使用 Pickle 加載保存的 model - 在加載的程序中完成 fit_transform 時出現錯誤

Question

我創建了第一個程序來訓練算法並保存它。

程序 1

import numpy as np
from sklearn.model_selection import StratifiedShuffleSplit 
from sklearn.impute import SimpleImputer  
from sklearn.tree import DecisionTreeRegressor # import for Decision Tree Algorithm
import pickle
from sklearn.preprocessing import StandardScaler

SourceData=pd.read_excel("ASML Stock Predict.xlsx") # Load the data into Pandas DataFrame
SourceData["Nasdaq Category"]=pd.cut(SourceData["Adj Close Nasdaq 100"],
                                     bins=[0., 4500, 5500, 6500, 7500,8500, 9500, 10500, np.inf],
                                     labels=[1, 2, 3, 4,5,6,7,8])

""" Split the data source into test and train subset """
split = StratifiedShuffleSplit(n_splits=1, test_size=0.01, random_state=42)
for train_index, test_index in split.split(SourceData, SourceData["Nasdaq Category"]):
    strat_train_set = SourceData.loc[train_index]  # stratfied train dataset with all columns in original source data 
    strat_test_set = SourceData.loc[test_index] #stratified test dataset with all columns in original source data

""" Drop the new Nasdaq Category Cloumn from the data source after the train and test subset is prepared"""
for set_ in (strat_train_set, strat_test_set): 
    set_.drop("Nasdaq Category", axis=1, inplace=True)

DataSource_train_independent= strat_train_set.drop(["Date", "Adj Close ASML"], axis=1) # Drop depedent variable from training dataset
DataSource_train_dependent=strat_train_set["Adj Close ASML"].copy() #  New dataframe with only independent variable value for training dataset



imputer = SimpleImputer(strategy="median") # declated imputer to fill the blank values with Median value of the variable
imputer.fit(DataSource_train_independent) # calulate the median for different independent variables

""" Scale the independent variables training set. No need to scale the dependent variable """
sc_X = StandardScaler()
X=sc_X.fit_transform(DataSource_train_independent.values) # scale the independent variables
X_test=sc_X.transform(testdata.values) # scale the independent variables for test data
##sc_y = StandardScaler()
y=DataSource_train_dependent # scaling is not required for dependent variable


"""Decision Tree Regressor """

tree_reg = DecisionTreeRegressor()
tree_reg.fit(X,y)

filename = 'DecisionTree_TrainedModel.sav'
pickle.dump(tree_reg, open(filename, 'wb'))

節目二

from sklearn.tree import DecisionTreeRegressor # import for Decision Tree Algorithm
from sklearn.preprocessing import StandardScaler
from sklearn.tree import DecisionTreeRegressor # import for Decision Tree Algorithm
import pandas as pd

testdata=pd.read_excel("ASML Test  Stock Predict.xlsx") # Load the test data

sc_X = StandardScaler()
X_test=sc_X.transform(testdata.values) # scale the independent variables for test data



loaded_model = pickle.load(open('DecisionTree_TrainedModel.sav', 'rb'))
decision_predictions = loaded_model.predict(X_test) # Predict the value of dependent variable
print("The prediction by Decision Treemodel is " , decision_predictions )

由於我在程序 1 中有“fit_transform”並保存了 model，因此在加載 model 后的第二個程序中，我只轉換了自變量。

運行第二個程序時出現錯誤消息“sklearn.exceptions.NotFittedError：尚未安裝此 StandardScaler 實例。在使用此估算器之前，請使用適當的 arguments 調用 'fit'。”

請建議。 據我了解，我只需要轉換而不適合測試自變量。

Answer 1

您還必須腌制訓練有素的 StandardScaler：

# train and pickle
sc = StandardScaler()
X = sc.fit_transform(DataSource_train_independent.values)

tree_reg = DecisionTreeRegressor()
tree_reg.fit(X, y)

pickle.dump(sc, open('StandardScaler.pk', 'wb'))
pickle.dump(tree_reg, open('DecisionTree.pk', 'wb'))

# load and predict
sc = pickle.load(open('StandardScaler.pk', 'rb'))
model = pickle.load(open('DecisionTree.pk', 'rb'))

X_test = sc.transform(testdata.values)
predictions = model.predict(X_test)

更好的方法是將所有步驟包裝在單個管道中：

pipeline = Pipeline(steps=[('sc', StandardScaler()), 
                           ('tree_reg', DecisionTreeRegressor())])

pipeline.fit(X, y)
pipeline.predict(testdata.values)