In [1]:

    

import argparse
import os
import shutil
import gzip

import torch
import torch.nn as nn
from torch.autograd import Variable

import torch
import torch.nn as nn
from torch.autograd import Variable

from dpp_nets.utils.language import Vocabulary, BeerDataset, custom_collate
from dpp_nets.layers.baselines import NetBaseline, SetNetBaseline, AttentionBaseline

from dpp_nets.utils.language import EvalSet


    

In [2]:

    

# Load saved checkpoint
model = 'shortsentsNet1lr0.01best_ckp.pth.tar'
model_dir = '/Users/Max/checkpoints/beer_reviews/baseline/' 
model_path = model_dir + model
model = torch.load(model_path, map_location=lambda storage, loc: storage)


    

In [3]:

    

from dpp_nets.utils.language import Vocabulary

embd_path = '/Users/Max/data/beer_reviews/review+wiki.filtered.200.txt.gz'
word_path = '/Users/Max/data/beer_reviews/reviews.all.train.words.txt.gz'

# Set-up Vocabulary
vocab = Vocabulary()
vocab.loadPretrained(embd_path)
vocab.setStops()
vocab.loadCorpus(word_path)
vocab.updateEmbedding()
vocab.setCuda(False)
vocab.EmbeddingBag.load_state_dict(model['embedding'])


    

In [4]:

    

EMBD_DIM = 200
KERNEL_DIM = 200
HIDDEN_DIM = 500
ENC_DIM = 200
TARGET_DIM = 3 if model['aspect'] in set(['all', 'short']) else 1

if model['model_type'] == NetBaseline:
    trainer = NetBaseline(EMBD_DIM, HIDDEN_DIM, TARGET_DIM)
if model['model_type'] == SetNetBaseline:
    trainer = NetBaseline(EMBD_DIM, HIDDEN_DIM, KERNEL_DIM, ENC_DIM, TARGET_DIM)
if model['model_type'] == AttentionBaseline:
    trainer = SetNetBaseline(EMBD_DIM, HIDDEN_DIM, ENC_DIM, TARGET_DIM)

trainer.load_state_dict(model['model'])
#trainer.activation = nn.Sigmoid()

rat_path = '/Users/Max/data/beer_reviews/annotations.json'
evalset = EvalSet(rat_path, vocab)


    

In [5]:

    

evalset.evaluateBaseline(trainer, model['mode'])


    

    
Out[5]:





0.01592683966787016

In [ ]:

    

print('__________________________Training Table__________________________')
for k, v in model['train_loss'].items():
    print(str.join(" | ", ['Epoch: %d' % (k), 'Loss: %.5f' % (v)]))


    

In [ ]:

    

from dpp_nets.helper.plotting import plot_floats

# Training Plots
plot_floats(model['train_loss'], xlabel='Epochs', ylabel='MSE + Reg', title='Training MSE + Reg')


    

In [ ]:

    

print('_________________________Validation Table_________________________')
for k, v in model['val_loss'].items():
    print(str.join(" | ", ['Epoch: %d' % (k), 'Loss: %.5f' % (v)]))


    

In [ ]:

    

from dpp_nets.helper.plotting import plot_floats

# Training Plots
plot_floats(model['val_loss'], xlabel='Epochs', ylabel='MSE + Reg', title='Validation MSE + Reg')


    

In [ ]:

    

# Evaluation on Test Set

loss, pred_loss, reg_loss = evalset.computeLoss(trainer, model['mode'])
print(str.join(" | ", ['Test Set:', 'Loss: %.5f' % (loss), 
                              'Pred Loss: %.5f' % (pred_loss), 'Reg Loss: %.5f' % (reg_loss)]))

prec, extract = evalset.evaluatePrecision(trainer,model['mode'])
print(str.join(" | ", ['Test Set:', 'Precision: %.5f' % (prec), 'Extract: %.5f' % (extract)]))


    

In [ ]:

    

# Random Samples

evalset.sample(trainer, model['mode'])


    

In [ ]:

    

# Random Marginals
evalset.computeMarginals(trainer, model['mode'])


    

In [5]:

    

evalset.reviews[713]


    

    
Out[5]:





{'0': [[0, 5], [5, 8], [8, 14], [14, 23]],
 '1': [[23, 33], [33, 42]],
 '2': [[73, 82]],
 '3': [[42, 46], [46, 50], [50, 59], [59, 64], [64, 69], [69, 73]],
 '4': [[82, 100]],
 'raw': '{\'review/appearance\': 4.0, \'beer/style\': \'American Double / Imperial IPA\', \'review/palate\': 4.0, \'review/taste\': 4.0, \'beer/name\': \'Green Flash Imperial India Pale Ale\', \'review/timeUnix\': 1300608461, \'beer/ABV\': 9.4, \'beer/beerId\': \'34085\', \'beer/brewerId\': \'2743\', \'review/timeStruct\': {\'isdst\': 0, \'mday\': 20, \'hour\': 8, \'min\': 7, \'sec\': 41, \'mon\': 3, \'year\': 2011, \'yday\': 79, \'wday\': 6}, \'review/overall\': 4.0, \'review/text\': "Appearance: Golden Honey. Slightly Orange. It\'s a little opaque. It has a weak head with minimal retention.\\t\\tSmell: A huge dose of bread pale malts. There is a huge blast of very citric hops. \\t\\tTaste: Wow. This taste great. It has a good blend of cocoa malts. Very bitter piney hops. Slight tropical fruit sweetness. Apricot. Pineapple. Very bitter finish.\\t\\tMouthfeel: Medium bodied with a chalky finish.\\t\\tDrinkability: Good but not quite as enjoyable as the Pliny the Elder which she had before.", \'user/profileName\': \'BerkeleyBeerMan\', \'review/aroma\': 4.0}\n',
 'rid': 192715,
 'x': ['appearance',
  ':',
  'golden',
  'honey',
  '.',
  'slightly',
  'orange',
  '.',
  'it',
  "'s",
  'a',
  'little',
  'opaque',
  '.',
  'it',
  'has',
  'a',
  'weak',
  'head',
  'with',
  'minimal',
  'retention',
  '.',
  'smell',
  ':',
  'a',
  'huge',
  'dose',
  'of',
  'bread',
  'pale',
  'malts',
  '.',
  'there',
  'is',
  'a',
  'huge',
  'blast',
  'of',
  'very',
  'citric',
  'hops',
  'taste',
  ':',
  'wow',
  '.',
  'this',
  'taste',
  'great',
  '.',
  'it',
  'has',
  'a',
  'good',
  'blend',
  'of',
  'cocoa',
  'malts',
  '.',
  'very',
  'bitter',
  'piney',
  'hops',
  '.',
  'slight',
  'tropical',
  'fruit',
  'sweetness',
  '.',
  'very',
  'bitter',
  'finish',
  '.',
  'mouthfeel',
  ':',
  'medium',
  'bodied',
  'with',
  'a',
  'chalky',
  'finish',
  '.',
  'drinkability',
  ':',
  'good',
  'but',
  'not',
  'quite',
  'as',
  'enjoyable',
  'as',
  'the',
  'pliny',
  'the',
  'elder',
  'which',
  'she',
  'had',
  'before',
  '.'],
 'y': [0.8, 0.8, 0.8, 0.8, 0.8]}

In [ ]: