def get_feature_for_coalition_opposition():
train, validate, test = load_prepared_data()
df = pd.concat([train, validate, test])
X, y = df.drop(['Vote'], axis=1), df['Vote'].map(
lambda x: 0 if x in {'Reds', 'Greys', 'Oranges'} else 1)
plot_feature_ranks('Coalition/Opposition', party_feature_mi, X, y, 'MI')
def get_feature_for_all_parties():
train, validate, test = load_prepared_data()
df = pd.concat([train, validate, test])
X, y = df.drop(['Vote'], axis=1), df['Vote']
for party in np.unique(df['Vote']):
plot_feature_ranks(party, party_feature_mi, X,
y.map(lambda p: 1 if p == party else 0), 'MI')
def manipulate_winning_party(manipulation, f):
train, validate, test = load_prepared_data()
gbc = GradientBoostingClassifier(max_depth=7,
max_features=10).fit(*split_label(train))
test = pd.concat([validate, test])
test[f] = test[f].map(manipulation)
test_x, _ = split_label(test)
return test, gbc.predict(test_x)
def count_feature_before_after_dp(f):
count_feature(*load_prepared_data(), f)
count_feature(*load_unprepared_data(), f)
def calculate_feature_before_after_dp(f):
calculate_mean_feature(*load_prepared_data(), f)
calculate_mean_feature(*load_unprepared_data(), f)