使用pickle保存模型

Question

我已经建立了一个分类器，希望将其保存以备将来使用。该分类器包含不同的算法（逻辑回归、朴素贝叶斯、支持向量机）：

X, y = tfidf(df, ngrams = 1)
X, y = under_sample.fit_resample(X, y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=40)
df_result = df_result.append(training_naive(X_train, X_test, y_train, y_test), ignore_index = True)
df_result = df_result.append(training_logreg(X_train, X_test, y_train, y_test), ignore_index = True)
df_result = df_result.append(training_svm(X_train, X_test, y_train, y_test), ignore_index = True)

这是我的代码的最后一步，我在这里比较不同的算法。training_svm / logreg 和 naive 是函数。例如，training_svm 的定义如下：

def training_svm(X_train_log, X_test_log, y_train_log, y_test_log):
    
    folds = StratifiedKFold(n_splits = 3, shuffle = True, random_state = 40)
    
    clf = svm.SVC(kernel='linear') # Linear Kernel
    
    clf.fit(X_train_log, y_train_log)

    res = pd.DataFrame(columns = ['Preprocessing', 'Model', 'Precision', 'Recall', 'F1-score', 'Accuracy'])
    
    y_pred = clf.predict(X_test_log)
    
    f1 = f1_score(y_pred, y_test_log, average = 'weighted')
    pres = precision_score(y_pred, y_test_log, average = 'weighted')
    rec = recall_score(y_pred, y_test_log, average = 'weighted')
    acc = accuracy_score(y_pred, y_test_log)
    
    res = res.append({'Model': f'SVM', 'Precision': pres, 
                     'Recall': rec, 'F1-score': f1, 'Accuracy': acc}, ignore_index = True)

    return res

我想使用和测试新数据，因此我想知道如何保存并重复使用它。 我认为应该像这样做：

import pickle

# save
with open('model.pkl','wb') as f:
    pickle.dump(clf,f)

# load
with open('model.pkl', 'rb') as f:
    clf2 = pickle.load(f)

clf2.predict(X[0:1])

请说明如何将其扩展到我的项目中？

- V_sqrt

Answer 1

根据sklearn的说法:

可以通过使用Python的内置持久化模型pickle在scikit-learn中保存模型。

示例：

from sklearn import svm
from sklearn import datasets
clf = svm.SVC()
X, y= datasets.load_iris(return_X_y=True)
clf.fit(X, y)

import pickle
s = pickle.dumps(clf)
clf2 = pickle.loads(s)
clf2.predict(X[0:1])

然后您可以将其包含在每个模型的代码中，创建一个名为的函数

def predict_svm(to_predict):
    with open("'your_svm_model'",'rb') as f_input:
        clf = pickle.loads(f_input) # maybe handled with a singleton to reduce loading for multiple predictions
    return clf.predict(to_predict)

无论如何，scikit-learn建议使用joblib：

对于scikit-learn的特定情况，最好使用joblib代替pickle（dump&load）进行对象的序列化和反序列化，这对于内部包含大型numpy数组的拟合scikit-learn估计器通常更为高效，但只能将其序列化到磁盘而不能序列化到字符串中：

from joblib import dump, load
dump(clf, 'filename.joblib') 

clf = load('filename.joblib') 

这里详细介绍

- Nikaido