def make_adaboost_tree_fit_pipeline():
items = []
items.append(
('features', process_data.make_predictor_pipeline(do_one_hot=True)))
items.append(('model',
sklearn.ensemble.AdaBoostClassifier(
sklearn.tree.DecisionTreeClassifier())))
return sklearn.pipeline.Pipeline(items)
def make_bagging_tree_fit_pipeline():
items = []
items.append(
("features", process_data.make_predictor_pipeline(do_one_hot=True)))
items.append(("model",
sklearn.ensemble.BaggingClassifier(
sklearn.tree.DecisionTreeClassifier())))
return sklearn.pipeline.Pipeline(items)
def main(argv):
if len(argv) > 1:
filename = argv[1]
else:
filename = 'a.csv'
if os.path.exists(filename):
basename, ext = filename.split('.')
data = process_data.get_data(filename)
predictor_pipeline = process_data.make_predictor_pipeline(
do_one_hot=False)
label_pipeline = process_data.make_label_pipeline()
predictors_processed = predictor_pipeline.fit_transform(data)
labels_processed = label_pipeline.fit_transform(data)
display_data(predictors_processed, labels_processed, basename)
else:
print(filename + " doesn't exist.")
return
def make_svm_fit_pipeline():
items = []
items.append(("features", process_data.make_predictor_pipeline(do_one_hot=True)))
items.append(("model", sklearn.svm.SVC()))
return sklearn.pipeline.Pipeline(items)