def score_per_add_al(labeled_pool_df, base_training_df, validation_data_df):
# type: (DataFrame, DataFrame, DataFrame) -> tuple
gen_pool_df = labeled_pool_df.copy(deep=True)
gen_pool_df[cn.col_names.tag] = [np.NaN] * len(
gen_pool_df) # clear all tags
enriched_train_df = pd.concat([base_training_df, gen_pool_df],
ignore_index=True)
extractor = cn.Feature_Extractor(
enriched_train_df, cn.col_names) # build the feature extractor
trn_ds = TextDataset(enriched_train_df, cn.col_names, extractor)
qs = UncertaintySampling(trn_ds, method='lc', model=LogisticRegression())
ideal_df = pd.concat([base_training_df, labeled_pool_df],
ignore_index=True)
lbr = IdealTextLabeler(TextDataset(ideal_df, cn.col_names, extractor))
scoring_fun = lambda ds: run_classifier(ds.extract_labeled_dataframe(),
validation_data_df)
ex_added_list, res_list = run_active_learning(
trn_ds, scoring_fun, lbr, qs, len(enriched_train_df)) # label all df
return ex_added_list, res_list
def prepare_trn_ds(balanced_train_df, generated_pool_df, labeled_pool_df):
enriched_train_df = pd.concat([balanced_train_df, generated_pool_df], ignore_index=True)
extractor = cn.Feature_Extractor(enriched_train_df, cn.col_names) # build the feature extractor
trn_ds = TextDataset(enriched_train_df, cn.col_names, extractor)
ideal_df = pd.concat([balanced_train_df, labeled_pool_df], ignore_index=True)
lbr = IdealTextLabeler(TextDataset(ideal_df, cn.col_names, extractor))
return trn_ds, lbr, extractor
def build_query_strategy(sent_df, col_names):
# type: (DataFrame, ColumnNames) -> QueryStrategy
"""
Builds and returns a QueryStrategy
using a feature extractor and a base_df
"""
init_extractor = SynStateALHeuristic.build_feature_extractor(
sent_df, col_names)
combined_features = init_extractor.transform(sent_df, col_names)
trn_ds = TextDataset(sent_df,
col_names,
None,
features=combined_features)
return ActiveLearningByLearning(
trn_ds,
query_strategies=[
UncertaintySampling(trn_ds,
model=SVM(C=100,
gamma=3.1,
kernel='rbf',
decision_function_shape='ovr')),
QUIRE(trn_ds),
HintSVM(trn_ds, cl=1.0, ch=1.0),
],
T=1000,
uniform_sampler=True,
model=SVM(C=100,
gamma=3.1,
kernel='rbf',
decision_function_shape='ovr'))
def build_query_strategy(sent_df, col_names):
# type: (DataFrame, ColumnNames) -> QueryStrategy
"""
Builds and returns a QueryStrategy
using a feature extractor and a base_df
"""
init_extractor = SynStateALHeuristic.build_feature_extractor(sent_df, col_names)
combined_features = init_extractor.transform(sent_df, col_names)
return UncertaintySampling(TextDataset(sent_df, col_names, None, features=combined_features),
method='lc', model=LogisticRegression())
def build_query_strategy(sent_df, col_names):
# type: (DataFrame, ColumnNames) -> QueryStrategy
"""
Builds and returns a QueryStrategy
using a feature extractor and a base_df
"""
init_extractor = SynStateALHeuristic.build_feature_extractor(sent_df, col_names)
combined_features = init_extractor.transform(sent_df, col_names)
return HintSVM(TextDataset(sent_df, col_names, None, features=combined_features),
Cl=0.01, p=0.8)
def build_query_strategy(sent_df, col_names):
# type: (DataFrame, ColumnNames) -> QueryStrategy
"""
Builds and returns a QueryStrategy
using a feature extractor and a base_df
"""
init_extractor = SynStateALHeuristic.build_feature_extractor(sent_df, col_names)
combined_features = init_extractor.transform(sent_df, col_names)
return VarianceReduction(TextDataset(sent_df, col_names, None, features=combined_features),
model=LogisticRegression(), sigma=0.1)
def heuristic_score_fun(inst_idx, ss_type):
if ss_type == "Random":
if "qs2" not in shared_variables:
extractor = SynStateALHeuristic.build_feature_extractor(enriched_train_df, col_names)
qs2 = RandomSampling(TextDataset(enriched_train_df, col_names, extractor))
shared_variables["qs2"] = qs2
qs2 = shared_variables["qs2"]
return qs2.get_score(inst_idx)
class Object(object):
pass
PS_type = type(ss_type.__name__, (object,), dict(orig_state=Object())) # python hack for naming a type
def prepare_prev_state(ss_type, prev_state=None):
if prev_state is None:
prev_state = PS_type()
if issubclass(ss_type, SynStateALHeuristic):
if str(ss_type)+"qs" not in shared_variables:
qs = ss_type.build_query_strategy(enriched_train_df, col_names)
shared_variables[str(ss_type)+"qs"] = qs
qs = shared_variables[str(ss_type)+"qs"]
prev_state.build_next_states_qs = lambda _: qs
elif ss_type == SynStateTestDataGain:
if "en_labeled_train_df" not in shared_variables:
enriched_labeled_train_df = SynStateTestDataGain. \
label_dataframe_with_expert(enriched_train_df, col_names, labeled_df)
shared_variables["en_labeled_train_df"] = enriched_labeled_train_df
enriched_labeled_train_df = shared_variables["en_labeled_train_df"]
prev_state.build_next_states_labeled_df = lambda _: enriched_labeled_train_df
elif ss_type == SynStateRandom:
pass # return prev_state as it is
return prev_state
ss_prev_state = prepare_prev_state(ss_type)
ss = ss_type(inst_idx, enriched_train_df, col_names, ss_prev_state)
return ss.get_state_score()