import os
import tarfile
from six.moves import urllib
URL = 'http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz'
PATH = 'aclImdb'
def fetch_data(url = URL, path = PATH):
if not os.path.isdir(path):
os.makedirs(path)
file_path = os.path.join(oath, "aclImdb_v1.tar.gz")
urllib.request.urlretrieve(url, file_path)
file_gz = tarfile.open(file_path)
file_gz.extractall(path = path)
file_gz.close()
import pyprind # for progress visualisation
import pandas as pd
PATH = 'aclImdb'
labels = {'pos': 1, 'neg': 0} # int class labels for 'positive' and 'negative'
pbar = pyprind.ProgBar(50000) # initialise a progress bar with 50k iterations = no. of docs
df = pd.DataFrame()
# use nested for loops to iterate over 'train' & 'test' subdir
for s in ('test', 'train'):
for l in ('pos', 'neg'): # and read text files from 'pos' and 'neg' subdir
path = os.path.join(PATH, s, l)
for file in os.listdir(path):
# append to the df pandas DataFrame with an int class (post = 1, neg = 0)
with open(os.path.join(path, file), 'r', encoding = 'utf-8') as infile:
txt = infile.read()
df = df.append([[txt, labels[l]]], ignore_index = True)
pbar.update()
df.columns = ['review', 'sentiment']
import numpy as np
np. random.seed(0)
df = df.reindex(np.random.permutation(df.index))
df.to_csv('movie_data.csv', index = False, encoding = 'utf-8')
n_words = max(list(word_to_int.values())) + 1
df = pd.read_csv('movie_data.csv', encoding = 'utf-8')
df.head(3)
# Separate words and count each word's occurence
import pyprind # for progress visualisation
from collections import Counter
from string import punctuation
import re
counts = Counter() # collects the counts of occurence of each unique word
pbar = pyprind.ProgBar(len(df['review']),
title = 'Counting word occurences...') # progress bar
for i, review in enumerate(df['review']):
text = ''.join([c if c not in punctuation else ' '+c+' '
for c in review]).lower()
df.loc[i, 'review'] = text
pbar.update()
counts.update(text.split())
# Mapping each unique word to an int
word_counts = sorted(counts, key = counts.get, reverse = True)
print(word_counts[:5])
word_to_int = {word: ii for ii, word in enumerate(word_counts, 1)}
mapped_reviews = []
pbar = pyprind.ProgBar(len(df['review']),
title = 'Map movie reviews to integers...')
# Left-pad with zeros if the sequence length < 200
# Use 200 elements if the length > 200
sequence_length = 200
sequences = np.zeros((len(mapped_reviews), sequence_length), dtype = int)
for i, row in enumerate(mapped_reviews):
review_arr = np.array(row)
sequences[i, -len(row):] = review_arr[-sequence_length:]
# Split the dataset into training and test sets
X_train = sequences[:25000, :]
y_train = df.loc[:25000, 'sentiment'].values
X_test = sequences[25000:, :]
y_test = df.loc[25000:, 'sentiment'].values
# Define the mini-batches generator
np.random.seed(123)
def batch_gen(x, y = None, batch_size = 64):
n_batches = len(x) // batch_size
x = x[:n_batches * batch_size]
if y is not None:
y = y[:n_batches * batch_size]
for ii in range(0, len(x), batch_size):
if y is not None:
yield x[ii : ii + batch_size], y[ii : ii + batch_size]
else:
yield x[ii : ii + batch_size]
import tensorflow as tf
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' ## suppress the 3.5 warning if using TF 1.4
class SentimentRNN(object):
# Define __init__
def __init__(self,
n_words,
seq_len = 200,
lstm_size = 256,
num_layers = 1,
batch_size = 64,
learning_rate = 0.0001,
embed_size = 200):
self.n_words = n_words
self.seq_len = seq_len
self.lstm_size = lstm_size # no. of hidden units
self.num_layers = num_layers
self.batch_size = batch_size
self.learning_rate = learning_rate
self.embed_size = embed_size
self.g = tf.Graph()
with self.g.as_default():
tf.set_random_seed(123)
self.build()
self.saver = tf.train.Saver()
self.init_op = tf.global_variables_initializer()
# Define the build method
def build(self):
# Define the placeholders
tf_x = tf.placeholder(tf.int32,
shape = (self.batch_size, self.seq_len),
name = 'tf_x')
tf_y = tf.placeholder(tf.float32,
shape = (self.batch_size),
name = 'tf_y')
tf_keepprob = tf.placeholder(tf.float32,
name = 'tf_keepprob')
# Create the embedding layer
embedding = tf.Variable(
tf.random_uniform(
shape = (self.n_words, self.embed_size),
minval = -1,
maxval = 1),
name = 'embedding')
embed_x = tf.nn.embedding_lookup(embedding,
tf_x,
name = 'embed_x')
# Define LSTM cells and stack them
cells = tf.contrib.rnn.MultiRNNCell(
[tf.contrib.rnn.DropoutWrapper(
tf.contrib.rnn.BasicLSTMCell(num_units = self.lstm_size),
output_keep_prob = tf_keepprob)
for i in range(self.num_layers)])
# Define the initial state:
self.initial_state = cells.zero_state(
self.batch_size, tf.float32)
print(' << initial state >> ', self.initial_state)
# Put together components with tf.nn.dynamic_rnn
lstm_outputs, self.final_state = tf.nn.dynamic_rnn(
cell = cells,
inputs = embed_x,
initial_state = self.initial_state)
## lstm_outputs shape: [batch_size, max_time, cells.output_size]
print('\n << lstm_output >> ', lstm_outputs)
print('\n << final state >> ', self.final_state)
# Apply a full-connected layer on the RNN output
logits = tf.layers.dense(
inputs = lstm_outputs[:, -1],
units = 1, # dimensionality of the output space
activation = None,
name = 'logits')
# Remove dimensions of size 1 from the tensor shape
logits = tf.squeeze(input = logits,
name = 'logits_squeezed')
print ('\n << logits >> ', logits)
# If you want prob's
y_proba = tf.nn.sigmoid(logits, name = 'probabilities')
predictions = {'probabilities' : y_proba,
'labels' : tf.cast(tf.round(y_proba),
tf.int32,
name = 'labels')}
print('\n << predictions >> ', predictions)
# Define the cost function
cost = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(
labels = tf_y,
logits = logits),
name = 'cost')
# Define the optimiser
optimizer = tf.train.AdamOptimizer(self.learning_rate)
train_op = optimizer.minimize(cost, name = 'train_op')
# Define the train method
def train(self, X_train, y_train, num_epochs):
with tf.Session(graph = self.g) as sess:
sess.run(self.init_op)
iteration = 1
for epoch in range(num_epochs):
state = sess.run(self.initial_state)
for batch_x, batch_y in batch_gen(
X_train,
y_train,
batch_size = self.batch_size):
feed = {'tf_x:0' : batch_x,
'tf_y:0' : batch_y,
'tf_keepprob:0' : 0.5,
self.initial_state : state}
loss, _, state = sess.run(
['cost:0',
'train_op',
self.final_state],
feed_dict=feed)
if iteration % 20 == 0:
print("Epoch: %d/%d Iteration: %d "
"| Train loss: %.5f" % (
epoch + 1,
num_epochs,
iteration,
loss))
iteration += 1
if (epoch + 1) % 10 == 0:
self.saver.save(
sess,
"model/sentiment-%d.ckpt" % epoch)
# Define the predict method
def predict(self, X_data, return_proba=False):
preds = []
with tf.Session(graph = self.g) as sess:
self.saver.restore(
sess,
tf.train.latest_checkpoint('model/'))
test_state = sess.run(self.initial_state)
for ii, batch_x in enumerate(batch_gen(
x = X_data,
y = None,
batch_size = self.batch_size), 1):
feed = {'tf_x:0' : batch_x,
'tf_keepprob:0' : 1.0,
self.initial_state : test_state}
if return_proba:
pred, test_state = sess.run(
['probabilities:0', self.final_state],
feed_dict=feed)
else:
pred, test_state = sess.run(
['labels:0', self.final_state],
feed_dict=feed)
preds.append(pred)
return np.concatenate(preds)
for review in df['review']:
mapped_reviews.append([word_to_int[word] for word in review.split()])
pbar.update()
rnn = SentimentRNN(n_words = n_words,
seq_len = sequence_length,
embed_size = 256,
lstm_size = 128,
num_layers = 1,
batch_size = 100,
learning_rate = 0.001)
preds = rnn.predict(X_test)
y_true = y_test\[:len(preds)\]
print('Test accuracy... %.3f' % (np.sum(preds == y_true) / len(y_true)))][1]
使用以下参数创建SentimentRNN类的对象：
n_words = n_words，seq_len = sequence_length，embed_size = 256，lstm_size = 128，num_layers = 1，batch_size = 100，learning_rate = 0.001。
由于我们有一个相对较小的数据集，层数= 1可能会更好地概括
ValueError Traceback (most recent call last)
<ipython-input-23-a3cfe03a9a49> in <module>()
----> 1 preds = rnn.predict(X_test)
2 y_true = y_test[:len(preds)]
3 print('Test accuracy... %.3f' % (np.sum(preds == y_true) / len(y_true)))
<ipython-input-12-d83ee67c43b6> in predict(self, X_data, return_proba)
173 self.saver.restore(
174 sess,
--> 175 tf.train.latest_checkpoint('model/'))
176 test_state = sess.run(self.initial_state)
177
/usr/local/anaconda/lib/python3.6/site-packages/tensorflow/python/training/saver.py in restore(self, sess, save_path)
1680 return
1681 if save_path is None:
-> 1682 raise ValueError("Can't load save_path when it is None.")
1683 logging.info("Restoring parameters from %s", save_path)
1684 if context.in_graph_mode():
ValueError: Can't load save_path when it is None.
答案 0 :(得分：0)
错误只表示toString()没有找到任何内容。它返回tf.train.latest_checkpoint，然后None投诉，因为它已通过Saver。所以该目录中没有检查点。