#username = mzr3
import EM as em
import pandas as pd
if __name__ == "__main__":
breast_cancer = pd.read_csv('./breast-cancer-wisconsin.csv')
li = list(breast_cancer)
breast_cancer = pd.DataFrame(breast_cancer.values, columns=li)
# Class=li[-1]
arr = breast_cancer.values
y = arr[:, -1]
X = arr[:, 0:-1]
tester = em.ExpectationMaximizationTestCluster(X,
y,
clusters=range(2, 15),
plot=True,
stats=True)
tester.run()
li = list(breast_cancer)
breast_cancer = pd.DataFrame(breast_cancer.values, columns=li)
Class = li[-1]
arr = breast_cancer.values
y = arr[:, -1]
X = arr[:, 0:-1]
clusters = range(2, 15)
sp = SparseRandomProjection(n_components=4)
output = sp.fit_transform(X)
tester = em.ExpectationMaximizationTestCluster(output,
y,
clusters=range(2, 15),
plot=False,
stats=True)
silhouette_EM, vmeasure_scores = tester.run()
tester = kmtc.KMeansTestCluster(output,
y,
clusters=range(2, 15),
plot=False,
stats=True)
silhouette_kmeans, V_measure = tester.run()
"""
Plot Silhouette Score from observations from the cluster centroid
to use the Elbow Method to identify number of clusters to choose
"""
plt.plot(clusters, silhouette_kmeans, 'r^-', label="K Means")