Commit c961e6c

author

Algorithmica

authored

Add files via upload

1 parent 3c57156 commit c961e6cCopy full SHA for c961e6c

File tree

+111

-0

lines changed

+111

-0

lines changed

Lines changed: 20 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,20 @@`
	`1`	`+import sys`
	`2`	`+path = 'J://utils'`
	`3`	`+sys.path.append(path)`
	`4`	`+`
	`5`	`+import common_utils as utils`
	`6`	`+import clustering_utils as cl_utils`
	`7`	`+import classification_utils as cutils`
	`8`	`+`
	`9`	`+X, y = cl_utils.generate_synthetic_data_2d_clusters(n_samples=300, n_centers=4, cluster_std=0.60)`
	`10`	`+utils.plot_data_2d(X)`
	`11`	`+`
	`12`	`+X, _ = cl_utils.generate_synthetic_data_3d_clusters(n_samples=500, n_centers=3, cluster_std=1.4)`
	`13`	`+utils.plot_data_3d(X)`
	`14`	`+`
	`15`	`+X, _ = cutils.generate_nonlinear_synthetic_data_classification2(n_samples=300)`
	`16`	`+utils.plot_data_2d(X)`
	`17`	`+`
	`18`	`+X, _ = cutils.generate_nonlinear_synthetic_data_classification3(n_samples=300)`
	`19`	`+utils.plot_data_2d(X)`
	`20`	`+`

Lines changed: 24 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,24 @@`
	`1`	`+import sys`
	`2`	`+path = 'J://utils'`
	`3`	`+sys.path.append(path)`
	`4`	`+`
	`5`	`+from sklearn import cluster`
	`6`	`+import common_utils as utils`
	`7`	`+import clustering_utils as cl_utils`
	`8`	`+`
	`9`	`+X, _= cl_utils.generate_synthetic_data_2d_clusters(n_samples=300, n_centers=4, cluster_std=0.60)`
	`10`	`+utils.plot_data_2d(X)`
	`11`	`+`
	`12`	`+kmeans = cluster.KMeans(5)`
	`13`	`+kmeans.fit(X)`
	`14`	`+print(kmeans.cluster_centers_)`
	`15`	`+print(kmeans.labels_)`
	`16`	`+cl_utils.plot_model_2d_clustering(kmeans, X)`
	`17`	`+`
	`18`	`+scoring = 's_score'`
	`19`	`+kmeans_estimator = cluster.KMeans()`
	`20`	`+kmeans_grid = {'n_clusters':list(range(3,9))}`
	`21`	`+kmeans_final_model = cl_utils.grid_search_best_model_clustering(kmeans_estimator, kmeans_grid, X, scoring=scoring)`
	`22`	`+print(kmeans_final_model.labels_)`
	`23`	`+print(kmeans_final_model.cluster_centers_)`
	`24`	`+cl_utils.plot_model_2d_clustering(kmeans_final_model, X)`

Lines changed: 26 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,26 @@`
	`1`	`+import sys`
	`2`	`+path = 'J://utils'`
	`3`	`+sys.path.append(path)`
	`4`	`+`
	`5`	`+from sklearn import cluster, manifold`
	`6`	`+import common_utils as utils`
	`7`	`+import clustering_utils as cl_utils`
	`8`	`+import classification_utils as cutils`
	`9`	`+`
	`10`	`+X, _ = cutils.generate_nonlinear_synthetic_data_classification2(n_samples=300)`
	`11`	`+utils.plot_data_2d(X)`
	`12`	`+`
	`13`	`+X, _ = cutils.generate_nonlinear_synthetic_data_classification3(n_samples=300)`
	`14`	`+utils.plot_data_2d(X)`
	`15`	`+`
	`16`	`+tsne = manifold.TSNE()`
	`17`	`+X_tsne = tsne.fit_transform(X)`
	`18`	`+utils.plot_data_2d(X_tsne)`
	`19`	`+`
	`20`	`+scoring = 's_score'`
	`21`	`+kmeans_estimator = cluster.KMeans()`
	`22`	`+kmeans_grid = {'n_clusters':list(range(2,7))}`
	`23`	`+kmeans_final_model = cl_utils.grid_search_best_model_clustering(kmeans_estimator, kmeans_grid, X, scoring=scoring)`
	`24`	`+print(kmeans_final_model.labels_)`
	`25`	`+print(kmeans_final_model.cluster_centers_)`
	`26`	`+cl_utils.plot_model_2d_clustering(kmeans_final_model, X)`

Lines changed: 23 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,23 @@`
	`1`	`+import sys`
	`2`	`+path = 'J://utils'`
	`3`	`+sys.path.append(path)`
	`4`	`+`
	`5`	`+from sklearn import cluster`
	`6`	`+import common_utils as utils`
	`7`	`+import clustering_utils as cl_utils`
	`8`	`+import classification_utils as cutils`
	`9`	`+`
	`10`	`+X, _= cl_utils.generate_synthetic_data_2d_clusters(n_samples=300, n_centers=4, cluster_std=0.60)`
	`11`	`+utils.plot_data_2d(X)`
	`12`	`+`
	`13`	`+X, _ = cutils.generate_nonlinear_synthetic_data_classification2(n_samples=300)`
	`14`	`+utils.plot_data_2d(X)`
	`15`	`+`
	`16`	`+X, _ = cutils.generate_nonlinear_synthetic_data_classification3(n_samples=300)`
	`17`	`+utils.plot_data_2d(X)`
	`18`	`+`
	`19`	`+scoring = 's_score'`
	`20`	`+agg_estimator = cluster.AgglomerativeClustering()`
	`21`	`+agg_grid = {'linkage':['ward', 'complete', 'average'], 'n_clusters':list(range(2,7))}`
	`22`	`+agg_final_model = cl_utils.grid_search_best_model_clustering(agg_estimator, agg_grid, X, scoring=scoring)`
	`23`	`+cl_utils.plot_model_2d_clustering(agg_final_model, X)`

Lines changed: 18 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,18 @@`
	`1`	`+import sys`
	`2`	`+path = 'E://utils'`
	`3`	`+sys.path.append(path)`
	`4`	`+`
	`5`	`+from sklearn import cluster, mixture`
	`6`	`+import common_utils as utils`
	`7`	`+import clustering_utils as cl_utils`
	`8`	`+`
	`9`	`+X, _= cl_utils.generate_synthetic_data_2d_clusters(n_samples=300, n_centers=4, cluster_std=0.60)`
	`10`	`+utils.plot_data_2d(X)`
	`11`	`+`
	`12`	`+scoring = 's_score'`
	`13`	`+gmm_estimator = mixture.GaussianMixture(n_components=3)`
	`14`	`+gmm_grid = {'n_components':list(range(10,40))}`
	`15`	`+gmm_estimator.fit(X)`
	`16`	`+gmm_estimator.predict(X)`
	`17`	`+gmm_final_model = cl_utils.grid_search_best_model_clustering(gmm_estimator, gmm_grid, X, scoring=scoring)`
	`18`	`+cl_utils.plot_model_2d_clustering(gmm_estimator, X)`

Comments

(0)