def main():
digits = mnist()
"""
do_LDA2D_KNN(digits,7,7)
do_LDA2D_KNN(digits,9,9)
do_LDA2D_KNN(digits,10,10)
do_LDA2D_KNN(digits,7,9)
do_LDA2D_KNN(digits,9,11)
do_LDA2D_KNN(digits,9,7)
"""
to_plt(digits,7,7)
plt.legend(loc='upper right')
plt.title('Plot of Error rates for different distance measures')
plt.show()
to_plt(digits,9,9)
plt.legend(loc='upper right')
plt.title('Plot of Error rates for different distance measures')
plt.show()
to_plt(digits,10,10)
plt.legend(loc='upper right')
plt.title('Plot of Error rates for different distance measures')
plt.show()
to_plt(digits,7,9)
plt.legend(loc='upper right')
plt.title('Plot of Error rates for different distance measures')
plt.show()
to_plt(digits,9,11)
plt.legend(loc='upper right')
plt.title('Plot of Error rates for different distance measures')
plt.show()
to_plt(digits,9,9)
to_plt(digits,9,7)
plt.legend(loc='upper right')
plt.title('Plot of Error rates for different distance measures')
plt.show()
def main():
digits = mnist()
mynvb = nvb()
x = center_matrix_SVD(digits.train_Images)
mynvb.fit(digits.train_Images,digits.train_Labels)
labels = mynvb.predict(digits.test_Images)
errors_Full, error_Full_index = class_error_rate(labels,digits.test_Labels)
mynvb.fit(x.PCA[:,:154],digits.train_Labels)
newtest = (digits.test_Images -x.centers)@np.transpose(x.V[:154,:])
labels = mynvb.predict(newtest)
errors_154, error_Full_index = class_error_rate(labels,digits.test_Labels)
mynvb.fit(digits.train_Images,digits.train_Labels)
mynvb.fit(x.PCA[:,:50],digits.train_Labels)
newtest = (digits.test_Images -x.centers)@np.transpose(x.V[:50,:])
labels = mynvb.predict(newtest)
errors_50, error_Full_index = class_error_rate(labels,digits.test_Labels)
mynvb.fit(digits.train_Images,digits.train_Labels)
mynvb.fit(x.PCA[:,:70],digits.train_Labels)
newtest = (digits.test_Images -x.centers)@np.transpose(x.V[:70,:])
labels = mynvb.predict(newtest)
errors_70, error_Full_index = class_error_rate(labels,digits.test_Labels)
print(errors_Full)
print(errors_154)
print(errors_50)
print(errors_70)
prob3_plots(mynvb,digits,newtest,pc=0)
prob3_plots(mynvb,digits,newtest,pc=1)
prob3_plots(mynvb,digits,newtest,pc=2)
prob3_plots(mynvb,digits,newtest,pc=3)
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 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 0: # change to 1 if you want to rerun the knn stuff
do_KNN(x,digits)
KNN_Plots(x,digits)
def main():
digits = mnist()
x = center_matrix_SVD(digits.train_Images)
errors_154 = doLDA(x,digits,154)
pickle.dump(errors_154,open('LDA_154.p','wb'))
errors_50 = doLDA(x,digits,50)
pickle.dump(errors_50,open('LDA_50.p','wb'))
errors_10 = doLDA(x,digits,10)
pickle.dump(errors_10,open('LDA_10.p','wb'))
errors_60 = doLDA(x,digits,60)
pickle.dump(errors_60,open('LDA_60.p','wb'))
prob1_plots(digits)
put_into_excel(digits)
def main(): # Our main function
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 0: # change 0 to 1 if you want to run this agian
merror = mfoldX(x.PCA[:,:],digits.train_Labels,6,10) # Run X-validation and return error rates for the full dataset
pickle.dump(merror,open('MFoldErrors','wb')) # Put our error rates in a file
merror = mfoldX(x.PCA[:,:154],digits.train_Labels,6,10) # For the 95% dataset
pickle.dump(merror,open('MFoldErrors154','wb'))
merror = mfoldX(x.PCA[:,:50],digits.train_Labels,6,10) # for the 82.5% dataset
pickle.dump(merror,open('MFoldErrors50','wb'))
MFold_plots(x) # Makes graphs from our data
def main(): # Our main function
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 0: # change 0 to 1 if you want to run this agian
merror = mfoldX(
x.PCA[:, :], digits.train_Labels, 6, 10
) # Run X-validation and return error rates for the full dataset
pickle.dump(merror, open("MFoldErrors", "wb")) # Put our error rates in a file
merror = mfoldX(x.PCA[:, :154], digits.train_Labels, 6, 10) # For the 95% dataset
pickle.dump(merror, open("MFoldErrors154", "wb"))
merror = mfoldX(x.PCA[:, :50], digits.train_Labels, 6, 10) # for the 82.5% dataset
pickle.dump(merror, open("MFoldErrors50", "wb"))
MFold_plots(x) # Makes graphs from our data
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]))
"""
from sklearn.naive_bayes import GaussianNB from PCA import mnist, center_matrix_SVD digits = mnist()
