def get_mean_relationship(wiki, n, m, freq_func):
subsamples1 = (Sentences.subsample(wiki, n) for _ in range(m))
subsamples2 = (Sentences.subsample(wiki, n) for _ in range(m))
ranks = [compute_ranks(sub) for sub in subsamples1]
ranks_joined = pool_ranks(ranks)
mean_ranks = reduce_pooled(ranks_joined)
freqs = [freq_func(sub) for sub in subsamples2]
freqs_joined = pool_freqs(freqs)
mean_freqs = reduce_pooled(freqs_joined)
return mean_ranks, mean_freqs
def variance_main(wiki, n, m, save_dir="./"):
subsamples1 = (Sentences.subsample(wiki, n) for _ in range(m))
subsamples2 = (Sentences.subsample(wiki, n) for _ in range(m))
ranks = [compute_ranks(sub) for sub in subsamples1]
ranks_joined = pool_ranks(ranks)
freqs = [compute_freqs(sub) for sub in subsamples2]
freqs_joined = pool_freqs(freqs)
mean_vs_pooled(ranks_joined, freqs_joined, save_dir)
do_mles(ranks, freqs, save_dir)
covariance_across_words(ranks_joined, freqs_joined, save_dir)
def get_model(corpus, n):
big_ranks = compute_ranks(Sentences.subsample(corpus, n))
freqs = compute_freqs(Sentences.subsample(corpus, n))
joint = merge_to_joint(big_ranks, freqs)
xs, ys = list(zip(*sorted(joint.values())))
mandelbrot = Mandelbrot(ys, xs)
mandelbrot_fit = mandelbrot.fit(start_params=np.asarray([1.0, 1.0]),
method="powell",
full_output=True)
mandelbrot.register_fit(mandelbrot_fit)
mandelbrot.print_result()
auto_typ = typicality(mandelbrot, joint)
return big_ranks, mandelbrot, auto_typ
def heap(corp, rng):
vocab_sizes = []
for i, ntoks in enumerate(rng):
if i % 10 == 0:
print(i, ntoks)
subsample = Sentences.subsample(corp, ntoks)
vocab_size = compute_vocab_size(subsample)
vocab_sizes.append(vocab_size)
return vocab_sizes
def establish_typical_set(corpus, rank_dict, zipf_model, n, m):
typicalities = []
for i in range(m):
sub = Sentences.subsample(corpus, n)
sub_freqs = compute_freqs(sub)
sub_joints = merge_to_joint(rank_dict, sub_freqs)
sub_typicality = typicality(zipf_model, sub_joints)
typicalities.append(sub_typicality)
mean_typ, std_typ = np.mean(typicalities), np.var(typicalities)**.5
return mean_typ, std_typ
def get_reference_dist(wiki):
n = int(10e6)
m = 10
wiki_ls = list(wiki)
subsamples = [Sentences.subsample(wiki_ls, n) for _ in range(m)]
mean_ranks, mean_freqs = mean_rank_freq_from_samples(subsamples)
joints = merge_to_joint(mean_ranks, mean_freqs)
xs, ys = list(zip(*sorted(joints.values())))
mandelbrot = Mandelbrot(ys, xs)
mandelbrot_fit = mandelbrot.fit(start_params=np.asarray([1.0, 1.0]),
method="powell",
full_output=True)
mandelbrot.register_fit(mandelbrot_fit)
mandelbrot.print_result()
return mandelbrot, mean_ranks
# -*- coding: utf-8 -*-
from data.reader import wiki_from_pickles, corpus_to_pickle
from data.corpus import Sentences
from stats.stat_functions import compute_freqs, merge_to_joint
import argparse
def parse_args():
p = argparse.ArgumentParser()
p.add_argument("--lang", type=str)
p.add_argument("--n_tokens", type=int)
args = p.parse_args()
return args.lang, args.n_tokens
if __name__ == "__main__":
lang, n = parse_args()
m = 10
wiki = list(wiki_from_pickles("data/" + lang + "_pkl"))
for i in range(m):
sampled = Sentences.subsample(wiki, n)
sampled_sents = list(sampled.sentences())
name = "_".join((str(n), str(i)))
corpus_to_pickle(sampled_sents, "results/" + lang + "/UNI", name)
hexbin_plot(xs, ys, xlbl="$\log$ $r(w)$", ylbl="$\log$ $f(w)$")
plt.savefig(d + "rank_freq_" + str(n) + "_piantadosi.png", dpi=300)
plt.close()
if __name__ == "__main__":
lang = parse_args()
d = "results/" + lang + "/plots/"
wiki = list(wiki_from_pickles("data/" + lang + "_pkl"))
n = int(10e6)
m = 10
zipf_wrong(wiki, n, d)
zipf_piantadosi(wiki, n, d)
subsamples1 = (Sentences.subsample(wiki, n) for _ in range(m))
subsamples2 = (Sentences.subsample(wiki, n) for _ in range(m))
ranks = [compute_ranks(sub) for sub in subsamples1]
ranks_joined = pool_ranks(ranks)
mean_ranks = reduce_pooled(ranks_joined)
freqs = [compute_freqs(sub) for sub in subsamples2]
freqs_joined = pool_freqs(freqs)
mean_freqs = reduce_pooled(freqs_joined)
print("subsampling done")
joints = merge_to_joint(mean_ranks, mean_freqs)
xs, ys = list(zip(*sorted(joints.values())))
