Python 朴素贝叶斯与使用 GaussianNB 分类器的交叉验证

Question

我想对我的数据应用具有 10 倍分层交叉验证的朴素贝叶斯，然后我想看看模型在我最初留出的测试数据上的表现如何。 但是，我得到的结果(即预测结果和概率值y_pred_nb2和y_score_nb2(与我在没有任何交叉验证的情况下运行代码时相同。 问：我该如何纠正这个问题？

代码如下，其中X_train占整个数据集的 75%，X_test占 25%。

from sklearn.model_selection import StratifiedKFold 
params = {}
#gridsearch searches for the best hyperparameters and keeps the classifier with the highest recall score
skf = StratifiedKFold(n_splits=10)
nb2 = GridSearchCV(GaussianNB(), cv=skf, param_grid=params)
%time nb2.fit(X_train, y_train)
# predict values on the test set
y_pred_nb2 = nb2.predict(X_test) 
print(y_pred_nb2)
# predicted probabilities on the test set
y_scores_nb2 = nb2.predict_proba(X_test)[:, 1]
print(y_scores_nb2)

Answer 1

首先，GaussianNB只接受priors作为参数，所以除非你提前为模型设置了一些先验，否则你没有什么可以网格搜索的。

此外，您的param_grid设置为空字典，以确保您仅将一个估计器与GridSearchCV拟合。这与不使用网格搜索拟合估计器相同(例如，我使用MultinomialNB来显示超参数的使用(：

from sklearn.datasets import load_iris
from sklearn.model_selection import GridSearchCV, StratifiedKFold, train_test_split
from sklearn.naive_bayes import MultinomialNB
skf = StratifiedKFold(n_splits=10)
params = {}
nb = MultinomialNB()
gs = GridSearchCV(nb, cv=skf, param_grid=params, return_train_score=True)
data = load_iris()
x_train, x_test, y_train, y_test = train_test_split(data.data, data.target)
gs.fit(x_train, y_train)
gs.cv_results_
{'mean_fit_time': array([0.]),
'mean_score_time': array([0.]),
'mean_test_score': array([0.85714286]),
'mean_train_score': array([0.85992157]),
'params': [{}],
'rank_test_score': array([1]),
'split0_test_score': array([0.91666667]),
'split0_train_score': array([0.84]),
'split1_test_score': array([0.75]),
'split1_train_score': array([0.86]),
'split2_test_score': array([0.83333333]),
'split2_train_score': array([0.84]),
'split3_test_score': array([0.91666667]),
'split3_train_score': array([0.83]),
'split4_test_score': array([0.83333333]),
'split4_train_score': array([0.85]),
'split5_test_score': array([0.91666667]),
'split5_train_score': array([0.84]),
'split6_test_score': array([0.9]),
'split6_train_score': array([0.88235294]),
'split7_test_score': array([0.8]),
'split7_train_score': array([0.88235294]),
'split8_test_score': array([0.8]),
'split8_train_score': array([0.89215686]),
'split9_test_score': array([0.9]),
'split9_train_score': array([0.88235294]),
'std_fit_time': array([0.]),
'std_score_time': array([0.]),
'std_test_score': array([0.05832118]),
'std_train_score': array([0.02175538])}
nb.fit(x_train, y_train)
nb.score(x_test, y_test)
0.8157894736842105
gs.score(x_test, y_test)
0.8157894736842105
gs.param_grid = {'alpha': [0.1, 2]}
gs.fit(x_train, y_train)
gs.score(x_test, y_test)
0.8421052631578947
gs.cv_results_
{'mean_fit_time': array([0.00090394, 0.00049713]),
'mean_score_time': array([0.00029924, 0.0003005 ]),
'mean_test_score': array([0.86607143, 0.85714286]),
'mean_train_score': array([0.86092157, 0.85494118]),
'param_alpha': masked_array(data=[0.1, 2],
mask=[False, False],
fill_value='?',
dtype=object),
'params': [{'alpha': 0.1}, {'alpha': 2}],
'rank_test_score': array([1, 2]),
'split0_test_score': array([0.91666667, 0.91666667]),
'split0_train_score': array([0.84, 0.83]),
'split1_test_score': array([0.75, 0.75]),
'split1_train_score': array([0.86, 0.86]),
'split2_test_score': array([0.83333333, 0.83333333]),
'split2_train_score': array([0.85, 0.84]),
'split3_test_score': array([0.91666667, 0.91666667]),
'split3_train_score': array([0.83, 0.81]),
'split4_test_score': array([0.83333333, 0.83333333]),
'split4_train_score': array([0.85, 0.84]),
'split5_test_score': array([0.91666667, 0.91666667]),
'split5_train_score': array([0.84, 0.84]),
'split6_test_score': array([0.9, 0.9]),
'split6_train_score': array([0.88235294, 0.88235294]),
'split7_test_score': array([0.9, 0.8]),
'split7_train_score': array([0.88235294, 0.88235294]),
'split8_test_score': array([0.8, 0.8]),
'split8_train_score': array([0.89215686, 0.89215686]),
'split9_test_score': array([0.9, 0.9]),
'split9_train_score': array([0.88235294, 0.87254902]),
'std_fit_time': array([0.00030147, 0.00049713]),
'std_score_time': array([0.00045711, 0.00045921]),
'std_test_score': array([0.05651628, 0.05832118]),
'std_train_score': array([0.02103457, 0.02556351])}

Answer 2

像这样的事情怎么样

import pandas as pd
from sklearn.model_selection import cross_val_score
from sklearn.naive_bayes import GaussianNB
#because only var_smoothing can be 'tuned'
#do a cross validation on different var_smoothing values
def cross_val(params):
model = GaussianNB()
model.set_params(**params)
cv_results = cross_val_score(model, X_train, y_train,
cv = 10, #10 folds
scoring = "accuracy",
verbose = 2
)
#return the mean of the 10 fold cross validation
return cv_results.mean()
#baseline parameters
params = {
"priors" : "None",
"var_smoothing" : 1e-9
}
#create an list of var_smoothing to cross validate
steps = [1e-8, 1e-7, 1e-6, 1e-5, 1e-4]
#will contain the cv results
results = []
for step in steps:        
params["var_smoothing"] = step        
cv_result = cross_val(params)
#save result
results.append(cv_result)
#print results
#convert results to pandas dataframe for easier visualization
df = pd.DataFrame({"var_smoothing" : steps, "accuracy" : results})
#sort it
df_sorted = df.sort_values("accuracy", ascending=False)
#reset the index of the sorted dataframe
df_sorted.reset_index(inplace=True, drop=True)
df_sorted.head()