scikit-learn 机器学习库学习小计

scikit-learn是一个非常流行的工具，也是最有名的Python机器学习库。

在此对以前学的知识进行整理，记录在这里。

首先是经典的鸢尾花数据，KNN分类：

from  sklearn  import datasets
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
import matplotlib.pyplot as plt
import pandas as pd
%matplotlib inline

iris_data = datasets.load_iris()
print(type(iris_data))  #iris_data 是一个bunch属性，类似于字典
print('iris_data.keys:\n',iris_data.keys())#iris_data 查看其键值
iris_dataFrame = pd.DataFrame(iris_data['data'],columns = iris_data['feature_names'])
#利用pd中的dataframe来创建散点图，iris_data['targert']来选择颜色
grr = pd.scatter_matrix(iris_dataFrame,c = iris_data['target'],figsize = (15,15),marker = 'o',s =30,hist_kwds = {'bins':20})

 

由图可看到其实鸢尾花的特性是可以分类的。

X_train,X_test,y_train,y_test = train_test_split(iris_data['data'],iris_data['target'],random_state = 0,test_size = 0.3)#random_state是随机种子，test_size为测试集所占的比例
print(X_train.shape)
print(X_test.shape)
print(y_train.shape)
print(y_test.shape)
print(y_test)

knn = KNeighborsClassifier(n_neighbors=5)#默认参数n_neighbors = 5
knn.fit(X_train,y_train)
prediction = knn.predict(X_test)
acc = (prediction == y_test).mean()#也可以使用knn.score()的方法查看准确率
print(acc)
print(knn.score(X_test,y_test))

datasets 除了有iris_load()数据集，其实还有其他的数据集，比如波士顿房价等：

from sklearn import datasets
from sklearn.linear_model import LinearRegression
data = datasets.load_boston()
X_data = data['data']
y_data = data['target']
model = LinearRegression()#定义个模型就是线性回归
model.fit(X_data,y_data) #模型训练
#print(model.predict(X_data[:4,:]))
#print(y_data[:4])

#model常用属性
print(model.coef_)  #打印线性回归的系数
print(model.intercept_)#打印线性回归的截距
print(model.get_params())
print(model.score(X_data,y_data))#将预测值和实际进行对比打分

 

datasets 除了导入现有的数据，还可以生成数据：

#创造数据点
X,y = datasets.make_regression(n_samples= 100,n_features= 1,n_targets= 1,noise = 1)
plt.scatter(X,y)
plt.show()
print(X.shape,y.shape)

sklearn 的归一化：

#scikit_learn 归一化
from sklearn import preprocessing
import numpy as np
a = np.array([[10,2.7,3.6],[-100,5,-2],[120,20,40]])
print(a)
print(preprocessing.scale(a))

 

小例子：

#小例子
import numpy as np
from sklearn import preprocessing
from sklearn.cross_validation import train_test_split
from sklearn.datasets.samples_generator import make_classification
from sklearn.svm import SVC
import matplotlib.pyplot as plt
%matplotlib inline

#生成数据
X,y = make_classification(n_samples=300,n_features=2,n_redundant=0,n_informative=2
         ,random_state = 22,n_clusters_per_class = 1,scale = 100)
print(X.shape,y.shape)

plt.scatter(X[:,0],X[:,1],c = y)
X = preprocessing.scale(X) #取值范围默认为0~1，归一化
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size  =.3)
clf = SVC()
clf.fit(X_train,y_train)
print(clf.score(X_test,y_test))