def build_model(
X,
y,
X_train,
y_train,
X_test,
y_test,
seed,
method,
):
model = model.Model()
evc_meta = model.model_ensemble(X, y, method=method)
model.model_predict(evc_meta, X_train, y_train, X_test, y_test, seed=seed)
model.cross_validate(evc_meta, X, y, seed)
print("Start dumping Meta classifier...")
joblib.dump(evc_meta, "meta_clf.pkl")
print("Done dumping Meta classifier ! \n")
return evc_meta
def task():
year, months = 2019, [10, 11, 12]
select = None
radius, aperture_size, incident_interval, time_step = '100', '6', '25', '1'
config = {
'year': year,
'months': months,
'radius': radius,
'aperture_size': aperture_size,
'incident_interval': incident_interval,
'time_step': time_step,
'select': select
}
month = months[0]
df = pd.read_pickle(
f'output/waze/{year}_{month}_{radius}_{aperture_size}_features.pkl')
for month in months[1:]:
temp_df = pd.read_pickle(
f'output/waze/{year}_{month}_{radius}_{aperture_size}_features.pkl'
)
df = df.append(temp_df, sort=False)
df.fillna(0, inplace=True)
# if select is not None:
# df = df[-1 * int(select):]
if os.path.exists(
f'output/{year}_{month}_{radius}_{aperture_size}_predict_proba.pkl'
):
x = pd.read_pickle(
f'output/{year}_{month}_{radius}_{aperture_size}_predict_proba.pkl'
)
else:
x = model.predict_proba(df, int(incident_interval), time_step)
x = model.extract_features(x, df)
x.to_pickle(
f'output/{year}_{month}_{radius}_{aperture_size}_predict_proba.pkl'
)
incident_df = load_incidents(aperture_size)
if os.path.exists(f'output/{year}_{month}_{radius}_{aperture_size}_y.pkl'):
y = pd.read_pickle(
f'output/{year}_{month}_{radius}_{aperture_size}_y.pkl')
else:
y = label_mapper(x, incident_df)
pd.Series(y).to_pickle(
f'output/{year}_{month}_{radius}_{aperture_size}_y.pkl')
models = [
'LogisticRegression', 'DecisionTreeClassifier',
'RandomForestClassifier'
]
for m in models:
print('model', m)
cv_results, y_pred = model.cross_validate(x, y, m)
for k, v in config.items():
print(k, ',', v)
for k, v in cv_results.items():
print(k, ',', np.average(v))
print()
def predict(year, month, radius, aperture_size, incident_interval, time_step,
select):
config = {
'year': year,
'month': month,
'radius': radius,
'aperture_size': aperture_size,
'incident_interval': incident_interval,
'time_step': time_step,
'select': select
}
df = pd.read_pickle(
f'output/waze/{year}_{month}_{radius}_{aperture_size}_features.pkl')
if select is not None:
df = df[-1 * int(select):]
x = model.predict_proba(df, int(incident_interval), time_step)
incident_df = load_incidents(aperture_size)
y = label_mapper(x, incident_df)
print(np.unique(y, return_counts=True))
cv_results = model.cross_validate(x, y)
for k, v in config.items():
print(k, v)
for k, v in cv_results.items():
print(k, np.average(v))
train_data, train_labels = load_data('../data/data-splits/data.train',
n_features=n_features,
neg_labels=True,
bias=True,
preprocessor=preprocessor)
test_data, test_labels = load_data('../data/data-splits/data.test',
n_features=n_features,
neg_labels=True,
bias=True,
preprocessor=preprocessor)
cv_data = np.array_split(np.hstack((train_data, train_labels)), 5)
cv_acc = 0
if max_param is None:
cv_acc, max_param = cross_validate(cv_data, weights, update_weights,
params, update_params)
max_weights = train(train_data,
train_labels,
weights,
update_weights,
max_param,
update_params,
epochs=10)
train_acc = classify(train_data, train_labels, max_weights)
test_acc = classify(test_data, test_labels, max_weights)
def predictor(row):
label = np.sign(np.dot(row, max_weights))
if label == -1: