生工学院大二py实验报告2（sklearn）

```python

import tkinter 
import tkinter.messagebox
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt 
from sklearn import neighbors 
from sklearn.cluster import KMeans 
from sklearn.decomposition import PCA 
from sklearn.preprocessing import scale 
from sklearn.preprocessing import StandardScaler 
from sklearn import metrics
from mpl_toolkits.mplot3d import Axes3D

top = tkinter.Tk()
top.title("title名")
top.geometry("400x100+630+80")

def import_data():
    data = pd.read_csv("Seeds.csv") 
    tkinter.messagebox.showinfo("提示", "导入数据集'Seeds'成功！")
    return data

def classification():
    data = import_data()
    result = data[['A', 'P', 'C', 'LK', 'WK', 'A_Coef', 'LKG']]
    pd.plotting.scatter_matrix(result)
    plt.show()
    ##K近邻预测，KNeighborsClassifier为实现K近邻算法的一个类
    knn = neighbors.KNeighborsClassifier() # 模型初始化
    knn.fit(data[['A', 'P', 'C', 'LK', 'WK', 'A_Coef', 'LKG']], data['target']) #模型学习
    predict = knn.predict([[12.32, 10.35, 0.4865, 7.3274, 4.376, 1.569, 8.485]]) #模型预测
    print('预测类型为:', predict)
    tkinter.messagebox.showinfo('预测类型', "[12.32, 10.35, 0.4865, 7.3274, 4.376, 1.569, 8.485]的预测类型为{}".format(predict))# 预测结果展示
    return

#接口函数3
def PCA_Clustering():
    seed = import_data()
    X = seed.loc[:, ['A', 'P', 'C', 'LK', 'WK', 'A_Coef', 'LKG']].values
    y = seed['target'].values.tolist()
    pca = PCA(n_components=3) #pca降维
    X_scale = StandardScaler().fit_transform(X)
    X_reduce = StandardScaler().fit_transform(scale(X_scale))

model = KMeans(n_clusters=3) #模型初始化
    model.fit(X_reduce) #模型学习
    labels = model.labels_ #获取聚类标签
    print(labels)

#输出模型的准确度
    print('%.3f %.3f %.3f %.3f %.3f %.3f' % \
          (metrics.homogeneity_score(y, labels),
           metrics.completeness_score(y, labels),
           metrics.v_measure_score(y, labels),
           metrics.adjusted_rand_score(y, labels),
           metrics.adjusted_mutual_info_score(y, labels),
           metrics.silhouette_score(X_reduce, labels)
           ))

#绘制模型的分布图
    fig = plt.figure()
    ax = Axes3D(fig, auto_add_to_figure=False)
    fig.add_axes(ax)
    ax.scatter(X_reduce[:, 0], X_reduce[:, 1], X_reduce[:, 2],
               c=labels.astype(np.float64))
    tkinter.messagebox.showinfo("聚类结果","聚类结果如图所示(点击确定即可显示)")
    plt.show()
    return

A = tkinter.Button(top, text="搜集‘种子seed’数据", command=import_data) # 单击第一个按钮时采集一批专业数据
A.pack()
B = tkinter.Button(top, text="种子(seed)种类分类预测", command=classification) # 单击第二个按钮时进行分类或回归预测
B.pack()
C = tkinter.Button(top, text="种子seed数据降维和聚类", command=PCA_Clustering) # 单击第三个按钮时进行降维和聚类
C.pack()
top.mainloop()