sklearn是非常流行的机器学习库，实现了很多的机器学习模型。官网：http://scikit-learn.org/stable/ 里面有全面的实例和模型参数讲解，用到哪个模型就去官方查看说明文档。
基本功能主要被分为六大部分：分类，回归，聚类，数据降维，模型选择和数据预处理。
Estimator框架的基本使用套路：
model = EstimatorObject() #得到模型
model.fit(dataset.data, dataset.target) #训练模型
model.predict(dataser.data) #预测
本文对主要的机器学习模型进行实例演示，具体模型的参数结合的自己需求设置。
1.分类问题
数据集为 Car Ecaluation,根据汽车的若干属性对汽车性能进行评价。下载地址：
http://archive.ics.uci.edu/ml/datasets/Car+Evaluation
预处理：将数据集保存后将后缀直接改为csv，并将里面用字符串表示的等级转化为数字。如small,low,unacc转化为1，2，3
1.1 SVM支持向量机模型
from sklearn import svm
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
#SVM模型实现汽车性能评测
car_data = pd.read_csv(r'D:\pyproject\sklearn\car.csv')
car_data = car_data.dropna() #去掉缺失值
#提取特征和类别
X= car_data.ix[:, :'safety']
y= car_data.ix[:,'class']
#划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
# 建立模型。 设置算法内核类型，有 'linear’, ‘poly’, ‘rbf’, ‘sigmoid’;惩罚参数为1，一般为10的幂次方
svc_model = svm.SVC(kernel='rbf', C= 1)
svc_model.fit(X_train, y_train)
predict_data = svc_model.predict(X_test)
accuracy = np.mean(predict_data==y_test)
print(accuracy)运行结果：
1.2 MLP神经网络模型
from sklearn.neural_network import MLPClassifier
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
#MLP神经网络模型实现汽车性能评测
car_data = pd.read_csv(r'D:\pyproject\sklearn\car.csv')
car_data = car_data.dropna() #去掉缺失值
#提取特征和对象类别
X= car_data.ix[:, :'safety']
y= car_data.ix[:,'class']
#划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
#建立MLP神经网络模型 ，MLP的求解方法为adam，可选lbfgs、sgd，正则化惩罚alpha = 0.1
mpl_model = MLPClassifier(solver='adam', learning_rate='constant', learning_rate_init=0.01,max_iter = 500,alpha =0.01)
mpl_model.fit(X_train, y_train)
predict_data = mpl_model.predict(X_test)
accuracy = np.mean(predict_data == y_test)
print(accuracy)运行结果：
1.3 逻辑回归模型
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
#逻辑回归模型实现汽车性能预测
car_data = pd.read_csv(r'D:\pyproject\sklearn\car.csv')
car_data = car_data.dropna() #去掉缺失值
#提取特征和对象类别
X= car_data.ix[:, :'safety']
y= car_data.ix[:, 'class']
#划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
#建立逻辑回归模型 ，惩罚参数为100
lr_model = LogisticRegression(C= 100, max_iter=1000)
lr_model.fit(X_train, y_train)
predict_data = lr_model.predict(X_test)
accuracy = np.mean(predict_data == y_test)
print(accuracy)运行结果：
1.4 决策树模型
from sklearn import tree
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
#决策树模型实现汽车性能预测
car_data = pd.read_csv(r'D:\pyproject\sklearn\car.csv')
car_data = car_data.dropna() #去掉缺失值
#提取特征和类别
X= car_data.ix[:, :'safety']
y= car_data.ix[:,'class']
#划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
# 建立决策树模型，选择算法为熵增益，可选gini,entropy,默认为gini
tree_model = tree.DecisionTreeClassifier(criterion='gini')
tree_model.fit(X_train, y_train)
predict_data = tree_model.predict(X_test)
accuracy = np.mean(predict_data==y_test)
print(accuracy)运行结果：
1.5 KNN（K最临近模型）
from sklearn import neighbors
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
#K最邻模型实现汽车性能预测
car_data = pd.read_csv(r'D:\pyproject\sklearn\car.csv')
car_data = car_data.dropna() #去掉缺失值
#提取特征和类别
X= car_data.ix[:, :'safety']
y= car_data.ix[:, 'class']
#划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
# 建立KNN模型，邻居数选为7，默认为5
knn_model = neighbors.KNeighborsClassifier(n_neighbors = 7)
knn_model.fit(X_train, y_train)
#对测试集进行预测
predict_data = knn_model.predict(X_test)
accuracy = np.mean(predict_data==y_test)
print(accuracy)运行结果：
2. 回归问题
这里使用sklearn自带的数据集，数据集为波斯顿房价，根据波斯顿地区若干指标对房价进行预测。
2.1 线性回归模型实现
from sklearn.linear_model import LinearRegression
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
#导入结果评价包
from sklearn.metrics import mean_absolute_error
#利用线性回归模型预测波斯顿房价
#下载sklearn自带的数据集
data = load_boston()
#建立线性回归模型
clf = LinearRegression()
#划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(data.data, data.target, test_size=0.3, random_state=0)
clf.fit(X_train, y_train)
predict_data = clf.predict(X_test)
print(predict_data)
#平均绝对值误差对结果进行评价
appraise = mean_absolute_error(y_test, predict_data)
print(appraise)运行结果：
