AdaBoost_Adaboostregression_adaboost回归_adaboost-svm_adaboost_

# -*- coding: utf-8 -*- """ Created on Thu May 9 20:54:16 2019 @author: Liu Shijian """ import pandas as pd import numpy as np import itertools import matplotlib as mpl import matplotlib.pyplot as plt import pandas as p # importing necessary libraries import pandas as pd #from keras.datasets import boston_housing from sklearn.tree import DecisionTreeRegressor from sklearn.ensemble import AdaBoostRegressor from sklearn.ensemble import RandomForestRegressor from sklearn.linear_model import LinearRegression, Lasso, LassoCV,Ridge,RidgeCV,LarsCV,Lars,ElasticNetCV,ElasticNet from sklearn.cross_decomposition import PLSRegression import warnings warnings.filterwarnings("ignore") # Create the dataset rng = np.random.RandomState(1) #X = np.linspace(0, 6, 100)[:, np.newaxis] #y = np.sin(X).ravel() + np.sin(6 * X).ravel() + rng.normal(0, 0.1, X.shape[0]) #(X_train,y_train),(X_test,y_test)=boston_housing.load_data(path='boston_housing.npz') #mean = X_train.mean(axis = 0) #std = X_train.std(axis=0) #X_train = (X_train - mean) / std #X_test = (X_test - mean) / std # Load data data = pd.read_csv("CO2.csv") #print(data.head()) # Train-test split y_train = np.array(data[data.train == "T"]['CO2']) y_test = np.array(data[data.train == "F"]['CO2']) X_train = np.array(data[data.train == "T"].drop(['CO2', 'train'], axis=1)) X_test = np.array(data[data.train == "F"].drop(['CO2', 'train'], axis=1)) # Fit regression model #套索# #regr_1 = LassoCV(normalize=True, alphas=np.logspace(-10, 10, 400)) #regr_1.fit(X_train,y_train) #regr_2 = AdaBoostRegressor(Lasso(normalize=True), # n_estimators=300, random_state=rng) #regr_2.fit(X_train,y_train) #y_1 = regr_1.predict(X_test) #y_2 = regr_2.predict(X_test) #print(y_1) #print(y_2) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_1))) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_2))) #t = np.arange(len(X_test)) #mpl.rcParams['font.sans-serif'] = [u'simHei'] #mpl.rcParams['axes.unicode_minus'] = False #plt.figure(facecolor='w') #plt.plot(t, y_test, 'r-', linewidth=2, label=u'Real data') #plt.plot(t, y_1 , 'g-', linewidth=2, label=u'LASSO Forecast data') #plt.plot(t, y_2 , 'blue', linewidth=2, label=u'Adaboost-LASSO Forecast data') #plt.title(u'carbon emissions forecast-Adaboost-LASSO regression model fitting', fontsize=18) #plt.legend(loc='upper left') #plt.grid() #plt.show() #线性回归# #regr_1 = LinearRegression(normalize=True) #regr_1.fit(X_train,y_train) #regr_2 = AdaBoostRegressor(LinearRegression(normalize=True), # n_estimators=300, random_state=rng) #regr_2.fit(X_train,y_train) #y_1 = regr_1.predict(X_test) #y_2 = regr_2.predict(X_test) #print(y_1) #print(y_2) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_1))) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_2))) #t = np.arange(len(X_test)) #mpl.rcParams['font.sans-serif'] = [u'simHei'] #mpl.rcParams['axes.unicode_minus'] = False #plt.figure(facecolor='w') #plt.plot(t, y_test, 'r-', linewidth=2, label=u'Real data') #plt.plot(t, y_1 , 'g-', linewidth=2, label=u' LinearRegression Forecast data') #plt.plot(t, y_2 , 'blue', linewidth=2, label=u'Adaboost- LinearRegression Forecast data') #plt.title(u'carbon emissions forecast-Adaboost- LinearRegression model fitting', fontsize=18) #plt.legend(loc='upper left') #plt.grid() #plt.show() #岭回归# #regr_1 = RidgeCV(normalize=True, alphas=np.logspace(-10, 10,400)) #regr_1.fit(X_train,y_train) #regr_2 = AdaBoostRegressor(Ridge(normalize=True), # n_estimators=300, random_state=rng) #regr_2.fit(X_train,y_train) #y_1 = regr_1.predict(X_test) #y_2 = regr_2.predict(X_test) #print(y_1) #print(y_2) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_1))) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_2))) #t = np.arange(len(X_test)) #mpl.rcParams['font.sans-serif'] = [u'simHei'] #mpl.rcParams['axes.unicode_minus'] = False #plt.figure(facecolor='w') #plt.plot(t, y_test, 'r-', linewidth=2, label=u'Real data') #plt.plot(t, y_1 , 'g-', linewidth=2, label=u' RidgeRegression Forecast data') #plt.plot(t, y_2 , 'blue', linewidth=2, label=u'Adaboost- RidgeRegression Forecast data') #plt.title(u'carbon emissions forecast-Adaboost- RidgeRegression model fitting', fontsize=18) #plt.legend(loc='upper left') #plt.grid() #plt.show() #弹性网# #regr_1 = ElasticNetCV(normalize=True, alphas=np.logspace(-10, 10, 400),l1_ratio=np.linspace(0, 1, 100)) #regr_1.fit(X_train,y_train) #regr_2 = AdaBoostRegressor( ElasticNet(normalize=True),n_estimators=300, random_state=rng) #regr_2.fit(X_train,y_train) #y_1 = regr_1.predict(X_test) #y_2 = regr_2.predict(X_test) #print(y_1) #print(y_2) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_1))) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_2))) #t = np.arange(len(X_test)) #mpl.rcParams['font.sans-serif'] = [u'simHei'] #mpl.rcParams['axes.unicode_minus'] = False #plt.figure(facecolor='w') #plt.plot(t, y_test, 'r-', linewidth=2, label=u'Real data') #plt.plot(t, y_1 , 'g-', linewidth=2, label=u' ElasticNetRegression Forecast data') #plt.plot(t, y_2 , 'blue', linewidth=2, label=u'Adaboost- ElasticNetRegression Forecast data') #plt.title(u'carbon emissions forecast-Adaboost- ElasticNetRegression model fitting', fontsize=18) #plt.legend(loc='upper left') #plt.grid() #plt.show() # 最小角度回归# #regr_1 =LarsCV(normalize=True) #regr_1.fit(X_train,y_train) #regr_2 = AdaBoostRegressor(Lars(normalize=True), # n_estimators=280, random_state=rng) #regr_2.fit(X_train,y_train) #y_1 = regr_1.predict(X_test) #y_2 = regr_2.predict(X_test) #print(y_1) #print(y_2) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_1))) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_2))) #t = np.arange(len(X_test)) #mpl.rcParams['font.sans-serif'] = [u'simHei'] #mpl.rcParams['axes.unicode_minus'] = False #plt.figure(facecolor='w') #plt.plot(t, y_test, 'r-', linewidth=2, label=u'Real data') #plt.plot(t, y_1 , 'g-', linewidth=2, label=u' LarsRegression Forecast data') #plt.plot(t, y_2 , 'blue', linewidth=2, label=u'Adaboost- LarsRegression Forecast data') #plt.title(u'carbon emissions forecast-Adaboost-LarsRegression model fitting', fontsize=18) #plt.legend(loc='upper left') #plt.grid() #plt.show() #偏最小二乘回归# #pls_model_setup = PLSRegression(scale=True) #param_grid = {'n_components': range(1, 19)} #search = GridSearchCV(pls_model_setup, param_grid) #regr_1 =PLSRegression(scale=True) #regr_2 = AdaBoostRegressor(PLSRegression(scale=True), n_estimators=6, random_state=rng) #regr_1=search.fit(X_train, y_train) #regr_2=search.fit(X_train, y_train) # ## Predict #y_1 = regr_1.predict(X_test) #y_2 = regr_2.predict(X_test) #print(y_1) #print(y_2) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_1))) #print("Mean Squared Error: %.4f" # % np.mean(np.abs(y_test - y_2))) #t = np.arange(len(X_test)) #mpl.rcParams['font.sans-serif'] = [u'simHei'] #mpl.rcParams['axes.unicode_minus'] = False #plt.figure(facecolor='w') #plt.plot(t, y_test, 'r-', linewidth=2, label=u'Real data') #plt.plot(t, y_1 , 'g-', linewidth=2, label=u' LarsRegression Forecast data') #plt.plot(t, y_2 , 'blue', linewidth=2, label=u'Adaboost- LarsRegression Forecast data') #plt.title(u'carbon emissions forecast-Adaboost-LarsRegression model fitting', fontsize=18) #plt.legend(loc='upper left') #plt.grid() #plt.show() # Evaluate and visualize the fit # Plot the results #plt.figure() #plt.scatter(np.linspace(1, 3, 3), yt, c="k", label="training samples") #plt.plot(np.linspace(1, 3, 3), y_1, c="g", label="n_estimators=1", linewidth=2) #plt.