我正在做一个很少的部署。我使用 sklearn 创建了自定义管道,它位于MyPipelines/CustomPipelines.py目录中。主要代码即。my_prediction.py是 seldon 默认执行的文件(基于我的配置)。在这个文件中,我正在导入自定义管道。如果我在本地(PyCharm)中执行 my_prediction.py ,它执行得很好。但是如果我使用 Seldon 部署它,我会收到错误消息:Attribute Error: Can't get Attribute 'MyEncoder'
它无法在 CustomPipelines.py 中加载模块。我尝试了Unable to load files using pickle and multiple modules中的所有解决方案,但它们都不起作用。
MyPipelines/CustomPipelines.py
from sklearn.preprocessing import LabelEncoder
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.pipeline import Pipeline
class MyEncoder(BaseEstimator, TransformerMixin):
def __init__(self):
super().__init__()
def fit(self, X, y=None):
return self
def transform(self, X, y=None):
df = X
vars_cat = [var for var in df.columns if df[var].dtypes == 'O']
cat_with_na = [var for var in vars_cat if df[var].isnull().sum() > 0]
df[cat_with_na] = df[cat_with_na].fillna('Missing')
return df
我的预测.py
import pickle
import pandas as pd
import dill
from MyPipelines.CustomPipelines import MyEncoder
from MyPipelines.CustomPipelines import *
import MyPipelines.CustomPipelines
class my_prediction:
def __init__(self):
file_name = 'model.sav'
with open(file_name, 'rb') as model_file:
self.model = pickle.load(model_file)
def predict(self, request):
data = request.get('ndarray')
columns = request.get('names')
X = pd.DataFrame(data, columns = columns)
predictions = self.model.predict(X)
return predictions
错误:
File microservice/my_prediction.py in __init__
self.model = pickle.load(model_file)
Attribute Error: Can't get Attribute 'MyEncoder' on <module '__main__' from 'opt/conda/bin/seldon-core-microservice'