所以我试图将模块/脚本(.py 文件)导入 Jupyter 笔记本,主要是为了可读性和简洁性。但是,当我尝试在脚本中运行该类时,我收到以下错误消息:
NameError Traceback (most recent call last)
<ipython-input-48-4d8cbba46ed0> in <module>()
8
9 test_KMeans = KMeans(k=3, maxiter=1000, tol=1e-9)
---> 10 cluster_center = test_KMeans.fit(X)
11 clusters = test_KMeans.predict(X)
12
~/KMeans.py in fit(self, X)
42 #Choose k random rows of X as the initial cluster centers.
43 initial_cluster_centers = []
---> 44
45 sample = np.random.randint(0,m,size=k)
46
NameError: name 'maxiter' is not defined
这是我的脚本:
import numpy as np
from sklearn.decomposition import PCA
k = 3
maxiter = 1000
tol = 1e-9
class KMeans:
"""A K-Means object class. Implements basic k-means clustering.
Attributes:
k (int): The number of clusters
maxiter (int): The maximum number of iterations
tol (float): A convergence tolerance
"""
def __init__(self, k, maxiter, tol):
"""Set the paramters.
Parameters:
k (int): The number of clusters
maxiter (int): The maximum number of iterations
tol (float): A convergence tolerance
"""
k = 3
maxiter = 1000
tol = 1e-9
self.k = k # Initialize some attributes.
self.maxiter = maxiter
self.tol = tol
def fit(self, X):
"""Accepts an mxn matrix X of m data points with n features.
"""
m,n = X.shape
k = 3
maxiter = 1000
tol = 1e-9
self.m = m
self.n = n
#Choose k random rows of X as the initial cluster centers.
initial_cluster_centers = []
sample = np.random.randint(0,m,size=k)
initial_cluster_centers = X[sample, :]
# Run the k-means iteration until consecutive centers are within the convergence tolerance, or until
# iterating the maximum number of times.
iterations = 0
old_cluster = np.zeros(initial_cluster_centers.shape)
new_cluster = initial_cluster_centers
while iterations < maxiter or np.linalg.norm(old_cluster - new_cluster) >= tol:
#assign each data point to the cluster center that is closest, forming k clusters
clusters = np.zeros(m)
for i in range(0,m):
distances = np.linalg.norm(X[i] - initial_cluster_centers, ord=2, axis=1) # axis=1 was crucial
cluster = np.argmin(distances) #in getting this to work
clusters[i] = cluster
# Store the old/initial centroid values
old_cluster = np.copy(new_cluster)
#Recompute the cluster centers as the means of the new clusters
for i in range(k):
points = [X[j] for j in range(m) if clusters[j] == i]
new_cluster[i] = np.mean(points, axis=0)
#If a cluster is empty, reassign the cluster center as a random row of X.
if new_cluster[i] == []:
new_cluster[i] = X[np.random.randint(0,m,size=1)]
iterations += 1
#Save the cluster centers as attributes.
self.new_cluster = new_cluster
#print("New cluster centers:\n", new_cluster)
return new_cluster
def predict(self, X):
"""Accept an l × n matrix X of data.
"""
# Return an array of l integers where the ith entry indicates which
# cluster center the ith row of X is closest to.
clusters = np.zeros(self.m)
for i in range(0,self.m):
distances = np.linalg.norm(X[i] - self.new_cluster, ord=2, axis=1)
cluster = np.argmin(distances)
clusters[i] = cluster
print("\nClusters:", clusters)
return clusters
然后我尝试执行以下操作:
from KMeans import KMeans
X = features_scaled
# k = 3
# maxiter = 1000
# tol = 1e-9
test_KMeans = KMeans(k=3, maxiter=1000, tol=1e-9)
cluster_center = test_KMeans.fit(X)
clusters = test_KMeans.predict(X)
pca = PCA(n_components=2)
pr_components = pca.fit_transform(X) # these are the first 2 principal components
#plot the first two principal components as a scatter plot, where the color of each point is det by the clusters
plt.scatter(pr_components[:,0], pr_components[:,1],
c=clusters, edgecolor='none', alpha=0.5, #color by clusters
cmap=plt.cm.get_cmap('tab10', 3))
plt.xlabel('principal component 1')
plt.ylabel('principal component 2')
plt.colorbar()
plt.title("K-Means Clustering:")
plt.show()
运行上面的代码部分后,我得到了我描述的 NameError。我不明白为什么它告诉我maxiter
没有定义。你会看到我k, maxiter, tol
在脚本中多次定义变量试图让它工作,但没有。我曾经有过self.maxiter
,self.tol
但也没有解决。
我知道此代码有效,因为我现在已经多次使用它。最初我只是定义了这些变量 k、maxiter 和 tol.. 然后实例化了类并调用了 fit 和 predict 方法,因为它们作为属性存储在 self 中,所以一切正常。但是现在我尝试将它作为模块导入我不知道为什么它不起作用。
谢谢你的帮助!
编辑:这是我的代码在 Jupyter 笔记本中的单个单元格中的样子.. 在这种情况下它确实可以运行和工作:
from sklearn.decomposition import PCA
class KMeans:
"""A K-Means object class. Implements basic k-means clustering.
Attributes:
k (int): The number of clusters
maxiter (int): The maximum number of iterations
tol (float): A convergence tolerance
"""
def __init__(self, k, maxiter, tol):
"""Set the paramters.
Parameters:
k (int): The number of clusters
maxiter (int): The maximum number of iterations
tol (float): A convergence tolerance
"""
self.k = k # Initialize some attributes.
self.maxiter = maxiter
self.tol = tol
def fit(self, X):
"""Accepts an mxn matrix X of m data points with n features.
"""
m,n = X.shape
self.m = m
self.n = n
#Choose k random rows of X as the initial cluster centers.
initial_cluster_centers = []
sample = np.random.randint(0,m,size=self.k)
initial_cluster_centers = X[sample, :]
# Run the k-means iteration until consecutive centers are within the convergence tolerance, or until
# iterating the maximum number of times.
iterations = 0
old_cluster = np.zeros(initial_cluster_centers.shape)
new_cluster = initial_cluster_centers
while iterations < maxiter or np.linalg.norm(old_cluster - new_cluster) >= tol:
#assign each data point to the cluster center that is closest, forming k clusters
clusters = np.zeros(m)
for i in range(0,m):
distances = np.linalg.norm(X[i] - initial_cluster_centers, ord=2, axis=1) # axis=1 was crucial
cluster = np.argmin(distances) #in getting this to work
clusters[i] = cluster
# Store the old/initial centroid values
old_cluster = np.copy(new_cluster)
#Recompute the cluster centers as the means of the new clusters
for i in range(k):
points = [X[j] for j in range(m) if clusters[j] == i]
new_cluster[i] = np.mean(points, axis=0)
#If a cluster is empty, reassign the cluster center as a random row of X.
if new_cluster[i] == []:
new_cluster[i] = X[np.random.randint(0,m,size=1)]
iterations += 1
#Save the cluster centers as attributes.
self.new_cluster = new_cluster
#print("New cluster centers:\n", new_cluster)
return new_cluster
def predict(self, X):
"""Accept an l × n matrix X of data.
"""
# Return an array of l integers where the ith entry indicates which
# cluster center the ith row of X is closest to.
clusters = np.zeros(self.m)
for i in range(0,self.m):
distances = np.linalg.norm(X[i] - self.new_cluster, ord=2, axis=1)
cluster = np.argmin(distances)
clusters[i] = cluster
print("\nClusters:", clusters)
return clusters
X = features_scaled
k = 3
maxiter = 1000
tol = 1e-9
test_KMeans = KMeans(k,maxiter,tol)
test_KMeans.fit(X)
clusters = test_KMeans.predict(X)
pca = PCA(n_components=2)
pr_components = pca.fit_transform(X) # these are the first 2 principal components
#plot the first two principal components as a scatter plot, where the color of each point is det by the clusters
plt.scatter(pr_components[:,0], pr_components[:,1],
c=clusters, edgecolor='none', alpha=0.5, #color by clusters
cmap=plt.cm.get_cmap('tab10', 3))
plt.xlabel('principal component 1')
plt.ylabel('principal component 2')
plt.colorbar()
plt.title("K-Means Clustering:")
plt.show()
回溯似乎显示 Jupyter 与 Kmeans.py 中的当前代码状态不同步(因为它指向第 44 行......这是空的)。因此,如果计算时间不会太长,您可以尝试通过退出并重新启动 Jupyter 来解决问题。
Python 在导入模块时执行模块的代码。如果在导入模块后对模块代码进行更改,则这些更改不会反映在 Python 解释器的状态中。这可以解释为什么 Jupyter notebook 的错误似乎与 Kmeans.py 的状态不同步。
除了退出并重新启动 Python,您还可以重新加载模块。例如,在 Python3.4 或更新版本中,您可以使用
import sys
import importlib
from Kmeans import Kmeans
# make changes to Kmeans.py
importlib.reload(sys.modules['Kmeans'])
# now the Python interpreter should be aware of changes made to Kmeans.py
但是,使用 IPython,有一种更简单的方法。您可以启用自动重新加载:
从命令行运行:
ipython profile create
然后~/.ipython/profile_default/ipython_config.py
通过添加编辑
c.InteractiveShellApp.extensions = ['autoreload']
c.InteractiveShellApp.exec_lines = ['%autoreload 2']
退出并重新启动 IPython 以使此更改生效。现在,当对定义该模块的底层代码进行更改时,IPython 将自动重新加载任何模块。在大多数情况下 autoreload 运行良好,但也有可能无法重新加载模块的情况。有关autoreload 及其警告的更多信息,请参阅文档。
本文收集自互联网,转载请注明来源。
如有侵权,请联系 [email protected] 删除。
我来说两句