gistfile1.txt

In [1]: %load_ext autoreload

In [2]: %autoreload 2

In [3]: from stan_lda import *

In [4]: import os

In [5]: os.environ['CC'] = 'gcc-4.8'

In [6]: word_ids, doc_ids, vocab = read_corpus("ptb.train.txt", 100)

In [7]: fit = run_stan(word_ids, doc_ids, vocab, n_topics=7)
INFO:pystan:COMPILING THE C++ CODE FOR MODEL anon_model_d8759dc0e20014dd3ccabfc20650f402 NOW.
Iteration:   1 / 300 [  0%]  (Warmup) (Chain 2)
Iteration:   1 / 300 [  0%]  (Warmup) (Chain 3)
Iteration:   1 / 300 [  0%]  (Warmup) (Chain 0)
Iteration:   1 / 300 [  0%]  (Warmup) (Chain 1)
Iteration:  30 / 300 [ 10%]  (Warmup) (Chain 1)
Iteration:  30 / 300 [ 10%]  (Warmup) (Chain 3)
Iteration:  30 / 300 [ 10%]  (Warmup) (Chain 0)
Iteration:  30 / 300 [ 10%]  (Warmup) (Chain 2)
Iteration:  60 / 300 [ 20%]  (Warmup) (Chain 1)
Iteration:  60 / 300 [ 20%]  (Warmup) (Chain 2)
Iteration:  60 / 300 [ 20%]  (Warmup) (Chain 0)
Iteration:  60 / 300 [ 20%]  (Warmup) (Chain 3)
Iteration:  90 / 300 [ 30%]  (Warmup) (Chain 2)
Iteration:  90 / 300 [ 30%]  (Warmup) (Chain 1)
Iteration:  90 / 300 [ 30%]  (Warmup) (Chain 0)
Iteration:  90 / 300 [ 30%]  (Warmup) (Chain 3)
Iteration: 120 / 300 [ 40%]  (Warmup) (Chain 1)
Iteration: 120 / 300 [ 40%]  (Warmup) (Chain 0)
Iteration: 120 / 300 [ 40%]  (Warmup) (Chain 2)
Iteration: 120 / 300 [ 40%]  (Warmup) (Chain 3)
Iteration: 150 / 300 [ 50%]  (Warmup) (Chain 1)
Iteration: 151 / 300 [ 50%]  (Sampling) (Chain 1)
Iteration: 150 / 300 [ 50%]  (Warmup) (Chain 0)
Iteration: 151 / 300 [ 50%]  (Sampling) (Chain 0)
Iteration: 150 / 300 [ 50%]  (Warmup) (Chain 2)
Iteration: 151 / 300 [ 50%]  (Sampling) (Chain 2)
Iteration: 150 / 300 [ 50%]  (Warmup) (Chain 3)
Iteration: 151 / 300 [ 50%]  (Sampling) (Chain 3)
Iteration: 180 / 300 [ 60%]  (Sampling) (Chain 0)
Iteration: 180 / 300 [ 60%]  (Sampling) (Chain 1)
Iteration: 180 / 300 [ 60%]  (Sampling) (Chain 3)
Iteration: 180 / 300 [ 60%]  (Sampling) (Chain 2)
Iteration: 210 / 300 [ 70%]  (Sampling) (Chain 0)
Iteration: 240 / 300 [ 80%]  (Sampling) (Chain 0)
Iteration: 210 / 300 [ 70%]  (Sampling) (Chain 1)
Iteration: 210 / 300 [ 70%]  (Sampling) (Chain 3)
Iteration: 210 / 300 [ 70%]  (Sampling) (Chain 2)
Iteration: 270 / 300 [ 90%]  (Sampling) (Chain 0)
Iteration: 300 / 300 [100%]  (Sampling) (Chain 0)
Iteration: 240 / 300 [ 80%]  (Sampling) (Chain 3)
# 
#  Elapsed Time: 365.896 seconds (Warm-up)
#                356.369 seconds (Sampling)
#                722.266 seconds (Total)
# 
Iteration: 240 / 300 [ 80%]  (Sampling) (Chain 1)
Iteration: 240 / 300 [ 80%]  (Sampling) (Chain 2)
Iteration: 270 / 300 [ 90%]  (Sampling) (Chain 3)
Iteration: 270 / 300 [ 90%]  (Sampling) (Chain 1)
Iteration: 270 / 300 [ 90%]  (Sampling) (Chain 2)
Iteration: 300 / 300 [100%]  (Sampling) (Chain 3)
# 
#  Elapsed Time: 383.557 seconds (Warm-up)
#                559.784 seconds (Sampling)
#                943.34 seconds (Total)
# 
Iteration: 300 / 300 [100%]  (Sampling) (Chain 1)
# 
#  Elapsed Time: 342.031 seconds (Warm-up)
#                641.288 seconds (Sampling)
#                983.319 seconds (Total)
# 
Iteration: 300 / 300 [100%]  (Sampling) (Chain 2)
# 
#  Elapsed Time: 377.516 seconds (Warm-up)
#                656.548 seconds (Sampling)
#                1034.06 seconds (Total)
# 

gistfile2.txt

phi[5,740]  5.8e-4  5.9e-5 1.5e-32.7e-17 4.8e-9 7.9e-6 3.2e-4 5.7e-3    600    1.0
phi[6,740]  8.3e-4  8.2e-5 2.0e-36.8e-18 2.5e-9 5.6e-6 5.5e-4 6.8e-3    600    1.0
phi[0,741]  7.3e-4  7.5e-5 1.7e-35.5e-16 1.1e-8 7.4e-6 4.4e-4 6.3e-3    547    1.0
phi[1,741]  7.0e-4  7.5e-5 1.8e-31.5e-18 1.1e-8 7.1e-6 3.6e-4 6.3e-3    600    1.0
phi[2,741]  6.9e-4  7.0e-5 1.6e-39.0e-18 1.7e-8 1.3e-5 4.7e-4 6.1e-3    497    1.0
phi[3,741]  7.7e-4  8.0e-5 1.9e-38.6e-18 1.4e-8 1.3e-5 5.5e-4 5.7e-3    580    1.0
phi[4,741]  5.8e-4  6.8e-5 1.6e-31.0e-15 1.5e-8 7.6e-6 3.1e-4 4.8e-3    562   1.01
phi[5,741]  5.2e-4  6.0e-5 1.4e-36.2e-18 4.6e-9 2.5e-6 2.2e-4 4.4e-3    558    1.0
phi[6,741]  7.6e-4  7.1e-5 1.7e-32.4e-17 1.7e-8 9.3e-6 5.1e-4 6.4e-3    600    1.0
phi[0,742]  7.4e-4  8.2e-5 1.8e-31.9e-19 2.7e-9 4.2e-6 5.4e-4 5.9e-3    477    1.0
phi[1,742]  6.5e-4  7.4e-5 1.5e-36.4e-20 1.3e-9 5.3e-6 4.8e-4 6.0e-3    417   1.01
phi[2,742]  5.5e-4  6.3e-5 1.5e-31.7e-16 4.1e-9 2.1e-6 2.4e-4 4.6e-3    567    1.0
phi[3,742]  6.2e-4  5.7e-5 1.4e-31.6e-18 6.5e-9 1.1e-5 4.9e-4 5.4e-3    600    1.0
phi[4,742]  6.1e-4  6.4e-5 1.5e-31.2e-18 6.4e-9 6.2e-6 4.2e-4 4.8e-3    521    1.0
phi[5,742]  5.9e-4  6.4e-5 1.5e-33.1e-16 8.2e-9 7.2e-6 3.1e-4 5.3e-3    529    1.0
phi[6,742]  7.5e-4  7.6e-5 1.9e-33.1e-16 1.6e-8 5.7e-6 5.4e-4 6.8e-3    600    1.0
phi[0,743]  6.7e-4  6.8e-5 1.7e-31.3e-16 2.4e-8 2.0e-5 6.3e-4 5.7e-3    600    1.0
phi[1,743]  7.6e-4  7.3e-5 1.8e-31.1e-16 7.2e-9 1.1e-5 4.7e-4 6.3e-3    583    1.0
phi[2,743]  7.0e-4  7.9e-5 1.7e-33.1e-17 6.4e-9 3.4e-6 4.2e-4 5.5e-3    459    1.0
phi[3,743]  5.6e-4  5.9e-5 1.4e-36.1e-17 2.9e-8 1.2e-5 3.3e-4 4.8e-3    600    1.0
phi[4,743]  6.7e-4  6.9e-5 1.7e-34.0e-16 7.4e-9 5.5e-6 3.5e-4 5.6e-3    600    1.0
phi[5,743]  6.2e-4  6.8e-5 1.7e-39.7e-16 5.0e-9 6.9e-6 3.3e-4 5.3e-3    600    1.0
phi[6,743]  7.6e-4  7.4e-5 1.8e-31.5e-16 1.8e-8 7.4e-6 5.6e-4 6.5e-3    600    1.0
lp__        -2.9e4    7.58  74.65 -2.9e4 -2.9e4 -2.9e4 -2.9e4 -2.9e4     97   1.04

Samples were drawn using NUTS at 2018年03月08日 02時40分57秒.
For each parameter, n_eff is a crude measure of effective sample size,
and Rhat is the potential scale reduction factor on split chains (at 
convergence, Rhat=1).

gistfile3.txt

In [58]: m = fit.extract()

In [59]: phi = m["phi"]

In [60]: phi.shape
Out[60]: (600, 7, 744)

In [61]: mphi = np.mean(phi, axis=0)

In [62]: mphi
Out[62]: 
array([[ 0.01934522,  0.00067797,  0.00067912, ...,  0.00073079,
         0.00074387,  0.00066906],
       [ 0.05383168,  0.0005909 ,  0.00057828, ...,  0.00069623,
         0.00064964,  0.00076267],
       [ 0.02318433,  0.00062504,  0.00082581, ...,  0.0006914 ,
         0.00054864,  0.00070076],
       ..., 
       [ 0.06520887,  0.00069524,  0.00068922, ...,  0.00058358,
         0.00060854,  0.00067   ],
       [ 0.12132906,  0.00059118,  0.00060603, ...,  0.00052047,
         0.00058573,  0.0006186 ],
       [ 0.0069193 ,  0.00072506,  0.00085234, ...,  0.00076468,
         0.00074746,  0.00076338]])

In [63]: for row in mphi.argsort(axis=1):
    ...:     print([vocab.word(wid+1) for wid in row[-20:]])
    ...: 
['on', 'with', 'year', 'billion', 'at', 'yield', 'by', 'said', 'in', "'s", 'for', 'and', '$', 'from', 'a', '<unk>', 'to', 'of', 'the', 'N']
['by', 'are', 'workers', 'was', 'with', 'asbestos', 'it', 'that', 'is', 'on', "'s", 'said', 'and', 'for', 'in', 'to', 'a', 'of', '<unk>', 'the']
['funds', 'average', 'year', 'said', 'by', 'at', 'yield', "'s", 'billion', 'for', 'and', 'in', '$', 'a', 'from', 'of', 'to', '<unk>', 'the', 'N']
['year', 'at', 'asbestos', 'with', 'by', 'on', 'was', 'it', 'is', 'that', "'s", 'said', 'for', 'in', 'to', 'and', 'a', 'of', 'the', '<unk>']
['asbestos', 'it', 'is', 'was', 'with', 'on', 'that', 'from', '$', 'said', "'s", 'for', 'in', 'and', 'to', 'a', 'N', 'of', 'the', '<unk>']
['this', 'workers', 'was', 'by', 'it', 'asbestos', 'on', 'is', "'s", 'with', 'that', 'said', 'for', 'to', 'in', 'a', 'and', 'of', 'the', '<unk>']
['with', 'that', 'year', 'was', 'asbestos', 'it', 'by', 'on', '<unk>', 'is', 'said', "'s", 'N', 'for', 'and', 'in', 'to', 'of', 'a', 'the']