sklearn

来自莫烦python教程

线性回归

from sklearn import datasets
from sklearn.linear_model import LinearRegression
data = datasets.load_boston()
x = data.data
y = data.target
#选择线性回归模型
model = LinearRegression()
#训练模型
model.fit(x, y)
#模型参数
print(model.coef_, model.intercept_)
#预测
print(x[1:5])
print(model.predict(x[1:5]))
#评价模型得分
print(model.score(x, y))   

支持向量机-数据标准化

from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from sklearn.datasets.samples_generator import make_classification
from sklearn.svm import SVC
import matplotlib.pyplot as plt
x, y = make_classification(n_samples=300, n_features=2, n_informative=2,
                        n_redundant=0, n_repeated=0, n_classes=2,
                        n_clusters_per_class=1, weights=None, flip_y=0.01,
                        class_sep=1.0, hypercube=True, shift=0.0, scale=100,
                        shuffle=True, random_state=22)
# plt.scatter(x[:,0], x[:,1], c=y)
# plt.show()
x = preprocessing.scale(x)  #数据标准化(normalization)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=.3)  #拆分为训练集和测试集
clf = SVC()
clf.fit(x_train, y_train)
print(clf.score(x_test, y_test))

knn-交叉验证

from sklearn.model_selection import cross_val_score
from sklearn.datasets import load_iris
from sklearn.neighbors import KNeighborsClassifier
iris = load_iris()
x = iris.data
y = iris.target
knn = KNeighborsClassifier(n_neighbors=5)
score = cross_val_score(knn, x, y, cv=5, scoring='accuracy')
print(score.mean())

       ## 对于线性回归

loss = -cross_val_score(knn, x, y, cv=5, scoring='neg_mean_squared_error_')

训练次数-损失曲线

from sklearn.model_selection import learning_curve
from sklearn.datasets import load_digits
from sklearn.svm import SVC
import matplotlib.pyplot as plt
import numpy as np
digit = load_digits()
x = digit.data
y = digit.target
train_sizes, train_loss, test_loss = learning_curve(
    SVC(gamma=0.001), x, y, cv=10, scoring='neg_mean_squared_error',
    train_sizes=[0.1, 0.25, 0.5, 0.75, 1])
train_loss_mean = -np.mean(train_loss, axis=1)
test_loss_mean = -np.mean(test_loss, axis=1)
plt.plot(train_sizes, train_loss_mean, color='r', label='train_loss')
plt.plot(train_sizes, test_loss_mean, color='b', label='test_loss')
plt.legend()
plt.show()

SVC参数gamma值-损失曲线

from sklearn.model_selection import validation_curve
from sklearn.datasets import load_digits
from sklearn.svm import SVC
import matplotlib.pyplot as plt
import numpy as np
digit = load_digits()
x = digit.data
y = digit.target
param_range = np.logspace(-6, -2.3, 5)
train_loss, test_loss = validation_curve(
    SVC(), x, y, param_name='gamma', param_range=param_range, cv=10, scoring='neg_mean_squared_error')
train_loss_mean = -np.mean(train_loss, axis=1)
test_loss_mean = -np.mean(test_loss, axis=1)
plt.plot(param_range, train_loss_mean, color='r', label='train_loss')
plt.plot(param_range, test_loss_mean, color='b', label='test_loss')
plt.xlabel('gamma')
plt.ylabel('loss')
plt.legend()
plt.show()

模型保存和读取

from sklearn.externals import joblib
from sklearn.datasets import load_iris
from sklearn import svm
data = load_iris()
x, y = data.data, data.target
clf = svm.SVC()
clf.fit(x, y)
joblib.dump(clf, 'clf')  #保存
clf2 = joblib.load('clf')  #读取