def selection(fold, seedval, path, agg):
seed(seedval)
initial_ensemble_size = 2
max_ensemble_size = 50
max_candidates = 50
max_diversity_candidates = 5
accuracy_weight = 0.5
max_clusters = 20
train_df, train_labels, test_df, test_labels = common.read_fold(path, fold)
train_df = common.unbag(train_df, agg)
test_df = common.unbag(test_df, agg)
best_classifiers = train_df.apply(lambda x: common.fmax_score(
train_labels, x)).sort_values(ascending=not common.greater_is_better)
train_performance = []
test_performance = []
ensemble = []
for i in range(min(max_ensemble_size, len(best_classifiers))):
best_candidate = select_candidate_enhanced(train_df, train_labels,
best_classifiers, ensemble,
i)
ensemble.append(best_candidate)
train_performance.append(
get_performance(train_df, ensemble, fold, seedval))
test_performance.append(
get_performance(test_df, ensemble, fold, seedval))
train_performance_df = pd.DataFrame.from_records(train_performance)
best_ensemble_size = common.get_best_performer(
train_performance_df).ensemble_size.values
best_ensemble = train_performance_df.ensemble[:best_ensemble_size.item(0) +
1]
return get_predictions(
test_df, best_ensemble, fold,
seedval), pd.DataFrame.from_records(test_performance)
def stacked_generalization(fold):
train_df, train_labels, test_df, test_labels = common.read_fold(path, fold)
if method == 'aggregate':
train_df = common.unbag(train_df, bag_count)
test_df = common.unbag(test_df, bag_count)
test_predictions = stacker.fit(train_df, train_labels).predict_proba(test_df)[:, 1]
return DataFrame({'fold': fold, 'id': test_df.index.get_level_values('id'), 'label': test_labels, 'prediction': test_predictions, 'diversity': common.diversity_score(test_df.values)})
def stacked_generalization(fold):
seed(seedval)
train_df, train_labels, test_df, test_labels = read_fold(path, fold)
if method == 'aggregate':
train_df = unbag(train_df, bag_count)
test_df = unbag(test_df, bag_count)
predictions = stacker.fit(train_df, train_labels).predict_proba(test_df)[:, 1]
return eval_metrics(test_df, test_labels, predictions, [[fold], [seedval]])
def stacked_generalization(fold):
seed(seedval)
train_df, train_labels, test_df, test_labels = read_fold(path, fold)
if method == 'aggregate':
train_df = unbag(train_df, bag_count)
test_df = unbag(test_df, bag_count)
predictions = stacker.fit(train_df, train_labels).predict_proba(test_df)[:,
1]
return eval_metrics(test_df, test_labels, predictions, [[fold], [seedval]])
def stacked_generalization(path,stacker_name,stacker,fold,agg):
train_df, train_labels, test_df, test_labels = common.read_fold(path, fold)
train_df = common.unbag(train_df,agg)
test_df = common.unbag(test_df,agg)
try:
test_predictions = stacker.fit(train_df, train_labels).predict_proba(test_df)[:, 1]
except:
test_predictions = stacker.fit(train_df,train_labels).predict(test_df)[:,1]
df = pd.DataFrame({'fold': fold, 'id': test_df.index.get_level_values('id'), 'label': test_labels, 'prediction': test_predictions, 'diversity': common.diversity_score(test_df.values)})
return df
def bestbase_fmax(path,fold_count=5,agg=1):
assert exists(path)
if not exists('%s/analysis' % path):
mkdir('%s/analysis' % path)
predictions = []
labels = []
for fold in range(fold_count):
_,_,test_df,label = common.read_fold(path,fold)
test_df = common.unbag(test_df, agg)
predictions.append(test_df)
labels = append(labels,label)
predictions = pd.concat(predictions)
fmax_list = [common.fmax_score(labels,predictions.iloc[:,i]) for i in range(len(predictions.columns))]
return max(fmax_list)
def mean_fmax(path,fold_count=5,agg=1):
assert exists(path)
if not exists('%s/analysis' % path):
mkdir('%s/analysis' % path)
predictions = []
labels = []
for fold in range(fold_count):
_,_,test_df,label = common.read_fold(path,fold)
test_df = common.unbag(test_df, agg)
predict = test_df.mean(axis=1).values
predictions = append(predictions,predict)
labels = append(labels,label)
fmax = '%.3f' %(common.fmax_score(labels,predictions))
return float(fmax)
def mean_fmax(path):
assert exists(path)
if not exists('%s/analysis' % path):
mkdir('%s/analysis' % path)
p = common.load_properties(path)
fold_count = int(p['foldCount'])
predictions = []
labels = []
for fold in range(fold_count):
_, _, test_df, label = common.read_fold(path, fold)
test_df = common.unbag(test_df, 10)
predict = test_df.mean(axis=1).values
predictions += predict
labels += label
fmax = '%.3f' % (common.fmax_score(labels, predictions))
return fmax
def bestbase_fmax(path):
assert exists(path)
if not exists('%s/analysis' % path):
mkdir('%s/analysis' % path)
p = common.load_properties(path)
fold_count = int(p['foldCount'])
predictions = []
labels = []
for fold in range(fold_count):
_, _, test_df, label = common.read_fold(path, fold)
test_df = common.unbag(test_df, 10)
predictions.append(test_df)
labels += label
predictions = concat(predictions)
fmax_list = [
common.fmax_core(labels, predictions[col].tolist())
for col in list(predictions)
]
return max(fmax_list)