文本分类实战

  本次采用的数据集分别是亚马逊商品评论数据（amazon_cells_labelled.txt）、IMDB电影评论数据(imdb_labelled.txt)、Yelp网站点评数据(yelp_labelled.txt)。数据下载地址为：https://download.youkuaiyun.com/download/herosunly/13183198

0. 读取数据

import pandas as pd

file_dict = {
    'amazon': 'amazon_cells_labelled.txt',
    'imdb': 'imdb_labelled.txt',
    'yelp':'yelp_labelled.txt'
}

total_df = pd.DataFrame()

for k, v in file_dict.items():
    single_df = pd.read_csv(v, sep = '\t', names = ['sent', 'label'])
    single_df['source'] = k
    total_df = total_df.append(single_df)
    
total_df = total_df.dropna() #取出所有只要有NA的行

1. baseline模型

  每次都先以Yelp数据集为例。

1.1 词袋模型 + 逻辑回归

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

yelp = total_df[total_df.source == 'yelp']
x = yelp['sent']
y = yelp['label']

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.25, random_state = 1000)
vectorizer.fit(x_train)
x_train = vectorizer.transform(x_train)
x_test = vectorizer.transform(x_test)

logisitic_regression = LogisticRegression()
logisitic_regression.fit(x_train, y_train)
logisitic_regression.score(x_test, y_test)  # 0.796

def get_df_predict_score(df):
    df = df[df['label'].notnull()]
    
    x = df['sent']
    y = df['label']
    
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.25, random_state = 1000)
    
    vectorizer = CountVectorizer()
    vectorizer.fit(x_train)
    x_train = vectorizer.transform(x_train).toarray()
    x_test = vectorizer.transform(x_test).toarray()
   
    logisitic_regression = LogisticRegression()
    logisitic_regression.fit(x_train, y_train)
    score = logisitic_regression.score(x_test, y_test) 
    return score

for i in file_dict.keys():
    score = get_df_predict_score(total_df[total_df['source'] == i])
    print('{} data score is {}'.format(i, score))

1.2 TF-IDF模型 + 逻辑回归

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

yelp = total_df[total_df.source == 'yelp']
x = yelp['sent']
y = yelp['label']

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.25, random_state = 1000)
vectorizer.fit(x_train)
x_train = vectorizer.transform(x_train)
x_test = vectorizer.transform(x_test)

logisitic_regression = LogisticRegression()
logisitic_regression.fit(x_train, y_train)
logisitic_regression.score(x_test, y_test)  # 0.796

def get_df_predict_score(df):
    df = df[df['label'].notnull()]
    
    x = df['sent']
    y = df['label']
    
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.25, random_state = 1000)
    
    vectorizer = TfidfVectorizer()
    vectorizer.fit(x_train)
    x_train = vectorizer.transform(x_train).toarray()
    x_test = vectorizer.transform(x_test).toarray()
   
    logisitic_regression = LogisticRegression()
    logisitic_regression.fit(x_train, y_train)
    score = logisitic_regression.score(x_test, y_test) 
    return score

for i in file_dict.keys():
    score = get_df_predict_score(total_df[total_df['source'] == i])
    print('{} data score is {}'.format(i, score))

2. 深度学习模型

  在深度学习中，通过观察训练过程中loss和metrics（在分类问题中可能为准确率）的变化，才能对模型的质量有个大体的评估。在Keras中，绘制loss和准确率曲线的代码如下所示：

  其中plt.legend()是显示图例，如下图所示：

import matplotlib.pyplot as plt

def plot_history(history, name):
    train_acc = history.history['acc']
    train_loss = history.history['loss']
    val_acc = history.history['val_acc']
    val_loss = history.history['val_loss']
    
    x = range(1, len(train_acc) + 1)
    plt.figure(figsize=(12, 5))
    plt.subplot(1, 2, 1)
    plt.plot(x, train_acc, 'b', label='Training acc')
    plt.plot(x, val_acc, 'r', label='Validation acc')
    
    plt.title('Training and Validation accuracy')
    plt.legend()
    plt.subplot(1, 2, 2)
    
    plt.plot(x, train_loss, 'b', label='Training loss')
    plt.plot(x, val_loss, 'r', label='Validation loss')
    plt.title('Training and Validation loss')
    plt.legend()
    plt.show()
    plt.savefig(str(name) + '.png')

2.1 词袋模型 + MLP

from sklearn.feature_extraction.text import CountVectorizer
import keras
from keras.models import Sequential
from keras.layers import Dense, Activation
from sklearn.model_selection import train_test_split


x = yelp['sent']
y = yelp['label']

#划分训练集和测试集
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.25, random_state = 1000)

vectorizer = CountVectorizer()
vectorizer.fit(x_train)
x_train = vectorizer.transform(x_train).toarray()
x_test = vectorizer.transform(x_test).toarray()

input_dim = x_train.shape[1]
model = Sequential()
model.add(Dense(units = 10, input_dim = input_dim))
model.add(Dense(units = 1, activation = 'sigmoid'))

model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
history = model.fit(x_train, y_train, batch_size = 32, epochs = 20)

loss, accuracy = model.evaluate(x_test, y_test)
print('test accuracy is', accuracy)

import keras
from keras.layers import Dense
from keras.models import Sequential
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split

def get_df_predict_score(df):
    df = df[df['label'].notnull()]
    
    x = df['sent']
    y = df['label']
    
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.25, random_state = 1000)
    
    vectorizer = CountVectorizer()
    vectorizer.fit(x_train)
    x_train = vectorizer.transform(x_train).toarray()
    x_test = vectorizer.transform(x_test).toarray()
    
    input_dim = x_train.shape[1]
    
    model = Sequential()
    model.add(Dense(input_dim = input_dim, units = 10, activation="relu"))
    model.add(Dense(units = 1, activation = 'sigmoid'))
    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    
    history = model.fit(x_train, y_train, epochs = 20, batch_size = 32, validation_split=0.2, verbose = False)
    plot_history(history, 'result')
    
    loss, accuracy = model.evaluate(x_test, y_test)
    
    return accuracy

for i in file_dict.keys():
    score = get_df_predict_score(total_df[total_df['source'] == i])
    print('{} data score is {}'.format(i, score))