# import 
import numpy as np
import matplotlib.pyplot as plt
import scipy.cluster.hierarchy as sch
from sklearn.cluster import AgglomerativeClustering

# fake data
gradesy=np.array([94.28379291,86.98982195,86.63611546,85.7203357,84.52017914,83.11406572,82.5180994,80.0522343,77.76367201,76.87708018,74.87290704,74.43641397,70.92109845,70.74501915,69.955087,68.72333003,67.43377364,65.31794233,65.19391681,64.07626518,46.06843416])
gradesx=np.zeros(gradesy.size)
grades=np.concatenate((gradesx.reshape(gradesy.size,1),gradesy.reshape(gradesy.size,1)),axis=1)

#plot fake date before sorting to see input
plt.scatter(grades[:,0], grades[:,1], s=100)

# make dendrogram
dendrogram = sch.dendrogram(sch.linkage(grades, method='ward'))

# find clusters
clusters=11
hc = AgglomerativeClustering(n_clusters=clusters, affinity = 'euclidean', linkage = 'ward')

# make 2d scatter plot even though its not the best way to visualize this
y_hc = hc.fit_predict(grades)
for i in range(0,clusters):
    plt.scatter(grades[y_hc ==i,0], grades[y_hc == i,1], s=100)
    print("Cluster ",i," ", grades[y_hc == i,1])