def main():
"""Do something with the project code! Have fun :) """
preprocessor = Preprocessor()
preprocessor.import_labeled_data("data/train.csv")
X_total, t_total = preprocessor.encode_labels(use_new_encoder=True)
X_train, X_test, t_train, t_test = preprocessor.train_test_split(
X_total, t_total)
# transform data and overwrite non-transformed data
X_train_scaled = preprocessor.scale_data(X_train, use_new_scaler=True)
X_test_scaled = preprocessor.scale_data(X_test, use_new_scaler=False)
# apply PCA
X_train = preprocessor.apply_pca(X_train_scaled,
use_new_pca=True,
n_components=27,
whiten=False)
X_test = preprocessor.apply_pca(X_test_scaled, use_new_pca=False)
clf = NaiveBayes(X_train, t_train)
clf.optimize_hyperparameters()
clf.display_general_validation_results()
clf.display_cv_results()
print("Test accuracy : {:.03f}".format(clf.get_accuracy(X_test, t_test)))
print("Test f1-score : {:.03f}".format(clf.get_f1_score(X_test, t_test)))
label_predictions = make_new_predictions("data/test.csv", preprocessor,
clf)
def run_all_classifiers():
"""Naive demonstration of all classifiers on default settings.
Does not give optimal solutions because different PCA transformations are needed.
"""
preprocessor = Preprocessor()
preprocessor.import_labeled_data("data/train.csv")
# encode labels and split 80/20 train/test
X_total, t_total = preprocessor.encode_labels(use_new_encoder=True)
X_train, X_test, t_train, t_test = preprocessor.train_test_split(
X_total, t_total)
# transform data and overwrite non-transformed data
X_train = preprocessor.scale_data(X_train, use_new_scaler=True)
X_test = preprocessor.scale_data(X_test)
# apply pca
X_train = preprocessor.apply_pca(X_train, use_new_pca=True)
X_test = preprocessor.apply_pca(X_test)
# init classifiers
clfs = [
clf(X_train, t_train) for clf in
[LogisticRegression, Perceptron, SVM, MLP, RandomForest, NaiveBayes]
]
# training and cross-validation on default hyperparameters
for clf in clfs:
clf.optimize_hyperparameters()
clf.display_general_validation_results()
print("Test accuracy : {:.03f}".format(clf.get_accuracy(
X_test, t_test)))
print("Test f1-score : {:.03f}".format(clf.get_f1_score(
X_test, t_test)))