Add files via upload

Author: Algorithmica

2019-october/15.clustering/1.clustering-pattern.py

@@ -0,0 +1,20 @@
+import sys
+path = 'J://utils'
+sys.path.append(path)
+
+import common_utils as utils
+import clustering_utils as cl_utils
+import classification_utils as cutils
+
+X, y = cl_utils.generate_synthetic_data_2d_clusters(n_samples=300, n_centers=4, cluster_std=0.60)
+utils.plot_data_2d(X)
+
+X, _ = cl_utils.generate_synthetic_data_3d_clusters(n_samples=500, n_centers=3, cluster_std=1.4)
+utils.plot_data_3d(X)
+
+X, _ = cutils.generate_nonlinear_synthetic_data_classification2(n_samples=300)
+utils.plot_data_2d(X)
+
+X, _ = cutils.generate_nonlinear_synthetic_data_classification3(n_samples=300)
+utils.plot_data_2d(X)
+

2019-october/15.clustering/2.clustering-kmeans.py

@@ -0,0 +1,24 @@
+import sys
+path = 'J://utils'
+sys.path.append(path)
+
+from sklearn import cluster
+import common_utils as utils
+import clustering_utils as cl_utils
+
+X, _= cl_utils.generate_synthetic_data_2d_clusters(n_samples=300, n_centers=4, cluster_std=0.60)
+utils.plot_data_2d(X)
+
+kmeans = cluster.KMeans(5)
+kmeans.fit(X)
+print(kmeans.cluster_centers_)
+print(kmeans.labels_)
+cl_utils.plot_model_2d_clustering(kmeans, X)
+
+scoring = 's_score'
+kmeans_estimator = cluster.KMeans()
+kmeans_grid = {'n_clusters':list(range(3,9))}
+kmeans_final_model = cl_utils.grid_search_best_model_clustering(kmeans_estimator, kmeans_grid, X, scoring=scoring)
+print(kmeans_final_model.labels_)
+print(kmeans_final_model.cluster_centers_)
+cl_utils.plot_model_2d_clustering(kmeans_final_model, X)

2019-october/15.clustering/3.kmeans-limitations.py

@@ -0,0 +1,26 @@
+import sys
+path = 'J://utils'
+sys.path.append(path)
+
+from sklearn import cluster, manifold
+import common_utils as utils
+import clustering_utils as cl_utils
+import classification_utils as cutils
+
+X, _ = cutils.generate_nonlinear_synthetic_data_classification2(n_samples=300)
+utils.plot_data_2d(X)
+
+X, _ = cutils.generate_nonlinear_synthetic_data_classification3(n_samples=300)
+utils.plot_data_2d(X)
+
+tsne = manifold.TSNE()
+X_tsne = tsne.fit_transform(X)
+utils.plot_data_2d(X_tsne)
+
+scoring = 's_score'
+kmeans_estimator = cluster.KMeans()
+kmeans_grid = {'n_clusters':list(range(2,7))}
+kmeans_final_model = cl_utils.grid_search_best_model_clustering(kmeans_estimator, kmeans_grid, X, scoring=scoring)
+print(kmeans_final_model.labels_)
+print(kmeans_final_model.cluster_centers_)
+cl_utils.plot_model_2d_clustering(kmeans_final_model, X)

2019-october/15.clustering/4.clustering-hierarchical.py

@@ -0,0 +1,23 @@
+import sys
+path = 'J://utils'
+sys.path.append(path)
+
+from sklearn import cluster
+import common_utils as utils
+import clustering_utils as cl_utils
+import classification_utils as cutils
+
+X, _= cl_utils.generate_synthetic_data_2d_clusters(n_samples=300, n_centers=4, cluster_std=0.60)
+utils.plot_data_2d(X)
+
+X, _ = cutils.generate_nonlinear_synthetic_data_classification2(n_samples=300)
+utils.plot_data_2d(X)
+
+X, _ = cutils.generate_nonlinear_synthetic_data_classification3(n_samples=300)
+utils.plot_data_2d(X)
+
+scoring = 's_score'
+agg_estimator = cluster.AgglomerativeClustering()
+agg_grid = {'linkage':['ward', 'complete', 'average'], 'n_clusters':list(range(2,7))}
+agg_final_model = cl_utils.grid_search_best_model_clustering(agg_estimator, agg_grid, X, scoring=scoring)
+cl_utils.plot_model_2d_clustering(agg_final_model, X)

2019-october/15.clustering/5.clustering-gmm.py

@@ -0,0 +1,18 @@
+import sys
+path = 'E://utils'
+sys.path.append(path)
+
+from sklearn import cluster, mixture
+import common_utils as utils
+import clustering_utils as cl_utils
+
+X, _= cl_utils.generate_synthetic_data_2d_clusters(n_samples=300, n_centers=4, cluster_std=0.60)
+utils.plot_data_2d(X)
+
+scoring = 's_score'
+gmm_estimator = mixture.GaussianMixture(n_components=3)
+gmm_grid = {'n_components':list(range(10,40))}
+gmm_estimator.fit(X)
+gmm_estimator.predict(X)
+gmm_final_model = cl_utils.grid_search_best_model_clustering(gmm_estimator, gmm_grid, X, scoring=scoring)
+cl_utils.plot_model_2d_clustering(gmm_estimator, X)