利用TfidfVectorizer进行中文文本分类（数据集是复旦中文语料）
上一节我们利用了RNN（GRU）对中文文本进行了分类，本节我们将继续使用CNN对中文文本进行分类。
数据处理还是没有变，只是换了个模型，代码如下：
# coding: utf-8 from __future__ import print_function import os import sys import time from datetime import timedelta import keras import numpy as np import tensorflow as tf from sklearn import metrics #将词汇表中的单词映射成id def word2id(): vocabulary_path = '/content/drive/My Drive/NLP/dataset/Fudan/vocabulary.txt' fp1 = open(vocabulary_path,'r',encoding='utf-8') word2id_dict = {} for i,line in enumerate(fp1.readlines()): word2id_dict[line.strip()] = i print(len(word2id_dict)) fp1.close() return word2id_dict #得到文本内容及对应的标签 def get_content_label(path): #data = '/content/drive/My Drive/NLP/dataset/Fudan/data/train_clean_jieba.txt' fp = open(path,'r',encoding='utf-8') content_list = [] label_list = [] for line in fp.readlines(): line = line.strip().split(' ') if len(line) == 2: content_list.append(line[0]) label_list.append(line[1]) print(content_list[:5]) print(label_list[:5]) fp.close() return content_list,label_list #得到标签对应的id def get_label_id(): label = '/content/drive/My Drive/NLP/dataset/Fudan/label.txt' label2id_dict = {} fp = open(label,'r',encoding='utf-8') for line in fp.readlines(): line = line.strip().split(' ') label2id_dict[line[0]] = line[1] #print(label2id_dict) return label2id_dict #将文本内容中的词替换成词对应的id，并设定文本的最大长度 #对标签进行one-hot编码 def process(path,max_length): contents,labels = get_content_label(path) word_to_id = word2id() cat_to_id = get_label_id() data_id = [] label_id = [] for i in range(len(contents)): data_id.append([word_to_id[x] for x in contents[i] if x in word_to_id]) label_id.append(cat_to_id[labels[i]]) # 使用keras提供的pad_sequences来将文本pad为固定长度 x_pad = keras.preprocessing.sequence.pad_sequences(data_id, max_length) y_pad = keras.utils.to_categorical(label_id, num_classes=len(cat_to_id)) # 将标签转换为one-hot表示 return x_pad,y_pad def batch_iter(x, y, batch_size=64): """生成批次数据""" data_len = len(x) num_batch = int((data_len - 1) / batch_size) + 1 indices = np.random.permutation(np.arange(data_len)) x_shuffle = x[indices] y_shuffle = y[indices] for i in range(num_batch): start_id = i * batch_size end_id = min((i + 1) * batch_size, data_len) yield x_shuffle[start_id:end_id], y_shuffle[start_id:end_id] def evaluate(sess, x_, y_): """评估在某一数据上的准确率和损失""" data_len = len(x_) batch_eval = batch_iter(x_, y_, 128) total_loss = 0.0 total_acc = 0.0 for x_batch, y_batch in batch_eval: batch_len = len(x_batch) feed_dict = feed_data(x_batch, y_batch, 1.0) loss, acc = sess.run([model.loss, model.acc], feed_dict=feed_dict) total_loss += loss * batch_len total_acc += acc * batch_len return total_loss / data_len, total_acc / data_len def get_time_dif(start_time): """获取已使用时间""" end_time = time.time() time_dif = end_time - start_time return timedelta(seconds=int(round(time_dif))) def feed_data(x_batch, y_batch, keep_prob): feed_dict = { model.input_x: x_batch, model.input_y: y_batch, model.keep_prob: keep_prob } return feed_dict def get_training_word2vec_vectors(filename): with np.load(filename) as data: return data["embeddings"] class TCNNConfig(object): """CNN配置参数""" embedding_dim = 100 # 词向量维度 seq_length = 600 # 序列长度 num_classes = 20 # 类别数 num_filters = 256 # 卷积核数目 kernel_size = 5 # 卷积核尺寸 vocab_size = 183664 # 词汇表达小 hidden_dim = 128 # 全连接层神经元 dropout_keep_prob = 0.5 # dropout保留比例 learning_rate = 1e-3 # 学习率 batch_size = 64 # 每批训练大小 num_epochs = 10 # 总迭代轮次 print_per_batch = 20 # 每多少轮输出一次结果 save_per_batch = 10 # 每多少轮存入tensorboard pre_trianing = None vector_word_npz = '/content/drive/My Drive/NLP/dataset/Fudan/vector_word.npz' class TextCNN(object): """文本分类，CNN模型""" def __init__(self, config): self.config = config # 三个待输入的数据 self.input_x = tf.placeholder(tf.int32, [None, self.config.seq_length], name='input_x') self.input_y = tf.placeholder(tf.float32, [None, self.config.num_classes], name='input_y') self.keep_prob = tf.placeholder(tf.float32, name='keep_prob') self.cnn() def cnn(self): """CNN模型""" # 词向量映射 with tf.device('/cpu:0'): #embedding = tf.get_variable('embedding', [self.config.vocab_size, self.config.embedding_dim]) embedding = tf.get_variable("embeddings", shape=[self.config.vocab_size, self.config.embedding_dim], initializer=tf.constant_initializer(self.config.pre_trianing)) embedding_inputs = tf.nn.embedding_lookup(embedding, self.input_x) with tf.name_scope("cnn"): # CNN layer conv = tf.layers.conv1d(embedding_inputs, self.config.num_filters, self.config.kernel_size, name='conv') # global max pooling layer gmp = tf.reduce_max(conv, reduction_indices=[1], name='gmp') with tf.name_scope("score"): # 全连接层，后面接dropout以及relu激活 fc = tf.layers.dense(gmp, self.config.hidden_dim, name='fc1') fc = tf.contrib.layers.dropout(fc, self.keep_prob) fc = tf.nn.relu(fc) # 分类器 self.logits = tf.layers.dense(fc, self.config.num_classes, name='fc2') self.y_pred_cls = tf.argmax(tf.nn.softmax(self.logits), 1) # 预测类别 with tf.name_scope("optimize"): # 损失函数，交叉熵 cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=self.logits, labels=self.input_y) self.loss = tf.reduce_mean(cross_entropy) # 优化器 self.optim = tf.train.AdamOptimizer(learning_rate=self.config.learning_rate).minimize(self.loss) with tf.name_scope("accuracy"): # 准确率 correct_pred = tf.equal(tf.argmax(self.input_y, 1), self.y_pred_cls) self.acc = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) def train(): print("Configuring TensorBoard and Saver...") # 配置 Tensorboard，重新训练时，请将tensorboard文件夹删除，不然图会覆盖 tensorboard_dir = 'tensorboard/textcnn' if not os.path.exists(tensorboard_dir): os.makedirs(tensorboard_dir) tf.summary.scalar("loss", model.loss) tf.summary.scalar("accuracy", model.acc) merged_summary = tf.summary.merge_all() writer = tf.summary.FileWriter(tensorboard_dir) save_dir = 'checkpoint/textcnn/' save_path = os.path.join(save_dir, 'best_validation') # 最佳验证结果保存路径 # 配置 Saver saver = tf.train.Saver() if not os.path.exists(save_dir): os.makedirs(save_dir) print("Loading training and validation data...") # 载入训练集与验证集 start_time = time.time() train_dir = '/content/drive/My Drive/NLP/dataset/Fudan/data/train_clean_jieba.txt' val_dir = '/content/drive/My Drive/NLP/dataset/Fudan/data/test_clean_jieba.txt' x_train, y_train = process(train_dir, config.seq_length) x_val, y_val = process(val_dir, config.seq_length) time_dif = get_time_dif(start_time) print("Time usage:", time_dif) # 创建session session = tf.Session() session.run(tf.global_variables_initializer()) writer.add_graph(session.graph) print('Training and evaluating...') start_time = time.time() total_batch = 0 # 总批次 best_acc_val = 0.0 # 最佳验证集准确率 last_improved = 0 # 记录上一次提升批次 require_improvement = 1000 # 如果超过1000轮未提升，提前结束训练 flag = False for epoch in range(config.num_epochs): print('Epoch:', epoch + 1) batch_train = batch_iter(x_train, y_train, config.batch_size) for x_batch, y_batch in batch_train: feed_dict = feed_data(x_batch, y_batch, config.dropout_keep_prob) if total_batch % config.save_per_batch == 0: # 每多少轮次将训练结果写入tensorboard scalar s = session.run(merged_summary, feed_dict=feed_dict) writer.add_summary(s, total_batch) if total_batch % config.print_per_batch == 0: # 每多少轮次输出在训练集和验证集上的性能 feed_dict[model.keep_prob] = 1.0 loss_train, acc_train = session.run([model.loss, model.acc], feed_dict=feed_dict) loss_val, acc_val = evaluate(session, x_val, y_val) # todo if acc_val > best_acc_val: # 保存最好结果 best_acc_val = acc_val last_improved = total_batch saver.save(sess=session, save_path=save_path) improved_str = '*' else: improved_str = '' time_dif = get_time_dif(start_time) msg = 'Iter: {0:>6}, Train Loss: {1:>6.2}, Train Acc: {2:>7.2%},' + ' Val Loss: {3:>6.2}, Val Acc: {4:>7.2%}, Time: {5} {6}' print(msg.format(total_batch, loss_train, acc_train, loss_val, acc_val, time_dif, improved_str)) feed_dict[model.keep_prob] = config.dropout_keep_prob session.run(model.optim, feed_dict=feed_dict) # 运行优化 total_batch += 1 if total_batch - last_improved > require_improvement: # 验证集正确率长期不提升，提前结束训练 print("No optimization for a long time, auto-stopping...") flag = True break # 跳出循环 if flag: # 同上 break def test(): print("Loading test data...") start_time = time.time() test_dir = '/content/drive/My Drive/NLP/dataset/Fudan/data/test_clean_jieba.txt' x_test, y_test = process(test_dir, config.seq_length) save_path = 'checkpoint/textcnn/best_validation' session = tf.Session() session.run(tf.global_variables_initializer()) saver = tf.train.Saver() saver.restore(sess=session, save_path=save_path) # 读取保存的模型 print('Testing...') loss_test, acc_test = evaluate(session, x_test, y_test) msg = 'Test Loss: {0:>6.2}, Test Acc: {1:>7.2%}' print(msg.format(loss_test, acc_test)) batch_size = 128 data_len = len(x_test) num_batch = int((data_len - 1) / batch_size) + 1 y_test_cls = np.argmax(y_test, 1) y_pred_cls = np.zeros(shape=len(x_test), dtype=np.int32) # 保存预测结果 for i in range(num_batch): # 逐批次处理 start_id = i * batch_size end_id = min((i + 1) * batch_size, data_len) feed_dict = { model.input_x: x_test[start_id:end_id], model.keep_prob: 1.0 } y_pred_cls[start_id:end_id] = session.run(model.y_pred_cls, feed_dict=feed_dict) categories = get_label_id().values() # 评估 print("Precision, Recall and F1-Score...") print(metrics.classification_report(y_test_cls, y_pred_cls, target_names=categories)) # 混淆矩阵 print("Confusion Matrix...") cm = metrics.confusion_matrix(y_test_cls, y_pred_cls) print(cm) time_dif = get_time_dif(start_time) print("Time usage:", time_dif) if __name__ == '__main__': print('Configuring CNN model...') config = TCNNConfig() config.pre_trianing = get_training_word2vec_vectors(config.vector_word_npz) model = TextCNN(config) test()
结果如下：
Epoch: 8 Iter: 1080, Train Loss: 0.13, Train Acc: 95.31%, Val Loss: 0.44, Val Acc: 87.19%, Time: 0:04:33 Iter: 1100, Train Loss: 0.24, Train Acc: 95.31%, Val Loss: 0.44, Val Acc: 87.03%, Time: 0:04:38 Iter: 1120, Train Loss: 0.19, Train Acc: 93.75%, Val Loss: 0.43, Val Acc: 87.38%, Time: 0:04:42 Iter: 1140, Train Loss: 0.17, Train Acc: 92.19%, Val Loss: 0.42, Val Acc: 87.80%, Time: 0:04:47 * Iter: 1160, Train Loss: 0.21, Train Acc: 90.62%, Val Loss: 0.41, Val Acc: 87.89%, Time: 0:04:53 * Iter: 1180, Train Loss: 0.34, Train Acc: 89.06%, Val Loss: 0.43, Val Acc: 87.57%, Time: 0:04:57 Iter: 1200, Train Loss: 0.22, Train Acc: 92.19%, Val Loss: 0.41, Val Acc: 87.62%, Time: 0:05:01 Iter: 1220, Train Loss: 0.24, Train Acc: 90.62%, Val Loss: 0.41, Val Acc: 87.87%, Time: 0:05:06 Epoch: 9 Iter: 1240, Train Loss: 0.096, Train Acc: 95.31%, Val Loss: 0.4, Val Acc: 88.34%, Time: 0:05:11 * Iter: 1260, Train Loss: 0.21, Train Acc: 92.19%, Val Loss: 0.41, Val Acc: 87.98%, Time: 0:05:16 Iter: 1280, Train Loss: 0.13, Train Acc: 95.31%, Val Loss: 0.42, Val Acc: 88.14%, Time: 0:05:20 Iter: 1300, Train Loss: 0.1, Train Acc: 98.44%, Val Loss: 0.43, Val Acc: 87.76%, Time: 0:05:25 Iter: 1320, Train Loss: 0.27, Train Acc: 92.19%, Val Loss: 0.39, Val Acc: 87.93%, Time: 0:05:29 Iter: 1340, Train Loss: 0.19, Train Acc: 92.19%, Val Loss: 0.45, Val Acc: 87.67%, Time: 0:05:33 Iter: 1360, Train Loss: 0.27, Train Acc: 92.19%, Val Loss: 0.42, Val Acc: 87.57%, Time: 0:05:38 Iter: 1380, Train Loss: 0.17, Train Acc: 92.19%, Val Loss: 0.41, Val Acc: 88.07%, Time: 0:05:42 Epoch: 10 Iter: 1400, Train Loss: 0.1, Train Acc: 98.44%, Val Loss: 0.39, Val Acc: 88.64%, Time: 0:05:47 * Iter: 1420, Train Loss: 0.069, Train Acc: 96.88%, Val Loss: 0.4, Val Acc: 88.46%, Time: 0:05:51 Iter: 1440, Train Loss: 0.15, Train Acc: 98.44%, Val Loss: 0.41, Val Acc: 88.16%, Time: 0:05:56 Iter: 1460, Train Loss: 0.073, Train Acc: 98.44%, Val Loss: 0.4, Val Acc: 88.38%, Time: 0:06:00 Iter: 1480, Train Loss: 0.16, Train Acc: 95.31%, Val Loss: 0.42, Val Acc: 88.12%, Time: 0:06:05 Iter: 1500, Train Loss: 0.21, Train Acc: 92.19%, Val Loss: 0.41, Val Acc: 87.79%, Time: 0:06:09 Iter: 1520, Train Loss: 0.16, Train Acc: 93.75%, Val Loss: 0.41, Val Acc: 88.03%, Time: 0:06:13
进行测试，测试结果如下：
Testing... 2020-10-19 12:51:46.979827: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10 2020-10-19 12:51:47.221023: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 Test Loss: 0.39, Test Acc: 88.64% Precision, Recall and F1-Score... /usr/local/lib/python3.6/dist-packages/sklearn/metrics/_classification.py:1272: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior. _warn_prf(average, modifier, msg_start, len(result)) precision recall f1-score support 0 0.33 0.05 0.09 61 1 0.89 0.96 0.93 1022 2 0.39 0.15 0.22 59 3 0.89 0.95 0.92 1254 4 0.33 0.08 0.12 52 5 0.83 0.90 0.86 1026 6 0.95 0.98 0.96 1358 7 0.67 0.04 0.08 45 8 0.39 0.28 0.32 76 9 0.85 0.94 0.89 742 10 0.00 0.00 0.00 34 11 0.00 0.00 0.00 28 12 0.96 0.96 0.96 1218 13 0.87 0.92 0.89 642 14 0.50 0.15 0.23 33 15 0.67 0.07 0.13 27 16 0.91 0.91 0.91 1601 17 0.86 0.11 0.20 53 18 0.00 0.00 0.00 34 19 0.74 0.69 0.72 468 accuracy 0.89 9833 macro avg 0.60 0.46 0.47 9833 weighted avg 0.87 0.89 0.87 9833 Confusion Matrix... [[ 3 1 0 42 0 5 0 0 4 3 0 0 0 2 0 0 1 0 0 0] [ 0 983 0 5 0 1 0 0 0 0 0 0 8 3 0 0 14 1 0 7] [ 1 2 9 3 0 4 2 0 3 1 0 0 2 15 3 0 13 0 0 1] [ 0 3 0 1195 0 12 2 0 0 16 0 0 3 2 0 0 8 0 0 13] [ 0 6 1 1 4 14 5 0 5 0 0 0 1 1 0 0 14 0 0 0] [ 0 7 0 16 0 924 1 0 3 5 0 0 1 0 0 0 39 0 0 30] [ 0 1 0 3 0 0 1328 1 1 0 0 0 1 17 0 0 5 0 0 1] [ 0 0 0 13 0 12 0 2 0 8 0 0 1 2 0 0 0 0 0 7] [ 2 1 1 7 0 39 0 0 21 0 0 0 0 4 0 0 0 0 0 1] [ 0 1 0 10 0 10 1 0 1 696 0 0 0 0 0 0 3 0 0 20] [ 0 0 0 4 0 0 0 0 0 15 0 0 0 1 0 0 1 0 0 13] [ 0 0 0 2 1 0 5 0 2 0 0 0 0 10 1 0 7 0 0 0] [ 0 11 0 1 1 1 8 0 3 0 0 0 1175 6 0 0 7 0 0 5] [ 0 0 0 6 0 0 31 0 0 1 0 0 12 589 0 0 3 0 0 0] [ 0 2 4 1 1 1 0 0 1 0 0 0 4 6 5 1 7 0 0 0] [ 0 0 2 1 0 1 6 0 0 0 0 0 0 11 0 2 4 0 0 0] [ 0 70 2 10 2 39 5 0 2 2 0 0 7 0 0 0 1451 0 0 11] [ 3 4 0 10 3 12 0 0 6 3 0 0 0 0 0 0 5 6 0 1] [ 0 7 4 0 0 1 0 0 1 1 0 0 6 5 1 0 7 0 0 1] [ 0 4 0 7 0 43 5 0 1 72 0 0 1 1 0 0 11 0 0 323]] Time usage: 0:00:13
至此使用传统的TF-IDF+朴素贝叶斯、RNN（LSTM、GRU）和CNN从数据的处理到模型的训练和测试就全部完成了，接下来准备弄弄Transformer和Bert了，欢迎关注。
参考：
https://github.com/gaussic/text-classification-cnn-rnn