进阶任务四

【Task4 Linear Regression(多变量)】(2天)

1. 波士顿房产数据(完整数据)
   
2. 实现多变量(手写代码)
   import numpy as np
   x=[[1,10,1],[1,20,1],[1,30,1],[1,30,2],[1,70,3],[1,70,2]]
   x=np.mat(x)
   print(x)
   print(x[1])
   print(x.T[1])#取单个x特征
   y=[0.8,1.2,2.2,2.5,5.5,5.2]
   h=lambda th0,th1,th2,x:th0+th1x[1]+th2x[2]
   print(h(1,1,2,[1,10,1]))
   y=np.mat(y).T#y转换为列向量
   th=np.mat([0.1,0.2,0.3]).T#thta转为列向量
   y_th0=lambda th,x,y:np.sum(xth-y)
   print(y_th0(th,x,y))
   y_th1=lambda th,x,y:np.sum(x.T[1](xth-y))
   print(y_th1(th,x,y))
   y_th2=lambda th,x,y:np.sum(x.T[2](xth-y))
   y_th2(th,x,y)
   lr=0.0001
   for _ in range(100000):
   th0=float(th[0])-lry_th0(th,x,y)
   th1=float(th[1])-lry_th1(th,x,y)
   th2=float(th[2])-lry_th2(th,x,y)
   th=np.mat([[th0],[th1],[th2]])
   print(th)
   th=(x.Tx).Ix.T*y
   th
3. 数据标准化(手写代码)
   ss=StandardScaler()
   ss.fit(x_train.y_train)
4. 网格搜索调参
   5 from sklearn.linear_model import LinearRegression对比
   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.model_selection import train_test_split
   from sklearn.preprocessing import StandardScaler
   from sklearn.model_selection import GridSearchCV
   from sklearn import metrics
   path = ‘E:\AI10\housing.data’
   fd = pd.read_csv(path,header=None,names=names)
   fd.head()
   x, y = np.split(data, (13,), axis=1)
   print (x[0:5])
   y = y.ravel()
   models = [
   Pipeline([
   (‘ss’, StandardScaler()),
   (‘poly’, PolynomialFeatures()),
   (‘linear’, RidgeCV(alphas=np.logspace(-3,1,20)))
   ])
   ]
   parameters = {
   “linear__fit_intercept”: [True, False]
   }
   model = GridSearchCV(models[t], param_grid=parameters,cv=5, n_jobs=1)
   model.fit(x_train, y_train)
   print ("%s算法:最优参数:" % titles[t],model.best_params_)
   print ("%s算法:R值=%.3f" % (titles[t], model.best_score_))