class PCR:
def __init__(self, X, Y):
self.X = X
self.Y = Y
# 对X进行SVD分解，返回分解后的矩阵，可以使用compare，和cum来确定独立分组数目
def confirmPCs(self):
self.pca = PCA(self.X)
compare, cum = self.pca.SVDdecompose()
return compare, cum
# PCs为独立分组数
def fit(self, PCs):
T, P = self.pca.PCAdecompose(PCs)
self.P = P
self.T = T
self.mlr = MLR(T, self.Y, False)
self.mlr.fit()
self.A = self.mlr.getCoef()
def predict(self, Xnew):
T = np.dot(Xnew, self.P)
ans = self.mlr.predict(T)
return ans
def fTest(self, arfa):
return self.mlr.Ftest(arfa)
class PCR:
def __init__(self, X, Y):
self.X = X
self.Y = Y
def confirmPCs(self):
self.pca = PCA(self.X)
compare = self.pca.SVDdecompose()
return compare
def fit(self, PCs):
T, P = self.pca.PCAdecompose(PCs)
print('T=', T)
self.P = P
oneCol = np.ones(T.shape[0])
T = np.c_[oneCol, T]
self.mlr = MLR(T, self.Y)
self.mlr.fit()
self.A = self.mlr.getCoef()
def predict(self, Xnew):
T = np.dot(Xnew, self.P)
oneCol = np.ones(T.shape[0])
T = np.c_[oneCol, T]
ans = self.mlr.predict(T)
return ans
def fTest(self, arfa):
return self.mlr.Ftest(arfa)
def model(self, k):
pca = PCA(self.X)
U, S, V, compare = pca.SVDdecompose() # 不可去，会用到计算得到的结果
# 得到得分矩阵和载荷矩阵
T, P = pca.PCAdecompose(k)
#print("得分矩阵T: ", T)
#print("载荷矩阵P: ", P)
mlr = MLR(T, self.Y)
mlr.modelling()
self.A = np.dot(P, mlr.A)
def computePCs(self):
# 确定主成分
Percentage = 0.95
pca = PCA(self.X)
U, S, V, compare = pca.SVDdecompose()
self.kcount = compare.__len__() # 记录主成分最大数
comSum = 0
cSum = sum(compare)
for i in compare:
comSum += i
if comSum / cSum >= Percentage:
PCs = int(np.where(compare == i)[0][-1]) + 1
#print("主成分数k: ", PCs)
self.k = PCs # 记录符合条件的最佳主成分数
break
import numpy as np import matplotlib.pyplot as plt A = np.loadtxt(r".\wheat_train_PCA_X.txt") B = np.loadtxt(r".\wheat_train_PCA_Y.txt") from PCA import PCA aver = A.mean(axis=0) std = A.std(axis=0) X = (A - aver) / std pca = PCA(X) print(pca.SVDdecompose()) T, P = pca.PCAdecompose(6) cls1 = B == 1.0 cls2 = B != 1.0 plt.subplot(1, 2, 1) plt.plot(T[cls1, 0], T[cls1, 1], 'ro') plt.plot(T[cls2, 0], T[cls2, 1], 'b^') #PLSR from sklearn.cross_decomposition import PLSRegression pls = PLSRegression(n_components=3, scale=True) pls.fit(A, B) T = pls.x_scores_ plt.subplot(1, 2, 2) plt.plot(T[cls1, 0], T[cls1, 1], 'ro') plt.plot(T[cls2, 0], T[cls2, 1], 'b^')
# %%
from sklearn.feature_selection import SelectPercentile, f_classif, mutual_info_classif
import numpy as np
X1 = X = np.loadtxt(
r"C:\Users\51770\Desktop\pythonModeling\wheat_train_PCA_X.txt")
y = np.loadtxt(r"C:\Users\51770\Desktop\pythonModeling\wheat_train_PCA_Y.txt")
avg = X.mean(axis=0)
std = X.std(axis=0)
X = (X - avg) / std
# selector2= SelectPercentile(f_classif, 30)
selector2 = SelectPercentile(mutual_info_classif, 30)
Xnew = selector2.fit_transform(X, y) # 用选择的变量重构矩阵
print(selector2.pvalues_)
print(selector2.get_support())
indx = np.argwhere(selector2.get_support())[:, 0]
print(indx)
from PCA import PCA
pca = PCA(Xnew)
ans = pca.SVDdecompose()
print(ans[1])
pca.plotScore(y)
# %%
