def pred_on_pca():
# load data
raw_data = load_digits()
X = raw_data.data
y = raw_data.target
# organize data
X_train = X[:60]
y_train = y[:60]
X_valid = X[60:80]
y_valid = y[60:80]
# train
pca, X_proj = pca_X(X_train, n_comp=30)
md_clf_new = svm_train(X_proj, y_train)
# validate
file = "unseen_dig.png"
prediction = pca_svm_pred(file, pca, md_clf_new)
print("The prediction: ", prediction[0])
ytrain = np.delete(y, i, axis = 0)
md_pca, Xproj = prf.pca_X(Xtrain, n_comp = 50)
XtestProj = md_pca.transform(Xtest.reshape(1,-1))
md_clf = prf.svm_train(Xproj, ytrain)
predic = md_clf.predict(XtestProj)
if(predic[0] != ytest):
Errors +=1
print("success rate: ", (1 - (Errors/X.shape[0])) * 100, "%")
# START OF PART C
#NOTE MUST CHANGE PICTURE DIRECTORY TO MATCH YOUR INDIVIDUAL DIRECTORY
GuessPicture = "../Pictures/whoswho.JPG"
faces = prf.get_faces(GuessPicture)
predictions = prf.pca_svm_pred(faces, md_pca, md_clf)
print("PCA+SVM predition for person 1: {}".format(name_dic[predictions[0]]))
print("PCA+SVM predition for person 2: {}".format(name_dic[predictions[1]]))
print("PCA+SVM predition for person 3: {}".format(name_dic[predictions[2]]))
plt.imshow(cv2.imread(GuessPicture))
plt.axis("off")
plt.show()
p = md_clf.predict(Xtest_proj)[0]
if ytest == p:
perc += 1.
print('Pred: {} Ans: {}'.format(p, ytest))
else:
print('Pred: {} Ans: {} <--- incorrect; image index: {}'.format(
p, ytest, select_idx))
print(
'The percentage of correct predictions (for validation) is: {:1f}%'.format(
perc * 100. / tot))
######################################## Testing #####################################
md_pca.fit(X) # Re-fit the PCA axis onto X, the original data set
pre1 = phys_dict[pca_svm_pred('unseen_phys1.jpg',
md_pca,
md_clf,
dim1=45,
dim2=60)[0]]
print('PCA+SVM prediction for physicist 1: {}'.format(pre1))
pre2 = phys_dict[pca_svm_pred('unseen_phys2.jpg',
md_pca,
md_clf,
dim1=45,
dim2=60)[0]]
print('PCA+SVM prediction for physicist 2: {}'.format(pre2))
# set_trace()
Xtrain = np.delete(X, select_idx, axis=0)
ytrain = np.delete(y, select_idx)
md_pca.fit(Xtrain)
Xtrain_proj = md_pca.transform(Xtrain)
Xtest = X[select_idx].reshape(1, -1)
ytest = y[select_idx]
Xtest_proj = md_pca.transform(Xtest)
md_clf = svm_train(Xtrain_proj, ytrain)
pre = md_clf.predict(Xtest_proj)
if pre == ytest:
perc += 1.0
perc /= tot / 100.0
print("Success rate: {:f}".format(perc))
unseen_phys1 = "unseen_phys1.jpg"
unseen_phys2 = "unseen_phys2.jpg"
pre1 = pca_svm_pred(unseen_phys1, md_pca, md_clf)
pre2 = pca_svm_pred(unseen_phys2, md_pca, md_clf)
pre_ein_statement = "PCA+SVM prediction for physicist 1: {:s}".format(phys_dict[pre1[0]])
pre_bohr_statement = "PCA+SVM prediction for physicist 2: {:s}".format(phys_dict[pre2[0]])
print(pre_ein_statement)
print(pre_bohr_statement)
Xtest = X[select_idx].reshape(1, -1)
ytest = y[select_idx]
Xtest_proj = md_pca.transform(Xtest)
### if uses line55, the success rate will become about 81%
### because for every loop, it re-trains the svm with a 'less complete' data reference
# md_clf = svm_train(Xtrain_proj, ytrain)
p = md_clf.predict(Xtest_proj)[0]
if ytest == p:
perc += 1.
print('Pred: {} Ans: {}'.format(p, ytest))
else:
print('Pred: {} Ans: {} <--- incorrect; image index: {}'.format(p, ytest, select_idx))
print('The percentage of correct predictions (for validation) is: {:1f}%'.format(perc*100./tot))
######################################## Testing #####################################
md_pca.fit(X) # Re-fit the PCA axis onto X, the original data set
pre1 = phys_dict[pca_svm_pred('unseen_phys1.jpg', md_pca, md_clf, dim1 = 45, dim2 = 60)[0]]
print('PCA+SVM prediction for physicist 1: {}'.format(pre1))
pre2 = phys_dict[pca_svm_pred('unseen_phys2.jpg', md_pca, md_clf, dim1 = 45, dim2 = 60)[0]]
print('PCA+SVM prediction for physicist 2: {}'.format(pre2))