第五次课后作业.pptxVIP

第五次课后作业; Input variables (based on physicochemical tests) Output variable (based on sensory data): 1 - fixed acidity 12 - quality (score between 0 and 10) 2 - volatile acidity 3 - citric acid 4 - residual sugar 5 - chlorides 6 - free sulfur dioxide 7 - total sulfur dioxide 8 - density 9 - pH 10 - sulphates 11 - alcohol ;import numpy as np import matplotlib as mpl import matplotlib.pyplot as plt import pandas as pd import warnings import sklearn from sklearn.linear_model import LinearRegression, LassoCV, RidgeCV, ElasticNetCV from sklearn.preprocessing import PolynomialFeatures from sklearn.pipeline import Pipeline from sklearn.linear_model.coordinate_descent import ConvergenceWarning from sklearn.cross_validation import train_test_split;# 异常数据处理 new_df = df.replace(?, np.nan) datas = new_df.dropna(how = any) # 只要有列为空，就进行删除操作 X = datas[names] Y = datas[quality];plt.figure(figsize=(16,8), facecolor=w) titles = u线性回归预测, uRidge回归预测, uLasso回归预测, uElasticNet预测 # 将数据分为训练数据和测试数据 X_train,X_test,Y_train,Y_test = train_test_split(X, Y, test_size=0.01, random_state=0) ln_x_test = range(len(X_test)) # 给定阶以及颜色 d_pool = np.arange(1,4,1) # 1 2 3 阶 m = len(d_pool) # clrs = [] # 颜色 # for c in np.linspace(5570560, 255, m): # clrs.append(#%06x % c) clrs = [black, blue, green] # 颜色 ;for t in range(4): plt.subplot(2, 2, t + 1) model = models[t] plt.plot(ln_x_test, Y_test, c=r, lw=2, alpha=0.75, zorder=10, label=u真实值) for i,d in enumerate(d_pool): # 设置参数 model.set_params(Poly__degree=d) # 模型训练 model.fit(X_train, Y_train) # 模型预测及计算R^2 Y_pre = model.predict(X_test) R = model.score(X_train, Y_train) # 输出信息 lin = model.get_params(Linear)[Linear] output = u%s:%d阶, 截距:%d, 系数: % (titles[t], d, lin.intercept_) print(output, lin.coef_) # 图形展示 plt.plot(ln_x_te