def evaluation_scores(groundtruth, labels_pred):
"""
Eval scores of the predicted results.
:param: groundtruth (type list): the groundtruth (GT) of cluster assignment. Each element denotes an item's GT cluster_id.
:param: labels_pred (type list): the predicted cluster assignments. Each element denotes an item's predicted cluster_id.
"""
NMI = metrics.normalized_mutual_info_score(groundtruth,labels_pred)
A = metrics.accuracy(groundtruth,labels_pred)
F1 = metrics.f_measure(groundtruth,labels_pred)
P = metrics.purity(groundtruth,labels_pred)
RI = metrics.random_index(groundtruth,labels_pred)
ARI = metrics.adjusted_rand_score(groundtruth,labels_pred)
map_pairs = metrics.get_map_pairs(groundtruth,labels_pred)
return NMI, A, F1, P, RI, ARI, map_pairs
# casestudy_iris_pca.py
import data_iris
import hierarchical
import matplotlib.pyplot as plt
import metrics
import numpy as np
import pca
import plot_data
# (1) load data
iris = data_iris.iris()
X,class_label = iris.load()
# perform pca and reduce dimension to 2
model_pca = pca.pca()
model_pca.fit(X)
R = model_pca.data_reduced_dimension(reduced_dim=2)
plot_data.plot_scatter_class(R,class_label,"Iris Data Projected to 2 Dimensions using PCA","u0","u1")
# (2) create model
model = hierarchical.hierarchical()
# (3) fit model
model.fit(R)
print("Time fit: {}".format(model.time_fit))
# (4) results
level = -3
print("Purity: {}".format(metrics.purity(model.clustersave[level],class_label)))
print("Davies-Bouldin: {}".format(metrics.davies_bouldin(R,model.clustersave[level])))
print("Silhouette: {}".format(metrics.silhouette(R,model.clustersave[level])))
model.plot_cluster(nlevel=level,title="Hierarchical Clustering for Iris Dataset reduced to 2d",xlabel="u0",ylabel="u1")
metrics.plot_cluster_distribution(model.clustersave[level],class_label)
plt.show()
start = time.time()
print("# Tuning hyper-parameters for", score, "\n")
clf = GridSearchCV(LinearSVC(C=1, max_iter=1000),
param_grid,
cv=5,
scoring='%s' % score)
clf.fit(x_train, y_train)
print("Best parameters set found on development set:\n")
print(clf.best_params_)
print("Best value for ", score, ":\n")
print(clf.best_score_)
Y_true, Y_pred = y_test, clf.predict(x_test)
print("Report")
print(classification_report(Y_true, Y_pred, digits=6))
print(metrics.purity(Y_true, Y_pred))
print(metrics.entropy(Y_true, Y_pred))
print("Accuracy: ", clf.score(x_test, y_test))
print("Time taken:", time.time() - start, "\n")
endtime = time.time()
print("svc time cost: ", time.time() - start)
print("Total time taken: ", endtime - start, "seconds.")
print("********************************************************")
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from matplotlib.ticker import NullFormatter
from sklearn import manifold, datasets
import numpy as np
import matplotlib