.gitignore

*.csv
__pycache__
.ipynb_checkpoints

analyze.Rmd

---
title: "R Notebook"
output: html_notebook
---

```{r}
library(tidyverse)
library(lme4)
library(lmerTest)
```

```{r}
SUITE = "number_prep"
```


```{r}
predictions_df <- read_csv(paste0(SUITE, ".predictions.csv"))
glimpse(predictions_df)
```

```{r}
predictions_df = predictions_df %>% 
  mutate(first_item_number=str_extract(used_item_numbers, "^(\\d+)"))
```

```{r}
lm = glmer(prediction_0 ~ log(prefix_length + 1) + (log(prefix_length + 1) | first_item_number),
           family=binomial, data=predictions_df)
summary(lm)
```
```{r}
ranef(lm)
```


```{r}
#region_df = read_csv(paste0(SUITE, ".regions.csv"))
#glimpse(region_df)
region_df = rbind(read_csv("number_prep.regions.csv"), read_csv("number_prep2.regions.csv"))
glimpse(region_df)
```

```{r}
crit_region_data = region_df %>% 
  left_join(predictions_df %>% select(c(item_number, prefix_length, first_item_number)), by="item_number") %>% 
  filter(region_number == 7) %>% 
  mutate(grammatical=!grepl("mismatch", condition),
         feature=str_extract(condition, "_(.+)$"))
```

```{r}
contrasts(crit_region_data$grammatical) = c(-1, 1)
lm = lmer(value ~ grammatical * log(prefix_length + 1) + (1 | first_item_number) + (1 | feature), data=crit_region_data,
          control=lmerControl(optimizer="bobyqa", optCtrl=list(maxfun=100000)))
summary(lm)
```

```{r}
ranef(lm)
```

analyze.ipynb

analyze.nb.html

analyze_repetitions.py