def make_data_for_prepro():
accuracys = []
training_sett, train_set_labelts, validation_set, validation_set_labels = LoadData(
'labeled_images.mat', True, True)
# training_set, train_set_labels, idst = LoadData('labeled_images.mat', True, False)
# kknn_class = KNeighborsClassifier(weights='distance', n_neighbors=5)
# logistic_regression_solver = sklearn.linear_model.LogisticRegression(penalty='l2', dual=False, tol=0.001, C=1.2, fit_intercept=True,
# intercept_scaling=1, class_weight=None, random_state=None, solver='newton-cg',
# max_iter=200, multi_class='ovr', verbose=0, warm_start=False, n_jobs=2)
# svm_class = svm.SVC(kernel='rbf', C=50, shrinking = False,decision_function_shape='ovr', tol=0.001, max_iter=-1)
standard_train_inputs = standard_data(training_sett)
standard_valid_inputs = standard_data(validation_set)
fixed_train_set = fix_pixels(training_sett)
fixed_valid = fix_pixels(validation_set)
# garbored_train_set = gabor_filter(training_sett)
# garbored_valid_set = gabor_filter(validation_set)
data_list = [(training_sett, validation_set),
(standard_train_inputs, standard_valid_inputs),
(fixed_train_set, fixed_valid)
] #,(garbored_train_set,garbored_valid_set)]
for (t, v) in data_list:
# accuracys.append(knn(t, train_set_labelts, v, validation_set_labels, False))
# accuracys.append(logistic_regression(t,train_set_labelts , v, validation_set_labels, False))
# accuracys.append(run_svm(t, train_set_labelts, v, validation_set_labels, False))
net_clf = net_class(t, train_set_labelts, v, validation_set_labels,
False)
net_preds = []
for in_data in v:
net_preds.append(net_clf.activate(in_data))
accuracys.append(get_acc(net_preds, validation_set_labels, True))
print "done iter"
create_csv(accuracys, 'barplot_pre_accuracy.csv')
fig = plt.figure()
ax = fig.add_subplot(111)
barplot_preprocess(ax, accuracys)
def make_data_for_prepro():
accuracys = []
training_sett, train_set_labelts, validation_set, validation_set_labels = LoadData('labeled_images.mat', True, True)
# training_set, train_set_labels, idst = LoadData('labeled_images.mat', True, False)
# kknn_class = KNeighborsClassifier(weights='distance', n_neighbors=5)
# logistic_regression_solver = sklearn.linear_model.LogisticRegression(penalty='l2', dual=False, tol=0.001, C=1.2, fit_intercept=True,
# intercept_scaling=1, class_weight=None, random_state=None, solver='newton-cg',
# max_iter=200, multi_class='ovr', verbose=0, warm_start=False, n_jobs=2)
# svm_class = svm.SVC(kernel='rbf', C=50, shrinking = False,decision_function_shape='ovr', tol=0.001, max_iter=-1)
standard_train_inputs = standard_data(training_sett)
standard_valid_inputs = standard_data(validation_set)
fixed_train_set = fix_pixels(training_sett)
fixed_valid = fix_pixels(validation_set)
# garbored_train_set = gabor_filter(training_sett)
# garbored_valid_set = gabor_filter(validation_set)
data_list = [(training_sett,validation_set), (standard_train_inputs, standard_valid_inputs),
(fixed_train_set,fixed_valid)]#,(garbored_train_set,garbored_valid_set)]
for (t,v) in data_list:
# accuracys.append(knn(t, train_set_labelts, v, validation_set_labels, False))
# accuracys.append(logistic_regression(t,train_set_labelts , v, validation_set_labels, False))
# accuracys.append(run_svm(t, train_set_labelts, v, validation_set_labels, False))
net_clf = net_class(t, train_set_labelts, v, validation_set_labels, False)
net_preds =[]
for in_data in v:
net_preds.append(net_clf.activate(in_data))
accuracys.append(get_acc(net_preds,validation_set_labels, True))
print"done iter"
create_csv(accuracys,'barplot_pre_accuracy.csv')
fig = plt.figure()
ax = fig.add_subplot(111)
barplot_preprocess(ax,accuracys)
def run_my_votin(training_set, train_set_labels, validation_set=None, validation_set_labels=None, train=True):
from sklearn.ensemble import VotingClassifier
from pybrain.datasets import ClassificationDataSet
standard_valid_inputs = standard_data(validation_set)
fixed_valid = fix_pixels(validation_set)
equalize_and_standard_validation= standard_data(fixed_valid)
if train:
standard_train_inputs = standard_data(training_set)
fixed_train_set = fix_pixels(training_set)
equalize_and_standard = standard_data(fixed_train_set)
kknn_class = KNeighborsClassifier(weights='distance', n_neighbors=11)
# kknn_class.fit(standard_train_inputs, train_set_labels.ravel())
logistic_regression_solver = sklearn.linear_model.LogisticRegression(penalty='l2', dual=False, tol=0.01, C=1.0, fit_intercept=True,
intercept_scaling=1, class_weight=None, random_state=None, solver='newton-cg',
max_iter=200, multi_class='ovr', verbose=0, warm_start=False, n_jobs=2)
svm_class = svm.SVC(kernel='rbf', C=50, shrinking = False,decision_function_shape='ovr', tol=0.001, max_iter=-1)
print"train knn"
bg1 = run_bagging(fixed_train_set, train_set_labels, kknn_class, None, None, False)
res_f = open('bg1knn.dump', 'w')
pickle.dump(bg1,res_f )
res_f.close()
print "Knn done"
print"train Logistic Regression"
bg2 = run_bagging(standard_train_inputs, train_set_labels, logistic_regression_solver, None, None, False)
res_f = open('bg2lr.dump', 'w')
pickle.dump(bg2,res_f )
res_f.close()
print "done bg LR"
print"train SVM"
bg3 = run_bagging(equalize_and_standard, train_set_labels ,svm_class, None, None, False)
res_f = open('bg3svm.dump', 'w')
pickle.dump(bg3,res_f )
res_f.close()
print "done bg svm"
print"train Neural-Nets"
net_clf = net_class(standard_train_inputs,train_set_labels, None, None, False)
res_f = open('net.dump', 'w')
pickle.dump(net_clf,res_f)
res_f.close()
print "nets done"
else:
print"Load knn"
res_1 = open('bg1knn.dump', 'r')
bg1 = pickle.load(res_1)
res_1.close()
print "knn done"
print"Load LR"
res_2 = open('bg2lr.dump', 'r')
bg2 = pickle.load(res_2)
res_2.close()
print "LR done"
print"Load SVM"
res_3 = open('bg3svm.dump', 'r')
bg3 = pickle.load(res_3)
res_3.close()
print "svm done"
print"Load Neural-nets"
res_4 = open('net.dump', 'r')
net_clf = pickle.load(res_4)
res_4.close()
print "net done"
preds_arr = []
pred_weights = [0.1, 0.26,0.34]
net_weight = 0.30
preds_arr.append(bg1.predict_proba(fixed_valid))
preds_arr.append(bg2.predict_proba(standard_valid_inputs))
preds_arr.append(bg3.predict_proba(equalize_and_standard_validation))
net_preds =[]
for in_data in standard_valid_inputs:
net_preds.append(net_clf.activate(in_data))
# preds_arr.append(net_preds)
fin_pred = []
for i in range(len(standard_valid_inputs)):
tmp_np = np.zeros(7)
for w ,pp in zip(pred_weights, preds_arr):
tmp_np += pp[i] * w
tmp_np += net_preds[i] * net_weight
fin_pred.append(tmp_np)
fin_labels = [(np.argmax(ar, axis=0)+1) for ar in fin_pred]
create_csv(fin_labels,'test_csv.csv')
if validation_set_labels:
fin_acc, err = get_acc(fin_labels, validation_set_labels)
print 'The final accuracy after bagging and votig is :', fin_acc
fin_one_of_k = []
for c in fin_labels:
carr = [int(i==c-1) for i in range(0,7)]
fin_one_of_k.append(carr)
return fin_one_of_k
def run_my_votin(training_set,
train_set_labels,
validation_set=None,
validation_set_labels=None,
train=True):
from sklearn.ensemble import VotingClassifier
from pybrain.datasets import ClassificationDataSet
standard_valid_inputs = standard_data(validation_set)
fixed_valid = fix_pixels(validation_set)
equalize_and_standard_validation = standard_data(fixed_valid)
if train:
standard_train_inputs = standard_data(training_set)
fixed_train_set = fix_pixels(training_set)
equalize_and_standard = standard_data(fixed_train_set)
kknn_class = KNeighborsClassifier(weights='distance', n_neighbors=11)
# kknn_class.fit(standard_train_inputs, train_set_labels.ravel())
logistic_regression_solver = sklearn.linear_model.LogisticRegression(
penalty='l2',
dual=False,
tol=0.01,
C=1.0,
fit_intercept=True,
intercept_scaling=1,
class_weight=None,
random_state=None,
solver='newton-cg',
max_iter=200,
multi_class='ovr',
verbose=0,
warm_start=False,
n_jobs=2)
svm_class = svm.SVC(kernel='rbf',
C=50,
shrinking=False,
decision_function_shape='ovr',
tol=0.001,
max_iter=-1)
print "train knn"
bg1 = run_bagging(fixed_train_set, train_set_labels, kknn_class, None,
None, False)
res_f = open('bg1knn.dump', 'w')
pickle.dump(bg1, res_f)
res_f.close()
print "Knn done"
print "train Logistic Regression"
bg2 = run_bagging(standard_train_inputs, train_set_labels,
logistic_regression_solver, None, None, False)
res_f = open('bg2lr.dump', 'w')
pickle.dump(bg2, res_f)
res_f.close()
print "done bg LR"
print "train SVM"
bg3 = run_bagging(equalize_and_standard, train_set_labels, svm_class,
None, None, False)
res_f = open('bg3svm.dump', 'w')
pickle.dump(bg3, res_f)
res_f.close()
print "done bg svm"
print "train Neural-Nets"
net_clf = net_class(standard_train_inputs, train_set_labels, None,
None, False)
res_f = open('net.dump', 'w')
pickle.dump(net_clf, res_f)
res_f.close()
print "nets done"
else:
print "Load knn"
res_1 = open('bg1knn.dump', 'r')
bg1 = pickle.load(res_1)
res_1.close()
print "knn done"
print "Load LR"
res_2 = open('bg2lr.dump', 'r')
bg2 = pickle.load(res_2)
res_2.close()
print "LR done"
print "Load SVM"
res_3 = open('bg3svm.dump', 'r')
bg3 = pickle.load(res_3)
res_3.close()
print "svm done"
print "Load Neural-nets"
res_4 = open('net.dump', 'r')
net_clf = pickle.load(res_4)
res_4.close()
print "net done"
preds_arr = []
pred_weights = [0.1, 0.26, 0.34]
net_weight = 0.30
preds_arr.append(bg1.predict_proba(fixed_valid))
preds_arr.append(bg2.predict_proba(standard_valid_inputs))
preds_arr.append(bg3.predict_proba(equalize_and_standard_validation))
net_preds = []
for in_data in standard_valid_inputs:
net_preds.append(net_clf.activate(in_data))
# preds_arr.append(net_preds)
fin_pred = []
for i in range(len(standard_valid_inputs)):
tmp_np = np.zeros(7)
for w, pp in zip(pred_weights, preds_arr):
tmp_np += pp[i] * w
tmp_np += net_preds[i] * net_weight
fin_pred.append(tmp_np)
fin_labels = [(np.argmax(ar, axis=0) + 1) for ar in fin_pred]
create_csv(fin_labels, 'test_csv.csv')
if validation_set_labels:
fin_acc, err = get_acc(fin_labels, validation_set_labels)
print 'The final accuracy after bagging and votig is :', fin_acc
fin_one_of_k = []
for c in fin_labels:
carr = [int(i == c - 1) for i in range(0, 7)]
fin_one_of_k.append(carr)
return fin_one_of_k