sklearn处理分类或者回归问题

 sklearn处理回归问题

import numpy as np
import matplotlib.pyplot as plt
 
 
# 生成数据
def gen_data(x1, x2):
    y = np.sin(x1) * 1/2 + np.cos(x2) * 1/2 + 0.1 * x1
    return y
 
 
def load_data():
    x1_train = np.linspace(0, 50, 500)
    x2_train = np.linspace(-10, 10, 500)
    data_train = np.array([[x1, x2, gen_data(x1, x2) + np.random.random(1) - 0.5] for x1, x2 in zip(x1_train, x2_train)])
    x1_test = np.linspace(0, 50, 100) + np.random.random(100) * 0.5
    x2_test = np.linspace(-10, 10, 100) + 0.02 * np.random.random(100)
    data_test = np.array([[x1, x2, gen_data(x1, x2)] for x1, x2 in zip(x1_test, x2_test)])
    return data_train, data_test
 
 
train, test = load_data()
# train的前两列是x，后一列是y，这里的y有随机噪声
x_train, y_train = train[:, :2], train[:, 2]
x_test, y_test = test[:, :2], test[:, 2]  # 同上，但这里的y没有噪声
 
# 回归部分
def try_different_method(model, method):
    model.fit(x_train, y_train)
    score = model.score(x_test, y_test)
    result = model.predict(x_test)
    plt.figure()
    plt.plot(np.arange(len(result)), y_test, "go-", label="True value")
    plt.plot(np.arange(len(result)), result, "ro-", label="Predict value")
    plt.title(f"method:{method}---score:{score}")
    plt.legend(loc="best")
    plt.show()
 
 
# 方法选择
# 1.决策树回归
from sklearn import tree
model_decision_tree_regression = tree.DecisionTreeRegressor()
 
# 2.线性回归
from sklearn.linear_model import LinearRegression
model_linear_regression = LinearRegression()
 
# 3.SVM回归
from sklearn import svm
model_svm = svm.SVR()
 
# 4.kNN回归
from sklearn import neighbors
model_k_neighbor = neighbors.KNeighborsRegressor()
 
# 5.随机森林回归
from sklearn import ensemble
model_random_forest_regressor = ensemble.RandomForestRegressor(n_estimators=20)  # 使用20个决策树
 
# 6.Adaboost回归
from sklearn import ensemble
model_adaboost_regressor = ensemble.AdaBoostRegressor(n_estimators=50)  # 这里使用50个决策树
 
# 7.GBRT回归
from sklearn import ensemble
model_gradient_boosting_regressor = ensemble.GradientBoostingRegressor(n_estimators=100)  # 这里使用100个决策树
 
# 8.Bagging回归
from sklearn import ensemble
model_bagging_regressor = ensemble.BaggingRegressor()
 
# 9.ExtraTree极端随机数回归
from sklearn.tree import ExtraTreeRegressor
model_extra_tree_regressor = ExtraTreeRegressor()

 

 sklearn处理分类问题

import numpy as np
import pandas 
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import Lasso,LassoCV,LassoLarsCV
from sklearn.svm import SVC
from sklearn.svm import LinearSVC  #支持向量机
from sklearn.naive_bayes import MultinomialNB #朴素也贝斯
from sklearn.tree import DecisionTreeClassifier #决策树
from sklearn.ensemble import RandomForestClassifier #随机森林
from sklearn.ensemble import GradientBoostingClassifier #GBDT
from xgboost import XGBClassifier #xgboost


def modelReturn(model,name):
    
    model =  RandomForestClassifier();
    model.fit(x_train,y_train);
    predict = model.predict(x_test);
    trueNum = 0;
    for i in range(len(y_test)):
        if(y_test[i]==predict[i]):
            trueNum+=1;
    print(name,":",trueNum/len(y_test));
# modelReturn(model,"随机森林")
    
## 特征工程
# 读取数据
dataframe = pandas.read_csv("export.csv");
#获取 CVS中的值
dataset = dataframe.values;

#本身数据有53列  下标我0开始 取52列  53列是标签
X = dataset[:,0:53].astype(np.float);

Y =dataset[:,53];
x_train,x_test,y_train,y_test = train_test_split(X,Y);

# 1 laoss   
model = Lasso(alpha=0.005);  
#调节aplha 可以实现对拟合的程度
modelReturn(model,"laoss")

# 2 决策树  
model =  DecisionTreeClassifier();
modelReturn(model,"决策树")

# 3 随机森林 
model =RandomForestClassifier();
modelReturn(model,"随机森林")

# 4 朴素也贝斯 
model =  MultinomialNB();
modelReturn(model,"朴素也贝斯")

# 5 支持向量机  
model = LinearSVC();
modelReturn(model,"支持向量机")

# 6 SVM  
model = SVC()
modelReturn(model,"SVM")

# 7 KNN
model = KNeighborsClassifier(n_neighbors=11);
modelReturn(model,"KNN")

# 8 Logist
model =LogisticRegression();
modelReturn(model,"Logist")

# 线性回归
from sklearn import linear_model
linear = linear_model.LinearRegression()
linear.fit(x,y)
print ("linear‘s score: ",linear.score(x,y))
print ("w:",linear.coef_)       
print ("b:",linear.intercept_)  
print ("predict: ",linear.predict(test_vector))

# 9 xgboost 
model =XGBClassifier();
modelReturn(model,"xgboost")

# 10 GBDT 
model =GradientBoostingClassifier();
modelReturn(model,"GBDT")

"""
model.fit(x_train,y_train);

predict =model.predict(x_test);

trueNum =0;

print(predict)

for i  in range(len(y_test)):
    if ((abs(y_test[i])-abs(predict[i])< 0.5)):
        trueNum += 1;
        
        
print(trueNum/len(y_test));
"""

"""
#降到27个维度
pca = PCA(n_components=27);
xTrainPca = pca.fit_transform(x_train);
xTestPca = pca.fit_transform(x_test);


log =LogisticRegression();
log.fit(xTrainPca,y_train);

print("准确率:",log.score(xTestPca,y_test));
"""


"""
#降到50个维度
pca = PCA(n_components=50);

xTrainPca = pca.fit_transform(x_train);
xTestPca = pca.fit_transform(x_test);

knn = KNeighborsClassifier(n_neighbors=11);
knn.fit(xTrainPca,y_train);

print(knn.score(xTestPca,y_test))
"""