机器学习_sklearn_一般使用

通用学习模式

1.导入需要的模块
2.获取数据
3.划分测试集和训练集
4.建立模型-训练-预测

# 1.导入模块
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier

# 2.获得数据
iris = datasets.load_iris()
iris_X = iris.data
iris_Y = iris.target

# 3.划分测试集和训练集
'''
1.传入数据集实例和数据集标签，test_size=0.3，即测试集占总数据的 30%
2.分开后的数据集顺序也被打乱
'''
X_train,X_test,Y_train,Y_test = train_test_split(iris_X,iris_Y,test_size=0.3)


# 4.建立模型-训练-预测
knn = KNeighborsClassifier()
knn.fit(X_train,Y_train)
print(knn.predict(X_test)) # 打印预测的结果
print(Y_test) # 打印标签
print(knn.score(X_test,Y_test)) #计算准确率

sklearn 强大数据库

from sklearn import datasets
import matplotlib.pyplot as plt
# noise:噪声
X,Y = datasets.make_regression(n_samples=100,n_features=1,n_targets=1,noise=10)
plt.scatter(X,Y)
plt.show()

sklearn 常用属性与功能

from sklearn import datasets
from sklearn.linear_model import LinearRegression

loaded_data = datasets.load_boston()
data_X = loaded_data.data
data_Y = loaded_data.target

model = LinearRegression()

# 训练 fit
model.fit(data_X,data_Y)

# 预测 predict
print(model.predict(data_X[:4,:]))

# 输出权重 weight
print(model.coef_)
# 输出偏置 bias
print(model.intercept_)

# 获得之前定义的参数
print(model.get_params())

# 获得准确率 score
model.score(data_X, data_Y)