使用 Iris 数据集在 Python 上进行模糊聚类

Question

我正在研究虹膜数据集的模糊c均值聚类，但是由于一些错误而无法可视化。使用本教程我为虹膜编写了以下内容，但是它显示了名为“AttributeError：shape”的错误。这是我的代码：

from sklearn import datasets
from sklearn.cluster import KMeans
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import sklearn.metrics as sm
import skfuzzy as fuzz

iris = datasets.load_iris()

x = pd.DataFrame(iris.data, columns=['Sepal Length', 'Sepal Width', 'Petal Length', 'Petal Width'])
y = pd.DataFrame(iris.target, columns=['Target'])
plt.figure(figsize=(6, 3))

model =fuzz.cluster.cmeans(iris,3,2,error=0.005,maxiter=1000,init=None,seed=None)
model.fit(x)
plt.show()

我认为在变量模型中传递参数就足够了，但是它显示了上述错误。如果可以的话，你能指出我在哪里犯了错误吗？如何解决这个问题？我真的很感谢你的帮助！

Answer 1

我首先尝试预处理数据，创建了一个很好的绘图，我只是按照教程进行操作，然后执行 SVD 将维度减少为二维，然后开始绘图，似乎对于教程来说，您只需要二维(x,y)。你不需要做 model.fit() 我在documentation中没有找到这种命令，这里是代码：

import numpy as np, pandas as pd, os
import matplotlib
import matplotlib.pyplot as plt
import itertools
from sklearn.metrics import confusion_matrix
import statsmodels.api as sm
import statsmodels.formula.api as smf
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import [![TruncatedSVD
from skle][1]][1]arn.preprocessing import Normalizer
import skfuzzy as fuzz
from sklearn import datasets
################################################################################
iris = datasets.load_iris()

x = pd.DataFrame(iris.data, columns=['Sepal Length', 'Sepal Width', 'Petal Length', 'Petal Width'])
y = pd.DataFrame(iris.target, columns=['Target'])
scaler = StandardScaler()
X_std = scaler.fit_transform(x)
lsa = TruncatedSVD(2, algorithm = 'arpack')
dtm_lsa = lsa.fit_transform(X_std)
dtm_lsa = Normalizer(copy=False).fit_transform(dtm_lsa)
a= pd.DataFrame(dtm_lsa, columns = ["component_1","component_2"])
a['targets']=y
fig1, axes1 = plt.subplots(3, 3, figsize=(8, 8))
alldata = np.vstack((a['component_1'], a['component_2']))
fpcs = []

colors = ['b', 'orange', 'g', 'r', 'c', 'm', 'y', 'k', 'Brown', 'ForestGreen'] 

for ncenters, ax in enumerate(axes1.reshape(-1), 2):
    cntr, u, u0, d, jm, p, fpc = fuzz.cluster.cmeans(
        alldata, ncenters, 2, error=0.005, maxiter=1000, init=None)

    # Store fpc values for later plots
    fpcs.append(fpc)

    # Plot assigned clusters, for each data point in training set
    cluster_membership = np.argmax(u, axis=0)
    for j in range(ncenters):
        ax.plot(a['component_1'][cluster_membership == j],
                a['component_2'][cluster_membership == j], '.', color=colors[j])

    # Mark the center of each fuzzy cluster
    for pt in cntr:
        ax.plot(pt[0], pt[1], 'rs')

    ax.set_title('Centers = {0}; FPC = {1:.2f}'.format(ncenters, fpc))
    ax.axis('off')

fig1.tight_layout()
fig1.savefig('iris_dataset.png')