#Demonstration of semi-supervised learning
import numpy as np
import graphlearning as gl
import matplotlib.pyplot as plt
import sklearn.datasets as datasets
#data
n = 500
X, L = datasets.make_moons(n_samples=n, noise=0.1)
#Build graph
k = 10
I, J, D = gl.knnsearch(X, k)
W = gl.weight_matrix(I, J, D, k)
#Randomly choose labels
m = 5 #5 labels per class
ind = gl.randomize_labels(L, m) #indices of labeled points
#Semi-supervised learning
l = gl.graph_ssl(W, ind, L[ind], method='laplace')
#Compute accuracy
acc = gl.accuracy(l, L, m)
print("Accuracy=%f" % acc)
#Plot result (red points are labels)
plt.scatter(X[:, 0], X[:, 1], c=l)
plt.scatter(X[ind, 0], X[ind, 1], c='r')
plt.show()
k = 130
I, J, D = construct_graph(cleandata, k)
print(I)
print(J)
print(D)
W = gl.weight_matrix(I, J, D, k)
#Randomly choose labels
m = 140 #5 labels per class
ind = gl.randomize_labels(label, m) #indices of labeled points
#Semi-supervised learning
l = gl.graph_ssl(W, ind, label[ind], method='poisson')
#Compute accuracy
acc = gl.accuracy(l, label, len(ind))
print("Accuracy=%f" % acc)
'''
#xtrain,ytrain is training data, xtest contains label of bones, be careful
xtrain,xtest,ytrain,ytest=split(cleandata,split_percentage)
print(xtrain[0])
print(xtest[0])
#clf is the trained classifier
clf=train_classifier(xtrain,ytrain)
#prediction is a list in form of [bone label, prediction1, prediction2 ...]
prediction=curve_prediction(xtest,clf)
print(prediction)
#Result is a list in form of [bone label, prediction]
Result=voting(prediction)
#print(Result)
print(cleandata[0])
print(label[500:1000])
#Build graph
k = 500
I, J, D = gl.knnsearch(cleandata, k)
W = gl.weight_matrix(I, J, D, k)
#Randomly choose labels
m = 5 #5 labels per class
ind = gl.randomize_labels(label, m) #indices of labeled points
#Semi-supervised learning
l = gl.graph_ssl(W, ind, label[ind], method='Laplace')
#Compute accuracy
acc = gl.accuracy(l, label, m)
print("Accuracy=%f" % acc)
'''
#xtrain,ytrain is training data, xtest contains label of bones, be careful
xtrain,xtest,ytrain,ytest=split(cleandata,split_percentage)
print(xtrain[0])
print(xtest[0])
#clf is the trained classifier
clf=train_classifier(xtrain,ytrain)
#prediction is a list in form of [bone label, prediction1, prediction2 ...]
prediction=curve_prediction(xtest,clf)
print(prediction)
#Result is a list in form of [bone label, prediction]
Result=voting(prediction)
#print(Result)
knn_mask = utils.create_directed_KNN_mask(D=D.copy(),
knn_param=k,
D_type='distance')
sigma = np.mean(D[:, knn_mask[:, -1]]) / 2
G = np.exp(-(D**2) / (sigma**2))
W_knn = knn_graph(G, knn_mask, k, 1e-10, directed=True)
W_nnk = nnk_graph(G, knn_mask, k, 1e-10, directed=True)
# Randomly choose labels
m = 2 # 5 labels per class
ind = gl.randomize_labels(L, m) # indices of labeled points
# Semi-supervised learning
l_knn = gl.graph_ssl(W_knn, ind, L[ind], method='poissonmbo', symmetrize=False)
knn_acc = gl.accuracy(l_knn, L, m)
l_knn[ind] = 2
l_nnk = gl.graph_ssl(W_nnk, ind, L[ind], method='poissonmbo', symmetrize=False)
nnk_acc = gl.accuracy(l_nnk, L, m)
l_nnk[ind] = 2
# Plot result (red points are labels)
fig = plt.figure(figsize=(12, 6))
ax = plt.subplot(1, 2, 1)
utils.plot_graph(W_knn, X, vertex_color=l_knn, ax=ax)
ax.set_title(f"KNN graph, Acc:{knn_acc}")
ax = plt.subplot(1, 2, 2)
utils.plot_graph(W_nnk, X, vertex_color=l_nnk, ax=ax)
ax.set_title(f"NNK graph, Acc:{nnk_acc}")