基于 Python 实践感知器分类算法
Perceptron分类器是一种线性算法,可以应用于二进制分类任务。 如何使用带有Scikit-Learn的Perceptron模型进行拟合,评估和做出预测。 如何在给定的数据集上调整Perceptron算法的超参数。
感知器算法 Perceptron与Scikit-学习 音调感知器超参数
激活=权重*输入+偏差
如果激活> 0.0
如果激活<= 0.0
权重(t + 1)=权重(t)+学习率*(expected_i –预测值)* input_i
# define model
model = Perceptron(eta0=1.0)
# define model
model = Perceptron(max_iter=1000)
# test classification dataset
from sklearn.datasets import make_classification
# define dataset
X, y = make_classification(n_samples=1000, n_features=10, n_informative=10, n_redundant=0, random_state=1)
# summarize the dataset
print(X.shape, y.shape)
(1000, 10) (1000,)
RepeatedStratifiedKFold
类使用重复的分层k折交叉验证来拟合和评估Perceptron模型。我们将在测试装置中使用10折和3次重复。# create the model
model = Perceptron()
# evaluate a perceptron model on the dataset
from numpy import mean
from numpy import std
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.linear_model import Perceptron
# define dataset
X, y = make_classification(n_samples=1000, n_features=10, n_informative=10, n_redundant=0, random_state=1)
# define model
model = Perceptron()
# define model evaluation method
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# evaluate model
scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
# summarize result
print('Mean Accuracy: %.3f (%.3f)' % (mean(scores), std(scores)))
Mean Accuracy: 0.847 (0.052)
predict()
函数来实现。我们可以通过下面列出的完整示例进行演示。# make a prediction with a perceptron model on the dataset
from sklearn.datasets import make_classification
from sklearn.linear_model import Perceptron
# define dataset
X, y = make_classification(n_samples=1000, n_features=10, n_informative=10, n_redundant=0, random_state=1)
# define model
model = Perceptron()
# fit model
model.fit(X, y)
# define new data
row = [0.12777556,-3.64400522,-2.23268854,-1.82114386,1.75466361,0.1243966,1.03397657,2.35822076,1.01001752,0.56768485]
# make a prediction
yhat = model.predict([row])
# summarize prediction
print('Predicted Class: %d' % yhat)
Predicted Class: 1
# define grid
grid = dict()
grid['eta0'] = [0.0001, 0.001, 0.01, 0.1, 1.0]
# grid search learning rate for the perceptron
from sklearn.datasets import make_classification
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.linear_model import Perceptron
# define dataset
X, y = make_classification(n_samples=1000, n_features=10, n_informative=10, n_redundant=0, random_state=1)
# define model
model = Perceptron()
# define model evaluation method
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# define grid
grid = dict()
grid['eta0'] = [0.0001, 0.001, 0.01, 0.1, 1.0]
# define search
search = GridSearchCV(model, grid, scoring='accuracy', cv=cv, n_jobs=-1)
# perform the search
results = search.fit(X, y)
# summarize
print('Mean Accuracy: %.3f' % results.best_score_)
print('Config: %s' % results.best_params_)
# summarize all
means = results.cv_results_['mean_test_score']
params = results.cv_results_['params']
for mean, param in zip(means, params):
print(">%.3f with: %r" % (mean, param))
Mean Accuracy: 0.857
Config: {'eta0': 0.0001}
>0.857 with: {'eta0': 0.0001}
>0.857 with: {'eta0': 0.001}
>0.853 with: {'eta0': 0.01}
>0.847 with: {'eta0': 0.1}
>0.847 with: {'eta0': 1.0}
# define grid
grid = dict()
grid['max_iter'] = [1, 10, 100, 1000, 10000]
# define model
model = Perceptron(eta0=0.0001)
# grid search total epochs for the perceptron
from sklearn.datasets import make_classification
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.linear_model import Perceptron
# define dataset
X, y = make_classification(n_samples=1000, n_features=10, n_informative=10, n_redundant=0, random_state=1)
# define model
model = Perceptron(eta0=0.0001)
# define model evaluation method
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
# define grid
grid = dict()
grid['max_iter'] = [1, 10, 100, 1000, 10000]
# define search
search = GridSearchCV(model, grid, scoring='accuracy', cv=cv, n_jobs=-1)
# perform the search
results = search.fit(X, y)
# summarize
print('Mean Accuracy: %.3f' % results.best_score_)
print('Config: %s' % results.best_params_)
# summarize all
means = results.cv_results_['mean_test_score']
params = results.cv_results_['params']
for mean, param in zip(means, params):
print(">%.3f with: %r" % (mean, param))
Mean Accuracy: 0.857
Config: {'max_iter': 10}
>0.850 with: {'max_iter': 1}
>0.857 with: {'max_iter': 10}
>0.857 with: {'max_iter': 100}
>0.857 with: {'max_iter': 1000}
>0.857 with: {'max_iter': 10000}
作者:沂水寒城,CSDN博客专家,个人研究方向:机器学习、深度学习、NLP、CV
Blog: http://yishuihancheng.blog.csdn.net
赞 赏 作 者
更多阅读
特别推荐
点击下方阅读原文加入社区会员
评论