keras neural network giving float ouputs but i need boolean outputs

Question

this is my code loaded the pre-trained weights and embedding matrices

from __future__ import print_function
import numpy as np
import pandas as pd
import csv, datetime, time, json
from zipfile import ZipFile
from os.path import expanduser, exists
from keras.preprocessing.text import Tokenizer
 from keras.preprocessing.sequence import pad_sequences
  from keras.models import Model
  from keras.layers import Input, TimeDistributed, Dense, Lambda, 
concatenate, Dropout, BatchNormalization
 from keras.layers.embeddings import Embedding
from keras.regularizers import l2
from keras.callbacks import Callback, ModelCheckpoint
from keras.utils.data_utils import get_file
from keras import backend as K
from sklearn.model_selection import train_test_split


**Initialize global variables**
 KERAS_DATASETS_DIR = expanduser('~/.keras/datasets/')
 QUESTION_PAIRS_FILE_URL = 
 'http://qim.ec.quoracdn.net/quora_duplicate_questions.tsv'
 QUESTION_PAIRS_FILE = 'test.csv'
 GLOVE_ZIP_FILE_URL = 'http://nlp.stanford.edu/data/glove.840B.300d.zip'
 GLOVE_ZIP_FILE = 'glove.840B.300d.zip'
 GLOVE_FILE = 'glove.840B.300d.txt'
 Q1_TRAINING_DATA_FILE = 'q1_train.npy'
 Q2_TRAINING_DATA_FILE = 'q2_train.npy'
 LABEL_TRAINING_DATA_FILE = 'label_train.npy'
 WORD_EMBEDDING_MATRIX_FILE = 'word_embedding_matrix.npy'
 NB_WORDS_DATA_FILE = 'nb_words.json'
 MAX_NB_WORDS = 200000
 MAX_SEQUENCE_LENGTH = 25
 EMBEDDING_DIM = 300
 MODEL_WEIGHTS_FILE = 'question_pairs_weights.h5'
 VALIDATION_SPLIT = 0.1
 TEST_SPLIT = 0.1
 RNG_SEED = 13371447
 NB_EPOCHS = 1
 DROPOUT = 0.1
 BATCH_SIZE = 32
 OPTIMIZER = 'adam'



word_embedding_matrix = np.load(open(WORD_EMBEDDING_MATRIX_FILE, 'rb'))
with open(NB_WORDS_DATA_FILE, 'r') as f:
nb_words = json.load(f)['nb_words']

print("Processing", QUESTION_PAIRS_FILE)
question1 = []
question2 = []

with open(KERAS_DATASETS_DIR + QUESTION_PAIRS_FILE, encoding='utf-8') as 
csvfile:
reader = csv.DictReader(csvfile, delimiter=',')
for row in reader:
    question1.append(row['question1'])
    question2.append(row['question2'])

 print('Question pairs: %d' % len(question1))
 T1=len(question1)
 print(T1)
 **Build tokenized word index**
 questions = question1 + question2
 tokenizer = Tokenizer(num_words=MAX_NB_WORDS)
 tokenizer.fit_on_texts(questions)
 question1_word_sequences = tokenizer.texts_to_sequences(question1)
 question2_word_sequences = tokenizer.texts_to_sequences(question2)
 word_index = tokenizer.word_index

 print("Words in index: %d" % len(word_index))

  Prepare word embedding matrix

 Prepare training data tensors
 q1_data = pad_sequences(question1_word_sequences, maxlen=MAX_SEQUENCE_LENGTH)
 q2_data = pad_sequences(question2_word_sequences, maxlen=MAX_SEQUENCE_LENGTH)

  print('Shape of question1 data tensor:', q1_data.shape)
  print('Shape of question2 data tensor:', q2_data.shape)




 **Define the model**
question1 = Input(shape=(MAX_SEQUENCE_LENGTH,))
question2 = Input(shape=(MAX_SEQUENCE_LENGTH,))


q1 = Embedding(nb_words + 1, 
             EMBEDDING_DIM, 
             weights=[word_embedding_matrix], 
             input_length=MAX_SEQUENCE_LENGTH, 
             trainable=False)(question1)
q1 = TimeDistributed(Dense(EMBEDDING_DIM, activation='relu'))(q1)
q1 = Lambda(lambda x: K.max(x, axis=1), output_shape=(EMBEDDING_DIM, ))(q1)

q2 = Embedding(nb_words + 1, 
             EMBEDDING_DIM, 
             weights=[word_embedding_matrix], 
             input_length=MAX_SEQUENCE_LENGTH, 
             trainable=False)(question2)
q2 = TimeDistributed(Dense(EMBEDDING_DIM, activation='relu'))(q2)
q2 = Lambda(lambda x: K.max(x, axis=1), output_shape=(EMBEDDING_DIM, ))(q2)

merged = concatenate([q1,q2])
merged = Dense(200, activation='relu')(merged)
merged = Dropout(DROPOUT)(merged)
merged = BatchNormalization()(merged)
merged = Dense(200, activation='relu')(merged)
merged = Dropout(DROPOUT)(merged)
merged = BatchNormalization()(merged)
merged = Dense(200, activation='relu')(merged)
merged = Dropout(DROPOUT)(merged)
merged = BatchNormalization()(merged)
merged = Dense(200, activation='relu')(merged)
merged = Dropout(DROPOUT)(merged)
merged = BatchNormalization()(merged)

is_duplicate = Dense(1, activation='sigmoid')(merged)

model = Model(inputs=[question1,question2], outputs=is_duplicate)
 model.compile(loss='binary_crossentropy', optimizer=OPTIMIZER, metrics= 
 ['accuracy'])
 model.load_weights(MODEL_WEIGHTS_FILE)

 temp= model.predict([q1_data, q2_data])

 df = pd.DataFrame(temp)
 df.to_csv("hero.csv",header=['is_duplicate'])

it giving me output like this

test id is_duplicate
0   0.585984
1   0.13437697
2   0.7458109
3   0.6282846
4   0.44692168

but i need boolean values

 test id    is_duplicate
 0       1
 1       0
 2       1
 3       1

dont tell me to round up the values

I want the neural network itself gives me the boolean values

is it possible to train the network like that

if yes, please suggest the things i can include in code

thanks in advance

score 1 · Accepted Answer · answered Apr 01 '18 at 09:45

The network cannot output plain boolean values, you just have to threshold the output of the network as it has a sigmoid activation. Say you set a threshold of 0.5, any value over 0.5 will be class 1, and an output lower than 0.5 will be class zero.

Additionally the network output value gives you a "confidence" estimate of the network's uncertainty of the output.

score 0 · Answer 2 · edited Apr 01 '18 at 10:25

0

try:

temp= model.predict([q1_data, q2_data])
y_classes = temp.argmax(axis=-1)
df = pd.DataFrame(y_classes)

as suggested in below post:

Get class labels from Keras functional model

Also, why cant you round the values?

edited Apr 01 '18 at 10:25

answered Apr 01 '18 at 09:44

gmatharu

83
1
8

1

@[Ivan](https://stackoverflow.com/users/1143634/ivan) updated my answer – gmatharu Apr 01 '18 at 10:14

keras neural network giving float ouputs but i need boolean outputs

2 Answers2