def update_best(task, score, ans):
files = glob(f"best/{task}@*@.txt")
logger.debug(f"Have files for {files}")
if len(files) == 0 or int(files[0].split('@')[1]) < score:
if len(files) > 0:
os.remove(files[0])
write_answer(ans, f"best/{task}@{score}@.txt")
def main():
train_x, train_y = read_data(train_fname)
ID, test_x = read_data(test_fname, train_mode=False)
print(ID)
print(train_x)
print(np.sum(train_y))
ind = random.shuffle(range(train_x[0]))
# train_x, train_y, val_x, val_y = split_data(train_x, train_y, val_ratio=0.2)
tr = xgb.DMatrix(train_x, label=train_y)
# val = xgb.DMatrix(val_x, label=val_y)
te = xgb.DMatrix(test_x)
param = {'bst:max_depth':3, 'bst:eta':0.1, 'silent':0, 'objective':'binary:logistic' }
param['nthread'] = 16
param['eval_metric'] = 'auc'
num_round = 100
xgb.cv(param, tr, num_round, nfold=5, metrics={"error"})
model = xgb.train(param, tr, num_round, early_stopping_rounds=10)
ypred = model.predict(xgmat, ntree_limit=model.best_ntree_limit)
clf = RandomForestClassifier(n_estimators=500,
criterion='entropy',
max_features='sqrt',
max_depth=None,
oob_score=False,
n_jobs=-1,
verbose=1)
clf.fit(X=train_x, y=train_y)
print(clf.score(train_x, train_y))
pred = clf.predict(X=test_x)
pred_prob = clf.predict_proba(X=test_x)[:,1]
write_answer(output_fname, ID, pred, print_prob=False)
write_answer("prob_"+output_fname, ID, pred_prob, print_prob=True)
def main():
train_x, train_y = read_data(train_fname)
ID, test_x = read_data(test_fname, train_mode=False)
print(ID)
print(train_x)
print(np.sum(train_y))
clf = RandomForestClassifier(n_estimators=500,
criterion='entropy',
max_features='sqrt',
max_depth=None,
oob_score=False,
n_jobs=-1,
verbose=1)
clf.fit(X=train_x, y=train_y)
print(clf.score(train_x, train_y))
pred = clf.predict(X=test_x)
pred_prob = clf.predict_proba(X=test_x)[:,1]
write_answer(output_fname, ID, pred, print_prob=False)
write_answer("prob_"+output_fname, ID, pred_prob, print_prob=True)
