shuffle=True,
n_class=True)
y_preds.append(y_pred)
model_all += models
nround_mean += len(ret['wloss-mean'])
wloss_list.append(ret['wloss-mean'][-1])
nround_mean = int((nround_mean / 2) * 1.3)
utils.send_line(f'nround_mean: {nround_mean}')
result = f"CV wloss: {np.mean(wloss_list)} + {np.std(wloss_list)}"
print(result)
utils.send_line(result)
for i, y_pred in enumerate(y_preds):
y_pred = pd.DataFrame(utils_metric.softmax(y_pred.astype(float).values))
if i == 0:
tmp = y_pred
else:
tmp += y_pred
tmp /= len(y_preds)
y_preds = tmp.copy().values.astype(float)
a_score = utils_metric.akiyama_metric(y.values, y_preds)
print(f'akiyama_metric: {a_score}')
utils.send_line(f'akiyama_metric: {a_score}')
# =============================================================================
# model
# =============================================================================
axis=1)
gc.collect()
is_gal = pd.read_pickle('../data/te_is_gal.pkl')
X_test_gal = X_test[is_gal][COL_gal]
X_test_exgal = X_test[~is_gal][COL_exgal]
del X_test
gc.collect()
for i, (model_gal,
model_exgal) in enumerate(zip(model_all_gal, model_all_exgal)):
y_pred_gal = model_gal.predict(X_test_gal)
y_pred_gal = utils_metric.softmax(y_pred_gal)
y_pred_exgal = model_exgal.predict(X_test_exgal)
y_pred_exgal = utils_metric.softmax(y_pred_exgal)
if i == 0:
y_pred_all_gal = y_pred_gal
y_pred_all_exgal = y_pred_exgal
else:
y_pred_all_gal += y_pred_gal
y_pred_all_exgal += y_pred_exgal
y_pred_all_gal /= int(LOOP)
y_pred_all_exgal /= int(LOOP)
sub_gal = pd.read_pickle('../data/te_oid_gal.pkl')
sub_exgal = pd.read_pickle('../data/te_oid_exgal.pkl')
verbose_eval=50,
seed=SEED)
y_pred = ex.eval_oob(X[COL],
y.values,
models,
SEED,
stratified=True,
shuffle=True,
n_class=y.unique().shape[0])
y_preds.append(y_pred)
model_all += models
nround_mean += len(ret['wloss-mean'])
wloss_list.append(ret['wloss-mean'][-1])
for i, y_pred in enumerate(y_preds):
y_pred = utils_metric.softmax(y_pred.astype(float).values)
if i == 0:
y_preds_ = y_pred
else:
y_preds_ += y_pred
y_preds_ /= len(y_preds)
# =============================================================================
#
# =============================================================================
utils_metric.multi_weighted_logloss(y, y_preds_)
def multi_weighted_logloss(y_true: np.array, y_preds: np.array):
# =============================================================================
# test
# =============================================================================
X_test = pd.concat([pd.read_pickle(f) for f in tqdm(files_te, mininterval=10)],
axis=1)[COL]
gc.collect()
for i in feature_set:
models = model_set[i]
col = feature_set[i]
for j, model in enumerate(tqdm(model_all)):
gc.collect()
y_pred = model.predict(X_test[col])
y_pred = utils_metric.softmax(y_pred)
if i == 0:
y_pred_all = y_pred
else:
y_pred_all += y_pred
y_pred_all /= int(LOOP * MOD_N)
sub = pd.read_csv('../input/sample_submission.csv.zip')
df = pd.DataFrame(y_pred_all, columns=sub.columns[1:-1])
sub = pd.concat([sub[['object_id']], df], axis=1)
# class_99
sub.to_pickle(f'../data/y_pred_raw_{__file__}.pkl')
utils.postprocess(sub, method='oli')
