def gen_fea():
sql_handler = SqlHandler()
audio_text_value = list()
with ThreadPoolExecutor(max_workers=30) as executor: #并行启动任务
task = [executor.submit(gen_sigle_fea, fold) for fold in PREFIX]
for future in as_completed(task):
try:
fea_item = future.result() #每一个文件下所有数据的特征 eg：300_P
audio_text_value.append(fea_item)
except:
continue
COVAREP_COLUMNS.remove('VUV')
audio_fea = list()
audio_fea.append('ID')
COVAREP_COLUMNS.extend(FORMANT_COLUMNS)
for a_fea, s_fea in itertools.product(COVAREP_COLUMNS,
stats_fea.columns): #笛卡尔积 相当于嵌套for循环
audio_fea.append(a_fea + '_' + s_fea)
audio_text_fea = audio_fea + TEXT_COLUMNS
assert len(audio_text_value[0]) == len(audio_text_fea)
audio_text_df = pd.DataFrame(audio_text_value, columns=audio_text_fea)
sql_handler.execute(f'drop table if exists {config.tbl_exp1_fea};'
) #因为每次选择特征不一样，所以入库之前需要删除原来的表
sql_handler.df_to_db(audio_text_df, config.tbl_exp1_fea)
logger.info('audio feature exp1 has been stored!')
def data_set():
df_train = pd.read_csv(config.data_dir + global_values.TRAIN_SET_NAME,
header=0)
df_dev = pd.read_csv(config.data_dir + global_values.DEL_SET_NAME,
header=0)
logger.debug(df_dev.head())
sql_handler = SqlHandler()
sql_handler.execute(f'drop table {config.tbl_develop_set}')
sql_handler.execute(f'drop table {config.tbl_training_set}')
sql_handler.df_to_db(df_train, config.tbl_training_set)
sql_handler.df_to_db(df_dev, config.tbl_develop_set)
def hog_pca():
sql_handler = SqlHandler()
pca = PCA(n_components=0.999)
hog = pd.read_csv(config.data_dir+FACE_HOG)
hog_pca_values = pca.fit_transform(hog)
hog_pca_names = ['hog_pca_'+str(i) for i in range(184)]
hog_pca = pd.DataFrame(hog_pca_values,columns = hog_pca_names)
id = [float(id[:-1]) for id in PREFIX]
col_name = hog_pca.columns.tolist()
col_name.insert(0,'ID')
hog_pca= hog_pca.reindex(columns = col_name,fill_value = 1)
hog_pca['ID'] = id
sql_handler.execute(f'drop table if exists {config.tbl_exp3_hog_fea};') #因为每次选择特征不一样，所以入库之前需要删除原来的表
sql_handler.df_to_db(hog_pca, config.tbl_exp3_hog_fea)
logger.info('hog feature exp3 has been stored!')
def gen_fea():
sql_handler = SqlHandler()
audio_feas, text_feas, vedio_feas = gen_sigle_fea(PREFIX[0])
#读取hog特征 应该在模型训练的地方做
#分三个表来提取数据
with ThreadPoolExecutor(max_workers=30) as executor: #并行启动任务
task = [executor.submit(gen_sigle_fea, fold) for fold in PREFIX[1:]]
for future in as_completed(task):
try:
audio_value, text_value, vedio_value = future.result(
) #每一个文件下所有数据的特征 eg：300_P
audio_feas = np.concatenate((audio_feas, audio_value))
vedio_feas = np.concatenate((vedio_feas, vedio_value))
text_feas = np.concatenate((text_feas, text_value))
except:
continue
COVAREP_COLUMNS.remove('VUV')
audio_fea_name = ['ID']
text_fea_name = ['ID']
vedio_fea_name = ['ID']
audio_fea_name.extend(COVAREP_COLUMNS + FORMANT_COLUMNS)
text_fea_name.extend(TEXT_COLUMNS)
vedio_fea_name.extend(STABLE_POINTS)
assert len(audio_feas[0]) == len(audio_fea_name) and len(text_feas[0]) == len(text_fea_name) \
and len(vedio_feas[0]) == len(vedio_fea_name)
audio_df = pd.DataFrame(audio_feas, columns=audio_fea_name)
vedio_df = pd.DataFrame(vedio_feas, columns=vedio_fea_name)
text_df = pd.DataFrame(text_feas, columns=text_fea_name)
hog_pca()
sql_handler.execute(f'drop table if exists {config.tbl_exp3_audio_fea};'
) #因为每次选择特征不一样，所以入库之前需要删除原来的表
sql_handler.df_to_db(audio_df, config.tbl_exp3_audio_fea)
logger.info('audio feature exp3 has been stored!')
sql_handler.execute(f'drop table if exists {config.tbl_exp3_vedio_fea};'
) #因为每次选择特征不一样，所以入库之前需要删除原来的表
sql_handler.df_to_db(vedio_df, config.tbl_exp3_vedio_fea)
logger.info('vedio feature exp3 has been stored!')
sql_handler.execute(f'drop table if exists {config.tbl_exp3_text_fea};'
) #因为每次选择特征不一样，所以入库之前需要删除原来的表
sql_handler.df_to_db(text_df, config.tbl_exp3_text_fea)
logger.info('text feature exp3 has been stored!')