Reticulate & Python

First, we build a conda environment (via the terminal) comprised of m3inference and pip (and their respective dependencies).

## <TERMINAL>
conda create -n m3demo
source activate m3demo
conda install pip 
/home/jtimm/anaconda3/envs/m3demo/bin/pip install m3inference

Then we establish Python and conda environment paths.

## <R-console>
Sys.setenv(RETICULATE_PYTHON = "/home/jtimm/anaconda3/envs/m3demo/bin/python")

library(reticulate)
#reticulate::use_python("/home/jtimm/anaconda3/envs/m3demo/bin/python")
reticulate::use_condaenv(condaenv = "m3demo",
                         conda = "/home/jtimm/anaconda3/bin/conda")

Twitter data

For demonstration purposes, we identify/extract my Twitter followers (and some of their M3-relevant features) using the rtweet package.

## <R-console>
library(tidyverse)
fws  <- rtweet::get_followers(user = 'DrJayTimm') 

users <- rtweet::lookup_users(fws$user_id) %>%
  select(user_id, name, screen_name, description, profile_image_url)

Below is a simple hack to provide the M3 model with an actual image file for Twitter profiles that lack profile pics.

## <R-console>
jk <- 'http://abs.twimg.com/sticky/default_profile_images/default_profile_normal.png'
jk0 <- 'https://twirpz.files.wordpress.com/2015/06/twitter-avi-gender-balanced-figure.png'

dir0 <- tempdir()

users2 <- users %>%
  mutate(profile_image_url = ifelse(profile_image_url == jk, jk0, profile_image_url)) %>%
  rename(id_str = user_id) 

Profile pics via M3

Output Twitter user details to local temp directory as a ~ ndjson file.

## <R-console>
tmp2 <- tempfile()
jsonlite::stream_out(users2, file(tmp1 <- tempfile()), verbose = F)

In a Python console, we then import the M3Twitter module, and set the directory in which Twitter profile pics will be stored. (Note that the directory established in the R chunk above is accessed below via the r. prefix.)

## <PYTHON-console>
from m3inference import M3Twitter
m3twitter = M3Twitter(cache_dir = r.dir0) 
## 06/10/2022 21:07:32 - INFO - m3inference.m3inference -   Version 1.1.5
## 06/10/2022 21:07:32 - INFO - m3inference.m3inference -   Running on cpu.
## 06/10/2022 21:07:32 - INFO - m3inference.m3inference -   Will use full M3 model.
## 06/10/2022 21:07:33 - INFO - m3inference.m3inference -   Model full_model exists at /home/jtimm/m3/models/full_model.mdl.
## 06/10/2022 21:07:33 - INFO - m3inference.utils -   Checking MD5 for model full_model at /home/jtimm/m3/models/full_model.mdl
## 06/10/2022 21:07:34 - INFO - m3inference.utils -   MD5s match.
## 06/10/2022 21:07:35 - INFO - m3inference.m3inference -   Loaded pretrained weight at /home/jtimm/m3/models/full_model.mdl

Then, via the transform_jsonl function, we restructure the ndjson/jsonl file and download Twitter users’ profile pics to the temp directory. This function also identifies description language. Note: While we can download profile images and identify description language in R, things tend to go much more smoothly (& quicker) using the functionality included in m3inference.

## <PYTHON-console>
m3twitter.transform_jsonl(input_file = r.tmp1, 
                          output_file = r.tmp2, 
                          img_path_key = "profile_image_url")#, 
                          #lang_key = "lang")
## /home/jtimm/anaconda3/envs/m3demo/lib/python3.10/site-packages/PIL/Image.py:992: UserWarning: Palette images with Transparency expressed in bytes should be converted to RGBA images
##   warnings.warn(

Deomgraphic inference via M3

Apply M3 classification model. Attribute classes:

• Gender: male, female;

• Age: <= 18, 19-29, 30-39, >=40; and

• Organization: non-org, is-org.

## <PYTHON-console>
from m3inference import M3Inference
m3 = M3Inference() 
pred = m3.infer(r.tmp2)

## <R-console>
py_predictions <- reticulate::py$pred

## <R-console>
df <- reshape2::melt(py_predictions) 
df0 <- data.table::setDT(df)[, .SD[which.max(value)], by = list(L1, L2)]
df1 <- data.table::dcast(df0, L1  ~ L2, value.var = 'L3')
## <R-console>
df1 %>% sample_n(10) %>% knitr::kable()

table(df1$org)
## 
##  is-org non-org 
##      16     159

## <R-console>
df2 <- df1 %>%
  mutate(age = factor(age, levels = c('<=18', '19-29', '30-39', '>=40'))) %>%
  filter(org != 'is-org') %>%
  count(gender, age) %>%
  mutate(percent = round(n/sum(n)*100,1)) %>%
  mutate(percent = ifelse(gender == "male", percent*-1, percent))

df2 %>% knitr::kable()

## <R-console>
maxs <- max(abs(df2$percent))
df2 %>%
  ggplot(aes(x = age, y = percent, fill =gender)) +
  geom_col(alpha = .75) + 
  ylim(-maxs - 1, maxs + 1) +
  coord_flip() +
  ggthemes::scale_fill_stata() +
  # scale_y_continuous(breaks = c(-5, 0, 5),
  #                    labels = c("5%", "0%", "5%")) +
  labs(title="Inferred age-gender demographics of my followers")

Profile pics & demographic inference

## <R-console>
users2$paths <- grep('224x224', dir(dir0, full.names = TRUE), value = T)

users3 <- users2 %>%
  arrange(id_str) %>%
  mutate(paths = grep('224x224', dir(dir0, full.names = TRUE), value = T)) %>%
  left_join(df1, by = c('id_str' = 'id'))

A simple function for modifying profile pics. Including: (1) “charcoal-ing” photos for user privacy, and (2) labeling photos with predicted age, gender, and organization classes.

## <R-console>
modify_images <- function(paths){
  
  for(i in 1:length(paths)){
    y1 <- magick::image_read(paths[i])
    y2 <- magick::image_charcoal(y1)
    y3 <- magick::image_border(y2, 'white', '5x5')
    
    ll <- paste0(users3$org[i], '\n',
                 users3$gender[i], '\n',
                 users3$age[i])
    
    y4 <- magick::image_annotate(y3, 
                                 text = ll, 
                                 color = "black", 
                                 size = 26,
                                 weight = 700,
                                 location = "+10+10")
        
    magick::image_write(y4, paths[i]) 
    }
}

Apply function, and build a collage of profile pics with predicted demographics using the photomoe package.

## <R-console>
modify_images(paths = users3$paths)

# devtools::install_github("jaytimm/photomoe")
photomoe::img_build_collage(paths = users3$paths, 
                            dimx = 7, 
                            dimy = 12)