def compute_l1(self,load,save=True):
print("subject:",self.inference_params.subject)
print("predicate",self.inference_params.predicate)
print("SIGs 1&2:",self.inference_params.sig1,self.inference_params.sig2)
print("L1 SIG",self.inference_params.l1_sig1)
# print("step_size",self.inference_params.step_size)
# print("utt weight, qud weight",self.inference_params.freq_weight,self.inference_params.qud_weight)
print("number of qud dimensions:",self.inference_params.number_of_qud_dimensions)
# print("trival qud prior on?",self.inference_params.trivial_qud_prior)
print("rationality:",self.inference_params.rationality)
# print("sample number",self.inference_params.sample_number)
message = "Running "+self.inference_params.model_type+" RSA with "+str(len(self.inference_params.possible_utterances))+" possible utterances and " + str(len(self.inference_params.quds))
print(message)
# tf_l1_discrete_only_trivial : discrete without quds: can drop :
# tf_l1_noncat : continuous quds: deprecate for now
# tf_l1_discrete : rename to: exact
# tf_l1_qud_only : the baseline model: rename
# tf_l1_with_trivial : includes the trivial qud: omit for now
# tf_l1_mixture : rename to: discrete approximate
# tf_l1_only_trivial : rename
# tf_l1: rename to: continuous approximate
# options: exact, approximate, then: later: make object: approximate.hmm: remove hmm vs var from inference_params
if self.inference_params.model_type=="discrete_exact":
print("RUNNING DISCRETE EXACT MODEL")
# if self.inference_params.only_trivial:
# tf_results = tf_l1_discrete_only_trivial(self.inference_params)
# else:
self.tf_results = tf_l1_discrete(self.inference_params)
# return None
# elif self.inference_params.only_trivial:
# print("RUNNING MODEL WITHOUT QUDS")
# tf_results = tf_l1_only_trivial(self.inference_params)
# self.world_samples = tf_results
# return None
# elif self.inference_params.model_type=='categorical':
# print("is baseline?",self.inference_params.baseline)
# if self.inference_params.baseline:
# print("RUNNING BASELINE MODEL")
# # tf_results = tf_l1_qud_only(self.inference_params)
# self.qud_samples = tf_l1_qud_only(self.inference_params)
# return None
# elif self.inference_params.trivial_qud_prior:
# print("RUNNING CAT WITH TRIVIAL MODEL")
# tf_results = tf_l1_with_trivial(self.inference_params)
elif self.inference_params.model_type=="discrete_mixture":
print("RUNNING DISCRETE MIXTURE MODEL")
self.tf_results = tf_l1_mixture(self.inference_params)
elif self.inference_params.model_type=="qud_only":
print("RUNNING QUD ONLY MODEL")
self.tf_results = tf_l1_qud_only(self.inference_params)
print("results",self.tf_results)
elif self.inference_params.model_type=="numpy_discrete_mixture":
print("RUNNING NUMPY DISCRETE MIXTURE MODEL")
self.tf_results = np_l1_mixture(self.inference_params)
print("results",self.tf_results)
elif self.inference_params.model_type=="baseline":
print("RUNNING BASELINE MODEL")
from dist_rsa.utils.load_data import get_words
vecs = self.inference_params.vecs
subj = self.inference_params.subject
pred = self.inference_params.predicate
self.inference_params.qud_combinations = [[q] for q in self.inference_params.quds]
nouns,adjs = get_words(with_freqs=False)
qud_words = [a for a in adjs if adjs[a] if a in vecs and a!=pred]
self.inference_params.qud_marginals = [-scipy.spatial.distance.cosine(np.mean([vecs[subj[0]],vecs[pred]],axis=0),vecs[qud]) for qud in qud_words][:100]
sorted_qud_words = sorted(qud_words,key=lambda x:scipy.spatial.distance.cosine(np.mean([vecs[subj[0]],vecs[pred]],axis=0),vecs[x]))
self.inference_params.ordered_quds = sorted_qud_words
# list(list(zip(*self.inference_params.qud_marginals))[0])
self.tf_results = None
print("results",self.tf_results)
from __future__ import division
from collections import defaultdict
import scipy
import numpy as np
import pickle
import itertools
from dist_rsa.dbm import *
from dist_rsa.utils.load_data import *
from dist_rsa.utils.helperfunctions import *
from dist_rsa.utils.load_data import get_words
from dist_rsa.lm_1b_eval import predict
vecs = load_vecs(mean=True, pca=True, vec_length=300, vec_type='glove.6B.')
nouns, adjs = get_words()
def l1_cat_2d_exp(metaphor):
vec_size, vec_kind = 25, 'glove.twitter.27B.'
subj, pred = metaphor
abstract_threshold = 2.5
print('abstract_threshold', abstract_threshold)
concrete_threshold = 3.0
print('concrete_threshold', concrete_threshold)
qud_words = [
a for a in list(adjs) if adjs[a] < abstract_threshold and a in vecs
]
sig2_distance = scipy.spatial.distance.cosine(vecs[subj], vecs[pred])
# prob_dict = get_freqs(preprocess=False)
def l1_iden_1d(metaphor):
vecs = pickle.load(open("dist_rsa/data/word_vectors/glove.6B.mean_vecs300",
'rb'),
encoding='latin1')
nouns, adjs = get_words()
vec_size, vec_kind = (25, 'glove.twitter.27B.')
subj, pred = metaphor
abstract_threshold = 2.5
print('abstract_threshold', abstract_threshold)
concrete_threshold = 3.0
print('concrete_threshold', concrete_threshold)
qud_words = [n for n in nouns if nouns[n] < 4.0 and n in vecs]
qud_words = sorted(qud_words,\
key=lambda x:scipy.spatial.distance.cosine(vecs[x],np.mean([vecs[subj],vecs[pred]],axis=0)),reverse=False)
# print(quds)
# break
quds = qud_words[:30]
# prob_dict = predict(" ".join([subj, "are"]))
possible_utterance_nouns = sorted([a for a in adjs if adjs[a] > concrete_threshold and a in vecs],\
# key=lambda x:prob_dict[x],reverse=True)
key=lambda x:scipy.spatial.distance.cosine(vecs[x],np.mean([vecs[subj],vecs[pred]],axis=0)),reverse=False)
possible_utterances = possible_utterance_nouns[:30]
print("QUDS:\n", quds[:20])
print("UTTERANCES:\n", possible_utterances[:20])
run = DistRSAInference(
subject=[subj],
predicate=pred,
# possible_utterances=animals,
# quds=animal_features,
quds=quds,
# quds = animal_features,
# ['unyielding']+list(list(zip(*visualize_cosine(np.mean([vecs['man'],vecs[word]],axis=0),freq_sorted_adjs,vecs)[:500:10]))[0]),
possible_utterances=list(set(possible_utterances).union(set([pred]))),
# possible_utterances=
# [noun for noun in nouns if noun not in adjectives][:100]+[adj for adj in adjectives if adj not in nouns][:100]+[pred],
# sorted_nouns[sorted_nouns.index(pred) if pred in sorted_nouns else 500]+['horse'],
object_name="animals_spec",
mean_vecs=True,
pca_remove_top_dims=True,
sig1=0.0005,
sig2=0.01,
# proposed_sig2*scaling_factor,
qud_weight=0.0,
freq_weight=0.0,
categorical="categorical",
vec_length=vec_size,
vec_type=vec_kind,
sample_number=400,
number_of_qud_dimensions=1,
burn_in=285,
seed=False,
trivial_qud_prior=True,
step_size=0.0005,
frequencies=defaultdict(lambda: 1),
qud_frequencies=defaultdict(lambda: 1),
qud_prior_weight=0.9,
rationality=1.0,
run_s2=False,
speaker_world=vecs[subj],
s1_only=False,
norm_vectors=True)
real_vecs = pickle.load(open(
"dist_rsa/data/word_vectors/" + vec_kind + "pca and mean" +
str(vec_size), 'rb'),
encoding='latin1')
# print(real_vecs[subj],real_vecs[pred])
run.compute_results(load=0, save=False)
# print(run.world_movement("cosine",do_projection=True,comparanda=[x for x in abstract_adjs+abstract_nouns if x in real_vecs]))
print(run.qud_results())
# print("QUDS:\n",results[:20])
# print("WORLD MOVEMENT\n:",run.world_movement("cosine",comparanda=[x for x in quds if x in real_vecs])[:50])
# print("WORLD MOVEMENT\n:",run.world_movement("euclidean",comparanda=[x for x in quds if x in real_vecs])[:50])
# print("BASELINE:\n:",run.baseline_model('mean')[:20])
return run.qud_samples