def local_kmeans_class(I, L, x, k):
from scipy.spatial.distance import cdist
sizex = len(np.atleast_2d(x))
label = np.zeros((sizex,k))
for rowsx in range(0, sizex):
tic()
dists = cdist(I, np.atleast_2d(x[rowsx]), metric='euclidean')
toc()
center = np.zeros((10,k,28*28))
label_order = np.unique(L)
l=0
tic()
thing = np.zeros((k,28*28))
for labs in np.unique(L):
indices = L == labs
k_smallest = np.argpartition(dists[indices],tuple(range(1,k)),axis=None)
for i in range(0,k):
M = I[indices]
#center[l,i,:] = np.average(M[k_smallest[:i+1]],axis = 0)
if i == 0:
thing[i] = M[k_smallest[i+1]]
else:
thing[i] = thing[i-1] + M[k_smallest[i+1]]
center[l,:,:] = np.divide(thing,np.repeat(np.arange(1,11).reshape(10,1),28*28,axis=1))
l+=1
toc()
for i in range(k):
#print(cdist(center[:,i,:], np.atleast_2d(x[rowsx]), metric='euclidean'))
dists2center = cdist(center[:,i,:], np.atleast_2d(x[rowsx]), metric='euclidean')
k_smallest = np.argpartition(dists2center,tuple(range(1)),axis=None)
label[rowsx,i] = label_order[k_smallest[0]]
return label
def main():
digits = mnist() # Creates a class with our mnist images and labels
if open('Training SVD Data','rb')._checkReadable() == 0: # Check if file exist create it if it doesn't
print("im here")
x = center_matrix_SVD(digits.train_Images) # Creates a class with our svd and associated info
pickle.dump(x,open('Training SVD Data','wb'))
else:
x = pickle.load(open('Training SVD Data','rb')) # If we already have the file just load it
if 0:
test_Images_Center = np.subtract(digits.test_Images,np.repeat(x.centers,digits.test_Images.shape[0],0))
tic()
labels = local_kmeans_class(x.PCA[:,:50],digits.train_Labels,[email protected](x.V[:50,:]),10)
toc()
pickle.dump(labels,open('Loc_kmeans_50_lab','wb'))
loc_full = pickle.load(open('Loc_kmeans_Full_lab','rb'))
loc_50 = pickle.load(open('Loc_kmeans_50_lab','rb'))
labels_Full = pickle.load(open('KNN_Full','rb'))
# Have to transpose these because they came out backwards should fix if i use this agian
errors_full,ind_full = class_error_rate(np.transpose(loc_full),digits.test_labels)
errors_50,ind_50 = class_error_rate(np.transpose(loc_50),digits.test_labels)
errors_near,ind_50 = class_error_rate(labels_Full,digits.test_labels)
plt.figure()
plt.plot(np.arange(10)+1, errors_full, color='Green', marker='o', markersize=10, label='Full') #plots the 82.5%
plt.plot(np.arange(10)+1, errors_50, color='Yellow', marker='o', markersize=10, label='82.5%')
plt.plot(np.arange(10)+1, errors_near, color='Blue', marker='o', markersize=10, label='kNN')
plt.grid(1) # Turns the grid on
plt.title('Plot of local KNN Error rates')
plt.legend(loc='upper right') # Puts a legend on the plot
plt.show()
def main():
digits = mnist() # Creates a class with our mnist images and labels
if open('Training SVD Data', 'rb')._checkReadable(
) == 0: # Check if file exist create it if it doesn't
print("im here") # Just wanted to check if it was going in here
x = center_matrix_SVD(
digits.train_Images
) # Creates a class with our svd and associated info
pickle.dump(x, open('Training SVD Data', 'wb'))
else:
x = pickle.load(open('Training SVD Data',
'rb')) # If we already have the file just load it
if 0: # if this is zero skip
test_Images_Center = np.subtract(
digits.test_Images,
np.repeat(x.centers, digits.test_Images.shape[0], 0))
tic()
myLDA = LDA() # Create a new instance of the LDA class
new_train = myLDA.fit_transform(
x.PCA[:, :154], digits.train_Labels) # It will fit based on x.PCA
new_test = myLDA.transform(test_Images_Center @ np.transpose(
x.V[:154, :])) # get my transformed test dataset
Knn_labels, nearest = KNN(new_train, digits.train_Labels, new_test,
10) # Run kNN on the new data
toc()
pickle.dump(Knn_labels, open('FDAKNN_Lables', 'wb'))
pickle.dump(nearest, open('FDAKNN_neastest', 'wb'))
fda = pickle.load(open('FDAKNN_Lables', 'rb'))
labels_Full = pickle.load(open('KNN_Full', 'rb'))
labels_50 = pickle.load(open('KNN_50', 'rb'))
errors_fda, ind_fda = class_error_rate(fda, digits.test_labels)
errors_near, ind_near = class_error_rate(labels_Full, digits.test_labels)
errors_50, ind_50 = class_error_rate(labels_50, digits.test_labels)
plt.figure()
plt.plot(np.arange(10) + 1,
errors_fda,
color='Green',
marker='o',
markersize=10,
label='fda') #plots the 82.5%
plt.plot(np.arange(10) + 1,
errors_near,
color='Blue',
marker='o',
markersize=10,
label='kNN')
plt.plot(np.arange(10) + 1,
errors_50,
color='Yellow',
marker='o',
markersize=10,
label='kNN 50')
plt.grid(1) # Turns the grid on
plt.title('Plot of Knn with FDA Error rates')
plt.legend(loc='upper right') # Puts a legend on the plot
plt.show()
print(confusion_matrix(digits.test_labels, labels_Full[5]))
print(confusion_matrix(digits.test_labels, fda[5]))
print(confusion_matrix(digits.test_labels, labels_50[5]))
"""
def main():
digits = mnist() # Creates a class with our mnist images and labels
if open('Training SVD Data', 'rb')._checkReadable(
) == 0: # Check if file exist create it if it doesn't
print("im here")
x = center_matrix_SVD(
digits.train_Images
) # Creates a class with our svd and associated info
pickle.dump(x, open('Training SVD Data', 'wb'))
else:
x = pickle.load(open('Training SVD Data',
'rb')) # If we already have the file just load it
if 0:
test_Images_Center = np.subtract(
digits.test_Images,
np.repeat(x.centers, digits.test_Images.shape[0], 0))
tic()
labels = local_kmeans_class(
x.PCA[:, :50], digits.train_Labels,
test_Images_Center @ np.transpose(x.V[:50, :]), 10)
toc()
pickle.dump(labels, open('Loc_kmeans_50_lab', 'wb'))
loc_full = pickle.load(open('Loc_kmeans_Full_lab', 'rb'))
loc_50 = pickle.load(open('Loc_kmeans_50_lab', 'rb'))
labels_Full = pickle.load(open('KNN_Full', 'rb'))
# Have to transpose these because they came out backwards should fix if i use this agian
errors_full, ind_full = class_error_rate(np.transpose(loc_full),
digits.test_labels)
errors_50, ind_50 = class_error_rate(np.transpose(loc_50),
digits.test_labels)
errors_near, ind_50 = class_error_rate(labels_Full, digits.test_labels)
plt.figure()
plt.plot(np.arange(10) + 1,
errors_full,
color='Green',
marker='o',
markersize=10,
label='Full') #plots the 82.5%
plt.plot(np.arange(10) + 1,
errors_50,
color='Yellow',
marker='o',
markersize=10,
label='82.5%')
plt.plot(np.arange(10) + 1,
errors_near,
color='Blue',
marker='o',
markersize=10,
label='kNN')
plt.grid(1) # Turns the grid on
plt.title('Plot of local KNN Error rates')
plt.legend(loc='upper right') # Puts a legend on the plot
plt.show()
def KNN(I, L, x, k, weights=1):
from scipy import stats
from scipy.spatial.distance import cdist
"""
I is the matrix of obs
L are the labels
x is what we are trying to classify
k are how many neighbors to look at or whatever
first we want to create a matrix of distances from each
object we want to classify to every object in our training set
"""
sizex = len(np.atleast_2d(x))
label = np.zeros((k, sizex))
for rowsx in range(0, sizex):
tic()
dists = cdist(I, np.atleast_2d(x[rowsx]), metric='euclidean')
# Now we should have all our distances in our dist array
# The next step is to use this info to classify each unknown obj
k_smallest = np.argpartition(dists, tuple(range(1, k + 1)), axis=None)
if weights == 1:
for i in range(0, k):
label[i, rowsx] = stats.mode(L[k_smallest[:i + 1]])[0]
else:
labs = np.unique(L)
myimage = x[rowsx].reshape(28, 28)
for i in range(k):
lab_weighted = np.zeros(np.unique(L).shape[0])
d = dists[k_smallest[:i + 2]][:, 0]
weight_function = np.add(
np.divide(d, np.subtract(np.min(d), np.max(d))),
1 - np.min(d) / np.subtract(np.min(d), np.max(d)))
for p in range(0, labs.shape[0]):
indices = inboth(
np.arange(0, L.shape[0])[L == labs[p]],
k_smallest[:i + 2])
lab_weighted[p] = np.sum(
np.multiply(weight_function, indices))
label[i, rowsx] = labs[np.argmax(lab_weighted)]
toc()
print(rowsx)
return label
def local_kmeans_class(I, L, x, k):
from scipy.spatial.distance import cdist
sizex = len(np.atleast_2d(x))
label = np.zeros((sizex, k))
for rowsx in range(0, sizex):
tic()
dists = cdist(I, np.atleast_2d(x[rowsx]), metric='euclidean')
toc()
center = np.zeros((10, k, 28 * 28))
label_order = np.unique(L)
l = 0
tic()
thing = np.zeros((k, 28 * 28))
for labs in np.unique(L):
indices = L == labs
k_smallest = np.argpartition(dists[indices],
tuple(range(1, k)),
axis=None)
for i in range(0, k):
M = I[indices]
#center[l,i,:] = np.average(M[k_smallest[:i+1]],axis = 0)
if i == 0:
thing[i] = M[k_smallest[i + 1]]
else:
thing[i] = thing[i - 1] + M[k_smallest[i + 1]]
center[l, :, :] = np.divide(
thing,
np.repeat(np.arange(1, 11).reshape(10, 1), 28 * 28, axis=1))
l += 1
toc()
for i in range(k):
#print(cdist(center[:,i,:], np.atleast_2d(x[rowsx]), metric='euclidean'))
dists2center = cdist(center[:, i, :],
np.atleast_2d(x[rowsx]),
metric='euclidean')
k_smallest = np.argpartition(dists2center,
tuple(range(1)),
axis=None)
label[rowsx, i] = label_order[k_smallest[0]]
return label
def main():
digits = mnist() # Creates a class with our mnist images and labels
if open('Training SVD Data','rb')._checkReadable() == 0: # Check if file exist create it if it doesn't
x = center_matrix_SVD(digits.train_Images) # Creates a class with our svd and associated info
pickle.dump(x,open('Training SVD Data','wb'))
else:
x = pickle.load(open('Training SVD Data','rb')) # If we already have the file just load it
if 1: # if this is zero skip
test_Images_Center = np.subtract(digits.test_Images,np.repeat(x.centers,digits.test_Images.shape[0],0))
tic()
myLDA = LDA() # Create a new instance of the LDA class
new_train = myLDA.fit_transform(x.PCA[:,:154],digits.train_Labels) # It will fit based on x.PCA
new_test = myLDA.transform([email protected](x.V[:154,:])) # get my transformed test dataset
Knn_labels = local_kmeans_class(new_train,digits.train_Labels,new_test,10) # Run kNN on the new data
toc()
pickle.dump(Knn_labels,open('Loc_kmeans_fda_lab','wb'))
fda = pickle.load(open('Loc_kmeans_fda_lab','rb'))
labels_Full = pickle.load(open('KNN_Full','rb'))
loc_full = pickle.load(open('Loc_kmeans_Full_lab','rb'))
errors_fda,ind_fda = class_error_rate(np.transpose(fda),digits.test_labels)
errors_near,ind_near = class_error_rate(labels_Full,digits.test_labels)
errors_full,ind_full = class_error_rate(np.transpose(loc_full),digits.test_labels)
labels_50 = pickle.load(open('KNN_50','rb'))
errors_50,ind_50 = class_error_rate(labels_50,digits.test_labels)
print(errors_full)
plt.figure()
plt.plot(np.arange(10)+1, errors_fda, color='Green', marker='o', markersize=10, label='fda Kmeans') #plots the 82.5%
plt.plot(np.arange(10)+1, errors_near, color='Blue', marker='o', markersize=10, label='kNN')
plt.plot(np.arange(10)+1, errors_full, color='Yellow', marker='o', markersize=10, label='Full Kmeans')
plt.plot(np.arange(10)+1, errors_50, color='Red', marker='o', markersize=10, label='kNN 50')
axes = plt.gca()
axes.set_ylim([0.015,0.12])
plt.grid(1) # Turns the grid on
plt.title('Plot of Local Kmeans with FDA Error rates')
plt.legend(loc='upper right') # Puts a legend on the plot
plt.show()
project_back(x,digits)
def main():
digits = mnist() # Creates a class with our mnist images and labels
if open('Training SVD Data','rb')._checkReadable() == 0: # Check if file exist create it if it doesn't
print("im here") # Just wanted to check if it was going in here
x = center_matrix_SVD(digits.train_Images) # Creates a class with our svd and associated info
pickle.dump(x,open('Training SVD Data','wb'))
else:
x = pickle.load(open('Training SVD Data','rb')) # If we already have the file just load it
if 0: # if this is zero skip
test_Images_Center = np.subtract(digits.test_Images,np.repeat(x.centers,digits.test_Images.shape[0],0))
tic()
myLDA = LDA() # Create a new instance of the LDA class
new_train = myLDA.fit_transform(x.PCA[:,:154],digits.train_Labels) # It will fit based on x.PCA
new_test = myLDA.transform([email protected](x.V[:154,:])) # get my transformed test dataset
Knn_labels, nearest = KNN(new_train,digits.train_Labels,new_test,10) # Run kNN on the new data
toc()
pickle.dump(Knn_labels,open('FDAKNN_Lables','wb'))
pickle.dump(nearest,open('FDAKNN_neastest','wb'))
fda = pickle.load(open('FDAKNN_Lables','rb'))
labels_Full = pickle.load(open('KNN_Full','rb'))
labels_50 = pickle.load(open('KNN_50','rb'))
errors_fda,ind_fda = class_error_rate(fda,digits.test_labels)
errors_near,ind_near = class_error_rate(labels_Full,digits.test_labels)
errors_50,ind_50 = class_error_rate(labels_50,digits.test_labels)
plt.figure()
plt.plot(np.arange(10)+1, errors_fda, color='Green', marker='o', markersize=10, label='fda') #plots the 82.5%
plt.plot(np.arange(10)+1, errors_near, color='Blue', marker='o', markersize=10, label='kNN')
plt.plot(np.arange(10)+1, errors_50, color='Yellow', marker='o', markersize=10, label='kNN 50')
plt.grid(1) # Turns the grid on
plt.title('Plot of Knn with FDA Error rates')
plt.legend(loc='upper right') # Puts a legend on the plot
plt.show()
print(confusion_matrix(digits.test_labels,labels_Full[5]))
print(confusion_matrix(digits.test_labels,fda[5]))
print(confusion_matrix(digits.test_labels,labels_50[5]))
"""
def KNN(I, L, x, k,weights = 1):
from scipy import stats
from scipy.spatial.distance import cdist
"""
I is the matrix of obs
L are the labels
x is what we are trying to classify
k are how many neighbors to look at or whatever
first we want to create a matrix of distances from each
object we want to classify to every object in our training set
"""
sizex = len(np.atleast_2d(x))
label = np.zeros((k,sizex))
for rowsx in range(0, sizex):
tic()
dists = cdist(I, np.atleast_2d(x[rowsx]), metric='euclidean')
# Now we should have all our distances in our dist array
# The next step is to use this info to classify each unknown obj
k_smallest = np.argpartition(dists,tuple(range(1,k+1)),axis=None)
if weights == 1:
for i in range(0,k):
label[i,rowsx] = stats.mode(L[k_smallest[:i+1]])[0]
else:
labs = np.unique(L)
myimage = x[rowsx].reshape(28,28)
for i in range(k):
lab_weighted = np.zeros(np.unique(L).shape[0])
d = dists[k_smallest[:i+2]][:,0]
weight_function = np.add(np.divide(d, np.subtract(np.min(d),np.max(d))),1-np.min(d)/np.subtract(np.min(d),np.max(d)))
for p in range(0,labs.shape[0]):
indices = inboth(np.arange(0,L.shape[0])[L == labs[p]],k_smallest[:i+2])
lab_weighted[p]= np.sum(np.multiply(weight_function,indices))
label[i,rowsx] = labs[np.argmax(lab_weighted)]
toc()
print(rowsx)
return label
"""
label = pickle.load(open('kNNWeight.p', 'rb'))
from sklearn.metrics import confusion_matrix
import pandas
print(test_labels.shape)
x = confusion_matrix(test_labels,label[2])
error = np.zeros(10)
for n in range(10):
error[n] = 1-x[n,n]/(np.sum(x,axis=0)[n])
print(error)
import matplotlib.pyplot as plt
plt.plot(range(10),error)
plt.show()
print(pandas.DataFrame(x,range(10),range(10)))
"""
"""
tic()
m = mfoldX(train_Images[:6000], train_Labels[:6000], 6, 10)
print(m)
toc()
pickle.dump(m, open('kisfive.p', 'wb'))
"""
"""
import matplotlib.pyplot as plt
m = pickle.load(open('kisfive.p', 'rb'))
plt.plot(range(1,11),m)
plt.show()
"""
"""
from sklearn import neighbors, datasets
"""
label = pickle.load(open('kNNWeight.p', 'rb'))
from sklearn.metrics import confusion_matrix
import pandas
print(test_labels.shape)
x = confusion_matrix(test_labels,label[2])
error = np.zeros(10)
for n in range(10):
error[n] = 1-x[n,n]/(np.sum(x,axis=0)[n])
print(error)
import matplotlib.pyplot as plt
plt.plot(range(10),error)
plt.show()
print(pandas.DataFrame(x,range(10),range(10)))
"""
"""
tic()
m = mfoldX(train_Images[:6000], train_Labels[:6000], 6, 10)
print(m)
toc()
pickle.dump(m, open('kisfive.p', 'wb'))
"""
"""
import matplotlib.pyplot as plt
m = pickle.load(open('kisfive.p', 'rb'))
plt.plot(range(1,11),m)
plt.show()
"""
"""
from sklearn import neighbors, datasets
