加快通过机器学习服务执行Python脚本的SQL过程

Question

我有一个SQL过程，我的网站每天要调用数千次。该过程执行一个Python脚本。我的问题是执行时间太长（大约6秒），而超过一半的运行时间花费在导入库和加载对象以供脚本使用上。

exec sp_execute_external_script  

    @language =N'Python',

    @script=N'
import pandas as pd
import numpy as np
from sklearn.svm import LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.calibration import CalibratedClassifierCV
from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPClassifier
import joblib

count_vect = joblib.load(''count_vect_V2.sav'')
tfidf_transformer = joblib.load(''tfidf_transformer_V2.sav'')
model_svm = joblib.load(''cs_svm_V2.sav'')
model_rf = joblib.load(''cs_rf_V2.sav'')
model_nb = joblib.load(''cs_nb_V2.sav'')
model_nn = joblib.load(''cs_nn_V2.sav'')
model_ensemble = joblib.load(''cs_ensemble_V2.sav'')

#Do something below


#End of doing something
    '

是否存在一种解决方案，可以存储这些对象/库供我的代码访问，以使我不必在每次运行脚本时都加载它们？