def get_imp(shuffle=True, loop=1):
if shuffle:
dtrain = lgb.Dataset(X, y.sample(frac=1).values, free_raw_data=False)
gc.collect()
else:
dtrain = lgb.Dataset(X, y.values, free_raw_data=False)
gc.collect()
model_all = []
nround_mean = 0
wloss_list = []
for i in range(loop):
gc.collect()
param['seed'] = np.random.randint(9999)
ret, models = lgb.cv(param,
dtrain,
99999,
nfold=NFOLD,
fobj=utils_metric.wloss_objective,
feval=utils_metric.wloss_metric,
early_stopping_rounds=100,
verbose_eval=200,
seed=SEED + i)
model_all += models
nround_mean += len(ret['multi_logloss-mean'])
wloss_list.append(ret['wloss-mean'][-1])
imp = ex.getImp(model_all)
imp['split'] /= imp['split'].max()
imp['gain'] /= imp['gain'].max()
imp['total'] = imp['split'] + imp['gain']
imp.sort_values('total', ascending=False, inplace=True)
imp.reset_index(drop=True, inplace=True)
return imp.set_index('feature')
CAT = list(set(X.columns) & set(utils_cat.ALL))
if X.columns.duplicated().sum() > 0:
raise Exception(f'duplicated!: { X.columns[X.columns.duplicated()] }')
print('no dup :) ')
print(f'X.shape {X.shape}')
gc.collect()
# =============================================================================
# imp
# =============================================================================
dtrain = lgb.Dataset(X, y, categorical_feature=CAT)
model = lgb.train(params, dtrain, 1000)
imp = ex.getImp(model).sort_values(['gain', 'feature'],
ascending=[False, True])
features_search = imp[imp['split'] > 0].feature.tolist()
features_curr = features_search[:20]
# =============================================================================
# stepwise
# =============================================================================
ex.stepwise(params,
X,
y,
features_search,
features_curr,
best_score=0,
send_line=utils.send_line,
shuffle=True,
feval=ex.eval_auc,
early_stopping_rounds=ESR,
verbose_eval=VERBOSE_EVAL,
categorical_feature=CAT,
seed=SEED)
for i, model in enumerate(models):
model.save_model(f'../data/lgb{i}.model')
#models = []
#for i in range(LOOP):
# model = lgb.Booster(model_file=f'../data/lgb{i}.model')
# models.append(model)
imp = ex.getImp(models)
imp['split'] /= imp['split'].max()
imp['gain'] /= imp['gain'].max()
imp['total'] = imp['split'] + imp['gain']
imp.sort_values('total', ascending=False, inplace=True)
imp.reset_index(drop=True, inplace=True)
imp.to_csv(f'LOG/imp_{__file__}.csv', index=False)
utils.savefig_imp(imp, f'LOG/imp_{__file__}.png', x='total')
RESULT_DICT['nfold'] = NFOLD
RESULT_DICT['seed'] = SEED
RESULT_DICT['eta'] = param['learning_rate']
RESULT_DICT['best NROUND'] = len(ret['auc-mean'])
RESULT_DICT['train AUC'] = ret['auc-mean'][-1]
feval=utils_metric.wloss_metric,
early_stopping_rounds=100, verbose_eval=50,
seed=SEED)
y_pred = ex.eval_oob(X, y, 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] )
nround_mean = int((nround_mean/1) * 1.3)
result = f"CV wloss: {np.mean(wloss_list)} + {np.std(wloss_list)}"
print(result)
imp = ex.getImp(model_all)
imp['split'] /= imp['split'].max()
imp['gain'] /= imp['gain'].max()
imp['total'] = imp['split'] + imp['gain']
imp.sort_values('total', ascending=False, inplace=True)
imp.reset_index(drop=True, inplace=True)
imp.to_csv(f'LOG/imp_{__file__}.csv', index=False)
png = f'LOG/imp_{__file__}.png'
utils.savefig_imp(imp, png, x='total', title=f'{__file__}')
utils.send_line(result, png)
for i,y_pred in enumerate(y_preds):
