跟着Leo机器学习实战：sklearn之clustering函数导图（干货分享）

一个很有趣的个人博客,不信你来撩 fangzengye.com



整篇函数导图（干货分享）

在这里插入图片描述

类包

class sklearn.cluster.KMeans(n_clusters=8, init='k-means++', n_init=10, max_iter=300, tol=0.0001, precompute_distances='auto', verbose=0, random_state=None, copy_x=True, n_jobs=None, algorithm='auto')

KMeans

from sklearn.cluster import KMeans
import numpy as np
X = np.array([[1, 2], [1, 4], [1, 0],
              [10, 2], [10, 4], [10, 0]])
kmeans = KMeans(n_clusters=2, random_state=0).fit(X)
kmeans.labels_

kmeans.predict([[0, 0], [12, 3]])


kmeans.cluster_centers_

源地址

https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html#sklearn.cluster.KMeans

2.3.3. Affinity Propagation

类包

class sklearn.cluster.AffinityPropagation(damping=0.5, max_iter=200, convergence_iter=15, copy=True, preference=None, affinity='euclidean', verbose=False)

例子

from sklearn.cluster import AffinityPropagation
import numpy as np
X = np.array([[1, 2], [1, 4], [1, 0],
              [4, 2], [4, 4], [4, 0]])
clustering = AffinityPropagation().fit(X)
clustering

clustering.labels_


clustering.predict([[0, 0], [4, 4]])


clustering.cluster_centers_

源地址

https://scikit-learn.org/stable/modules/generated/sklearn.cluster.AffinityPropagation.html#sklearn.cluster.AffinityPropagation

2.3.4. Mean Shift

类包

class sklearn.cluster.MeanShift(bandwidth=None, seeds=None, bin_seeding=False, min_bin_freq=1, cluster_all=True, n_jobs=None, max_iter=300)

例子

from sklearn.cluster import MeanShift
import numpy as np
X = np.array([[1, 1], [2, 1], [1, 0],
              [4, 7], [3, 5], [3, 6]])
clustering = MeanShift(bandwidth=2).fit(X)
clustering.labels_

clustering.predict([[0, 0], [5, 5]])


clustering

源地址

https://scikit-learn.org/stable/modules/generated/sklearn.cluster.MeanShift.html#sklearn.cluster.MeanShift

2.3.5. Spectral clustering

类包

class sklearn.cluster.SpectralClustering(n_clusters=8, eigen_solver=None, n_components=None, random_state=None, n_init=10, gamma=1.0, affinity='rbf', n_neighbors=10, eigen_tol=0.0, assign_labels='kmeans', degree=3, coef0=1, kernel_params=None, n_jobs=None)

例子

from sklearn.cluster import SpectralClustering
import numpy as np
X = np.array([[1, 1], [2, 1], [1, 0],
              [4, 7], [3, 5], [3, 6]])
clustering = SpectralClustering(n_clusters=2,
        assign_labels="discretize",
        random_state=0).fit(X)
clustering.labels_

clustering

源地址

https://scikit-learn.org/stable/modules/generated/sklearn.cluster.SpectralClustering.html#sklearn.cluster.SpectralClustering

2.3.6. Hierarchical clustering

类包

class sklearn.cluster.AgglomerativeClustering(n_clusters=2, affinity='euclidean', memory=None, connectivity=None, compute_full_tree='auto', linkage='ward', distance_threshold=None)

例子

from sklearn.cluster import AgglomerativeClustering
import numpy as np
X = np.array([[1, 2], [1, 4], [1, 0],
              [4, 2], [4, 4], [4, 0]])
clustering = AgglomerativeClustering().fit(X)
clustering

clustering.labels_

源地址

https://scikit-learn.org/stable/modules/generated/sklearn.cluster.AgglomerativeClustering.html#sklearn.cluster.AgglomerativeClustering

2.3.7. DBSCAN

类包

class sklearn.cluster.DBSCAN(eps=0.5, min_samples=5, metric='euclidean', metric_params=None, algorithm='auto', leaf_size=30, p=None, n_jobs=None)

例子

from sklearn.cluster import DBSCAN
import numpy as np
X = np.array([[1, 2], [2, 2], [2, 3],
              [8, 7], [8, 8], [25, 80]])
clustering = DBSCAN(eps=3, min_samples=2).fit(X)
clustering.labels_

clustering

源地址

https://scikit-learn.org/stable/modules/generated/sklearn.cluster.DBSCAN.html#sklearn.cluster.DBSCAN

2.3.8. OPTICS

类包

class sklearn.cluster.OPTICS(min_samples=5, max_eps=inf, metric='minkowski', p=2, metric_params=None, cluster_method='xi', eps=None, xi=0.05, predecessor_correction=True, min_cluster_size=None, algorithm='auto', leaf_size=30, n_jobs=None

例子

from sklearn.cluster import OPTICS
import numpy as np
X = np.array([[1, 2], [2, 5], [3, 6],
              [8, 7], [8, 8], [7, 3]])
clustering = OPTICS(min_samples=2).fit(X)
clustering.labels_

源地址

https://scikit-learn.org/stable/modules/generated/sklearn.cluster.OPTICS.html#sklearn.cluster.OPTICS

2.3.9. Birch

类包

class sklearn.cluster.Birch(threshold=0.5, branching_factor=50, n_clusters=3, compute_labels=True, copy=True)

例子

from sklearn.cluster import Birch
X = [[0, 1], [0.3, 1], [-0.3, 1], [0, -1], [0.3, -1], [-0.3, -1]]
brc = Birch(n_clusters=None)
brc.fit(X)

brc.predict(X)

源地址

https://scikit-learn.org/stable/modules/generated/sklearn.cluster.Birch.html#sklearn.cluster.Birch

2.3.10. Clustering performance evaluation

2.3.10.1. Adjusted Rand index

from sklearn import metrics
labels_true = [0, 0, 0, 1, 1, 1]
labels_pred = [0, 0, 1, 1, 2, 2]

metrics.adjusted_rand_score(labels_true, labels_pred)

2.3.10.2. Mutual Information based scores

from sklearn import metrics
labels_true = [0, 0, 0, 1, 1, 1]
labels_pred = [0, 0, 1, 1, 2, 2]

metrics.adjusted_mutual_info_score(labels_true, labels_pred)

normalized_mutual_info_score

metrics.normalized_mutual_info_score(labels_true, labels_pred)

mutual_info_score

metrics.mutual_info_score(labels_true, labels_pred)

2.3.10.3. Homogeneity, completeness and V-measure

from sklearn import metrics
labels_true = [0, 0, 0, 1, 1, 1]
labels_pred = [0, 0, 1, 1, 2, 2]

metrics.homogeneity_score(labels_true, labels_pred)


metrics.completeness_score(labels_true, labels_pred)


metrics.v_measure_score(labels_true, labels_pred)


metrics.homogeneity_completeness_v_measure(labels_true, labels_pred)

2.3.10.4. Fowlkes-Mallows scores

from sklearn import metrics
labels_true = [0, 0, 0, 1, 1, 1]
labels_pred = [0, 0, 1, 1, 2, 2]
metrics.fowlkes_mallows_score(labels_true, labels_pred)

2.3.10.5. Silhouette Coefficient

import numpy as np
from sklearn.cluster import KMeans
kmeans_model = KMeans(n_clusters=3, random_state=1).fit(X)
labels = kmeans_model.labels_
metrics.silhouette_score(X, labels, metric='euclidean')

2.3.10.6. Calinski-Harabasz Index

import numpy as np
from sklearn.cluster import KMeans
kmeans_model = KMeans(n_clusters=3, random_state=1).fit(X)
labels = kmeans_model.labels_
metrics.calinski_harabasz_score(X, labels)

2.3.10.7. Davies-Bouldin Index

from sklearn import datasets
iris = datasets.load_iris()
X = iris.data
from sklearn.cluster import KMeans
from sklearn.metrics import davies_bouldin_score
kmeans = KMeans(n_clusters=3, random_state=1).fit(X)
labels = kmeans.labels_
davies_bouldin_score(X, labels)

2.3.10.8. Contingency Matrix

from sklearn.metrics.cluster import contingency_matrix
x = ["a", "a", "a", "b", "b", "b"]
y = [0, 0, 1, 1, 2, 2]
contingency_matrix(x, y)

整篇源地址

https://scikit-learn.org/stable/modules/clustering.html#clustering

posted @ 2020-02-25 15:55  开源的Boy  阅读(390)  评论(0)    收藏  举报