Exploring shared text in elocution manuals

Data Files

hathi_ia_texts.csv : combined metadata and text for all books
all_counts.csv : n-gram occurences per book
top1000_w_cluster.csv : ngrams annotated with potential cluster/speech origin

Code

proc_into.ipynb : cleaning and downloading files
NgramExperiments.ipynb : ngram generation
visualization.ipynb: clustering and visualization