import numpy as np import matplotlib.pyplot as plt from math import pi from sklearn.cluster import KMeans k = 5 #数据个数 plot_data = kmodel.cluster_centers_ color = ['b', 'g', 'r', 'c', 'y'] #指定颜色 angles = np.linspace(0, 2*np.pi, k, endpoint=False) plot_data = np.concatenate((plot_data, plot_data[:,[0]]), axis=1) # 闭合 features = np.concatenate((features, features[0:1])) angles = np.linspace(0, 2 * np.pi, len(features), endpoint=False) angles = angles.astype(np.float16) fig=plt.figure(figsize=(10, 8)) ax = fig.add_subplot(111, polar=True) center_num = r.values feature = ["入会时间", "飞行次数", "平均每公里票价", "总里程", "时间间隔差值", "平均折扣率"] N =len(feature) for i, v in enumerate(center_num): # 设置雷达图的角度，用于平分切开一个圆面 angles=np.linspace(0, 2*np.pi, N, endpoint=False) # 为了使雷达图一圈封闭起来，需要下面的步骤 center = np.concatenate((v[:-1],[v[0]])) angles=np.concatenate((angles,[angles[0]])) # 绘制折线图 ax.plot(angles, center, 'o-', linewidth=2, label = "第%d簇人群,%d人"% (i+1,v[-1])) # 填充颜色 ax.fill(angles, center, alpha=0.25) # 添加每个特征的标签 # 设置雷达图的范围 ax.set_ylim(min-0.1, max+0.1) # 添加标题 plt.title('客户群特征分析图', fontsize=20) # 添加网格线 ax.grid(True) # 设置图例 plt.legend(loc='upper right', bbox_to_anchor=(1.3,1.0),ncol=1,fancybox=True,shadow=True) # 添加标题和图例 plt.title('Feature Radar Chart') plt.legend(loc='best') # 显示图形 plt.show()代码纠错

python 3.74 运行import numpy as np 报错lib\site-packages\numpy\init.py

import numpy as np import os,sys #获取当前文件夹，并根据文件名 def path(fileName): p=sys.path[0]+'\\'+fileName return p #读文件 def readFile(fileName): f=open(path(fileName)) str=f.read() ...

import numpy as np(2).py

np.mean np.cov numpy.corrcoef pyplot.scatter pyplot.contour函数

np.mean() 搬运 :https://blog.csdn.net/lilong117194/article/details/78397329?depth_1-utm_source=distribute.pc_relevant.none-task&utm_source=distribute.pc_relevant.none-task >>> a = np.array([[1, 2], [3...

import numpy as np import matplotlib.pyplot as plt from sklearn.preprocessing import StandardScaler from sklearn.decomposition import PCA from sklearn.cluster import KMeans from scipy.spatial import Voronoi, voronoi_plot_2d # 生成示例数据 data = df.iloc[:,1:15] # 标准化处理 scaler = StandardScaler() data_scaled = scaler.fit_transform(data) # 主成分分析 pca = PCA(n_components=5) data_pca = pca.fit_transform(data_scaled) # 聚类分析 kmeans = KMeans(n_clusters=3) kmeans.fit(data_pca) labels = kmeans.labels_ centers = kmeans.cluster_centers_ # 绘制Voronoi图 vor = Voronoi(centers) voronoi_plot_2d(vor) # 绘制样本点 plt.scatter(data_pca[:, 0], data_pca[:, 1], c=labels) # 设置坐标轴标签和标题 plt.xlabel('PC1') plt.ylabel('PC2') plt.title('Voronoi Diagram') # 显示图形 plt.show()

import matplotlib.pyplot as plt from sklearn.preprocessing import StandardScaler from sklearn.decomposition import PCA from sklearn.cluster import KMeans from scipy.spatial import Voronoi, voronoi_...

如何将该图改为折现簇状图import numpy as np import matplotlib.pyplot as plt from sklearn.cluster import KMeans# 生成随机数据 X = np.random.rand(100, 2)# 设置聚类的数量为3 kmeans = KMeans(n_clusters=3, random_state=0).fit(X)# 统计每个类别的数量 labels, counts = np.unique(kmeans.labels_, return_counts=True)# 绘制簇状图 plt.plot(labels, counts, align='center') plt.xticks(labels, ['Cluster {}'.format(i) for i in range(len(labels))]) plt.ylabel('Number of samples') plt.title('KMeans Clustering') plt.show()

import matplotlib.pyplot as plt from sklearn.cluster import KMeans # 生成随机数据 X = np.random.rand(100, 2) # 设置聚类的数量为3 kmeans = KMeans(n_clusters=3, random_state=0).fit(X) # 统计每个类别...

import numpy as np import matplotlib.pyplot as plt from sklearn.datasets import load_iris from sklearn.cluster import KMeans # 加载鸢尾花数据集 iris = load_iris() X = iris.data[:, :2] # 取前两个特征作为萼片长和宽 # 进行Kmeans聚类划分 kmeans = KMeans(n_clusters=3, random_state=0).fit(X) labels = kmeans.labels_ # 绘制散点图 plt.scatter(X[labels == 0, 0], X[labels == 0, 1], c='red', label='Cluster 1') plt.scatter(X[labels == 1, 0], X[labels == 1, 1], c='blue', label='Cluster 2') plt.scatter(X[labels == 2, 0], X[labels == 2, 1], c='green', label='Cluster 3') plt.xlabel('Sepal Length') plt.ylabel('Sepal Width') plt.title('Kmeans Clustering of Iris Dataset') plt.legend() plt.show()改进此代码

import matplotlib.pyplot as plt from sklearn.datasets import load_iris from sklearn.cluster import KMeans from sklearn.decomposition import PCA # 加载鸢尾花数据集 iris = load_iris() X = iris....

from sklearn.cluster import KMeans from sklearn.metrics import silhouette_score import numpy as np import seaborn as sns import matplotlib.pyplot as plt # 读取数据 data = np.loadtxt(r"D:\数学建模\重航数学建模校赛\附件1（前50行）.csv", encoding='gbk') # 定义肘部法函数 def find_best_k(data): SSE = [] for k in range(1, 11): estimator = KMeans(n_clusters=k) estimator.fit(data) SSE.append(estimator.inertia_) X = range(1, 11) plt.xlabel('k') plt.ylabel('SSE') plt.plot(X, SSE, 'o-') plt.show() # 计算轮廓系数 def calculate_silhouette_score(data, k): estimator = KMeans(n_clusters=k) estimator.fit(data) score = silhouette_score(data, estimator.labels_) return score # 调用函数 find_best_k(data) score = calculate_silhouette_score(data, 3) print(score)代码改进

import matplotlib.pyplot as plt # 读取数据 data = np.loadtxt(r"D:\数学建模\重航数学建模校赛\附件1（前50行）.csv", encoding='gbk') # 定义肘部法函数 def find_best_k(data): SSE = [] for k in ...

import time import numpy as np import matplotlib.pyplot as plt from sklearn.cluster import MiniBatchKMeans, KMeans from sklearn.metrics.pairwise import pairwise_distances_argmin from sklearn.datasets import make_blobs # Generate sample data np.random.seed(0) batch_size = 45 centers = [[1, 1], [-1, -1], [1, -1]] n_clusters = len(centers) X, labels_true = make_blobs(n_samples=3000, centers=centers, cluster_std=0.7) # Compute clustering with Means k_means = KMeans(init='k-means++', n_clusters=3, n_init=10) t0 = time.time() k_means.fit(X) t_batch = time.time() - t0 # Compute clustering with MiniBatchKMeans mbk = MiniBatchKMeans(init='k-means++', n_clusters=3, batch_size=batch_size, n_init=10, max_no_improvement=10, verbose=0) t0 = time.time() mbk.fit(X) t_mini_batch = time.time() - t0 # Plot result fig = plt.figure(figsize=(8, 3)) fig.subplots_adjust(left=0.02, right=0.98, bottom=0.05, top=0.9) colors = ['#4EACC5', '#FF9C34', '#4E9A06'] # We want to have the same colors for the same cluster from the # MiniBatchKMeans and the KMeans algorithm. Let's pair the cluster centers per # closest one. k_means_cluster_centers = k_means.cluster_centers_ order = pairwise_distances_argmin(k_means.cluster_centers_, mbk.cluster_centers_) mbk_means_cluster_centers = mbk.cluster_centers_[order] k_means_labels = pairwise_distances_argmin(X, k_means_cluster_centers) mbk_means_labels = pairwise_distances_argmin(X, mbk_means_cluster_centers) # KMeans for k, col in zip(range(n_clusters), colors): my_members = k_means_labels == k cluster_center = k_means_cluster_centers[k] plt.plot(X[my_members, 0], X[my_members, 1], 'w', markerfacecolor=col, marker='.') plt.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col, markeredgecolor='k', markersize=6) plt.title('KMeans') plt.xticks(()) plt.yticks(()) plt.show() 这段代码每一句在干什么

import matplotlib.pyplot as plt from sklearn.cluster import MiniBatchKMeans, KMeans from sklearn.metrics.pairwise import pairwise_distances_argmin from sklearn.datasets import make_blobs 2. 生成...

import numpy as np import pandas as pd X=pd.read_excel(r"C:\Users\Lenovo\Desktop\3.xlsx",header=None) #均方值规范化 from sklearn.preprocessing import StandardScaler scaler = StandardScaler() X=scaler.fit_transform(X) #给类别分类 from sklearn.cluster import KMeans model = KMeans(n_clusters = 2, random_state=0, max_iter = 500) #分类数，随机种子，最大迭代数 model.fit(X) c=model.labels_ c=c.reshape((31,1)) X=np.hstack((X,c)) x0=X[X[:,10]==0,0] y0=X[X[:,10]==0,1] x1=X[X[:,10]==1,0] y1=X[X[:,10]==1,1] import matplotlib.pyplot as plt plt.plot(x0,y0,'r*') plt.plot(x1,y1,'bo') plt.show()

这段代码是用 Python 对数据进行聚类分析的，主要使用了 sklearn 库中的 KMeans 模型和 matplotlib 库进行可视化。首先，使用 pandas 库中的 read_excel 函数读取一个 Excel 文件，然后使用 StandardScaler 类进行...

import numpy as np import matplotlib.pyplot as plt from sklearn.cluster import KMeans path_file = r"C:\Users\Lenovo\Desktop\TESTDATA.TXT" def loadFile(path_file): dataList=[] recordMat = loadFile(path_file) k = 4 X = np.array(recordMat) plt.figure() plt.axis([np.min(X[:,0])-1, np.max(X[:,0])+1, np.min(X[:,1])-1, np.max(X[:,1])+1]) plt.grid(True) colors = ['r', 'g', 'b','c'] markers = ['o', 's', 'D', '+'] kmeans_model = KMeans(n_clusters=k, init='k-means++') kmeans_model.fit(X) for i, l in enumerate(kmeans_model.labels_): plt.plot(X[i][0], X[i][1], color=colors[l],marker=markers[l],ls='None') plt.title('K = %s' %(k)) plt.show()报错怎么修改？

from sklearn.cluster import KMeans path_file = r"C:\Users\Lenovo\Desktop\TESTDATA.TXT" def loadFile(path_file): dataList = [] # 在这里编写读取文件的代码，并将数据存储在dataList中 return dataList ...

import numpy as np from sklearn.cluster import KMeans import collections from sklearn import metrics import matplotlib.pyplot as plt plt.rcParams['font.family'] = 'SimHei' # 正常显示中文 # 参数寻优 inertia = [] silhouettteScore = [] # 计算聚类数目为2至9时的轮廓系数值和簇内误差平方和 for i in range(2, 10): km = KMeans(n_clusters=i, random_state=12).fit(ScoreModel) y_pred = km.predict(ScoreModel) center_ = km.cluster_centers_ score = metrics.silhouette_score(ScoreModel, km.labels_) silhouettteScore.append([i, score]) inertia.append([i, km.inertia_]) # 绘制轮廓系数图 silhouettteScore = np.array(silhouettteScore) plt.plot(silhouettteScore[: , 0], silhouettteScore[: , 1]) plt.title('轮廓系数值 - 聚类数目') plt.show() #绘制簇内误差平方和图 inertia = np.array(inertia) plt.plot(inertia[: , 0], inertia[: , 1]) plt.title('簇内误差平方和 - 聚类数目') plt.show()

这段代码使用了 Python 中的 sklearn 库中的 KMeans 算法，对 ScoreModel 进行聚类分析，并绘制了聚类数目与轮廓系数值、簇内误差平方和之间的关系图。首先设置了中文字体，以便在图表中正常显示中文。然后定义了...

import numpy as np from sklearn.cluster import KMeans # 定义食材-指标矩阵 matrix_xiang = np.array([[...], # 第1行数据 [...], # 第2行数据 ... [...]]) # 第27行数据 # 创建K均值聚类模型 kmeans = KMeans(n_clusters=3) # 假设要将食材分为3个簇 # 进行聚类 kmeans.fit(matrix_xiang) # 获取每个食材所属的簇标签 labels = kmeans.labels_ # 打印每个食材的簇标签 for i, label in enumerate(labels): print(f"食材{i+1}的簇标签为：{label}") 请在这段代码中增加肘部法则以及轮廓系数的代码以确定聚类数量

import matplotlib.pyplot as plt from sklearn.cluster import KMeans from sklearn.metrics import silhouette_score # 定义食材-指标矩阵 matrix_xiang = np.array([[...], # 第1行数据 [...], # 第2行数据 .....

%matplotlib inline from sklearn.cluster import KMeans#导入sklearn中kmeans聚类包 import numpy as np from matplotlib import pyplot as plt import sklearn.datasets as datasets iris=datasets.load_iris() #1 查看iris包括哪些信息，比如数据，label等。将这些信息打印出来； #2 信息中是否已包含每一样本所属的类？没聚类之彰，是否可以打印iris每一个label的样本个数; #3 画出第一类label的前两列的散点图； #4 用KMeans对数据进行聚类； #5 打印各聚类中心； #6 打印聚类后几个点的类标号； #7 打印迭代次数； #8 说明以下代码的作用： data=iris.data k=[] for i in range(1,20): km=KMeans(n_clusters=i,init='random',n_init=10,max_iter=200,tol=1e-04,random_state=0) km.fit(data) # inertia_:Sum of squared distances of samples to their closest cluster center. k.append(km.inertia_) plt.plot(range(1,20),k,marker='o') plt.xlabel('Number of cluster') plt.ylabel('Distorton') #9 使用BIRCH算法对iris进行了聚类,将同一类中的前两维用相同的颜色画出来。 #10 使用DBSCAN算法对iris进行了聚类,将同一类中的前两维用相同的颜色画出来。

from sklearn.cluster import Birch birch = Birch(n_clusters=3) birch.fit(iris.data) plt.scatter(iris.data[birch.labels_==0, 0], iris.data[birch.labels_==0, 1], c='blue') plt.scatter(iris.data[birch....

对下面代码进行结果分析import numpy as np from sklearn.cluster import MiniBatchKMeans from sklearn.datasets import load_iris from sklearn import preprocessing import matplotlib.pyplot as plt np.random.seed(5) from sklearn.cluster import KMeans from sklearn.metrics import silhouette_score from pylab import mpl # 设置显示中文字体 mpl.rcParams["font.sans-serif"] = ["SimHei"] # 设置正常显示符号 mpl.rcParams["axes.unicode_minus"] = False # 加载鸢尾花数据集 iris = load_iris() X = iris.data y = iris.target #最小最大标准化 min_max_scaler = preprocessing.MinMaxScaler() X_minmax=min_max_scaler.fit_transform(X) batch_size =15 num_cluster =3 #K均值算法拟合 clf=MiniBatchKMeans(n_clusters=num_cluster,batch_size=batch_size,init="random") clf.fit(X_minmax) #拟合中心 centers = clf.cluster_centers_ #预测标签 pre_clu=clf.labels_ print(pre_clu) vmarker={0:'^',1:'s',2:'D',} mValue=[vmarker[i] for i in pre_clu] for _marker, _x, _y in zip(mValue, X_minmax[:,1],X_minmax[:,2]): plt.scatter(_x, _y,marker=_marker,c="grey") plt.scatter(centers[:,1],centers[:,2],marker="",s=200,c='black') plt.show() # 轮廓系统法最佳k值 def sc_k(): K = range(2, 10) score = [] for k in K: kmeans = KMeans(n_clusters=k) kmeans.fit(iris.data) score.append(silhouette_score(iris.data, kmeans.labels_, metric='euclidean')) plt.plot(K, score, 'r-') plt.xlabel('k') plt.ylabel(u'轮廓系数') plt.title(u'轮廓系数确定最佳的K值') plt.show() sc_k()

这段代码使用MiniBatchKMeans算法对鸢尾花数据集进行了聚类，并展示了聚类结果和最佳的K值。具体分析如下： 1. 数据预处理：使用MinMaxScaler对数据进行了最小最大标准化处理，将所有特征缩放到0到1之间。 2. ...

import random import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.cluster import KMeans from sklearn.metrics import silhouette_score plt.rcParams['font.sans-serif'] = ['SimHei'] dataset=pd.read_excel('C:\\Users\\86180\\Desktop\\附件2整理.xlsx') dataset = dataset.drop(dataset.index[:1], inplace=False) dataset = dataset.drop(dataset.columns[:1], axis=1, inplace=False) #matrix=dataset.values matrix=np.array(dataset) matrix_xiang=matrix[:27] print(matrix_xiang[0]) print(matrix_xiang[-1]) print(matrix_xiang.shape) # matrix_chuan=matrix[-28:] # print(matrix_chuan[0]) # print(matrix_chuan[-1]) cluster_nums = range(2, 10) inertia_values = [] silhouette_scores = [] # 迭代不同聚类数量 for num in cluster_nums: # 创建K均值聚类模型 kmeans = KMeans(n_clusters=num) # 进行聚类 kmeans.fit(matrix_xiang) # 计算损失函数值和轮廓系数 inertia_values.append(kmeans.inertia_) silhouette_scores.append(silhouette_score(matrix_xiang, kmeans.labels_)) # 绘制肘部法则图像 plt.plot(cluster_nums, inertia_values, 'bo-') plt.xlabel('聚类数量') plt.ylabel('损失函数值') plt.title('肘部法则') plt.show() # 绘制轮廓系数图像 plt.plot(cluster_nums, silhouette_scores, 'ro-') plt.xlabel('聚类数量') plt.ylabel('轮廓系数') plt.title('轮廓系数') plt.show() kmeans = KMeans(n_clusters=7) # 进行聚类 kmeans.fit(matrix_xiang) labels = kmeans.labels_ # 打印每个食材的簇标签 for i, label in enumerate(labels): print(f"食材{i+1}的簇标签为：{label}")如何在这段代码中加入对聚类结果的评估和解释

1. 导入相应的评估指标库：from sklearn.metrics import silhouette_score 2. 在迭代不同聚类数量的循环中，计算每个聚类数量对应的轮廓系数并保存到silhouette_scores列表中： silhouette_scores.append...

import numpy as np from sklearn.cluster import MiniBatchKMeans from sklearn.datasets import load_iris from sklearn import preprocessing import matplotlib.pyplot as plt from pylab import mpl from sklearn.cluster import KMeans from sklearn.metrics import silhouette_score from scipy.spatial.distance import cdist # 设置显示中文字体 mpl.rcParams["font.sans-serif"] = ["SimHei"] # 设置正常显示符号 mpl.rcParams["axes.unicode_minus"] = False np.random.seed(5) iris = load_iris() X = iris.data y = iris.target min_max_scaler = preprocessing.MinMaxScaler() X_minmax = min_max_scaler.fit_transform(X) batch_size = 15 num_cluster = 3 clf = MiniBatchKMeans(n_clusters=num_cluster, batch_size=batch_size, init='random') clf.fit(X_minmax) centers = clf.cluster_centers_ pre_clu = clf.labels_ vmarker = {0: '^', 1: 's', 2: 'D', } mValue = [vmarker[i] for i in pre_clu] for _marker, _x, _y in zip(mValue, X_minmax[:, 1], X_minmax[:, 2]): plt.scatter(_x, _y, marker=_marker,c='grey') plt.scatter(centers[:, 1], centers[:, 2], marker='',s=200,c='black') plt.show() #手肘法则最佳k值 def sse_k(): K = range(1, 10) sse_result = [] for k in K: kmeans = KMeans(n_clusters=k) kmeans.fit(iris.data) sse_result.append(sum(np.min(cdist(iris.data, kmeans.cluster_centers_, 'euclidean'), axis=1)) / iris.data.shape[0]) plt.plot(K, sse_result, 'gx-') plt.xlabel('k') plt.ylabel(u'平均畸变程度') plt.title(u'肘部法则确定最佳的K值') plt.show() # 轮廓系统法最佳k值 def sc_k(): K = range(2, 10) score = [] for k in K: kmeans = KMeans(n_clusters=k) kmeans.fit(iris.data) score.append(silhouette_score(iris.data, kmeans.labels_, metric='euclidean')) plt.plot(K, score, 'r-') plt.xlabel('k') plt.ylabel(u'轮廓系数') plt.title(u'轮廓系数确定最佳的K值') plt.show() sse_k() sc_k()

最后，使用 matplotlib 绘制聚类散点图，其中每个数据点的颜色、形状表示它所属的聚类类别，聚类中心用星号标出。在绘制完聚类散点图之后，代码使用肘部法则和轮廓系数法来确定最佳的聚类数量 k。具体来说，肘部...

from future import print_function from pandas import DataFrame,Series import pandas as pd datafile='/root/dataset/air_customer_Data/air_data.csv' data=pd.read_csv(datafile,encoding='utf-8') cleanedfile='cleaned.csv' data1=data[data['SUM_YR_1'].notnull() & data['SUM_YR_2'].notnull()] data1 index1=data['SUM_YR_1']!=0 index2=data['SUM_YR_2']!=0 index3=data['SEG_KM_SUM']>0 data1 = data1[(index1 | index2) & index3] data1.to_csv(cleanedfile) data2=data1[['LOAD_TIME','FFP_DATE','LAST_TO_END','FLIGHT_COUNT','SEG_KM_SUM','avg_discount']] data2.to_csv('datadecrese.csv') 3 import numpy as np data=pd.read_csv('datadecrese.csv') data['L']=pd.to_datetime(data['LOAD_TIME'])-pd.to_datetime(data['FFP_DATE']) data['L'] =data['L'].astype("str").str.split().str[0] # 去除数据中的days字符，只输出数字，再转化为数值型数据 data['L'] = data['L'].astype("int") / 30 data.drop(columns=['LOAD_TIME','FFP_DATE'], inplace=True) data.rename(columns = {'LAST_TO_END':'R','FLIGHT_COUNT':'F','SEG_KM_SUM':'M','avg_discount':'C'},inplace=True) data.drop(columns=['Unnamed: 0'], inplace=True) 4 data.describe() 5 P108 data=(data-data.mean())/data.std() 6 import pandas as pd from pandas import DataFrame,Series from sklearn.cluster import KMeans k=5 kmodel=KMeans(n_clusters=k,random_state=3) kmodel.fit(data) 7 import matplotlib import matplotlib.pyplot as plt clu=kmodel.cluster_centers_ x=[1,2,3,4,5] plt.rcParams['font.sans-serif'] = 'SimHei' plt.rcParams['axes.unicode_minus'] = False for i in range(5): plt.plot(x,clu[i]) plt.show

首先，从一个csv文件中读取数据，然后进行数据清洗，去除缺失值和异常值，再将数据保存为新的csv文件。接着，读取新的csv文件，对数据进行标准化处理，再使用KMeans算法进行聚类分析。最后，使用Matplotlib库对聚类...

补全代码，使用 PCA 对MNIST的数据降维到2维做一下KMeans并显示： import numpy as np from sklearn.datasets import fetch_openml # Load data from https://www.openml.org/d/554 X, y = fetch_openml("mnist_784", version=1, return_X_y=True, as_frame=False) print(X.shape,y.shape) #(70000, 784) (70000,) print(np.unique(y)) ##可只选择前10000条数据做实验 X=X[:10000] y=y[:10000]

import matplotlib.pyplot as plt # Load data from https://www.openml.org/d/554 X, y = fetch_openml("mnist_784", version=1, return_X_y=True, as_frame=False) # Print the shape of X and y print(X....

import pandas as pd from sklearn.cluster import KMeans import matplotlib.pyplot as plt import numpy as np from sklearn.preprocessing import StandardScaler from sklearn import metrics beer=pd.read_csv('data.txt',encoding='gbk',sep='') X=beer[["calories","sodium","alcohol","cost"]] km=KMeans(n_clusters=3).fit(X) beer['cluster']=km.labels_ centers=km.cluster_centers_ plt.rcParams['font.size']=14 colors=np.array(['red','green','blue','yellow']) plt.scatter(beer["calories"], beer["alcohol"], c=colors[beer["cluster"]]) plt.scatter(centers[:,0], centers[:,2], linewidths=3,marker='+',s=300,c='black') plt.xlabel("Calories") plt.ylable("Alcohol") plt.suptitle("Calories and Alcohol") pd.plotting.scatter_matrix(beer[["calories", "sodium","alcohol","cost"]],s=100,alpha=1,c=colors[beer["cluster"]],figsize=(10,10)) plt.suptitle("original data") scaler=StandardScaler() X_scaled=scaler.fit_transform(X) km=KMeans(n_clusters=3).fit(X_scaled) beer["scaled_cluster"]=km.labels_ centers=km.cluster_centers_ pd.plotting.scatter_matrix(X, c=colors[beer.scaled_cluster],alpha=1,figsize=(10,10),s=100) plt.suptitle("standard data") score_scaled=metrics.silhouette_score(X, beer.scaled_cluster) score=metrics.silhouette_score(X, beer.cluster) print("得分为",score_scaled,score) scores=[] for k in range(2,20): labels=KMeans(n_clusters=k).fit(X).labels_ score=metrics.silhouette_score(X, labels) scores.append(score) for i in range(len(scores)): print((i+2,scores[i])) print(max(scores[i])) plt.figure() plt.plot(list(range(2,20)), scores,"ro") plt.xlabel("Number of Clusters Initialized") plt.ylabel("Sihouette Score") plt.suptitle("K parameter optimize") plt.show() scores=[] for k in range(2,20): labels=KMeans(n_clusters=k).fit(X_scaled).labels_ score=metrics.silhouette_score(X_scaled, labels) scores.append(score) for i in range(len(scores)): print((i+2,scores[i]))

首先，它导入了一些必要的库，包括pandas用于数据处理，sklearn.cluster.KMeans用于聚类分析，matplotlib.pyplot用于数据可视化，numpy用于数值计算，以及sklearn.preprocessing.StandardScaler和sklearn...

相关推荐

python 3.74 运行import numpy as np 报错lib\site-packages\numpy\__init__.py

import numpy as np(2).py

np.mean np.cov numpy.corrcoef pyplot.scatter pyplot.contour函数

最新推荐

Python学习笔记16 - 猜数字小游戏

BSC绩效考核指标汇总 (2).docx

管理建模和仿真的文件

【进阶】Flask中的会话与用户管理

卷积神经网络实现手势识别程序

BSC资料.pdf

"互动学习：行动中的多样性与论文攻读经历"

【进阶】Flask中的请求处理

transformer模型对话

BSC绩效考核指标汇总 (3).pdf

python 3.74 运行import numpy as np 报错lib\site-packages\numpy\init.py