def extra_data():
pca = ("pca", IncrementalPCA(n_components=500))
scale = ("scale", StandardScaler())
bias = ("bias", AddBiasTerm())
svc = ("svc", SVC(kernel="poly", degree=best_degree, C=best_c, gamma=best_gamma))
p = Pipeline([pca, scale, bias, svc])
n = 50000
num_slices = 50
N,M = Xtrain_full.shape
scores_perturb = []
scores_extra = []
extra_data, extra_targets = gd.generate_extra_data(n)
perturbed_data, perturbed_targets = gd.perturb_modified_digits(Xtrain_full, Ytrain_full, n)
for i in range(-1,num_slices):
print "Iteration "+ str(i+2)
Xp = np.vstack((Xtrain_full, extra_data[0:(i+1)*n/num_slices]))
Yp = np.vstack((Ytrain_full, extra_targets[0:(i+1)*n/num_slices]))
p.fit(Xp, Yp)
scores_extra.append({"train_score": p.score(Xp, Yp), "test_score": p.score(Xtest, Ytest),
"num_examples":N+(i+1)*n/num_slices, "i":i})
Xp = np.vstack((Xtrain_full, perturbed_data[0:(i+1)*n/num_slices]))
Yp = np.vstack((Ytrain_full, perturbed_targets[0:(i+1)*n/num_slices]))
p.fit(Xp, Yp)
scores_perturb.append({"train_score": p.score(Xp, Yp), "test_score": p.score(Xtest, Ytest),
"num_examples":N+(i+1)*n/num_slices, "i":i})
d = {"scores_perturb":scores_perturb, "scores_extra": scores_extra}
with open("ignore/extra_data_graph.json", "w") as f:
json.dump(d, f)
Y = np.load('./data/train_outputs.npy')
# Y = Y.reshape( Y.shape[0] , 1 )
Y = Y.astype(np.int32)
PIXELS = 48
print 'Original Dataset size:'
print X.shape
import generate_extra_data as ged
x_new, y_new = ged.perturb_modified_digits(X,Y,500000)
X = np.vstack((X,x_new))
Y = np.hstack((Y,y_new))
print 'New dataset size:'
print X.shape, Y.shape
X = X.reshape((-1,1, PIXELS, PIXELS))
validation_division = int(len(X)*validate_split)
top = int(len(X)*max_split)
X_train, X_val = X[:validation_division,:], X[validation_division:top,:]
Y_train, Y_val = Y[:validation_division], Y[validation_division:top]
# In[6]:
X = np.load('./data/train_inputs.npy')
Y = np.load('./data/train_outputs.npy')
# Y = Y.reshape( Y.shape[0] , 1 )
Y = Y.astype(np.int32)
PIXELS = 48
print 'Original Dataset size:'
print X.shape
import generate_extra_data as ged
x_new, y_new = ged.perturb_modified_digits(X, Y, 500000)
X = np.vstack((X, x_new))
Y = np.hstack((Y, y_new))
print 'New dataset size:'
print X.shape, Y.shape
X = X.reshape((-1, 1, PIXELS, PIXELS))
validation_division = int(len(X) * validate_split)
top = int(len(X) * max_split)
X_train, X_val = X[:validation_division, :], X[validation_division:top, :]
Y_train, Y_val = Y[:validation_division], Y[validation_division:top]
# In[7]:
