def run(X, y, n_samples_for_intial, n_queries, n_comittee_members, estimator):
# start timer
start_time = time.time()
# init list of different learners
learners = []
X_train, y_train, X_pool, y_pool = create_random_pool_and_initial_sets(X, y, n_samples_for_intial)
for member_idx in range(n_comittee_members):
learners.append(ActiveLearner(estimator=estimator, X_training=X_train, y_training=y_train))
# init committee
committee = Committee(learner_list=learners, query_strategy=max_disagreement_sampling)
unqueried_score = committee.score(X, y)
print('Score over unqueried samples {:0.4f}'.format(unqueried_score))
performance_history = []
f1_score = 0
index = 0
while f1_score < 0.65:
index += 1
# get sample from pool
query_idx, query_instance = committee.query(X_pool)
# retrain comittee with new sample
committee.teach(
X=X_pool[query_idx].reshape(1, -1),
y=y_pool[query_idx].reshape(1, )
)
# remove queried instance from pool
X_pool = delete_rows_csr(X_pool, query_idx)
y_pool = np.delete(y_pool, query_idx)
y_pred = committee.predict(X)
f1_score = metrics.f1_score(y, y_pred, average='micro')
if index % 100 == 0:
print('F1 score after {n} training samples: {f1:0.4f}'.format(n=index, f1=f1_score))
# save accuracy score
performance_history.append(f1_score)
print("--- %s seconds ---" % (time.time() - start_time))
print(performance_history)
return index
def active_learn(df1, first_item_index_of_each_category):
train_idx = first_item_index_of_each_category
# X_train = iris['data'][train_idx]
# y_train = iris['target'][train_idx]
# initial training data
data = df1.values[:, 1:]
target = df1['label'].values
X_full = df1.values[:, 1:]
y_full = df1['label'].values
X_train = df1.values[:, 1:][
train_idx] #item from second column as the first column is the label..
y_train = df1['label'].values[train_idx]
# X_pool = np.delete(data, train_idx, axis=0)
# y_pool = np.delete(target, train_idx)
X_pool = deepcopy(X_full)
y_pool = deepcopy(y_full)
# initializing Committee members
n_members = 2
learner_list = list()
for member_idx in range(n_members):
# initial training data
# n_initial = 5
# train_idx = np.random.choice(range(X_pool.shape[0]), size=n_initial, replace=False)
# X_train = X_pool[train_idx]
# y_train = y_pool[train_idx]
# creating a reduced copy of the data with the known instances removed
X_pool = np.delete(X_pool, train_idx, axis=0)
y_pool = np.delete(y_pool, train_idx)
# initializing learner
learner = ActiveLearner(estimator=RandomForestClassifier(),
X_training=X_train,
y_training=y_train)
learner_list.append(learner)
# assembling the committee
committee = Committee(learner_list=learner_list)
# print('Committee initial predictions, accuracy = %1.3f' % committee.score(data, target))
print('%1.3f' % committee.score(data, target))
performance_array = []
n_queries = 505
for idx in range(n_queries):
query_idx, query_instance = committee.query(X_pool)
committee.teach(X=X_pool[query_idx].reshape(1, -1),
y=y_pool[query_idx].reshape(1, ))
# remove queried instance from pool
X_pool = np.delete(X_pool, query_idx, axis=0)
y_pool = np.delete(y_pool, query_idx)
learner_score = committee.score(data, target)
# print('Committee %d th query predictions, accuracy = %1.3f' % (idx , learner_score))
print('%1.3f' % (learner_score))
if (idx % 100 == 0):
performance_array.append(learner_score)
percentage_increase(performance_array)
plt.subplot(1, n_members, learner_idx + 1)
plt.scatter(x=pca[:, 0],
y=pca[:, 1],
c=learner.predict(iris['data']),
cmap='viridis',
s=50)
plt.title('Learner no. %d initial predictions' % (learner_idx + 1))
plt.show()
# visualizing the initial predictions
with plt.style.context('seaborn-white'):
plt.figure(figsize=(7, 7))
prediction = committee.predict(iris['data'])
plt.scatter(x=pca[:, 0], y=pca[:, 1], c=prediction, cmap='viridis', s=50)
plt.title('Committee initial predictions, accuracy = %1.3f' %
committee.score(iris['data'], iris['target']))
plt.show()
# query by committee
n_queries = 10
for idx in range(n_queries):
query_idx, query_instance = committee.query(X_pool)
committee.teach(X=X_pool[query_idx].reshape(1, -1),
y=y_pool[query_idx].reshape(1, ))
# remove queried instance from pool
X_pool = np.delete(X_pool, query_idx, axis=0)
y_pool = np.delete(y_pool, query_idx)
# visualizing the final predictions per learner
with plt.style.context('seaborn-white'):
plt.figure(figsize=(n_members * 7, 7))
# for learner_idx, learner in enumerate(committee):
# plt.subplot(1, n_members, learner_idx + 1)
# plt.scatter(x=pca[:, 0], y=pca[:, 1], c=learner.predict(iris['data']), cmap='viridis', s=5)
# plt.title('Learner no. %d initial predictions' % (learner_idx + 1))
# plt.show()
# visualizing the Committee's predictions per learner
# with plt.style.context('seaborn-white'):
# plt.figure(figsize=(7, 7))
# prediction = committee.predict(iris['data'])
# plt.scatter(x=pca[:, 0], y=pca[:, 1], c=prediction, cmap='viridis', s=5)
# plt.title('Committee initial predictions')
# plt.show()
# query by committee
unqueried_score = committee.score(train_features, train_labels)
performance_history = [unqueried_score]
n_queries = 100
for _ in range(n_queries):
query_idx, query_instance = committee.query(X_pool) # -> Here
print(query_instance, " ", query_idx)
committee.teach(X=X_pool[query_idx].reshape(1, -1),
y=y_pool[query_idx].reshape(1, ))
performance_history.append(committee.score(train_features, train_labels))
# remove queried instance from pool
X_pool = np.delete(X_pool, query_idx, axis=0)
y_pool = np.delete(y_pool, query_idx)
print(performance_history)
# visualizing the final predictions per learner
def query():
# n_initial = 100
# X, y = load_digits(return_X_y=True)
# X_train, X_test, y_train, y_test = train_test_split(X, y)
#
# initial_idx = np.random.choice(range(len(X_train)), size=n_initial, replace=False)
#
# X_initial, y_initial = X_train[initial_idx], y_train[initial_idx]
# X_pool, y_pool = np.delete(X_train, initial_idx, axis=0), np.delete(y_train, initial_idx, axis=0)
strategy = None
classifier = None
file = request.files['file']
# if user does not select file, browser also
# submit a empty part without filename
filename = secure_filename(file.filename)
# shutil.rmtree(os.path.join(app.config['UPLOAD_FOLDER'],filename.split(".")[0]))
if file and allowed_file(file.filename):
filename = secure_filename(file.filename)
file.save(os.path.join(UPLOAD_FOLDER, filename))
if(filename.split(".")[1]=="rar"):
patoolib.extract_archive(os.path.join(UPLOAD_FOLDER, filename), outdir=os.path.join(UPLOAD_FOLDER))
else:
zip_ref = zipfile.ZipFile(os.path.join(UPLOAD_FOLDER, filename), 'r')
zip_ref.extractall(UPLOAD_FOLDER)
zip_ref.close()
print("Succesfull")
st = request.form.get('strategy_select')
cl = request.form.get('classifier_select')
option = int(request.form.get('structure_select'))
print(cl)
if(str(cl)=='Random Forest'):
classifier = RandomForestClassifier()
elif(str(cl)=='KNN'):
classifier = KNeighborsClassifier()
else:
classifier = DecisionTreeClassifier()
n_queries = request.form['queries']
print(st)
classlist =[]
classes = {}
data = {}
data['image'] = []
data['label'] = []
filename = secure_filename(file.filename)
print(filename)
if option == 0:
for dirname, _, filenames in os.walk(os.path.join(UPLOAD_FOLDER,filename.split(".")[0])):
print(filenames)
for filename in filenames:
if('.jpg' in filename or 'jpeg' in filename or 'png' in filename):
image = Image.open(os.path.join(dirname, filename))
image = image.resize((200,200), Image.ANTIALIAS)
size = np.array(image).size
if(len(classes)==0):
data['image'] = np.array(numpy.array(image)).reshape((1,size))
else:
try:
x = numpy.array(image).reshape((1,size))
data['image'] = np.append(data['image'],x,axis=0)
except:
continue
if(dirname.split('\\')[-1] not in classes.keys()):
classlist.append({'name':dirname.split('\\')[-1],'number':len(classes)})
classes[dirname.split('\\')[-1]] = len(classes)
#print(os.path.join(dirname, filename))
#print(dirname)
data['label'].append(classes[dirname.split('\\')[-1]])
print(classes)
else:
for imfile in os.listdir(os.path.join(UPLOAD_FOLDER,filename.split(".")[0])):
if imfile.endswith(".jpg") or imfile.endswith(".jpeg") or imfile.endswith("png"):
image = Image.open(os.path.join(os.path.join(UPLOAD_FOLDER,filename.split(".")[0]), imfile))
image = image.resize((200,200), Image.ANTIALIAS)
size = np.array(image).size
if(len(classes)==0):
data['image'] = np.array(numpy.array(image)).reshape((1,size))
else:
try:
x = numpy.array(image).reshape((1,size))
data['image'] = np.append(data['image'],x,axis=0)
except:
continue
if(("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0]))) not in classes.keys()):
classlist.append({'name':("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0]))),'number':len(classes)})
classes[("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0])))] = len(classes)
data['label'].append(classes[("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0])))])
print(classes)
else:
continue
X = data['image']
y = data['label']
n_initial = 100
X_train, X_test, y_train, y_test = train_test_split(X, y)
initial_idx = np.random.choice(range(len(X_train)), size=n_initial, replace=False)
X_initial=[]
y_initial = []
print(type(X_initial))
for i in range(n_initial):
v = np.array(X_train[initial_idx[i]]).reshape((1,size))
#print(v.shape)
y_initial.append(y_train[i])
if(i==0):
X_initial = np.array(X_train[initial_idx[i]]).reshape((1,size))
print(X_initial.shape)
else:
X_initial = np.append(X_initial,v,axis=0)
#print("X Shape",X_initial.shape)
# X_initial = X_initial.append(X_train[initial_idx[i]])
X_pool, y_pool = np.delete(X_train, initial_idx, axis=0), np.delete(y_train, initial_idx, axis=0)
print(X.shape)
print(X[0].shape)
print(X_initial.shape)
params = {}
params["X_test"] = X_test
params["y_test"] = y_test
params["counter"] = n_queries
params["X_pool"] = X_pool
params["y_pool"] = y_pool
if(str(st)=='Uncertainty Sampling'):
print(classifier)
print(cl)
learner = ActiveLearner(
estimator=classifier,
query_strategy=uncertainty_sampling,
X_training=X_initial, y_training=y_initial
)
params["learner"] = learner
accuracy_scores = learner.score(X_test, y_test)
params["accuracy"] = accuracy_scores
print(accuracy_scores)
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,learner,None,accuracy,X_test,y_test,classlist,n_queries)
print("Calling Helper")
return helper()
elif(str(st)=='Entropy Sampling'):
print(classifier)
print(cl)
learner = ActiveLearner(
estimator=classifier,
query_strategy=entropy_sampling,
X_training=X_initial, y_training=y_initial
)
params["learner"] = learner
accuracy_scores = learner.score(X_test, y_test)
params["accuracy"] = accuracy_scores
print(accuracy_scores)
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,learner,None,accuracy,X_test,y_test,classlist,n_queries)
return helper()
elif(str(st)=='Random Sampling'):
learner = ActiveLearner(
estimator=classifier,
query_strategy=random_sampling,
X_training=X_train, y_training=y_train
)
accuracy_scores = learner.score(X_test, y_test)
params["accuracy"] = accuracy_scores
print(accuracy_scores)
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,learner,None,accuracy,X_test,y_test,classlist,n_queries)
return helper()
elif(str(st)=='Query By Committee(Vote Entropy Sampling)'):
learner1 = ActiveLearner(
estimator = RandomForestClassifier(),
X_training=X_train,y_training=y_train
)
learner2 = ActiveLearner(
estimator=KNeighborsClassifier(),
X_training=X_train,y_training=y_train
)
learner3 = ActiveLearner(
estimator=DecisionTreeClassifier(),
X_training=X_train,y_training=y_train
)
committee = Committee(
learner_list=[learner1,learner2,learner3],
query_strategy=vote_entropy_sampling
)
params["committee"] = committee
accuracy_scores = committee.score(X_test, y_test)
params["accuracy"] = accuracy_scores
print(accuracy_scores)
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,None,committee,accuracy,X_test,y_test,classlist,n_queries)
return helper()
elif(str(st)=='Query By Committee(Uncertainty Sampling)'):
learner1 = ActiveLearner(
estimator = RandomForestClassifier(),
X_training=X_train,y_training=y_train
)
learner2 = ActiveLearner(
estimator=KNeighborsClassifier(),
X_training=X_train,y_training=y_train
)
learner3 = ActiveLearner(
estimator=DecisionTreeClassifier(),
X_training=X_train,y_training=y_train
)
committee = Committee(
learner_list=[learner1,learner2,learner3],
query_strategy=uncertainty_sampling
)
params["committee"] = committee
accuracy_scores = committee.score(X_test, y_test)
params["accuracy"] = accuracy_scores
print(accuracy_scores)
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,None,committee,accuracy,X_test,y_test,classlist,n_queries)
return helper()
elif(str(st)=='Query By Committee(Max Disagreement Sampling)'):
learner1 = ActiveLearner(
estimator = RandomForestClassifier(),
X_training=X_train,y_training=y_train
)
learner2 = ActiveLearner(
estimator=KNeighborsClassifier(),
X_training=X_train,y_training=y_train
)
learner3 = ActiveLearner(
estimator=DecisionTreeClassifier(),
X_training=X_train,y_training=y_train
)
committee = Committee(
learner_list=[learner1,learner2,learner3],
query_strategy=max_disagreement_sampling
)
params["committee"] = committee
accuracy_scores = committee.score(X_test, y_test)
params["accuracy"] = accuracy_scores
print(accuracy_scores)
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,None,committee,accuracy,X_test,y_test,classlist,n_queries)
return helper()
elif(str(st)=='Query By Committee(Max STD Sampling)'):
learner1 = ActiveLearner(
estimator = RandomForestClassifier(),
X_training=X_train,y_training=y_train
)
learner2 = ActiveLearner(
estimator=KNeighborsClassifier(),
X_training=X_train,y_training=y_train
)
learner3 = ActiveLearner(
estimator=DecisionTreeClassifier(),
X_training=X_train,y_training=y_train
)
committee = Committee(
learner_list=[learner1,learner2,learner3],
query_strategy=max_std_sampling
)
params["committee"] = committee
accuracy_scores = committee.score(X_test, y_test)
params["accuracy"] = accuracy_scores
print(accuracy_scores)
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,None,committee,accuracy,X_test,y_test,classlist,n_queries)
return helper()
elif(str(st)=='Query By Committee(Consensus Entropy Sampling)'):
learner1 = ActiveLearner(
estimator = RandomForestClassifier(),
X_training=X_train,y_training=y_train
)
learner2 = ActiveLearner(
estimator=KNeighborsClassifier(),
X_training=X_train,y_training=y_train
)
learner3 = ActiveLearner(
estimator=DecisionTreeClassifier(),
X_training=X_train,y_training=y_train
)
committee = Committee(
learner_list=[learner1,learner2,learner3],
query_strategy=consensus_entropy_sampling
)
params["committee"] = committee
accuracy_scores = committee.score(X_test, y_test)
params["accuracy"] = accuracy_scores
print(accuracy_scores)
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,None,committee,accuracy,X_test,y_test,classlist,n_queries)
return helper()
# In[66]:
version_space_length = version_space.shape[0]
ind = np.argsort(version_space[:, 1])
print('Order of points to label:')
for i in range(version_space_length):
print('#{size:2d}'.format(size=i) + ' point:' +
str(version_space_points[ind[i]]) + ' label:' +
str(version_space_labels[ind[i]]))
# In[67]:
print("Initial accuracy =", committee.score(X, Y))
# In[68]:
x = 40
queries = int((x / 100) * 150)
accuracy_list = []
accuracy_list.append(committee.score(X, Y))
# In[69]:
iter = 0
print("Accuracy after", 0, "iterations :", committee.score(X, Y))
for i in range(0, queries):
plt.subplot(1, n_members, learner_idx + 1)
plt.scatter(x=pca[:, 0],
y=pca[:, 1],
c=learner.predict(data),
cmap='viridis',
s=50)
plt.title('Learner no. %d initial predictions' % (learner_idx + 1))
plt.show()
# visualizing the initial predictions
with plt.style.context('seaborn-white'):
plt.figure(figsize=(7, 7))
prediction = committee.predict(data)
plt.scatter(x=pca[:, 0], y=pca[:, 1], c=prediction, cmap='viridis', s=50)
plt.title('Committee initial predictions, accuracy = %1.3f' %
committee.score(data, target))
plt.show()
# query by committee
n_queries = 10
for idx in range(n_queries):
query_idx, query_instance = committee.query(X_pool)
committee.teach(X=X_pool[query_idx].reshape(1, -1),
y=y_pool[query_idx].reshape(1, ))
# remove queried instance from pool
X_pool = np.delete(X_pool, query_idx, axis=0)
y_pool = np.delete(y_pool, query_idx)
# visualizing the final predictions per learner
with plt.style.context('seaborn-white'):
plt.figure(figsize=(n_members * 7, 7))
learner_list.append(learner)
# assembling the committee
committee = Committee(learner_list=learner_list,
query_strategy=vote_entropy_sampling)
'''
with plt.style.context('seaborn-white'):
plt.figure(figsize=(n_members*7, 7))
for learner_idx, learner in enumerate(committee):
plt.subplot(1, n_members, learner_idx + 1)
plt.scatter(x=pca[:, 0], y=pca[:, 1], c=learner.predict(iris['data']), cmap='viridis', s=50)
plt.title('Learner no. %d initial predictions' % (learner_idx + 1))
plt.show()
'''
unqueried_score = committee.score(iris['data'], iris['target'])
'''
with plt.style.context('seaborn-white'):
plt.figure(figsize=(7, 7))
prediction = committee.predict(iris['data'])
plt.scatter(x=pca[:, 0], y=pca[:, 1], c=prediction, cmap='viridis', s=50)
plt.title('Committee initial predictions, accuracy = %1.3f' % unqueried_score)
plt.show()
'''
performance_history = [unqueried_score]
# query by committee
n_queries = 20
for idx in range(n_queries):
query_idx, query_instance = committee.query(X_pool)
def query():
strategy = None
classifier = None
file = request.files['file']
test = request.files['test_file']
filename = secure_filename(file.filename)
test_filename = secure_filename(test.filename)
if file and allowed_file(file.filename):
filename = secure_filename(file.filename)
file.save(os.path.join(UPLOAD_FOLDER, filename))
zip_ref = zipfile.ZipFile(os.path.join(UPLOAD_FOLDER, filename), 'r')
zip_ref.extractall(UPLOAD_FOLDER)
zip_ref.close()
if test and allowed_file(test.filename):
filename = secure_filename(test.filename)
test.save(os.path.join(UPLOAD_FOLDER, filename))
zip_ref = zipfile.ZipFile(os.path.join(UPLOAD_FOLDER, filename), 'r')
zip_ref.extractall(UPLOAD_FOLDER)
zip_ref.close()
st = request.form.get('strategy_select')
cl = request.form.get('classifier_select')
option = int(request.form.get('structure_select'))
if(str(cl)=='Random Forest'):
classifier = RandomForestClassifier()
elif(str(cl)=='KNN'):
classifier = KNeighborsClassifier()
else:
classifier = DecisionTreeClassifier()
n_queries = request.form['queries']
classlist =[]
classes = {}
data = {}
data['image'] = []
data['label'] = []
data['image_name'] = []
image_data = {}
filename = secure_filename(file.filename)
if option == 0:
for root,dirs,filename in os.walk(os.path.join(UPLOAD_FOLDER,filename.split(".")[0])):
for name in filename:
if name.endswith(".jpg") or name.endswith(".jpeg") or name.endswith(".png"):
image_file_name = os.path.join(root,name)
image = Image.open(image_file_name)
image = image.resize((200,200), Image.ANTIALIAS)
size = np.array(image).size
if(len(classes)==0):
data['image'] = np.array(numpy.array(image)).reshape((1,size))
image_data[(numpy.array(image).reshape((1,size))).tobytes()] = image_file_name
else:
try:
x = numpy.array(image).reshape((1,size))
image_data[(numpy.array(image).reshape((1,size))).tobytes()] = image_file_name
data['image'] = np.append(data['image'],x,axis=0)
except:
continue
if root.split("\\")[-1] not in classes.keys():
classlist.append({'name':root.split('\\')[-1],'number':len(classes)})
classes[root.split('\\')[-1]] = len(classes)
data['label'].append(classes[root.split('\\')[-1]])
data['image_name'].append(image_file_name)
else:
for imfile in os.listdir(os.path.join(UPLOAD_FOLDER,filename.split(".")[0])):
if imfile.endswith(".jpg") or imfile.endswith(".jpeg") or imfile.endswith(".png"):
image_file_name = os.path.join(os.path.join(UPLOAD_FOLDER,filename.split(".")[0]), imfile)
image = Image.open(os.path.join(os.path.join(UPLOAD_FOLDER,filename.split(".")[0]), imfile))
image = image.resize((200,200), Image.ANTIALIAS)
size = np.array(image).size
if(len(classes)==0):
data['image'] = np.array(numpy.array(image)).reshape((1,size))
image_data[(numpy.array(image).reshape((1,size))).tobytes()] = image_file_name
else:
try:
x = numpy.array(image).reshape((1,size))
image_data[(numpy.array(image).reshape((1,size))).tobytes()] = image_file_name
data['image'] = np.append(data['image'],x,axis=0)
except:
continue
if(("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0]))) not in classes.keys()):
classlist.append({'name':("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0]))),'number':len(classes)})
classes[("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0])))] = len(classes)
data['label'].append(classes[("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0])))])
data['image_name'].append(imfile)
else:
continue
test_classlist =[]
test_classes = {}
test_data = {}
test_data['image'] = []
test_data['label'] = []
test_data['image_name'] = []
if option == 0:
for dirname, _, filenames in os.walk(os.path.join(UPLOAD_FOLDER,test_filename.split(".")[0])):
for filename in filenames:
if('.jpg' in filename or 'jpeg' in filename or 'png' in filename):
image = Image.open(os.path.join(dirname, filename))
image = image.resize((200,200), Image.ANTIALIAS)
size = np.array(image).size
if(len(test_classes)==0):
test_data['image'] = np.array(numpy.array(image)).reshape((1,size))
else:
try:
x = numpy.array(image).reshape((1,size))
test_data['image'] = np.append(test_data['image'],x,axis=0)
except:
continue
if(dirname.split('\\')[-1] not in test_classes.keys()):
test_classlist.append({'name':dirname.split('\\')[-1],'number':len(test_classes)})
test_classes[dirname.split('\\')[-1]] = len(test_classes)
test_data['label'].append(test_classes[dirname.split('\\')[-1]])
test_data['image_name'].append(filename)
else:
for imfile in os.listdir(os.path.join(UPLOAD_FOLDER,test_filename.split(".")[0])):
if imfile.endswith(".jpg") or imfile.endswith(".jpeg") or imfile.endswith("png"):
image = Image.open(os.path.join(os.path.join(UPLOAD_FOLDER,test_filename.split(".")[0]), imfile))
image = image.resize((200,200), Image.ANTIALIAS)
size = np.array(image).size
if(len(test_classes)==0):
test_data['image'] = np.array(numpy.array(image)).reshape((1,size))
else:
try:
x = numpy.array(image).reshape((1,size))
test_data['image'] = np.append(test_data['image'],x,axis=0)
except:
continue
if(("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0]))) not in test_classes.keys()):
test_classlist.append({'name':("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0]))),'number':len(test_classes)})
test_classes[("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0])))] = len(test_classes)
test_data['label'].append(test_classes[("".join(re.split("[^a-zA-Z]*",imfile.split(".")[0])))])
test_data['image_name'].append(imfile)
else:
continue
X_train = data['image']
y_train = data['label']
X_test = test_data['image']
y_test = test_data['label']
n_initial = 100
initial_idx = np.random.choice(range(len(X_train)), size=n_initial, replace=False)
X_initial=[]
y_initial = []
for i in range(n_initial):
v = np.array(X_train[initial_idx[i]]).reshape((1,size))
y_initial.append(y_train[i])
if(i==0):
X_initial = np.array(X_train[initial_idx[i]]).reshape((1,size))
else:
X_initial = np.append(X_initial,v,axis=0)
X_pool, y_pool = np.delete(X_train, initial_idx, axis=0), np.delete(y_train, initial_idx, axis=0)
params = {}
params["X_test"] = X_test
params["y_test"] = y_test
params["counter"] = n_queries
params["X_pool"] = X_pool
params["y_pool"] = y_pool
if(str(st)=='Uncertainty Sampling'):
learner = ActiveLearner(
estimator=classifier,
query_strategy=uncertainty_sampling,
X_training=X_initial, y_training=y_initial
)
params["learner"] = learner
accuracy_scores = learner.score(X_test, y_test)
params["accuracy"] = accuracy_scores
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,learner,None,accuracy,X_test,y_test,classlist,n_queries,image_data)
return helper()
elif(str(st)=='Entropy Sampling'):
learner = ActiveLearner(
estimator=classifier,
query_strategy=entropy_sampling,
X_training=X_initial, y_training=y_initial
)
params["learner"] = learner
accuracy_scores = learner.score(X_test, y_test)
params["accuracy"] = accuracy_scores
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,learner,None,accuracy,X_test,y_test,classlist,n_queries,image_data)
return helper()
elif(str(st)=='Random Sampling'):
learner = ActiveLearner(
estimator=classifier,
query_strategy=random_sampling,
X_training=X_train, y_training=y_train
)
accuracy_scores = learner.score(X_test, y_test)
params["accuracy"] = accuracy_scores
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,learner,None,accuracy,X_test,y_test,classlist,n_queries,image_data)
return helper()
elif(str(st)=='Query By Committee(Vote Entropy Sampling)'):
learner1 = ActiveLearner(
estimator = RandomForestClassifier(),
X_training=X_train,y_training=y_train
)
learner2 = ActiveLearner(
estimator=KNeighborsClassifier(),
X_training=X_train,y_training=y_train
)
learner3 = ActiveLearner(
estimator=DecisionTreeClassifier(),
X_training=X_train,y_training=y_train
)
committee = Committee(
learner_list=[learner1,learner2,learner3],
query_strategy=vote_entropy_sampling
)
params["committee"] = committee
accuracy_scores = committee.score(X_test, y_test)
params["accuracy"] = accuracy_scores
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,None,committee,accuracy,X_test,y_test,classlist,n_queries,image_data)
return helper()
elif(str(st)=='Query By Committee(Uncertainty Sampling)'):
learner1 = ActiveLearner(
estimator = RandomForestClassifier(),
X_training=X_train,y_training=y_train
)
learner2 = ActiveLearner(
estimator=KNeighborsClassifier(),
X_training=X_train,y_training=y_train
)
learner3 = ActiveLearner(
estimator=DecisionTreeClassifier(),
X_training=X_train,y_training=y_train
)
committee = Committee(
learner_list=[learner1,learner2,learner3],
query_strategy=uncertainty_sampling
)
params["committee"] = committee
accuracy_scores = committee.score(X_test, y_test)
params["accuracy"] = accuracy_scores
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,None,committee,accuracy,X_test,y_test,classlist,n_queries,image_data)
return helper()
elif(str(st)=='Query By Committee(Max Disagreement Sampling)'):
learner1 = ActiveLearner(
estimator = RandomForestClassifier(),
X_training=X_train,y_training=y_train
)
learner2 = ActiveLearner(
estimator=KNeighborsClassifier(),
X_training=X_train,y_training=y_train
)
learner3 = ActiveLearner(
estimator=DecisionTreeClassifier(),
X_training=X_train,y_training=y_train
)
committee = Committee(
learner_list=[learner1,learner2,learner3],
query_strategy=max_disagreement_sampling
)
params["committee"] = committee
accuracy_scores = committee.score(X_test, y_test)
params["accuracy"] = accuracy_scores
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,None,committee,accuracy,X_test,y_test,classlist,n_queries,image_data)
return helper()
elif(str(st)=='Query By Committee(Consensus Entropy Sampling)'):
learner1 = ActiveLearner(
estimator = RandomForestClassifier(),
X_training=X_train,y_training=y_train
)
learner2 = ActiveLearner(
estimator=KNeighborsClassifier(),
X_training=X_train,y_training=y_train
)
learner3 = ActiveLearner(
estimator=DecisionTreeClassifier(),
X_training=X_train,y_training=y_train
)
committee = Committee(
learner_list=[learner1,learner2,learner3],
query_strategy=consensus_entropy_sampling
)
params["committee"] = committee
accuracy_scores = committee.score(X_test, y_test)
params["accuracy"] = accuracy_scores
accuracy = []
accuracy.append(accuracy_scores)
data = Data(n_queries,X_pool,y_pool,None,committee,accuracy,X_test,y_test,classlist,n_queries,image_data)
return helper()
query_strategy=strategy)
member4 = ActiveLearner(X_training=X_train,
y_training=Y_train,
estimator=KNeighborsClassifier(n_neighbors=8),
query_strategy=strategy)
member5 = ActiveLearner(X_training=X_train,
y_training=Y_train,
estimator=KNeighborsClassifier(n_neighbors=10),
query_strategy=strategy)
committee = Committee(
learner_list=[member1, member2, member3, member4, member5])
# In[8]:
print("Initial accuracy =", committee.score(X, Y))
# In[9]:
member1r = ActiveLearner(X_training=X_train,
y_training=Y_train,
estimator=RandomForestClassifier(n_estimators=8),
query_strategy=strategy)
member2r = ActiveLearner(X_training=X_train,
y_training=Y_train,
estimator=RandomForestClassifier(n_estimators=1),
query_strategy=strategy)
member3r = ActiveLearner(X_training=X_train,
y_training=Y_train,
estimator=RandomForestClassifier(n_estimators=10),
query_strategy=strategy)
