keras 情感分析的例子

例子1

from numpy import array
from keras.preprocessing.text import one_hot
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers.embeddings import Embedding
# define documents
docs = ['Well done!',
        'Good work',
        'Great effort',
        'nice work',
        'Excellent!',
        'Weak',
        'Poor effort!',
        'not good',
        'poor work',
        'Could have done better.']
# define class labels
labels = array([1,1,1,1,1,0,0,0,0,0])
# integer encode the documents
vocab_size = 50
encoded_docs = [one_hot(d, vocab_size) for d in docs]
print(encoded_docs)
# pad documents to a max length of 4 words
max_length = 4
padded_docs = pad_sequences(encoded_docs, maxlen=max_length, padding='post')
print(padded_docs)
# define the model
model = Sequential()
model.add(Embedding(vocab_size, 8, input_length=max_length))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
# compile the model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])
# summarize the model
print(model.summary())
# fit the model
model.fit(padded_docs, labels, epochs=50, verbose=0)
# evaluate the model
loss, accuracy = model.evaluate(padded_docs, labels, verbose=0)
print('Accuracy: %f' % (accuracy*100))

例子2

# -*- coding: utf-8 -*-
from keras.layers.core import Activation, Dense
from keras.layers.embeddings import Embedding
from keras.layers.recurrent import LSTM
from keras.models import Sequential
from keras.preprocessing import sequence
from sklearn.model_selection import train_test_split
import collections
import nltk
nltk.download('punkt')
import numpy as np

## EDA 
maxlen = 0
word_freqs = collections.Counter()
num_recs = 0
with open('train_data.txt','r+') as f:
    for line in f:
        label, sentence = line.strip().split("\t")
        words = nltk.word_tokenize(sentence.lower())
        if len(words) > maxlen:
            maxlen = len(words)
        for word in words:
            word_freqs[word] += 1
        num_recs += 1
print('max_len ',maxlen)
print('nb_words ', len(word_freqs))

## 准备数据
MAX_FEATURES = 2000
MAX_SENTENCE_LENGTH = 40
vocab_size = min(MAX_FEATURES, len(word_freqs)) + 2
word2index = {x[0]: i+2 for i, x in enumerate(word_freqs.most_common(MAX_FEATURES))}
word2index["PAD"] = 0
word2index["UNK"] = 1
index2word = {v:k for k, v in word2index.items()}
X = np.empty(num_recs,dtype=list)
y = np.zeros(num_recs)
i=0
with open('train_data.txt','r+') as f:
    for line in f:
        label, sentence = line.strip().split("\t")
        words = nltk.word_tokenize(sentence.lower())
        seqs = []
        for word in words:
            if word in word2index:
                seqs.append(word2index[word])
            else:
                seqs.append(word2index["UNK"])
        X[i] = seqs
        y[i] = int(label)
        i += 1
X = sequence.pad_sequences(X, maxlen=MAX_SENTENCE_LENGTH)
## 数据划分
Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, test_size=0.2, random_state=42)
## 网络构建
EMBEDDING_SIZE = 128
HIDDEN_LAYER_SIZE = 64
BATCH_SIZE = 32
NUM_EPOCHS = 10
model = Sequential()
model.add(Embedding(vocab_size, EMBEDDING_SIZE,input_length=MAX_SENTENCE_LENGTH))
model.add(LSTM(HIDDEN_LAYER_SIZE, dropout=0.2, recurrent_dropout=0.2))
model.add(Dense(1))
model.add(Activation("sigmoid"))
model.compile(loss="binary_crossentropy", optimizer="adam",metrics=["accuracy"])
## 网络训练
model.fit(Xtrain, ytrain, batch_size=BATCH_SIZE, epochs=NUM_EPOCHS,validation_data=(Xtest, ytest))
## 预测
score, acc = model.evaluate(Xtest, ytest, batch_size=BATCH_SIZE)
print("\nTest score: %.3f, accuracy: %.3f" % (score, acc))
print('{}   {}      {}'.format('预测','真实','句子'))
for i in range(5):
    idx = np.random.randint(len(Xtest))
    xtest = Xtest[idx].reshape(1,40)
    ylabel = ytest[idx]

    whk =model.predict(xtest)
    print whk
    ypred = model.predict(xtest)[0][0]
    sent = " ".join([index2word[x] for x in xtest[0] if x != 0])
    print(' {}      {}     {}'.format(int(round(ypred)), int(ylabel), sent))
##### 自己输入
INPUT_SENTENCES = ['I love reading.','You are so boring.']
XX = np.empty(len(INPUT_SENTENCES),dtype=list)
i=0
for sentence in  INPUT_SENTENCES:
    words = nltk.word_tokenize(sentence.lower())
    seq = []
    for word in words:
        if word in word2index:
            seq.append(word2index[word])
        else:
            seq.append(word2index['UNK'])
    XX[i] = seq
    i+=1

XX = sequence.pad_sequences(XX, maxlen=MAX_SENTENCE_LENGTH)
labels = [int(round(x[0])) for x in model.predict(XX) ]
label2word = {1:'积极', 0:'消极'}
for i in range(len(INPUT_SENTENCES)):
    print('{}   {}'.format(label2word[labels[i]], INPUT_SENTENCES[i]))

whk = model.predict(XX)
print whk

例子3，此例子是时间序列预测

import numpy
import matplotlib.pyplot as plt
from pandas import read_csv
import math
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error

def create_dataset(dataset, look_back=1):
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back-1):
        a = dataset[i:(i+look_back), 0]
        dataX.append(a)
        dataY.append(dataset[i + look_back, 0])
    return numpy.array(dataX), numpy.array(dataY)

dataframe = read_csv('international-airline-passengers.csv', usecols=[1], engine='python', skipfooter=3)
dataset = dataframe.values
dataset = dataset.astype('float32')

train_size = int(len(dataset) * 0.67)

print dataset

scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)

test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
# reshape into X=t and Y=t+1

look_back = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

trainX = numpy.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))

model = Sequential()
model.add(LSTM(4, input_shape=(1, look_back)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)

testPredict = model.predict(testX)

testPredict = scaler.inverse_transform(testPredict)

whk=[[112],[390],[622]]
whk = scaler.fit_transform(whk)

testOne=numpy.reshape(whk, (3, 1, 1))
print testOne
testPredict = model.predict(testOne)
testPredict = scaler.inverse_transform(testPredict)

print testPredict

其中 international-airline-passengers.csv 的内容较少，大致如下

"Month","International airline passengers: monthly totals in thousands. Jan 49 ? Dec 60"
"1949-01",112
"1949-02",118
"1949-03",132
"1949-04",129
"1949-05",121
"1949-06",135
"1949-07",148
"1949-08",148
"1949-09",136
"1949-10",119
"1949-11",104
"1949-12",118
"1950-01",115
"1950-02",126
"1950-03",141
"1950-04",135
"1950-05",125
"1950-06",149
"1950-07",170
"1950-08",170
"1950-09",158
"1950-10",133
"1950-11",114
"1950-12",140
"1951-01",145
"1951-02",150
"1951-03",178
"1951-04",163
"1951-05",172
"1951-06",178