# set booster parameters
simdir = sys.argv[1]
simnum = int(sys.argv[2])
num_rounds = int(sys.argv[3])
cv_params = {
"eval_metric": "mlogloss",
"objective": "multi:softprob",
"silent": 1,
"num_class": 9,
"nthread": 16,
"eta": sys.argv[4],
"gamma": sys.argv[5],
"max_depth": sys.argv[6],
"min_child_weight": sys.argv[7],
"colsample_bytree": sys.argv[8],
"subsample": sys.argv[9],
"early_stopping_rounds": 10,
}
print cv_params
mkdir_p(simdir)
paramfile = simdir + "/param_%d.txt" % simnum
with open(paramfile, "w") as fp:
json.dump(cv_params, fp)
logfile = simdir + "/log_%d.txt" % simnum
lls = xu.xgb_cv(cv_params, dtrain, num_rounds, nfold=3)
np.savetxt(logfile, lls)
cv_params = {}
cv_params['simdir'] = sys.argv[1]
cv_params['simnum'] = int(sys.argv[2])
cv_params['kernel'] = sys.argv[3]
cv_params['C'] = float(sys.argv[4])
cv_params['gamma'] = float(sys.argv[5])
clf_svc = svm.SVC(probability=True, verbose=False,
C=cv_params['C'], kernel=cv_params['kernel'],
gamma=cv_params['gamma'], cache_size=1000)
clf = make_pipeline(preprocessing.StandardScaler(), clf_svc)
mkdir_p(cv_params['simdir'])
scores = cross_validation.cross_val_score(clf, train, labels,
cv=n_cvs, n_jobs=-1,
scoring=logloss_mc,
verbose=1)
print "scores: ", scores
logfile = cv_params['simdir'] + '/%d.txt' % cv_params['simnum']
with open(logfile, 'w') as fscores:
fscores.write('%f %f\n' % (scores.mean(), scores.std()))
pfile = logfile.replace('.txt', 'p.txt')
with open(pfile, 'w') as f:
json.dump(cv_params, f)
sys.path.append(pardir)
import xgb_utils as xu
import otto_utils as ou
if len(sys.argv)<2:
sys.exit(1)
ncv = int(sys.argv[1])
if ncv not in [0, 1, 2, 3, 4]:
sys.exit(1)
simdir = 'kfcv'
ou.mkdir_p(simdir)
simdir = simdir + '/' + str(ncv)
ou.mkdir_p(simdir)
num_rounds = 2000
params = """{"eval_metric": "mlogloss", "early_stopping_rounds": 10, "colsample_bytree": "0.5", "num_class": 9, "silent": 1, "nthread": 16, "min_child_weight": "4", "subsample": "0.8", "eta": "0.0125","objective": "multi:softprob", "max_depth": "14", "gamma": "0.025"}"""
params = json.loads(params)
# files
train_csv = '../data/train.csv'
train_buf = 'data/train.buffer'
