ax3.plot([0, 1], [0, 1], color='gray', linestyle='--')
ax3.set_xlabel('Mean Predicted Value')
ax3.set_ylabel('Fraction of positives')
fig.tight_layout(pad=0)
if outputfile:
fig.savefig(outputfile)
else:
plt.show()
if __name__ == '__main__':
df = read_data('signal.csv', 'background.csv')
df = drop_useless(df)
print(80*'=')
print('{:^80}'.format('GaussianNB'))
print(80*'=')
gnb = GaussianNB()
df_nb_label = df.dropna(axis=1)['label']
df_nb = df.dropna(axis=1).drop('label', axis=1)
print('{} remaining features after dropping columns NaNs.'.format(
len(df_nb.columns)
))
nb_aucs = classifier_crossval_performance(
df_nb.values, df_nb_label.values, classifier=gnb
)
cval = StratifiedKFold(y, n_folds=n_folds, shuffle=True)
with Parallel(n_jobs=n_jobs) as pool:
performances = pool(
delayed(evaluate)(X, y, train, test)
for train, test in cval
)
performances = pd.Panel(dict(enumerate(performances)))
return performances
if __name__ == '__main__':
data = drop_useless(read_data('./signal.csv', './background.csv'))
nb = GaussianNB()
classifiers = {
'RandomForest': RandomForestClassifier(
n_estimators=100, criterion='entropy', n_jobs=2,
),
# 'ExtraTrees': ExtraTreesClassifier(
# n_estimators=100, criterion='entropy', n_jobs=-1
# ),
'AdaBoost': GradientBoostingClassifier(
n_estimators=100, loss='exponential',
),
'NaiveBayes': GaussianNB()
}
