y = df.loc[:, 'True Positive']
#parameters for models defined here, simply change init_labels, trn_tst_split, splits to change experiment
stop = 300 #stopping value for number of queries
init_labels = 0.005 #initially labelled portion of the dataset
trn_tst_split = 0.2 #train test split to use for each fold
splits = 5 #number of k folds
al_unc = AlExperiment(X,
y,
model=LogisticRegression(penalty='l1',
solver='liblinear'),
performance_metric='accuracy_score',
stopping_criteria='num_of_queries',
stopping_value=stop)
al_unc.split_AL(test_ratio=trn_tst_split,
initial_label_rate=init_labels,
split_count=splits,
all_class=True)
al_unc.set_query_strategy(strategy='QueryInstanceUncertainty')
al_unc.set_performance_metric(performance_metric='accuracy_score')
al_unc.start_query(multi_thread=False)
# print(al.get_experiment_result())
# al.plot_learning_curve()
analyser = ExperimentAnalyser(x_axis='num_of_queries')
analyser.add_method('uncertainty', al_unc.get_experiment_result())
al_qbc = AlExperiment(X,
y,
model=LogisticRegression(penalty='l1',
solver='liblinear'),
performance_metric='accuracy_score',
stopping_criteria='num_of_queries',
stopping_value=stop)
from sklearn.datasets import load_iris
from alipy.experiment import AlExperiment
# Get the data
X, y = load_iris(return_X_y=True)
# init the AlExperiment
al = AlExperiment(X, y)
# split the data by using split_AL()
al.split_AL(test_ratio=0.3, initial_label_rate=0.05, split_count=10)
# or set the data split indexes by input the specific parameters
from alipy.data_manipulate import split
train, test, lab, unlab = split(X=X,
y=y,
test_ratio=0.3,
initial_label_rate=0.05,
split_count=10)
al.set_data_split(train_idx=train,
test_idx=test,
label_idx=lab,
unlabel_idx=unlab)
# set the query strategy
# using the a pre-defined strategy
al.set_query_strategy(strategy="QueryInstanceUncertainty")
# or using your own query strategy
# class my_qs_class:
X, y = load_iris(return_X_y=True)
for strategy in [
'QueryInstanceQBC', 'QueryInstanceUncertainty', 'QueryInstanceRandom',
'QureyExpectedErrorReduction', 'QueryInstanceGraphDensity',
'QueryInstanceQUIRE', 'QueryInstanceBMDR', 'QueryInstanceSPAL',
'QueryInstanceLAL', 'QueryExpectedErrorReduction'
]:
# init the AlExperiment
al = AlExperiment(X,
y,
stopping_criteria='num_of_queries',
stopping_value=50)
# split the data by using split_AL()
al.split_AL(split_count=5)
# al.set_query_strategy(strategy=strategy)
# al.set_performance_metric('accuracy_score')
# al.start_query(multi_thread=True)
# or set the data split indexes by input the specific parameters
from alipy.data_manipulate import split
train, test, lab, unlab = split(X=X,
y=y,
test_ratio=0.3,
initial_label_rate=0.05,
split_count=1)
from sklearn.datasets import load_iris
from alipy.experiment import AlExperiment
# Get the data
X, y = load_iris(return_X_y=True)
# init the AlExperiment
al = AlExperiment(X, y)
# split the data by using split_AL()
al.split_AL()
# or set the data split indexes by input the specific parameters
from alipy.data_manipulate import split
train, test, lab, unlab = split(X=X, y=y, test_ratio=0.3, initial_label_rate=0.05,
split_count=10)
al.set_data_split(train_idx=train, test_idx=test, label_idx=lab, unlabel_idx=unlab)
# set the query strategy
# using the a pre-defined strategy
al.set_query_strategy(strategy="QueryInstanceUncertainty")
# or using your own query strategy
# class my_qs_class:
# def __init__(self, X=None, y=None, **kwargs):
# pass
# def select(self, label_index, unlabel_index, batch_size=1, **kwargs):
# """Select instances to query."""
# pass