2-poissonTC.R

# Determine intersection of compounds in features and responses
commonMols <- intersect(responses$CID,
                        molFeats$CID)
# Subset features and responses accordingly
responses %<>% filter(CID %in% commonMols)
molFeats %<>% filter(CID %in% commonMols)

# Compute median pleasantness across the population
medianPlsnt <- responses %>% 
      group_by(CID) %>% 
      dplyr::summarise(pleasantness = median(`VALENCE/PLEASANTNESS`, na.rm = T))
all(medianPlsnt$CID == molFeats$CID) # TRUE - rownames match

# Concatenate predictors (molFeats) and population pleasantness
X <-  mutate(molFeats, Y = medianPlsnt$pleasantness) %>% 
      select(-CID)