使用RNN预测文档归属作者

# 有两个作者的文章（A, B），定义为0， 1
A = 0 # hamilton
B = 1 # madison
UNKNOWN = -1

# 把同一作者的文章全部合并到一个文件
textA, textB = '', ''

import os
for file in os.listdir('./papers/A'):
    textA += preprocessing('./papers/A/'+file)
for file in os.listdir('./papers/B'):
    textB += preprocessing('./papers/B/'+file)

def preprocessing(file_path):
    with open(file_path, 'r') as f:
        lines = f.readlines()
        text = ' '.join(lines[1:]).replace('\n',' ').replace('  ', ' ').lower().replace('hamilton','').replace('madison','')
        text = ' '.join(text.split())
        return text

print("文本A的长度：{}".format(len(textA)))
print("文本B的长度：{}".format(len(textB)))

文本A的长度：216394
文本B的长度：230867

from keras.preprocessing.text import Tokenizer
char_tokenizer = Tokenizer(char_level=True)

char_tokenizer.fit_on_texts(textA + textB) # 训练tokenizer

long_seq_a = char_tokenizer.texts_to_sequences([textA])[0] # 文本转 ids 序列
long_seq_b = char_tokenizer.texts_to_sequences([textB])[0]

Xa, ya = make_subsequence(long_seq_a, A) # 切分成多个等长的子串样本
Xb, yb = make_subsequence(long_seq_b, B)

SEQ_LEN = 30 # 切分序列的长度，超参数
import numpy as np
def make_subsequence(long_seq, label, seq_len=SEQ_LEN):
    numofsubseq = len(long_seq)-seq_len+1 # 滑窗，可以取出来这么多种
    X = np.zeros((numofsubseq, seq_len)) # 数据
    y = np.zeros((numofsubseq, 1)) # 标签
    for i in range(numofsubseq):
        X[i] = long_seq[i:i+seq_len] # seq_len 大小的滑窗
        y[i] = label
    return X, y

print('字符的种类：{}'.format(len(char_tokenizer.word_index))) # 52
# {' ': 1, 'e': 2, 't': 3, 'o': 4, 'i': 5, 'n': 6, 'a': 7, 's': 8, 'r': 9, 'h': 10,
#  'l': 11, 'd': 12, 'c': 13, 'u': 14, 'f': 15, 'm': 16, 'p': 17, 'b': 18, 'y': 19, 'w': 20,
#  ',': 21, 'g': 22, 'v': 23, '.': 24, 'x': 25, 'k': 26, 'j': 27, ';': 28, 'q': 29, 'z': 30,
#  '-': 31, '?': 32, '"': 33, '1': 34, ':': 35, '8': 36, '7': 37, '(': 38, ')': 39, '2': 40,
#  '0': 41, '3': 42, '4': 43, '6': 44, "'": 45, '!': 46, ']': 47, '5': 48, '[': 49, '@': 50,
#  '9': 51, '%': 52}
print('A训练集大小：{}'.format(Xa.shape))
print('B训练集大小：{}'.format(Xb.shape))

A训练集大小：(216365, 30)
B训练集大小：(230838, 30)

# 堆叠AB训练数据在一起
X = np.vstack((Xa, Xb))
y = np.vstack((ya, yb))

# 训练集测试集拆分
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

from keras.models import Sequential
from keras.layers import SimpleRNN, Dense, Embedding

Embedding_dim = 128 # 输出的嵌入的维度
RNN_size = 256 #  RNN 单元个数

model = Sequential()
model.add(Embedding(input_dim=len(char_tokenizer.word_index)+1,
                    output_dim=Embedding_dim,
                    input_length=SEQ_LEN))
model.add(SimpleRNN(units=RNN_size, return_sequences=False)) # 只输出最后一步 
# return the last output in the output sequence
model.add(Dense(1, activation='sigmoid')) # 二分类

model.compile(optimizer='adam', loss='binary_crossentropy',metrics=['accuracy'])
model.summary()

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding (Embedding)        (None, 30, 128)           6784      
_________________________________________________________________
simple_rnn (SimpleRNN)       (None, 256)               98560     
_________________________________________________________________
dense (Dense)                (None, 1)                 257       
=================================================================
Total params: 105,601
Trainable params: 105,601
Non-trainable params: 0
_________________________________________________________________

simple_rnn_1 (SimpleRNN)     (None, 30, 256)           98560     
_________________________________________________________________
dense_1 (Dense)              (None, 30, 1)             257       

batch_size = 4096 # 一次梯度下降使用的样本数量
epochs = 20  # 训练轮数
history = model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs,
                    validation_data=(X_test, y_test),verbose=1)

Epoch 1/20
88/88 [==============================] - 59s 669ms/step - loss: 0.6877 - accuracy: 0.5436 - val_loss: 0.6856 - val_accuracy: 0.5540
Epoch 2/20
88/88 [==============================] - 56s 634ms/step - loss: 0.6830 - accuracy: 0.5564 - val_loss: 0.6844 - val_accuracy: 0.5550
Epoch 3/20
88/88 [==============================] - 56s 633ms/step - loss: 0.6825 - accuracy: 0.5577 - val_loss: 0.6829 - val_accuracy: 0.5563
Epoch 4/20
88/88 [==============================] - 56s 634ms/step - loss: 0.6816 - accuracy: 0.5585 - val_loss: 0.6788 - val_accuracy: 0.5641
Epoch 5/20
88/88 [==============================] - 56s 637ms/step - loss: 0.6714 - accuracy: 0.5813 - val_loss: 0.6670 - val_accuracy: 0.5877
Epoch 6/20
88/88 [==============================] - 56s 637ms/step - loss: 0.6532 - accuracy: 0.6113 - val_loss: 0.6435 - val_accuracy: 0.6235
Epoch 7/20
88/88 [==============================] - 57s 648ms/step - loss: 0.6287 - accuracy: 0.6424 - val_loss: 0.6159 - val_accuracy: 0.6563
Epoch 8/20
88/88 [==============================] - 55s 620ms/step - loss: 0.5932 - accuracy: 0.6807 - val_loss: 0.5747 - val_accuracy: 0.6971
Epoch 9/20
88/88 [==============================] - 54s 615ms/step - loss: 0.5383 - accuracy: 0.7271 - val_loss: 0.5822 - val_accuracy: 0.7178
Epoch 10/20
88/88 [==============================] - 56s 632ms/step - loss: 0.4803 - accuracy: 0.7687 - val_loss: 0.4536 - val_accuracy: 0.7846
Epoch 11/20
88/88 [==============================] - 61s 690ms/step - loss: 0.3979 - accuracy: 0.8190 - val_loss: 0.3940 - val_accuracy: 0.8195
Epoch 12/20
88/88 [==============================] - 60s 687ms/step - loss: 0.3257 - accuracy: 0.8572 - val_loss: 0.3248 - val_accuracy: 0.8564
Epoch 13/20
88/88 [==============================] - 59s 668ms/step - loss: 0.2637 - accuracy: 0.8897 - val_loss: 0.2980 - val_accuracy: 0.8742
Epoch 14/20
88/88 [==============================] - 56s 638ms/step - loss: 0.2154 - accuracy: 0.9115 - val_loss: 0.2326 - val_accuracy: 0.9023
Epoch 15/20
88/88 [==============================] - 56s 639ms/step - loss: 0.1822 - accuracy: 0.9277 - val_loss: 0.2112 - val_accuracy: 0.9130
Epoch 16/20
88/88 [==============================] - 56s 640ms/step - loss: 0.1504 - accuracy: 0.9412 - val_loss: 0.1803 - val_accuracy: 0.9267
Epoch 17/20
88/88 [==============================] - 58s 660ms/step - loss: 0.1298 - accuracy: 0.9499 - val_loss: 0.1662 - val_accuracy: 0.9331
Epoch 18/20
88/88 [==============================] - 57s 643ms/step - loss: 0.1132 - accuracy: 0.9567 - val_loss: 0.1643 - val_accuracy: 0.9358
Epoch 19/20
88/88 [==============================] - 58s 659ms/step - loss: 0.1018 - accuracy: 0.9613 - val_loss: 0.1409 - val_accuracy: 0.9441
Epoch 20/20
88/88 [==============================] - 57s 642ms/step - loss: 0.0907 - accuracy: 0.9659 - val_loss: 0.1325 - val_accuracy: 0.9475

import pandas as pd
import matplotlib.pyplot as plt
pd.DataFrame(history.history).plot(figsize=(8, 5))
plt.grid(True)
plt.gca().set_ylim(0, 1) # set the vertical range to [0-1]
plt.show()

# 测试

for file in os.listdir('./papers/Unknown'):
	# 测试文本处理
    unk_file = preprocessing('./papers/Unknown/'+file)
    # 文本转ids序列
    unk_file_seq = char_tokenizer.texts_to_sequences([unk_file])[0]
    # 提取固定长度的子串，形成多个样本
    X_unk, _ = make_subsequence(unk_file_seq, UNKNOWN)
    # 预测
    y_pred = model.predict(X_unk)
    y_pred = y_pred > 0.5
    votesA = np.sum(y_pred==0)
    votesB = np.sum(y_pred==1)
    print("文章 {} 被预测为 {} 写的，投票数 {} ： {}".format(
        file,
        "A:hamilton" if votesA > votesB else "B:madison",
        max(votesA, votesB),
        min(votesA, votesB)
    ))

文章 paper_1.txt 被预测为 B:madison 写的，投票数 12211 ： 8563
文章 paper_2.txt 被预测为 B:madison 写的，投票数 10899 ： 8747
文章 paper_3.txt 被预测为 A:hamilton 写的，投票数 7041 ： 6343
文章 paper_4.txt 被预测为 A:hamilton 写的，投票数 5063 ： 4710
文章 paper_5.txt 被预测为 A:hamilton 写的，投票数 6878 ： 4876