	0.04
italian	function_words	-0.02	lei	32	0.09	0.00
italian	function_words	-0.02	lo	29	0.08	0.00
italian	function_words	-0.02	lontano	29	0.01	0.00
italian	function_words	-0.02	loro	35	0.07	0.00
italian	function_words	-0.02	lui	30	0.11	0.00
italian	function_words	-0.02	ma	31	0.67	0.01
italian	function_words	-0.02	molto	30	0.20	0.00
italian	function_words	-0.02	nessuno	30	0.01	0.00
italian	function_words	-0.02	niente	27	0.08	0.00
italian	function_words	-0.02	noi	31	0.04	0.00
italian	function_words	-0.02	per	30	0.30	0.00
italian	function_words	-0.02	poco	24	0.03	0.00
italian	function_words	-0.02	quale	31	0.11	0.00
italian	function_words	-0.02	quando	31	0.19	0.00
italian	function_words	-0.02	se	34	0.30	0.00
italian	function_words	-0.02	si	29	0.85	0.01
italian	function_words	-0.02	sopra	26	0.07	0.00
italian	function_words	-0.02	sotto	25	0.07	0.00
italian	function_words	-0.02	su	26	0.18	0.00
italian	function_words	-0.02	tanto	24	0.08	0.00
italian	function_words	-0.02	troppo	31	0.06	0.00
italian	function_words	-0.02	tu	24	0.20	0.00
italian	function_words	-0.02	tutto	25	0.49	0.01
italian	function_words	-0.02	vicino	29	0.04	0.00
italian	other	0.41	asilo	24	0.02	0.00
italian	other	0.41	bar	29	0.03	0.00
italian	other	0.41	bosco	29	0.01	0.00
italian	other	0.41	bravo	21	0.19	0.00
italian	other	0.41	campagna	32	0.02	0.00
italian	other	0.41	casa	21	0.12	0.00
italian	other	0.41	chiesa	30	0.01	0.00
italian	other	0.41	città	32	0.02	0.00
italian	other	0.41	coccodè	21	0.01	0.00
italian	other	0.41	domani	26	0.03	0.00
italian	other	0.41	donna	33	0.01	0.00
italian	other	0.41	dottore	24	0.03	0.00
italian	other	0.41	festa	27	0.01	0.00
italian	other	0.41	fratello	31	0.01	0.00
italian	other	0.41	giardino	27	0.02	0.00
italian	other	0.41	giorno	29	0.03	0.00
italian	other	0.41	giostra	26	0.00	0.00
italian	other	0.41	ieri	31	0.04	0.00
italian	other	0.41	lavoro	25	0.01	0.00
italian	other	0.41	mare	21	0.09	0.00
italian	other	0.41	mattina	30	0.02	0.00
italian	other	0.41	mercato	30	0.01	0.00
italian	other	0.41	montagna	29	0.03	0.00
italian	other	0.41	negozio	29	0.00	0.00
italian	other	0.41	notte	26	0.01	0.00
italian	other	0.41	oggi	29	0.05	0.00
italian	other	0.41	ospedale	31	0.00	0.00
italian	other	0.41	poliziotto	31	0.01	0.00
italian	other	0.41	presto	30	0.01	0.00
italian	other	0.41	scuola	24	0.06	0.00
italian	other	0.41	sera	30	0.02	0.00
italian	other	0.41	soldato	36	0.02	0.00
italian	other	0.41	sorella	32	0.01	0.00
italian	other	0.41	spiaggia	29	0.01	0.00
italian	other	0.41	supermercato	30	0.00	0.00
italian	other	0.41	uomo	31	0.01	0.00
italian	other	0.41	via	19	0.27	0.00
italian	other	0.41	vigile	31	0.01	0.00
italian	other	0.41	zio	19	0.08	0.00
italian	other	0.41	zoo	32	0.02	0.00
french	all	0.00	NA	NA	NA	NA
french	nouns	0.33	abeille	28	0.01	0.00
french	nouns	0.33	âne	30	0.01	0.00
french	nouns	0.33	arbre	26	0.01	0.00
french	nouns	0.33	arrosoir	27	0.00	0.00
french	nouns	0.33	aspirateur	26	0.00	0.00
french	nouns	0.33	assiette	24	0.01	0.00
french	nouns	0.33	avion	22	0.02	0.00
french	nouns	0.33	baignoire	26	0.01	0.00
french	nouns	0.33	balai	25	0.01	0.00
french	nouns	0.33	balançoire	26	0.00	0.00
french	nouns	0.33	balle	23	0.02	0.00
french	nouns	0.33	ballon	20	0.04	0.00
french	nouns	0.33	banane	22	0.02	0.00
french	nouns	0.33	basket	29	0.01	0.00
french	nouns	0.33	bateau	22	0.03	0.00
french	nouns	0.33	beurre	25	0.01	0.00
french	nouns	0.33	biberon	22	0.02	0.00
french	nouns	0.33	body	27	0.00	0.00
french	nouns	0.33	boîte	26	0.02	0.00
french	nouns	0.33	bol	26	0.00	0.00
french	nouns	0.33	bouche	23	0.05	0.00
french	nouns	0.33	bouteille	26	0.01	0.00
french	nouns	0.33	bras	24	0.03	0.00
french	nouns	0.33	brosse	27	0.01	0.00
french	nouns	0.33	bus	29	0.00	0.00
french	nouns	0.33	cadeau	24	0.03	0.00
french	nouns	0.33	café	25	0.01	0.00
french	nouns	0.33	caillou	24	0.00	0.00
french	nouns	0.33	camion	23	0.02	0.00
french	nouns	0.33	canapé	26	0.01	0.00
french	nouns	0.33	canard	22	0.02	0.00
french	nouns	0.33	cassette	26	0.01	0.00
french	nouns	0.33	chaise	23	0.02	0.00
french	nouns	0.33	chambre	25	0.04	0.00
french	nouns	0.33	chapeau	21	0.02	0.00
french	nouns	0.33	chat	19	0.04	0.00
french	nouns	0.33	chaussure	19	0.03	0.00
french	nouns	0.33	chemise	28	0.00	0.00
french	nouns	0.33	cheval	23	0.04	0.00
french	nouns	0.33	chèvre	29	0.00	0.00
french	nouns	0.33	chien	20	0.05	0.00
french	nouns	0.33	chips	29	0.00	0.00
french	nouns	0.33	chocolat	22	0.03	0.00
french	nouns	0.33	ciel	27	0.01	0.00
french	nouns	0.33	coca	30	0.00	0.00
french	nouns	0.33	cochon	23	0.03	0.00
french	nouns	0.33	collier	28	0.01	0.00
french	nouns	0.33	compote	25	0.03	0.00
french	nouns	0.33	confiture	28	0.00	0.00
french	nouns	0.33	coq	26	0.01	0.00
french	nouns	0.33	couche	21	0.02	0.00
french	nouns	0.33	couteau	24	0.01	0.00
french	nouns	0.33	couverture	27	0.01	0.00
french	nouns	0.33	crayon	23	0.01	0.00
french	nouns	0.33	crêpe	29	0.01	0.00
french	nouns	0.33	crocodile	26	0.02	0.00
french	nouns	0.33	cube	30	0.02	0.00
french	nouns	0.33	cuillère	22	0.02	0.00
french	nouns	0.33	cuisine	25	0.02	0.00
french	nouns	0.33	dent	23	0.03	0.00
french	nouns	0.33	doigt	24	0.04	0.00
french	nouns	0.33	douche	25	0.01	0.00
french	nouns	0.33	eau	21	0.09	0.00
french	nouns	0.33	écharpe	28	0.00	0.00
french	nouns	0.33	échelle	29	0.00	0.00
french	nouns	0.33	écureuil	29	0.01	0.00
french	nouns	0.33	éléphant	24	0.02	0.00
french	nouns	0.33	escalier	26	0.01	0.00
french	nouns	0.33	étoile	26	0.01	0.00
french	nouns	0.33	fauteuil	28	0.01	0.00
french	nouns	0.33	fenêtre	27	0.01	0.00
french	nouns	0.33	feuille	27	0.03	0.00
french	nouns	0.33	feutre	30	0.01	0.00
french	nouns	0.33	fleur	22	0.03	0.00
french	nouns	0.33	four	28	0.01	0.00
french	nouns	0.33	fourchette	23	0.01	0.00
french	nouns	0.33	fourmi	27	0.01	0.00
french	nouns	0.33	fraise	26	0.01	0.00
french	nouns	0.33	frigo	27	0.01	0.00
french	nouns	0.33	fromage	24	0.01	0.00
french	nouns	0.33	garage	27	0.02	0.00
french	nouns	0.33	gâteau	19	0.05	0.00
french	nouns	0.33	genou	26	0.01	0.00
french	nouns	0.33	girafe	25	0.02	0.00
french	nouns	0.33	glace	26	0.01	0.00
french	nouns	0.33	glaçon	30	0.00	0.00
french	nouns	0.33	grenouille	26	0.02	0.00
french	nouns	0.33	haricot	27	0.00	0.00
french	nouns	0.33	hélicoptère	28	0.01	0.00
french	nouns	0.33	herbe	27	0.01	0.00
french	nouns	0.33	hibou	29	0.01	0.00
french	nouns	0.33	histoire	27	0.04	0.00
french	nouns	0.33	jambe	25	0.01	0.00
french	nouns	0.33	jardin	27	0.01	0.00
french	nouns	0.33	jeu	28	0.04	0.00
french	nouns	0.33	joue	25	0.06	0.00
french	nouns	0.33	jouet	25	0.02	0.00
french	nouns	0.33	lait	22	0.02	0.00
french	nouns	0.33	lampe	28	0.01	0.00
french	nouns	0.33	langue	26	0.01	0.00
french	nouns	0.33	lapin	21	0.05	0.00
french	nouns	0.33	lavabo	29	0.00	0.00
french	nouns	0.33	lèvre	30	0.00	0.00
french	nouns	0.33	lion	25	0.02	0.00
french	nouns	0.33	lit	22	0.04	0.00
french	nouns	0.33	livre	23	0.08	0.00
french	nouns	0.33	loup	25	0.03	0.00
french	nouns	0.33	lumière	24	0.01	0.00
french	nouns	0.33	lune	24	0.01	0.00
french	nouns	0.33	main	21	0.09	0.00
french	nouns	0.33	manteau	25	0.01	0.00
french	nouns	0.33	marteau	28	0.01	0.00
french	nouns	0.33	melon	30	0.00	0.00
french	nouns	0.33	menton	28	0.00	0.00
french	nouns	0.33	montre	27	0.08	0.00
french	nouns	0.33	moto	22	0.01	0.00
french	nouns	0.33	mouchoir	25	0.01	0.00
french	nouns	0.33	mouton	24	0.02	0.00
french	nouns	0.33	musique	24	0.02	0.00
french	nouns	0.33	neige	25	0.01	0.00
french	nouns	0.33	nez	20	0.05	0.00
french	nouns	0.33	nombril	29	0.00	0.00
french	nouns	0.33	nounours	22	0.01	0.00
french	nouns	0.33	nuage	26	0.01	0.00
french	nouns	0.33	œuf	26	0.02	0.00
french	nouns	0.33	oiseau	21	0.03	0.00
french	nouns	0.33	orange	26	0.02	0.00
french	nouns	0.33	oreille	22	0.03	0.00
french	nouns	0.33	oreiller	30	0.00	0.00
french	nouns	0.33	ours	25	0.03	0.00
french	nouns	0.33	pain	18	0.02	0.00
french	nouns	0.33	panier	29	0.01	0.00
french	nouns	0.33	pantalon	23	0.02	0.00
french	nouns	0.33	papier	25	0.01	0.00
french	nouns	0.33	papillon	25	0.02	0.00
french	nouns	0.33	peigne	27	0.00	0.00
french	nouns	0.33	pelle	26	0.01	0.00
french	nouns	0.33	photo	24	0.02	0.00
french	nouns	0.33	pied	21	0.08	0.00
french	nouns	0.33	pierre	29	0.01	0.00
french	nouns	0.33	piscine	25	0.01	0.00
french	nouns	0.33	pizza	28	0.00	0.00
french	nouns	0.33	pluie	24	0.01	0.00
french	nouns	0.33	poisson	22	0.06	0.00
french	nouns	0.33	pomme	21	0.03	0.00
french	nouns	0.33	porte	22	0.03	0.00
french	nouns	0.33	pot	22	0.02	0.00
french	nouns	0.33	poubelle	24	0.02	0.00
french	nouns	0.33	pouce	26	0.01	0.00
french	nouns	0.33	poule	23	0.02	0.00
french	nouns	0.33	poulet	26	0.01	0.00
french	nouns	0.33	poupée	24	0.02	0.00
french	nouns	0.33	poussette	23	0.01	0.00
french	nouns	0.33	pull	25	0.01	0.00
french	nouns	0.33	purée	26	0.01	0.00
french	nouns	0.33	puzzle	30	0.04	0.00
french	nouns	0.33	pyjama	23	0.02	0.00
french	nouns	0.33	raisin	29	0.00	0.00
french	nouns	0.33	robe	27	0.01	0.00
french	nouns	0.33	salon	30	0.01	0.00
french	nouns	0.33	salopette	28	0.00	0.00
french	nouns	0.33	sauce	30	0.00	0.00
french	nouns	0.33	savon	25	0.01	0.00
french	nouns	0.33	seau	27	0.01	0.00
french	nouns	0.33	sel	26	0.00	0.00
french	nouns	0.33	serviette	25	0.01	0.00
french	nouns	0.33	short	28	0.01	0.00
french	nouns	0.33	singe	26	0.01	0.00
french	nouns	0.33	sirop	28	0.00	0.00
french	nouns	0.33	soleil	24	0.02	0.00
french	nouns	0.33	soupe	25	0.01	0.00
french	nouns	0.33	souris	26	0.03	0.00
french	nouns	0.33	stylo	29	0.01	0.00
french	nouns	0.33	sucette	24	0.01	0.00
french	nouns	0.33	sucre	25	0.01	0.00
french	nouns	0.33	table	24	0.04	0.00
french	nouns	0.33	tartine	28	0.01	0.00
french	nouns	0.33	tasse	28	0.01	0.00
french	nouns	0.33	télé	23	0.01	0.00
french	nouns	0.33	télécommande	30	0.00	0.00
french	nouns	0.33	téléphone	24	0.02	0.00
french	nouns	0.33	tête	22	0.07	0.00
french	nouns	0.33	tigre	28	0.01	0.00
french	nouns	0.33	tiroir	28	0.01	0.00
french	nouns	0.33	toboggan	25	0.01	0.00
french	nouns	0.33	toit	30	0.01	0.00
french	nouns	0.33	tortue	24	0.02	0.00
french	nouns	0.33	tracteur	24	0.02	0.00
french	nouns	0.33	train	24	0.04	0.00
french	nouns	0.33	trottoir	29	0.00	0.00
french	nouns	0.33	vache	23	0.03	0.00
french	nouns	0.33	vanille	30	0.00	0.00
french	nouns	0.33	vélo	22	0.02	0.00
french	nouns	0.33	vent	25	0.01	0.00
french	nouns	0.33	ventre	24	0.02	0.00
french	nouns	0.33	verre	23	0.02	0.00
french	nouns	0.33	veste	28	0.01	0.00
french	nouns	0.33	viande	25	0.01	0.00
french	nouns	0.33	voiture	21	0.09	0.00
french	nouns	0.33	wc	28	0.00	0.00
french	nouns	0.33	yaourt	23	0.01	0.00
french	nouns	0.33	zèbre	30	0.01	0.00
french	adjectives	-0.06	attention	25	0.14	0.00
french	adjectives	-0.06	bien	27	0.43	0.01
french	adjectives	-0.06	bleu	26	0.06	0.00
french	adjectives	-0.06	cassé	22	0.03	0.00
french	adjectives	-0.06	dur	26	0.03	0.00
french	adjectives	-0.06	fatigué	27	0.00	0.00
french	adjectives	-0.06	froid	23	0.03	0.00
french	adjectives	-0.06	jaune	27	0.05	0.00
french	adjectives	-0.06	joli	26	0.05	0.00
french	adjectives	-0.06	malade	27	0.02	0.00
french	adjectives	-0.06	noir	29	0.02	0.00
french	adjectives	-0.06	orange	29	0.02	0.00
french	adjectives	-0.06	parti	22	0.00	0.00
french	adjectives	-0.06	propre	27	0.02	0.00
french	adjectives	-0.06	rouge	26	0.07	0.00
french	adjectives	-0.06	sale	23	0.02	0.00
french	adjectives	-0.06	triste	30	0.01	0.00
french	adjectives	-0.06	vite	27	0.05	0.00
french	verbs	-0.01	acheter	29	0.02	0.00
french	verbs	-0.01	aider	28	0.03	0.00
french	verbs	-0.01	aimer	27	0.05	0.00
french	verbs	-0.01	aller	26	1.01	0.02
french	verbs	-0.01	apporter	28	0.01	0.00
french	verbs	-0.01	arrêter	26	0.02	0.00
french	verbs	-0.01	attendre	28	0.27	0.00
french	verbs	-0.01	attraper	29	0.02	0.00
french	verbs	-0.01	avoir	29	1.22	0.02
french	verbs	-0.01	balancer	30	0.00	0.00
french	verbs	-0.01	balayer	28	0.00	0.00
french	verbs	-0.01	boire	21	0.04	0.00
french	verbs	-0.01	cacher	24	0.04	0.00
french	verbs	-0.01	casser	23	0.04	0.00
french	verbs	-0.01	chanter	26	0.02	0.00
french	verbs	-0.01	chatouiller	30	0.00	0.00
french	verbs	-0.01	conduire	29	0.00	0.00
french	verbs	-0.01	couper	27	0.02	0.00
french	verbs	-0.01	courir	25	0.01	0.00
french	verbs	-0.01	danser	25	0.01	0.00
french	verbs	-0.01	déchirer	29	0.01	0.00
french	verbs	-0.01	dessiner	26	0.03	0.00
french	verbs	-0.01	dire	29	0.34	0.00
french	verbs	-0.01	donner	25	0.10	0.00
french	verbs	-0.01	dormir	25	0.04	0.00
french	verbs	-0.01	écouter	26	0.01	0.00
french	verbs	-0.01	écrire	26	0.04	0.00
french	verbs	-0.01	entendre	29	0.05	0.00
french	verbs	-0.01	essuyer	27	0.01	0.00
french	verbs	-0.01	faire	27	0.88	0.01
french	verbs	-0.01	fermer	24	0.02	0.00
french	verbs	-0.01	finir	27	0.09	0.00
french	verbs	-0.01	glisser	29	0.01	0.00
french	verbs	-0.01	goûter	28	0.03	0.00
french	verbs	-0.01	goutter	29	0.00	0.00
french	verbs	-0.01	jeter	27	0.03	0.00
french	verbs	-0.01	jouer	25	0.11	0.00
french	verbs	-0.01	laver	26	0.03	0.00
french	verbs	-0.01	lire	26	0.06	0.00
french	verbs	-0.01	manger	23	0.18	0.00
french	verbs	-0.01	marcher	26	0.02	0.00
french	verbs	-0.01	mettre	28	0.48	0.01
french	verbs	-0.01	montrer	29	0.05	0.00
french	verbs	-0.01	mordre	27	0.01	0.00
french	verbs	-0.01	nager	28	0.01	0.00
french	verbs	-0.01	nettoyer	28	0.01	0.00
french	verbs	-0.01	ouvrir	25	0.05	0.00
french	verbs	-0.01	parler	28	0.03	0.00
french	verbs	-0.01	pleurer	24	0.01	0.00
french	verbs	-0.01	porter	26	0.00	0.00
french	verbs	-0.01	pousser	26	0.01	0.00
french	verbs	-0.01	prendre	28	0.17	0.00
french	verbs	-0.01	ramasser	28	0.02	0.00
french	verbs	-0.01	regarder	25	0.08	0.00
french	verbs	-0.01	renverser	30	0.01	0.00
french	verbs	-0.01	réparer	29	0.01	0.00
french	verbs	-0.01	rester	29	0.02	0.00
french	verbs	-0.01	sauter	25	0.01	0.00
french	verbs	-0.01	sécher	30	0.00	0.00
french	verbs	-0.01	souffler	27	0.01	0.00
french	verbs	-0.01	taper	26	0.01	0.00
french	verbs	-0.01	tenir	28	0.23	0.00
french	verbs	-0.01	tirer	30	0.01	0.00
french	verbs	-0.01	tomber	23	0.08	0.00
french	verbs	-0.01	toucher	28	0.02	0.00
french	verbs	-0.01	travailler	28	0.01	0.00
french	verbs	-0.01	trouver	29	0.06	0.00
french	verbs	-0.01	voir	28	0.45	0.01
french	function_words	-0.03	à	26	0.60	0.01
french	function_words	-0.03	aller	27	1.01	0.02
french	function_words	-0.03	aussi	28	0.19	0.00
french	function_words	-0.03	autre	30	0.19	0.00
french	function_words	-0.03	avec	28	0.33	0.00
french	function_words	-0.03	ça	25	0.04	0.00
french	function_words	-0.03	chez	28	0.04	0.00
french	function_words	-0.03	dans	26	0.41	0.01
french	function_words	-0.03	de	29	1.14	0.02
french	function_words	-0.03	dehors	25	0.02	0.00
french	function_words	-0.03	derrière	28	0.03	0.00
french	function_words	-0.03	elle	30	0.00	0.00
french	function_words	-0.03	encore	20	0.21	0.00
french	function_words	-0.03	et	28	0.88	0.02
french	function_words	-0.03	fait	28	0.07	0.00
french	function_words	-0.03	ici	26	0.08	0.00
french	function_words	-0.03	il	29	1.13	0.02
french	function_words	-0.03	je	30	0.90	0.01
french	function_words	-0.03	là	21	0.80	0.01
french	function_words	-0.03	loin	28	0.02	0.00
french	function_words	-0.03	lui	30	0.72	0.01
french	function_words	-0.03	moi	25	0.36	0.00
french	function_words	-0.03	où	25	0.35	0.00
french	function_words	-0.03	pas	22	0.95	0.02
french	function_words	-0.03	pour	28	0.34	0.00
french	function_words	-0.03	pourquoi	28	0.10	0.00
french	function_words	-0.03	qui	28	0.49	0.01
french	function_words	-0.03	quoi	26	0.39	0.01
french	function_words	-0.03	sous	29	0.03	0.00
french	function_words	-0.03	sur	27	0.25	0.00
french	function_words	-0.03	vouloir	30	0.56	0.01
french	other	0.05	aie	19	0.00	0.00
french	other	0.05	après	27	0.15	0.00
french	other	0.05	bain	19	0.04	0.00
french	other	0.05	bébé	18	0.09	0.00
french	other	0.05	bonjour	22	0.03	0.00
french	other	0.05	bravo	19	0.09	0.00
french	other	0.05	chut	21	0.02	0.00
french	other	0.05	clown	26	0.02	0.00
french	other	0.05	cocorico	30	0.00	0.00
french	other	0.05	coucou	18	0.06	0.00
french	other	0.05	crèche	29	0.02	0.00
french	other	0.05	dame	25	0.01	0.00
french	other	0.05	dehors	23	0.02	0.00
french	other	0.05	demain	28	0.02	0.00
french	other	0.05	docteur	26	0.02	0.00
french	other	0.05	école	25	0.05	0.00
french	other	0.05	enfant	28	0.03	0.00
french	other	0.05	fille	25	0.04	0.00
french	other	0.05	forêt	30	0.00	0.00
french	other	0.05	frère	30	0.02	0.00
french	other	0.05	garçon	25	0.04	0.00
french	other	0.05	goûter	26	0.03	0.00
french	other	0.05	grrrr	25	0.00	0.00
french	other	0.05	jour	30	0.03	0.00
french	other	0.05	magasin	28	0.00	0.00
french	other	0.05	maison	23	0.06	0.00
french	other	0.05	matin	30	0.03	0.00
french	other	0.05	merci	18	0.10	0.00
french	other	0.05	meuh	18	0.01	0.00
french	other	0.05	miaou	19	0.01	0.00
french	other	0.05	monsieur	24	0.06	0.00
french	other	0.05	nuit	26	0.02	0.00
french	other	0.05	oui	20	0.81	0.01
french	other	0.05	parc	28	0.01	0.00
french	other	0.05	plage	29	0.00	0.00
french	other	0.05	pompier	28	0.01	0.00
french	other	0.05	salut	28	0.01	0.00
french	other	0.05	sieste	27	0.01	0.00
french	other	0.05	travail	26	0.01	0.00

#divide into training and test set
### (1)Use this formula after freezing all coefficients: 1 - (sum of squared errors) / (sum of squares total). The denominator is (𝑛−1)× the observed variance of 𝑌 in the holdout sample.
### (2)1- sum squared differences between the predicted and observed value / sum of squared differences between the observed and overall mean value
### (3)Calculate mean square error and variance of each group 

xvalr2 <- function(d){
n<-nrow(d) #df size
ind <- sample(c(TRUE, FALSE), n, replace=TRUE, prob=c(0.9, 0.1)) #randomly split lines
train <- d[ind, ] 
test <- d[!ind, ]
model <- lm(aoa~ log_freq, data=train) 
predictions <- predict(model, test)
#crossvalr2 <- 1-(sum((test$aoa - predictions)^2)/(n-1)*var(test$aoa))  (1)
#crossvalr2 <- 1-(sum((predictions - test$aoa)^2)/sum((test$aoa - mean(test$aoa))^2) ) (2)
#crossvalr2 <- 1-(sum((test$aoa - predictions)^2)/var(test$aoa))   (3) 
crossvalr2 <- rsquare(model, test)
return(crossvalr2)
}

crossvalr2 <- expand_grid(lang = c("english", "italian", "french"), 
                            class = c("all", "nouns","adjectives","verbs",
                                           "function_words","other")) %>% 
  rowwise %>%
   mutate(crossvalr2 = ifelse(class == "all", 
                             xvalr2(filter(d, 
                                                   language == lang)),
                             xvalr2(filter(d, 
                                                   language == lang, lexical_class == class)))) %>%
  rename( language = lang,lexical_class = class) 

crossvalr2 %>%
  knitr::kable(digits = 2)

language	lexical_class	crossvalr2
english	all	-0.01
english	nouns	0.55
english	adjectives	-0.82
english	verbs	0.00
english	function_words	0.00
english	other	-1.73
italian	all	0.00
italian	nouns	0.04
italian	adjectives	0.05
italian	verbs	-0.06
italian	function_words	0.00
italian	other	-0.06
french	all	0.02
french	nouns	0.25
french	adjectives	-0.57
french	verbs	0.02
french	function_words	-0.20
french	other	-0.15

all_r2 <- r2 %>%
  left_join(crossvalr2) %>%
  select(language, lexical_class, r2, crossvalr2) %>%
  distinct() %>%
  rename(word_class = lexical_class) %>%
  mutate(language = sub("english", "English (American)", language)) %>%
  mutate(language = sub("italian", "Italian", language)) %>%
  mutate(language = sub("french", "French (French)", language))

## Joining, by = c("language", "lexical_class")

all_r2 %>%
  knitr::kable(digits = 2)

language	word_class	r2	crossvalr2
English (American)	all	0.00	-0.01
English (American)	nouns	0.35	0.55
English (American)	adjectives	0.04	-0.82
English (American)	verbs	0.03	0.00
English (American)	function_words	-0.01	0.00
English (American)	other	0.10	-1.73
Italian	all	0.00	0.00
Italian	nouns	0.17	0.04
Italian	adjectives	0.20	0.05
Italian	verbs	0.06	-0.06
Italian	function_words	-0.02	0.00
Italian	other	0.41	-0.06
French (French)	all	0.00	0.02
French (French)	nouns	0.33	0.25
French (French)	adjectives	-0.06	-0.57
French (French)	verbs	-0.01	0.02
French (French)	function_words	-0.03	-0.20
French (French)	other	0.05	-0.15

all_reliabilities <- reliabilities %>%
  left_join(reliabilities_aoa) %>%
    mutate(threshold_half = split_half_tau_sb * split_half_aoa_sb) 

## Joining, by = c("language", "word_class")

    # %>%
    # mutate(threshold_alpha = cronbach_alpha * split_half_aoa_sb) 

all_reliabilities %>%
  knitr::kable(digits = 2)

language	word_class	split_half_tau	split_half_tau_sb	split_half_aoa	split_half_aoa_sb	threshold_half
English (American)	all	0.90	0.95	0.97	0.98	0.93
English (American)	nouns	0.87	0.93	0.97	0.98	0.92
English (American)	adjectives	0.90	0.94	0.96	0.98	0.93
English (American)	verbs	0.89	0.94	0.94	0.97	0.91
English (American)	function_words	0.93	0.96	0.95	0.98	0.94
English (American)	other	0.87	0.93	0.97	0.99	0.92
Italian	all	0.81	0.90	0.93	0.96	0.86
Italian	nouns	0.77	0.87	0.92	0.96	0.83
Italian	adjectives	0.77	0.87	0.91	0.95	0.83
Italian	verbs	0.84	0.91	0.89	0.94	0.86
Italian	function_words	0.88	0.93	0.92	0.96	0.89
Italian	other	0.83	0.91	0.88	0.94	0.85
French (French)	all	0.89	0.94	0.88	0.94	0.89
French (French)	nouns	0.89	0.94	0.90	0.95	0.89
French (French)	adjectives	0.86	0.93	0.88	0.94	0.87
French (French)	verbs	0.91	0.95	0.82	0.90	0.86
French (French)	function_words	0.83	0.91	0.73	0.84	0.77
French (French)	other	0.86	0.93	0.92	0.96	0.89

dr<- all_reliabilities %>% 
  left_join(unique(all_r2)) 

## Joining, by = c("language", "word_class")

dr %>%
  knitr::kable(digits = 2)

language	word_class	split_half_tau	split_half_tau_sb	split_half_aoa	split_half_aoa_sb	threshold_half	r2	crossvalr2
English (American)	all	0.90	0.95	0.97	0.98	0.93	0.00	-0.01
English (American)	nouns	0.87	0.93	0.97	0.98	0.92	0.35	0.55
English (American)	adjectives	0.90	0.94	0.96	0.98	0.93	0.04	-0.82
English (American)	verbs	0.89	0.94	0.94	0.97	0.91	0.03	0.00
English (American)	function_words	0.93	0.96	0.95	0.98	0.94	-0.01	0.00
English (American)	other	0.87	0.93	0.97	0.99	0.92	0.10	-1.73
Italian	all	0.81	0.90	0.93	0.96	0.86	0.00	0.00
Italian	nouns	0.77	0.87	0.92	0.96	0.83	0.17	0.04
Italian	adjectives	0.77	0.87	0.91	0.95	0.83	0.20	0.05
Italian	verbs	0.84	0.91	0.89	0.94	0.86	0.06	-0.06
Italian	function_words	0.88	0.93	0.92	0.96	0.89	-0.02	0.00
Italian	other	0.83	0.91	0.88	0.94	0.85	0.41	-0.06
French (French)	all	0.89	0.94	0.88	0.94	0.89	0.00	0.02
French (French)	nouns	0.89	0.94	0.90	0.95	0.89	0.33	0.25
French (French)	adjectives	0.86	0.93	0.88	0.94	0.87	-0.06	-0.57
French (French)	verbs	0.91	0.95	0.82	0.90	0.86	-0.01	0.02
French (French)	function_words	0.83	0.91	0.73	0.84	0.77	-0.03	-0.20
French (French)	other	0.86	0.93	0.92	0.96	0.89	0.05	-0.15

ggplot(dr, aes(x = word_class, y=r2, fill=word_class)) + 
  geom_bar(stat="identity") + 
  facet_grid(rows = vars(language)) +
  geom_errorbar(data  = dr, aes(y=threshold_half, ymax=threshold_half, ymin=threshold_half, col=word_class)) + 
  theme(legend.position = "bottom") + 
  xlab("Lexical class") + 
  ylab("R2") + 
  theme(legend.title = element_blank())