def heap(corp, rng):
vocab_sizes = []
for ntoks in rng:
subsample = Sentences(sent_subsample(corp, ntoks))
vocab_size = compute_vocab_size(subsample)
vocab_sizes.append(vocab_size)
return vocab_sizes
def get_filters(filter_dir, k, names, param_name, param_ls):
filters_dict = {}
for param in param_ls:
all_samples = corpora_from_pickles(filter_dir, names=names)
cur_param_filters = [Sentences(c) for name_d, c in all_samples if
name_d["k"] == k and name_d[param_name] == param]
filters_dict[param] = cur_param_filters
return filters_dict
def filter_worker(i):
print("started ", i)
cur_seed = int.from_bytes(os.urandom(4), byteorder='little')
rand.seed(cur_seed)
filtered = list(filter_typicality_incremental(mp_array, zipf_model,
rank_dict, auto_typ, n, factor*epsilon_f_minus, lt))
filtered_freqs = compute_freqs(Sentences(filtered))
print("filtered ", i, " typicality: ",
typicality(zipf_model, merge_to_joint(rank_dict, filtered_freqs)))
name = "_".join((str(n), str(factor), str(i)))
corpus_to_pickle(filtered, "results/" + lang + "/TF", name)
setup_m = 100
m = 10
wiki = list(wiki_from_pickles("data/"+lang+"_pkl"))
sents = [s for a in wiki for s in a]
zipf_model, rank_dict, mean_typ, std_typ, auto_typ = setup_filtering(wiki,
big_n(wiki),
n,
setup_m)
mean_corrected = abs(mean_typ - auto_typ)
epsilon_f_plus = mean_corrected + std_typ*factor
epsilon_f_minus = - epsilon_f_plus
print("\nModel and Epsilon established")
print(auto_typ, mean_typ, std_typ)
print(epsilon_f_minus, epsilon_f_plus)
for m_i in range(m):
print("started ", m_i)
filtered = list(filter_typicality_incremental(sents, zipf_model,
rank_dict, auto_typ, n, epsilon_f_minus, lt))
filtered_freqs = compute_freqs(Sentences(filtered))
print("filtered ", m_i, " typicality: ",
typicality(zipf_model, merge_to_joint(rank_dict, filtered_freqs)))
name = "_".join((str(n), str(factor), str(m_i)))
corpus_to_pickle(filtered, "results/" + lang + "/TF", name)
print("ARGS: ", lang, factors, hist_lens, "\n")
d = "results/" + lang + "/"
results_d = d + "evaluation/"
k = 1000000
srfs = get_filters(d + "SRF/", k, ["k", "h", "i"], "h", hist_lens)
tfs = get_filters(d + "TF/", k, ["k", "f", "i"], "f", factors)
highest_three_factors = factors[-3:]
three_tfs = {k: tfs[k] for k in highest_three_factors}
highest_three_hist_lens = hist_lens[-3:]
three_srfs = {k: srfs[k] for k in highest_three_hist_lens}
unis = [
Sentences(c)
for _, c in corpora_from_pickles(d + "UNI", names=["k", "i"])
]
uni_mean_ranks, uni_mean_freqs = mean_rank_freq_from_samples(unis)
uni_joints = merge_to_joint(uni_mean_ranks, uni_mean_freqs)
uni_xs, uni_ys = list(zip(*sorted(uni_joints.values())))
print("filters loaded", flush=True)
# MLEs
tf_mles, srf_mles, uni_mandel = do_mles(tfs, srfs, unis)
with open(results_d + "mle_mandelbrot.txt", "w") as handle:
for param, mandel in tf_mles.items():
handle.write("TF " + str(param))
if __name__ == "__main__":
n = 100000
d = "results/ALS/"
# GET UNIVERSE
wiki = list(wiki_from_pickles("data/ALS_pkl"))
sent_d, label_f = number_sents((s for a in wiki for s in a))
word_d, word_label_f = number_words((w for a in wiki for s in a
for w in s))
## LOAD CORPORA
# SRFs
srf_samples = list(corpora_from_pickles(d + "SRF", names=["n", "h", "i"]))
srf_10 = [
Sentences(c) for name_d, c in srf_samples
if name_d["n"] == n and name_d["h"] == 10
]
srf_20 = [
Sentences(c) for name_d, c in srf_samples
if name_d["n"] == n and name_d["h"] == 20
]
srf_30 = [
Sentences(c) for name_d, c in srf_samples
if name_d["n"] == n and name_d["h"] == 30
]
#TFs
tf_samples = list(corpora_from_pickles(d + "TF", names=["n", "f", "i"]))
tf_50 = [
Sentences(c) for name_d, c in tf_samples
if name_d["n"] == n and name_d["f"] == 50
c_vec1, c_vec2 = [cs1[x] for x in sorted(universe)], [cs2[x] for x in sorted(universe)]
return sum(min(one, two) for one, two in zip(c_vec1, c_vec2))/sum(max(one, two) for one, two in zip(c_vec1, c_vec2))
if __name__ == "__main__":
n = 100000
d = "results/ALS/"
wiki = list(wiki_from_pickles("data/ALS_pkl"))
print("Total num sents", len([s for a in wiki for s in a]))
srf_samples = corpora_from_pickles(d + "SRF", names=["n", "h", "i"])
srf_30 = [Sentences(c) for name_d, c in srf_samples if name_d["n"] == n and
name_d["h"] == 30]
tf_samples = corpora_from_pickles(d + "TF", names=["n", "f", "i"])
tf_100 = [Sentences(c) for name_d, c in tf_samples if name_d["n"] == n and
name_d["f"] == 100]
uni_samples = corpora_from_pickles(d + "UNI", names=["n", "i"])
uni = [Sentences(c) for name_d, c in uni_samples if name_d["n"] == n]
for subcorp_set, name in zip([srf_30, tf_100, uni], ["SRF", "TF", "UNI"]):
print("\n", name)
shuffled_sents = rand.permutation([s for subcorp in subcorp_set
