利用TextCNN对IMDB Reviwe文本进行分类,数据集地址:https://pan.baidu.com/s/1EYoqAcW238saKy3uQCfC3w
提取码:ilze
import numpy as np
import logging
from keras import Input
from keras.layers import Conv1D, MaxPool1D, Dense, Flatten, concatenate, Embedding
from keras.models import Model
# from keras.utils import plot_model
from keras.utils.vis_utils import plot_model
import pandas as pd
import warnings
import keras
import re
import matplotlib.pyplot as plt
from nltk.stem import WordNetLemmatizer
from nltk.corpus import stopwords
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.layers import Dense, LSTM, Embedding, Dropout, Conv1D, MaxPooling1D, Bidirectional
from keras.models import Sequential
from keras.utils import np_utils
warnings.filterwarnings('ignore')
# get data
df1 = pd.read_csv('word2vec-nlp-tutorial/labeledTrainData.tsv', sep='\t', error_bad_lines=False)
df2 = pd.read_csv('word2vec-nlp-tutorial/imdb_master.csv', encoding="latin-1")
df3 = pd.read_csv('word2vec-nlp-tutorial/testData.tsv', sep='\t', error_bad_lines=False)
df2 = df2.drop(['Unnamed: 0','type','file'],axis=1)
df2.columns