def feature_engineer(self):
logger.info('generate embedding feature .. ')
train_tfidf, train = get_embedding_feature(self.ml_data.train,
self.ml_data.em.tfidf,
self.ml_data.em.w2v)
test_tfidf, test = get_embedding_feature(self.ml_data.test,
self.ml_data.em.tfidf,
self.ml_data.em.w2v)
train = formate_data(train, train_tfidf, train_ae)
test = formate_data(test, test_tfidf, test_ae)
# 生成训练，测试的数据
cols = [x for x in train.columns if str(x) not in ['labelIndex']]
X_train = train[cols]
X_test = test[cols]
train["labelIndex"] = train["labelIndex"].astype(int)
test["labelIndex"] = test["labelIndex"].astype(int)
y_train = train["labelIndex"]
y_test = test["labelIndex"]
return X_train, X_test, y_train, y_test
def process(self, title, desc):
###########################################
# TODO: module 5 task 1.1 #
###########################################
# 处理数据, 生成模型预测所需要的特征
df = pd.DataFrame([[title, desc]], columns=['title', 'desc'])
df['text'] = df['title'] + df['desc']
df["queryCut"] = df["text"].apply(query_cut)
df["queryCutRMStopWord"] = df["queryCut"].apply(
lambda x:
[word for word in x if word not in self.ml_data.em.stopWords])
df_tfidf, df = get_embedding_feature(df, self.ml_data.em.tfidf,
self.ml_data.em.w2v)
print("generate basic feature ")
df = get_basic_feature(df)
print("generate modal feature ")
df['cover'] = ''
df['res_embedding'] = df.cover.progress_apply(
lambda x: get_img_embedding(x, self.res_model))
df['resnext_embedding'] = df.cover.progress_apply(
lambda x: get_img_embedding(x, self.resnext_model))
df['wide_embedding'] = df.cover.progress_apply(
lambda x: get_img_embedding(x, self.wide_model))
print("generate bert feature ")
df['bert_embedding'] = df.text.progress_apply(
lambda x: get_pretrain_embedding(x, self.bert_tonkenizer, self.bert
))
print("generate lda feature ")
df['bow'] = df['queryCutRMStopWord'].apply(
lambda x: self.ml_data.em.lda.id2word.doc2bow(x))
df['lda'] = list(
map(lambda doc: get_lda_features(self.ml_data.em.lda, doc),
df.bow))
print("generate autoencoder feature ")
df_ae = get_autoencoder_feature(df,
self.ml_data.em.ae.max_features,
self.ml_data.em.ae.max_len,
self.ml_data.em.ae.encoder,
tokenizer=self.ml_data.em.ae.tokenizer)
print("formate data")
df['labelIndex'] = 1
df = formate_data(df, df_tfidf, df_ae)
cols = [x for x in df.columns if str(x) not in ['labelIndex']]
X_train = df[cols]
return X_train
def feature_engineer(self):
'''
@description: This function is building all kings of features
@param {type} None
@return:
X_train, feature of train set
X_test, feature of test set
y_train, label of train set
y_test, label of test set
'''
logger.info("generate embedding feature ")
# 获取tfidf 特征， word2vec 特征， word2vec不进行任何聚合
###########################################
# TODO: module 3 task 1.1 #
###########################################
train_tfidf, train = get_embedding_feature(self.ml_data.train,
self.ml_data.em.tfidf,
self.ml_data.em.w2v)
test_tfidf, test = get_embedding_feature(self.ml_data.dev,
self.ml_data.em.tfidf,
self.ml_data.em.w2v)
logger.info("generate autoencoder feature ")
# 获取到autoencoder 的embedding, 根据encoder 获取而不是decoder
train_ae = get_autoencoder_feature(
train,
self.ml_data.em.ae.max_features,
self.ml_data.em.ae.max_len,
self.ml_data.em.ae.encoder,
tokenizer=self.ml_data.em.ae.tokenizer)
test_ae = get_autoencoder_feature(
test,
self.ml_data.em.ae.max_features,
self.ml_data.em.ae.max_len,
self.ml_data.em.ae.encoder,
tokenizer=self.ml_data.em.ae.tokenizer)
logger.info("generate basic feature ")
# 获取nlp 基本特征
train = get_basic_feature(train)
test = get_basic_feature(test)
logger.info("generate modal feature ")
# 加载图书封面的文件
cover = os.listdir(config.root_path + '/data/book_cover/')
# 根据title 匹配图书封面
train['cover'] = train['title'].progress_apply(
lambda x: config.root_path + '/data/book_cover/' + x + '.jpg'
if x + '.jpg' in cover else '')
test['cover'] = test['title'].progress_apply(
lambda x: config.root_path + '/data/book_cover/' + x + '.jpg'
if x + '.jpg' in cover else '')
# 根据封面获取封面的embedding
###########################################
# TODO: module 3 task 1.2 #
###########################################
train['res_embedding'] = train['cover'].progress_apply(
lambda x: get_img_embedding(x, self.res_model))
test['res_embedding'] = test['cover'].progress_apply(
lambda x: get_img_embedding(x, self.res_model))
train['resnext_embedding'] = train['cover'].progress_apply(
lambda x: get_img_embedding(x, self.resnext_model))
test['resnext_embedding'] = test['cover'].progress_apply(
lambda x: get_img_embedding(x, self.resnext_model))
train['wide_embedding'] = train['cover'].progress_apply(
lambda x: get_img_embedding(x, self.wide_model))
test['wide_embedding'] = test['cover'].progress_apply(
lambda x: get_img_embedding(x, self.wide_model))
logger.info("generate bert feature ")
###########################################
# TODO: module 3 task 1.3 #
###########################################
train['bert_embedding'] = train['text'].progress_apply(
lambda x: get_pretrain_embedding(x, self.bert_tonkenizer, self.bert
))
test['bert_embedding'] = test['text'].progress_apply(
lambda x: get_pretrain_embedding(x, self.bert_tonkenizer, self.bert
))
logger.info("generate lda feature ")
###########################################
# TODO: module 3 task 1.4 #
###########################################
# 生成bag of word格式数据
train['bow'] = train['queryCutRMStopWord'].apply(
lambda x: self.ml_data.em.lda.id2word.doc2bow(x))
test['bow'] = test['queryCutRMStopWord'].apply(
lambda x: self.ml_data.em.lda.id2word.doc2bow(x))
# 在bag of word 基础上得到lda的embedding
train['lda'] = list(
map(lambda doc: get_lda_features(self.ml_data.em.lda, doc),
train['bow']))
test['lda'] = list(
map(lambda doc: get_lda_features(self.ml_data.em.lda, doc),
test['bow']))
logger.info("formate data")
# 将所有的特征拼接到一起
train = formate_data(train, train_tfidf, train_ae)
test = formate_data(test, test_tfidf, test_ae)
# 生成训练，测试的数据
cols = [x for x in train.columns if str(x) not in ['labelIndex']]
X_train = train[cols]
X_test = test[cols]
train["labelIndex"] = train["labelIndex"].astype(int)
test["labelIndex"] = test["labelIndex"].astype(int)
y_train = train["labelIndex"]
y_test = test["labelIndex"]
return X_train, X_test, y_train, y_test
def feature_engineer(self):
'''
@description: This function is building all kings of features
@param {type} None
@return:
X_train, feature of train set
X_test, feature of test set
y_train, label of train set
y_test, label of test set
'''
logger.info("generate embedding feature ")
train_tfidf, test_tfidf, train, test = get_embedding_feature(
self.ml_data)
logger.info("generate basic feature ")
# 1. 获取 基本的 NLP feature
train = get_basic_feature(train)
test = get_basic_feature(test)
print(test.loc[0])
logger.info("generate modal feature ")
cover = os.listdir(config.root_path + '/data/book_cover/')
train['cover'] = train.title.progress_apply(
lambda x: config.root_path + '/data/book_cover/' + x + '.jpg'
if x + '.jpg' in cover else '')
test['cover'] = test.title.progress_apply(
lambda x: config.root_path + '/data/book_cover/' + x + '.jpg'
if x + '.jpg' in cover else '')
# 1. 获取 三大CV模型的 modal embedding
train['res_embedding'] = train['cover'].progress_apply(
lambda x: get_img_embedding(x, self.res_model))
test['res_embedding'] = test['cover'].progress_apply(
lambda x: get_img_embedding(x, self.res_model))
print(len(test.loc[0, 'res_embedding']))
#train['resnext_embedding'] = test['cover'].progress_apply(lambda x: get_img_embedding(x,self.resnext_model))
#test['resnext_embedding'] = test['cover'].progress_apply(lambda x: get_img_embedding(x,self.resnext_model))
#train['wide_embedding'] = test['cover'].progress_apply(lambda x: get_img_embedding(x,self.wide_model))
#test['wide_embedding'] = test['cover'].progress_apply(lambda x: get_img_embedding(x,self.wide_model))
logger.info("generate bert feature ")
# 1. 获取bert embedding
train['bert_embedding'] = train['text'].progress_apply(
lambda x: get_pretrain_embedding(x, self.bert_tonkenizer, self.bert
))
test['bert_embedding'] = test['text'].progress_apply(
lambda x: get_pretrain_embedding(x, self.bert_tonkenizer, self.bert
))
print(test.loc[0])
logger.info("generate lda feature ")
# 1. 获取 lda feature
train['bow'] = train['queryCutRMStopWord'].apply(
lambda x: self.ml_data.em.lda.id2word.doc2bow(x))
test['bow'] = test['queryCutRMStopWord'].apply(
lambda x: self.ml_data.em.lda.id2word.doc2bow(x))
print(test['queryCutRMStopWord'])
print(test['bow'])
# 在bag of word 基础上得到lda的embedding
train['lda'] = list(
map(lambda doc: get_lda_features(self.ml_data.em.lda, doc),
train['bow']))
test['lda'] = list(
map(lambda doc: get_lda_features(self.ml_data.em.lda, doc),
test['bow']))
print(test['lda'])
print(test.loc[0])
logger.info("formate data")
print(test)
print(test_tfidf)
train, test = formate_data(train, test, train_tfidf, test_tfidf)
print(test)
print(test.loc[0])
cols = [x for x in train.columns if str(x) not in ['labelIndex']]
print(cols)
X_train = train[cols]
X_test = test[cols]
print(X_test)
train["labelIndex"] = train["labelIndex"].astype(int)
test["labelIndex"] = test["labelIndex"].astype(int)
y_train = train["labelIndex"]
y_test = test["labelIndex"]
print(y_test)
return X_train, X_test, y_train, y_test