PCA-ANN-小麦分类

from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
import numpy 
import pandas as pd
import numpy as np

fp=open('seeds_dataset.txt','r')
ls=[]
for line in fp:
    line=line.strip('\n')   #将\n去掉
    ls.append(line.split('\t'))   #将空格作为分隔符将一个字符切割成一个字符数组
fp.close()
ls=numpy.array(ls,dtype=float)   #将其转换成numpy的数组，并定义数据类型为float
print(ls)

# 将文件转为DataFrame表格
ls_pd = pd.DataFrame(ls)

from sklearn.utils import shuffle
ls_pd = shuffle(ls_pd)

y = ls_pd.loc[:,7]

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
data_std = sc.fit_transform(ls_pd.loc[:,1:6])

def plot_PCA(*data):
    ''' 绘制经过 KernelPCA 降维到二维之后的样本点'''
    X,y=data
    kernels=['linear','poly','rbf','sigmoid']
    fig=plt.figure()
    colors=((1,0,0),(0,1,0),(0,0,1),(0.5,0.5,0),(0,0.5,0.5),(0.5,0,0.5),
        (0.4,0.6,0),(0.6,0.4,0),(0,0.6,0.4),(0.5,0.3,0.2),)# 颜色集合，不同标记的样本染不同的颜色
    kpca= PCA(n_components=2)
    kpca.fit(X)
    X_r=kpca.transform(X)# 原始数据集转换到二维
    for label ,color in zip( np.unique(y),colors):
        position=y==label
        plt.scatter(X_r[position,0],X_r[position,1],label="target= %d"%label,
        color=color)
    plt.suptitle("PCA")
    plt.show()
    return X_r

reduced_x = plot_PCA(data_std,y)

y_onehot = list()
for value in y:
    letter = [0 for _ in range(3)]
    letter[int(value)-1] = 1
    y_onehot.append(letter)
print(y_onehot)

from sklearn.model_selection import train_test_split
x_train, x_test = train_test_split(reduced_x, test_size=0.2, shuffle = False)
y_train, y_test = train_test_split(y, test_size=0.2, shuffle = False)
y_train_onehot, y_test_onehot = train_test_split(y_onehot, test_size=0.2, shuffle = False)
y_onehot = np.array(y_onehot)
y_train_onehot, y_test_onehot = train_test_split(y_onehot, test_size=0.2, shuffle = False)

from tensorflow import keras

model = keras.Sequential([
        keras.layers.Dense(500,activation='relu',input_shape=[2]),#输入特征数目为4
        keras.layers.Dense(500,activation='relu'),
        keras.layers.Dense(250,activation='relu'),
        keras.layers.Dense(250,activation='relu'),
        keras.layers.Dense(3, activation='softmax')])#输出的类别为3个，所以输出层3个节点

# 编译模型,定义损失函数loss，采用的优化器optimizer为Adam
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.fit(x_train,y_train_onehot,batch_size = 32,epochs=20)#训练1000个批次，每个批次数据量为126

y_pre=model.predict(x_test).argmax(axis=1)#开始预测，axis=1表示返回每行中数值（表示每个类别的概率）最大的下标，就是对应的标签

y_pre = y_pre + 1

import  numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import accuracy_score, recall_score
acu = accuracy_score(y_test, y_pre)  # 准确率
recall = recall_score(y_test, y_pre, average="macro")  # 召回率

from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
import numpy as np
def plot_decision_regions(X, y, classifier,test_idx = None, resolution=0.02):
    #setup marker generator and colormap
    markers = ('s','x','o','^','v')
    colors = ('red','blue','lightgreen','gray','cyan')
    cmap = ListedColormap(colors[: len(np.unique(y))])
    # plot the decision surface
    x1_min, x1_max = X[:,0].min() -1, X[:,0].max()+1
    x2_min, x2_max = X[:,1].min() -1, X[:,1].max()+1
    # X[:,k] 冒号左边表示行范围，读取所有行，冒号右边表示列范围，读取第K列
    xx1, xx2 = np.meshgrid(np.arange(x1_min,x1_max,resolution),
                           np.arange(x2_min,x2_max,resolution))
    #arange(start,end,step) 返回一个一维数组
    #meshgrid(x,y)产生一个以x为行，y为列的矩阵
    #xx1是一个(305*235)大小的矩阵 xx1.ravel()是将所有的行放在一个行里面的长度71675的一维数组
    #xx2同理
    Z=classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T).argmax(axis=1) + 1
    #np.array([xx1.ravel(), xx2.ravel()]) 生成了一个 (2*71675)的矩阵
    # xx1.ravel() = (1,71675)
    #xx1.shape = (305,205) 将Z重新调整为(305,205)的格式
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())
    # plot class samples
    print(np.unique(y))
    # idx = 0,1 cl = -1 1
    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X[y==cl, 0], y=X[y==cl, 1],
                    alpha=0.8, c=cmap(idx),
                    marker = markers[idx],label = cl)
    #highlight test samples   
    #增加的模块
    if test_idx:
        X_test, y_test = X[test_idx:,:],y[test_idx:]
        plt.scatter(X_test[:,0],X_test[:,1],c='',edgecolors='0',
                    alpha=1.0, linewidths=1,marker='o',
                    s=55, label='test set')

plot_decision_regions(reduced_x, y,
                      classifier=model, test_idx=167)
plt.legend(loc='upper left')
plt.tight_layout()   #紧凑显示图片，居中显示；避免出现叠影
plt.show()