[英]python scikit-learn clustering with missing data
I want to cluster data with missing columns.我想对缺少列的数据进行聚类。 Doing it manually I would calculate the distance in case of a missing column simply without this column.
手动执行我会在没有此列的情况下计算缺少列的距离。
With scikit-learn, missing data is not possible.使用 scikit-learn,丢失数据是不可能的。 There is also no chance to specify a user distance function.
也没有机会指定用户距离函数。
Is there any chance to cluster with missing data?有没有机会用缺失的数据进行聚类?
Example data:示例数据:
n_samples = 1500
noise = 0.05
X, _ = make_swiss_roll(n_samples, noise)
rnd = np.random.rand(X.shape[0],X.shape[1])
X[rnd<0.1] = np.nan
I think you can use an iterative EM-type algorithm:我认为您可以使用迭代 EM 类型算法:
Initialize missing values to their column means
将缺失值初始化为其列均值
Repeat until convergence:
重复直到收敛:
Perform K-means clustering on the filled-in data
对填入的数据进行 K-means 聚类
Set the missing values to the centroid coordinates of the clusters to which they were assigned
将缺失值设置为它们被分配到的簇的质心坐标
import numpy as np
from sklearn.cluster import KMeans
def kmeans_missing(X, n_clusters, max_iter=10):
"""Perform K-Means clustering on data with missing values.
Args:
X: An [n_samples, n_features] array of data to cluster.
n_clusters: Number of clusters to form.
max_iter: Maximum number of EM iterations to perform.
Returns:
labels: An [n_samples] vector of integer labels.
centroids: An [n_clusters, n_features] array of cluster centroids.
X_hat: Copy of X with the missing values filled in.
"""
# Initialize missing values to their column means
missing = ~np.isfinite(X)
mu = np.nanmean(X, 0, keepdims=1)
X_hat = np.where(missing, mu, X)
for i in xrange(max_iter):
if i > 0:
# initialize KMeans with the previous set of centroids. this is much
# faster and makes it easier to check convergence (since labels
# won't be permuted on every iteration), but might be more prone to
# getting stuck in local minima.
cls = KMeans(n_clusters, init=prev_centroids)
else:
# do multiple random initializations in parallel
cls = KMeans(n_clusters, n_jobs=-1)
# perform clustering on the filled-in data
labels = cls.fit_predict(X_hat)
centroids = cls.cluster_centers_
# fill in the missing values based on their cluster centroids
X_hat[missing] = centroids[labels][missing]
# when the labels have stopped changing then we have converged
if i > 0 and np.all(labels == prev_labels):
break
prev_labels = labels
prev_centroids = cls.cluster_centers_
return labels, centroids, X_hat
from sklearn.datasets import make_blobs
from matplotlib import pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
def make_fake_data(fraction_missing, n_clusters=5, n_samples=1500,
n_features=3, seed=None):
# complete data
gen = np.random.RandomState(seed)
X, true_labels = make_blobs(n_samples, n_features, n_clusters,
random_state=gen)
# with missing values
missing = gen.rand(*X.shape) < fraction_missing
Xm = np.where(missing, np.nan, X)
return X, true_labels, Xm
X, true_labels, Xm = make_fake_data(fraction_missing=0.3, n_clusters=5, seed=0)
labels, centroids, X_hat = kmeans_missing(Xm, n_clusters=5)
# plot the inferred points, color-coded according to the true cluster labels
fig, ax = plt.subplots(1, 2, subplot_kw={'projection':'3d', 'aspect':'equal'})
ax[0].scatter3D(X[:, 0], X[:, 1], X[:, 2], c=true_labels, cmap='gist_rainbow')
ax[1].scatter3D(X_hat[:, 0], X_hat[:, 1], X_hat[:, 2], c=true_labels,
cmap='gist_rainbow')
ax[0].set_title('Original data')
ax[1].set_title('Imputed (30% missing values)')
fig.tight_layout()
To assess the algorithm's performance, we can use the adjusted mutual information between the true and inferred cluster labels.为了评估算法的性能,我们可以使用真实和推断的集群标签之间调整后的互信息。 A score of 1 is perfect performance and 0 represents chance:
1 分代表完美表现,0 代表机会:
from sklearn.metrics import adjusted_mutual_info_score
fraction = np.arange(0.0, 1.0, 0.05)
n_repeat = 10
scores = np.empty((2, fraction.shape[0], n_repeat))
for i, frac in enumerate(fraction):
for j in range(n_repeat):
X, true_labels, Xm = make_fake_data(fraction_missing=frac, n_clusters=5)
labels, centroids, X_hat = kmeans_missing(Xm, n_clusters=5)
any_missing = np.any(~np.isfinite(Xm), 1)
scores[0, i, j] = adjusted_mutual_info_score(labels, true_labels)
scores[1, i, j] = adjusted_mutual_info_score(labels[any_missing],
true_labels[any_missing])
fig, ax = plt.subplots(1, 1)
scores_all, scores_missing = scores
ax.errorbar(fraction * 100, scores_all.mean(-1),
yerr=scores_all.std(-1), label='All labels')
ax.errorbar(fraction * 100, scores_missing.mean(-1),
yerr=scores_missing.std(-1),
label='Labels with missing values')
ax.set_xlabel('% missing values')
ax.set_ylabel('Adjusted mutual information')
ax.legend(loc='best', frameon=False)
ax.set_ylim(0, 1)
ax.set_xlim(-5, 100)
In fact, after a quick Google search it seems that what I've come up with above is pretty much the same as the k -POD algorithm for K-means clustering of missing data (Chi, Chi & Baraniuk, 2016) .事实上,经过一个快速谷歌搜索似乎有什么我想出了上面几乎是一样的k个-POD算法K-均值聚类丢失的数据(志,志&Baraniuk,2016) 。
Here is a different algorithm that I use.这是我使用的不同算法。 Instead of replacing the missing values the values are ignored and in order to capture the differences between missing and non-missing i impliment missing dummies.
不是替换缺失值,而是忽略值,为了捕捉缺失和非缺失之间的差异,我暗示了缺失的假人。
Compared to Alis algorithm it seems is easier for observations with missing observatons to jump from class to class.与 Alis 算法相比,缺少观察的观察似乎更容易从一个班级跳到另一个班级。 Since I do not fill the missing values.
由于我没有填写缺失值。
I fortunely did not have the time to compare using Ali's beautiful code, but feel free to do it (I might do it when I get the time) and contribute to the discussion about the best method.幸好我没有时间用阿里的漂亮代码做对比,但可以随意做(有时间我可能会做),并为最佳方法的讨论做出贡献。
import numpy as np
class kmeans_missing(object):
def __init__(self,potential_centroids,n_clusters):
#initialize with potential centroids
self.n_clusters=n_clusters
self.potential_centroids=potential_centroids
def fit(self,data,max_iter=10,number_of_runs=1):
n_clusters=self.n_clusters
potential_centroids=self.potential_centroids
dist_mat=np.zeros((data.shape[0],n_clusters))
all_centroids=np.zeros((n_clusters,data.shape[1],number_of_runs))
costs=np.zeros((number_of_runs,))
for k in range(number_of_runs):
idx=np.random.choice(range(potential_centroids.shape[0]), size=(n_clusters), replace=False)
centroids=potential_centroids[idx]
clusters=np.zeros(data.shape[0])
old_clusters=np.zeros(data.shape[0])
for i in range(max_iter):
#Calc dist to centroids
for j in range(n_clusters):
dist_mat[:,j]=np.nansum((data-centroids[j])**2,axis=1)
#Assign to clusters
clusters=np.argmin(dist_mat,axis=1)
#Update clusters
for j in range(n_clusters):
centroids[j]=np.nanmean(data[clusters==j],axis=0)
if all(np.equal(clusters,old_clusters)):
break # Break when to change in clusters
if i==max_iter-1:
print('no convergence before maximal iterations are reached')
else:
clusters,old_clusters=old_clusters,clusters
all_centroids[:,:,k]=centroids
costs[k]=np.mean(np.min(dist_mat,axis=1))
self.costs=costs
self.cost=np.min(costs)
self.best_model=np.argmin(costs)
self.centroids=all_centroids[:,:,self.best_model]
self.all_centroids=all_centroids
def predict(self,data):
dist_mat=np.zeros((data.shape[0],self.n_clusters))
for j in range(self.n_clusters):
dist_mat[:,j]=np.nansum((data-self.centroids[j])**2,axis=1)
prediction=np.argmin(dist_mat,axis=1)
cost=np.min(dist_mat,axis=1)
return prediction,cost
Here is an example on how though it might be usefull.这是一个关于如何使用的示例。
from sklearn.datasets import make_blobs
from matplotlib import pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from kmeans_missing import *
def make_fake_data(fraction_missing, n_clusters=5, n_samples=1500,
n_features=2, seed=None):
# complete data
gen = np.random.RandomState(seed)
X, true_labels = make_blobs(n_samples, n_features, n_clusters,
random_state=gen)
# with missing values
missing = gen.rand(*X.shape) < fraction_missing
Xm = np.where(missing, np.nan, X)
return X, true_labels, Xm
X, true_labels, X_hat = make_fake_data(fraction_missing=0.3, n_clusters=3, seed=0)
X_missing_dummies=np.isnan(X_hat)
n_clusters=3
X_hat = np.concatenate((X_hat,X_missing_dummies),axis=1)
kmeans_m=kmeans_missing(X_hat,n_clusters)
kmeans_m.fit(X_hat,max_iter=100,number_of_runs=10)
print(kmeans_m.costs)
prediction,cost=kmeans_m.predict(X_hat)
for i in range(n_clusters):
print([np.mean((prediction==i)*(true_labels==j)) for j in range(3)],np.mean((prediction==i)))
--EDIT-- - 编辑 -
In this example the occurrences of missing values are completly random and when that is the case.在这个例子中,缺失值的出现是完全随机的,在这种情况下。 Not adding the missing value dummies preforms better, since missing value dummies in that case is noise.
不添加缺失值假人会更好,因为在这种情况下缺失值假人是噪音。 Not including them would also be the correct thing to do in order to compare with Ali's algorithm.
为了与阿里的算法进行比较,不包括它们也是正确的做法。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.