PyStyl is a Python package for stylometry or the quantitative analysis of writing style. Pronounced as "Pistol".

stylometry_pystyl.py

# 2-D Scatter Plot using PCA
from pystyl.analysis import distance_matrix, hierarchical_clustering

from pystyl.visualization import scatterplot, scatterplot_3d

from pystyl.analysis import pca

pca_coor, pca_loadings = pca(corpus, nb_dimensions=2)

scatterplot(corpus, coor=pca_coor, nb_clusters=0, loadings=pca_loadings, plot_type='static',\
           save=False, show=False, return_svg=False, outputfile="/Users/lord/Desktop/pca.pdf")

# 3-D Scatter Plot using PCA 
pca_coor, pca_loadings = pca(corpus, nb_dimensions=3)

scatterplot_3d(corpus, coor=pca_coor, outputfile="/Users/lord/Desktop/3d.pdf",\
           save=True, show=False, return_svg=False)

# Clustermap using Distance Matrix
from pystyl.analysis import distance_matrix

dm = distance_matrix(corpus, 'minmax')

from pystyl.visualization import clustermap

clustermap(corpus, distance_matrix=dm, fontsize=8, color_leafs=True,\
           outputfile='/Users/lord/Desktop/cm.pdf',
          show=False, save=False, return_svg=False)

# Building a tree using Heirarchial Clustering
from pystyl.analysis import hierarchical_clustering

cluster_tree = hierarchical_clustering(dm, linkage='ward')

#Regular Dendogram
from pystyl.visualization import scipy_dendrogram, ete_dendrogram

scipy_dendrogram(corpus=corpus, tree=cluster_tree, outputfile='~/Desktop/scipy_dendrogram.pdf',\
                 fontsize=5, color_leafs=True, show=False, save=F, return_svg=False)

# Circular Dendogram
ete_dendrogram(corpus=corpus, tree=cluster_tree, outputfile='~/Desktop/ete_dendrogram.png',\
                 fontsize=5, color_leafs=True, show=False, save=True, return_svg=False,
              save_newick=False)

from IPython.display import Image
Image(filename='/Users/lord/Desktop/ete_dendrogram.png')