问题
I am trying to implement lda using PyMC3.
However, when defining the last part of the model in which words are sampled based on their topics, I keep getting the error: TypeError: list indices must be integers, not TensorVariable
How to tackle the problem?
The code is as follows:
## Data Preparation
K = 2 # number of topics
N = 4 # number of words
D = 3 # number of documents
import numpy as np
data = np.array([[1, 1, 1, 1], [1, 1, 1, 1], [0, 0, 0, 0]])
Wd = [len(doc) for doc in data] # length of each document
## Model Specification
from pymc3 import Model, Normal, HalfNormal, Dirichlet, Categorical, constant
lda_model = Model()
with lda_model:
# Priors for unknown model parameters
alpha = HalfNormal('alpha', sd=1)
eta = HalfNormal('eta', sd=1)
a1 = eta*np.ones(shape=N)
a2 = alpha*np.ones(shape=K)
beta = [Dirichlet('beta_%i' % i, a1, shape=N) for i in range(K)]
theta = [Dirichlet('theta_%s' % i, a2, shape=K) for i in range(D)]
z = [Categorical('z_%i' % d, p = theta[d], shape=Wd[d]) for d in range(D)]
# That's when you get the error. It is caused by: beta[z[d][w]]
w = [Categorical('w_%i_%i' % (d, w), p = beta[z[d][w]], observed = data[i,j]) for d in range(D) for w in range(Wd[d])]
Any help would be much appreciated!
回答1:
beta[z[d][w]] is naturally incorrect because z[d][w] is a variable stored by PyMC instead of being an fixed index.
In pymc2 it is solved by lambda function
p=pm.Lambda("phi_z_%s_%s" % (d,i),
lambda z=z[d][w], beta=beta: beta[z])
In pymc3 it is suppose to be solved by
@theano.compile.ops.as_op
def your_function
But there is a problem here that it seems like Theano doesn't allow sending a python list of pymc variable. t.lvector baisically don't work.
More discussion is in this question: Unable to create lambda function in hierarchical pymc3 model
回答2:
check out this blog post. I haven't tested it.
import numpy as np
import pymc as pc
def wordDict(collection):
word_id = {}
idCounter = 0
for d in collection:
for w in d:
if (w not in word_id):
word_id[w] = idCounter
idCounter+=1
return word_id
def toNpArray(word_id, collection):
ds = []
for d in collection:
ws = []
for w in d:
ws.append(word_id.get(w,0))
ds.append(ws)
return np.array(ds)
###################################################
#doc1, doc2, ..., doc7
docs = [["sepak","bola","sepak","bola","bola","bola","sepak"],
["uang","ekonomi","uang","uang","uang","ekonomi","ekonomi"],
["sepak","bola","sepak","bola","sepak","sepak"],
["ekonomi","ekonomi","uang","uang"],
["sepak","uang","ekonomi"],
["komputer","komputer","teknologi","teknologi","komputer","teknologi"],
["teknologi","komputer","teknologi"]]
word_dict = wordDict(docs)
collection = toNpArray(word_dict,docs)
#number of topics
K = 3
#number of words (vocab)
V = len(word_dict)
#number of documents
D = len(collection)
#array([1, 1, 1, ..., 1]) K times
alpha = np.ones(K)
#array([1, 1, 1, ..., 1]) V times
beta = np.ones(V)
#array containing the information about doc length in our collection
Nd = [len(doc) for doc in collection]
######################## LDA model ##################################
#topic distribution per-document
theta = pc.Container([pc.CompletedDirichlet("theta_%s" % i,
pc.Dirichlet("ptheta_%s"%i, theta=alpha))
for i in range(D)])
#word distribution per-topic
phi = pc.Container([pc.CompletedDirichlet("phi_%s" % j,
pc.Dirichlet("pphi_%s" % j, theta=beta))
for j in range(K)])
#Please note that this is the tricky part :)
z = pc.Container([pc.Categorical("z_%i" % d,
p = theta[d],
size = Nd[d],
value = np.random.randint(K, size=Nd[d]))
for d in range(D)])
#word generated from phi, given a topic z
w = pc.Container([pc.Categorical("w_%i_%i" % (d,i),
p = pc.Lambda("phi_z_%i_%i" % (d,i),
lambda z=z[d][i], phi=phi : phi[z]),
value=collection[d][i],
observed=True)
for d in range(D) for i in range(Nd[d])])
####################################################################
model = pc.Model([theta, phi, z, w])
mcmc = pc.MCMC(model)
mcmc.sample(iter=5000, burn=1000)
#show the topic assignment for each word, using the last trace
for d in range(D):
print(mcmc.trace('z_%i'%d)[3999])
回答3:
The following code was adapted from what has been referenced by @Hanan. I've somehow made it work with pymc3.
import numpy as np
import pymc3 as pm
def get_word_dict(collection):
vocab_list = list({word for doc in collection for word in doc})
idx_list = [i for i in range(len(vocab_list))]
return dict(zip(vocab_list,idx_list))
def word_to_idx(dict_vocab_idx, collection):
return [[dict_vocab_idx[word] for word in doc] for doc in collection]
docs = [["sepak","bola","sepak","bola","bola","bola","sepak"],
["uang","ekonomi","uang","uang","uang","ekonomi","ekonomi"],
["sepak","bola","sepak","bola","sepak","sepak"],
["ekonomi","ekonomi","uang","uang"],
["sepak","uang","ekonomi"],
["komputer","komputer","teknologi","teknologi","komputer","teknologi"],
["teknologi","komputer","teknologi"]]
dict_vocab_idx = get_word_dict(docs)
idxed_collection = word_to_idx(dict_vocab_idx, docs)
n_topics = 3
n_vocab = len(dict_vocab_idx)
n_docs = len(idxed_collection)
length_docs = [len(doc) for doc in idxed_collection]
alpha = np.ones([n_docs, n_topics])
beta = np.ones([n_topics, n_vocab])
with pm.Model() as model:
theta = pm.distributions.Dirichlet('theta', a=alpha, shape=(n_docs, n_topics))
phi = pm.distributions.Dirichlet('phi', a=beta, shape=(n_topics, n_vocab))
zs = [pm.Categorical("z_d{}".format(d), p=theta[d], shape=length_docs[d]) for d in range(n_docs)]
ws = [pm.Categorical("w_{}_{}".format(d,i), p=phi[zs[d][i]], observed=idxed_collection[d][i])
for d in range(n_docs) for i in range(length_docs[d])]
trace = pm.sample(2000)
for d in range(n_docs):
value_z=trace.get_values("z_d{}".format(d))
print(value_z[1999])
来源：https://stackoverflow.com/questions/31473459/pymc3-how-to-implement-latent-dirichlet-allocation