free_raw_data=False)
gc.collect()
model_all = []
nround_mean = 0
wloss_list = []
y_preds = []
for i in range(1):
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=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']
# best(gal)
# =============================================================================
N = best_N
#N = 250
dtrain = lgb.Dataset(X_gal[COL[:N]], y_gal, #categorical_feature=CAT,
free_raw_data=False)
ret, models = lgb.cv(param, dtrain, 99999, nfold=NFOLD,
fobj=utils_metric.wloss_objective_gal,
feval=utils_metric.wloss_metric_gal,
folds=group_kfold.split(X_gal, y_gal, group_gal),
early_stopping_rounds=100, verbose_eval=50,
seed=SEED)
score = ret['wloss-mean'][-1]
y_pred_gal = ex.eval_oob(X_gal[COL[:N]], y_gal, models, SEED, stratified=True, shuffle=True,
n_class=y_exgal.unique().shape[0])
# =============================================================================
# cv(exgal)
# =============================================================================
print('==== EXGAL ====')
param['num_class'] = 9
param['learning_rate'] = 0.1
dtrain = lgb.Dataset(X_exgal, y_exgal, #categorical_feature=CAT,
free_raw_data=False)
gc.collect()
model_all = []
nround_mean = 0
wloss_list = []
param['seed'] = np.random.randint(9999)
ret, models = lgb.cv(param,
dtrain,
NROUND,
nfold=NFOLD,
stratified=True,
shuffle=True,
feval=ex.eval_auc,
early_stopping_rounds=ESR,
verbose_eval=VERBOSE_EVAL,
seed=SEED + i)
y_pred = ex.eval_oob(X_train,
y_train.values,
models,
SEED + i,
stratified=True,
shuffle=True)
y_preds.append(y_pred)
model_all += models
nround_mean += len(ret['auc-mean'])
loss_list.append(ret['auc-mean'][-1])
nround_mean = int((nround_mean / LOOP) * 1.3)
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)
def mk_submit(HEAD):
SUBMIT_FILE_PATH_ = SUBMIT_FILE_PATH.replace('feature', str(HEAD))
files_tr = ('../feature/train_' + imp.head(HEAD).feature + '.f').tolist()
files_te = ('../feature/test_' + imp.head(HEAD).feature + '.f').tolist()
# =============================================================================
# load
# =============================================================================
# train
X_train = pd.concat(
[pd.read_feather(f) for f in tqdm(files_tr, mininterval=60)], axis=1)
y_train = utils.read_pickles('../data/label').TARGET
X_train.head().to_csv(SUBMIT_FILE_PATH_.replace('.csv', '_X.csv'),
index=False,
compression='gzip')
if X_train.columns.duplicated().sum() > 0:
raise Exception(
f'duplicated!: { X_train.columns[X_train.columns.duplicated()] }')
print('no dup :) ')
print(f'X_train.shape {X_train.shape}')
gc.collect()
CAT = list(set(X_train.columns) & set(utils_cat.ALL))
COL = X_train.columns.tolist()
# test
X_test = pd.concat(
[pd.read_feather(f) for f in tqdm(files_te, mininterval=60)],
axis=1)[COL]
# =============================================================================
# training with cv
# =============================================================================
dtrain = lgb.Dataset(X_train,
y_train,
categorical_feature=CAT,
free_raw_data=False)
model_all = []
y_pred = pd.Series(0, index=y_train.index)
for i in range(LOOP):
gc.collect()
param['seed'] = i
ret, models = lgb.cv(param,
dtrain,
9999,
nfold=NFOLD,
early_stopping_rounds=100,
verbose_eval=50,
seed=i)
model_all += models
y_pred += ex.eval_oob(X_train, y_train, models, i).rank()
y_pred /= y_pred.max()
auc_mean = roc_auc_score(y_train, y_pred)
result = f"CV auc-mean(feature {HEAD}): {auc_mean}"
print(result)
utils.send_line(result)
# =============================================================================
# predict
# =============================================================================
sub = pd.read_pickle('../data/sub.p')
gc.collect()
label_name = 'TARGET'
sub[label_name] = 0
for model in model_all:
y_pred = model.predict(X_test)
sub[label_name] += pd.Series(y_pred).rank()
sub[label_name] /= len(model_all)
sub[label_name] /= sub[label_name].max()
sub['SK_ID_CURR'] = sub['SK_ID_CURR'].map(int)
sub.to_csv(SUBMIT_FILE_PATH_, index=False, compression='gzip')
def mk_submit():
# =============================================================================
# load
# =============================================================================
# train
X_train = loader.train()
col = [c for c in X_train.columns if c.startswith('f702_')]
X_train.drop(col, axis=1, inplace=True)
y_train = utils.read_pickles('../data/label').TARGET
X_train.head().to_csv(SUBMIT_FILE_PATH.replace('.csv', '_X.csv'),
index=False,
compression='gzip')
if X_train.columns.duplicated().sum() > 0:
raise Exception(
f'duplicated!: { X_train.columns[X_train.columns.duplicated()] }')
print('no dup :) ')
print(f'X_train.shape {X_train.shape}')
gc.collect()
CAT = list(set(X_train.columns) & set(loader.category()))
print('CAT :', CAT)
COL = X_train.columns.tolist()
# test
X_test = loader.test()[COL]
# =============================================================================
# training with cv
# =============================================================================
dtrain = lgb.Dataset(X_train,
y_train,
categorical_feature=CAT,
free_raw_data=False)
model_all = []
y_pred = pd.Series(0, index=y_train.index)
for i in range(LOOP):
gc.collect()
param['seed'] = i
ret, models = lgb.cv(param,
dtrain,
9999,
nfold=NFOLD,
early_stopping_rounds=100,
verbose_eval=50,
seed=i)
model_all += models
y_pred += ex.eval_oob(X_train, y_train, models, i).rank()
auc_mean = roc_auc_score(y_train, y_pred)
result = f"CV auc-mean(loop {i}): {auc_mean} {ret['auc-mean'][-1]}"
print(result)
utils.send_line(result)
y_pred /= y_pred.max()
auc_mean = roc_auc_score(y_train, y_pred)
result = f"CV auc-mean: {auc_mean}"
print(result)
utils.send_line(result)
# =============================================================================
# predict
# =============================================================================
sub = pd.read_pickle('../data/sub.p')
gc.collect()
label_name = 'TARGET'
sub[label_name] = 0
for model in model_all:
y_pred = model.predict(X_test)
sub[label_name] += pd.Series(y_pred).rank()
sub[label_name] /= len(model_all)
sub[label_name] /= sub[label_name].max()
sub['SK_ID_CURR'] = sub['SK_ID_CURR'].map(int)
sub.to_csv(SUBMIT_FILE_PATH, index=False, compression='gzip')
# =============================================================================
# submission
# =============================================================================
if EXE_SUBMIT:
print('submit')
utils.submit(SUBMIT_FILE_PATH, COMMENT)
oofs = []
for i in range(LOOP):
gc.collect()
param['seed'] = np.random.randint(9999)
ret, models = lgb.cv(param,
dtrain,
99999,
nfold=NFOLD,
early_stopping_rounds=100,
verbose_eval=50,
seed=SEED)
y_pred = ex.eval_oob(
X_52_90,
y_52_90.values,
models,
SEED,
stratified=True,
shuffle=True,
)
oofs.append(y_pred)
model_all += models
nround_mean += len(ret['auc-mean'])
wloss_list.append(ret['auc-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)}"
utils.send_line(result)
for i, y_pred in enumerate(oofs):
# =============================================================================
# cv
# =============================================================================
dtrain = lgb.Dataset(X, y, categorical_feature=CAT)
gc.collect()
ret, models = lgb.cv(param,
dtrain,
9999,
folds=folds,
early_stopping_rounds=100,
verbose_eval=50,
seed=SEED)
y_pred = ex.eval_oob(X, y, models, SEED)
result = f"CV auc-mean({COMMENT}): {ret['auc-mean'][-1]} + {ret['auc-stdv'][-1]}"
print(result)
utils.send_line(result)
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('LOG/imp_f021.csv', index=False)
param,
dtrain,
NROUND,
# nfold=NFOLD,
folds=group_kfold.split(X_train_, y_train_, group),
stratified=True,
shuffle=True,
feval=ex.eval_auc,
early_stopping_rounds=ESR,
verbose_eval=VERBOSE_EVAL,
seed=SEED + i)
y_pred = ex.eval_oob(X_train_,
y_train_.values,
models,
SEED + i,
folds=group_kfold.split(X_train_, y_train_, group),
stratified=True,
shuffle=True)
y_preds.append(y_pred)
model_all += models
nround_mean += len(ret['auc-mean'])
loss_list.append(ret['auc-mean'][-1])
nround_mean = int((nround_mean / LOOP) * 1.3)
# =============================================================================
# test
# =============================================================================
param['seed'] = np.random.randint(9999)
ret, models = lgb.cv(param,
dtrain,
NROUND,
nfold=NFOLD,
stratified=True,
shuffle=True,
feval=ex.eval_auc,
early_stopping_rounds=ESR,
verbose_eval=VERBOSE_EVAL,
seed=SEED + i)
p_train = ex.eval_oob(X_train[col],
y_train.values,
models,
SEED + i,
stratified=True,
shuffle=True)
model_all += models
nround_mean += len(ret['auc-mean'])
loss_list.append(ret['auc-mean'][-1])
utils.send_line(
f'oof AUC({i}): {round(roc_auc_score(y_train, p_train), 5)}')
#==============================================================================
utils.end(__file__)
#utils.stop_instance()
# =============================================================================
# cv
# =============================================================================
dtrain = lgb.Dataset(X, y)
gc.collect()
ret, models = lgb.cv(param,
dtrain,
99999,
nfold=7,
early_stopping_rounds=100,
verbose_eval=50,
seed=111)
y_pred = ex.eval_oob(X, y, models, 111)
result = f"CV auc-mean: {ret['auc-mean'][-1]} + {ret['auc-stdv'][-1]}"
print(result)
utils.send_line(result)
imp = ex.getImp(models)
# =============================================================================
# cv loop
# =============================================================================
from sklearn.metrics import roc_auc_score
dtrain = lgb.Dataset(X, y, free_raw_data=False)
gc.collect()
# =============================================================================
# cv loop
# =============================================================================
dtrain = lgb.Dataset(X_new, y, categorical_feature=CAT, free_raw_data=False)
gc.collect()
y_pred = pd.Series(0, index=y.index)
for i in range(5):
ret, models = lgb.cv(param, dtrain, 99999, nfold=7,
early_stopping_rounds=100, verbose_eval=50,
seed=i)
y_pred += ex.eval_oob(X_new, y, models, i).rank()
y_pred /= y_pred.max()
auc_mean = roc_auc_score(y, y_pred)
result = f"CV auc-mean(ext imp): {auc_mean}"
print(result)
utils.send_line(result)
#==============================================================================
utils.end(__file__)
#utils.stop_instance()
def mk_submit():
files_tr = ('../feature/train_' + features + '.f').tolist()
files_te = ('../feature/test_' + features + '.f').tolist()
# =============================================================================
# load
# =============================================================================
# train
X_train = pd.concat(
[pd.read_feather(f) for f in tqdm(files_tr, mininterval=60)], axis=1)
y_train = utils.read_pickles('../data/label').TARGET
# =============================================================================
# remove old users
# =============================================================================
X_train['SK_ID_CURR'] = SK_ID_CURR
y_train = y_train[~X_train.SK_ID_CURR.isin(drop_ids)]
X_train = X_train[~X_train.SK_ID_CURR.isin(drop_ids)]
oof_train = X_train[['SK_ID_CURR']]
X_train.drop('SK_ID_CURR', axis=1, inplace=True)
X_train.head().to_csv(SUBMIT_FILE_PATH.replace('.csv', '_X.csv'),
index=False,
compression='gzip')
if X_train.columns.duplicated().sum() > 0:
raise Exception(
f'duplicated!: { X_train.columns[X_train.columns.duplicated()] }')
print('no dup :) ')
print(f'X_train.shape {X_train.shape}')
gc.collect()
CAT = list(set(X_train.columns) & set(utils_cat.ALL))
COL = X_train.columns.tolist()
# test
X_test = pd.concat(
[pd.read_feather(f) for f in tqdm(files_te, mininterval=60)],
axis=1)[COL]
# =============================================================================
# training with cv
# =============================================================================
dtrain = lgb.Dataset(X_train,
y_train,
categorical_feature=CAT,
free_raw_data=False)
model_all = []
y_pred = pd.Series(0, index=y_train.index)
for i in range(LOOP):
gc.collect()
param['seed'] = i
ret, models = lgb.cv(param,
dtrain,
9999,
nfold=NFOLD,
early_stopping_rounds=100,
verbose_eval=50,
seed=i)
model_all += models
y_pred += ex.eval_oob(X_train, y_train, models, i).rank()
auc_mean = roc_auc_score(y_train, y_pred)
result = f"CV auc-mean(loop {i}): {auc_mean}"
print(result)
utils.send_line(result)
y_pred /= y_pred.max()
auc_mean = roc_auc_score(y_train, y_pred)
result = f"CV auc-mean: {auc_mean}"
print(result)
utils.send_line(result)
# save
oof_train['oof'] = y_pred
oof_train.to_csv('../output/onodera-last-oof.csv', index=False)
# =============================================================================
# predict
# =============================================================================
sub = pd.read_pickle('../data/sub.p')
gc.collect()
label_name = 'TARGET'
sub[label_name] = 0
for model in model_all:
y_pred = model.predict(X_test)
sub[label_name] += pd.Series(y_pred).rank()
sub[label_name] /= len(model_all)
sub[label_name] /= sub[label_name].max()
sub['SK_ID_CURR'] = sub['SK_ID_CURR'].map(int)
sub.to_csv(SUBMIT_FILE_PATH, index=False, compression='gzip')
# =============================================================================
# submission
# =============================================================================
if EXE_SUBMIT:
print('submit')
utils.submit(SUBMIT_FILE_PATH, COMMENT)
# =============================================================================
# cv
# =============================================================================
dtrain = lgb.Dataset(X, y, categorical_feature=CAT)
gc.collect()
ret, models = lgb.cv(param,
dtrain,
9999,
folds=folds,
early_stopping_rounds=100,
verbose_eval=50,
seed=SEED)
y_pred = ex.eval_oob(X, y, models, SEED)
result = f"CV auc-mean({COMMENT}): {ret['auc-mean'][-1]} + {ret['auc-stdv'][-1]}"
print(result)
utils.send_line(result)
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)
# =============================================================================
gc.collect()
param['seed'] = np.random.randint(9999)
ret, models = lgb.cv(param,
dtrain,
99999,
nfold=NFOLD,
fobj=utils_metric.wloss_objective_gal,
feval=utils_metric.wloss_metric_gal,
early_stopping_rounds=100,
verbose_eval=50,
folds=group_kfold.split(X_gal, y_gal, group_gal),
seed=SEED)
oof = ex.eval_oob(X_gal,
y_gal.values,
models,
SEED,
stratified=True,
shuffle=True,
n_class=True)
oofs_gal.append(oof)
# 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 GAL wloss: {np.mean(wloss_list)} + {np.std(wloss_list)}"
utils.send_line(result)
# =============================================================================
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=50,
seed=SEED)
y_pred = ex.eval_oob(X[feature_set[i]],
y.values,
models,
SEED,
stratified=True,
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 / MOD_N) * 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)
dtrain = lgb.Dataset(X, y, categorical_feature=CAT, free_raw_data=False)
model_all = []
y_pred = pd.Series(0, index=y.index)
for i in range(LOOP):
gc.collect()
param['seed'] = i
ret, models = lgb.cv(param,
dtrain,
9999,
nfold=NFOLD,
early_stopping_rounds=100,
verbose_eval=50,
seed=i)
model_all += models
y_pred += ex.eval_oob(X, y, models, i)
auc_mean = roc_auc_score(y, y_pred)
result = f"CV auc-mean(loop {i}): {auc_mean} {ret['auc-mean'][-1]}"
print(result)
utils.send_line(result)
y_pred /= LOOP
auc_mean = roc_auc_score(y, y_pred)
result = f"CV auc-mean: {auc_mean}"
print(result)
utils.send_line(result)
y_pred.name = 'f190_adv'
y_pred = y_pred.to_frame()
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=50,
seed=SEED)
y_pred = ex.eval_oob(X[COL],
y.values,
models,
SEED,
stratified=True,
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)
gc.collect()
model_all = []
nround_mean = 0
auc_list = []
for i in range(LOOP):
gc.collect()
param['seed'] = np.random.randint(9999)
ret, models = lgb.cv(param,
dtrain,
99999,
nfold=NFOLD,
early_stopping_rounds=100,
verbose_eval=50,
seed=SEED)
y_pred = ex.eval_oob(X, y, models, SEED, stratified=True, shuffle=True)
model_all += models
nround_mean += len(ret['auc-mean'])
auc_list.append(ret['auc-mean'][-1])
nround_mean = int((nround_mean / LOOP) * 1.3)
result = f"CV wloss: {np.mean(nround_mean)} + {np.std(nround_mean)}"
print(result)
utils.send_line(result)
imp = ex.getImp(model_all)
imp['split'] /= imp['split'].max()
imp['gain'] /= imp['gain'].max()
imp['total'] = imp['split'] + imp['gain']
