plt.xlim(min_first_value, max_first_value)
ax.set_ylabel(headers[first_feature], size='12')
plt.ylim(min_second_value, max_second_value)
ax.set_xlabel(headers[second_feature], size='12')
ax.scatter(test_corrected_first_feature, test_corrected_second_feature, alpha=0.5,
color='yellow')
fig.tight_layout()
fig.savefig('reports/by_pair_features/' +
str(first_feature) + " " + headers[first_feature] + "-" +
str(second_feature) + " " + headers[second_feature] + '.png', dpi=120)
print("Columns # " + str(first_feature) + "_" + headers[first_feature] + "-" +
str(second_feature) + "_" + headers[second_feature] + ": ok!")
def split_training_data(data, targets):
signals_indices = [index for index, value in enumerate(targets) if value == 's']
backgrounds_indices = [index for index, value in enumerate(targets) if value == 'b']
return data[signals_indices], data[backgrounds_indices]
if __name__ == "__main__":
data_handler = DataHandler()
training_data, training_targets = data_handler.get_training_data()
test_data = data_handler.get_test_data()
headers = data_handler.get_headers()
# by_one_features(training_data, training_targets, test_data, headers)
by_pair_features(training_data, training_targets, test_data, headers)
