def pre(self, s):
if self.input is None:
for i, a in enumerate(self.validation_data):
print(i, a.shape)
self.input = self.validation_data[:-2]
self.label = base_data_process.one_hot2label_index(self.validation_data[-2])
y_pre = self.model.predict(self.input)
y_index = base_data_process.one_hot2label_index(y_pre)
f1 = f1_score(self.label, y_index, average='macro')
log.info('{} f1: {}'.format(s, f1))
return f1
def write2file(col_id, pre_label, name=None):
with timer('write result {}'.format(name)):
y_pre = one_hot2label_index(pre_label)
df = pd.DataFrame()
df[ID] = col_id
df['predict'] = index2label(y_pre)
df.to_csv('result{}.csv'.format(name), index=False)
def cross_validation(train,
params,
ID_COLUMN_NAME,
LABEL_COLUMN_NAME,
N_FOLD=5):
'''
:return: loss
'''
NUM_BOOST_ROUND = 5
EARLY_STOPPING_ROUNDS = 2
# Cross validation model
folds = StratifiedKFold(n_splits=N_FOLD, shuffle=True, random_state=1001)
feats = [
f for f in train.columns
if f not in [LABEL_COLUMN_NAME, ID_COLUMN_NAME]
]
for i_fold, (train_idx, valid_idx) in enumerate(
folds.split(train[feats], train[LABEL_COLUMN_NAME])):
dtrain = lgb.Dataset(data=train[feats].iloc[train_idx],
label=train[LABEL_COLUMN_NAME].iloc[train_idx],
free_raw_data=False,
silent=True)
dvalid = lgb.Dataset(data=train[feats].iloc[valid_idx],
label=train[LABEL_COLUMN_NAME].iloc[valid_idx],
free_raw_data=False,
silent=True)
with timer('cross validation-fold {} train model'.format(i_fold)):
log.info('params is {}'.format(params))
clf = lgb.train(num_boost_round=NUM_BOOST_ROUND,
params=params,
verbose_eval=10,
train_set=dtrain,
valid_sets=[dvalid],
early_stopping_rounds=EARLY_STOPPING_ROUNDS)
with timer('cross validation-fold {} predict'.format(i_fold)):
v_data = clf.predict(dvalid.data)
y_pre = one_hot2label_index(v_data)
f1 = f1_score(dvalid.label, y_pre, average='macro')
return f1
def model(train,
test,
num_folds=5,
stratified=True,
num_boost_round=1000,
save_path='origin_data_save'):
LABEL_SIZE = train[LABEL].value_counts().count()
print("Starting LightGBM. Train shape: {}, test shape: {}".format(
train.shape, test.shape))
gc.collect()
# Cross validation model
if stratified:
folds = StratifiedKFold(n_splits=num_folds,
shuffle=True,
random_state=1001)
else:
folds = KFold(n_splits=num_folds, shuffle=True, random_state=1001)
# Create arrays and dataframes to store results
sub_preds = np.zeros(shape=(test.shape[0], LABEL_SIZE))
feature_importance_df = pd.DataFrame()
feats = [f for f in train.columns if f not in [LABEL, ID]]
for i_fold, (train_idx, valid_idx) in enumerate(
folds.split(train[feats], train[LABEL])):
dtrain = lgb.Dataset(data=train[feats].iloc[train_idx],
label=train[LABEL].iloc[train_idx],
free_raw_data=False,
silent=True)
dvalid = lgb.Dataset(data=train[feats].iloc[valid_idx],
label=train[LABEL].iloc[valid_idx],
free_raw_data=False,
silent=True)
params = {
'bagging_fraction': 0.94795171020152,
'bagging_freq': 6,
'bin_construct_sample_cnt': 200000,
'boosting_type': 'gbdt',
'feature_fraction': 0.9953235660931046,
'is_unbalance': False,
'learning_rate': 0.005,
'min_data_in_leaf': 30,
'num_class': 11,
'num_leaves': 80,
'num_threads': 40,
'objective': 'multiclass',
'reg_alpha': 0.001,
'reg_lambda': 0.1,
'verbose': -1
}
with timer('fold {} train model'.format(i_fold)):
clf = lgb.train(num_boost_round=num_boost_round,
params=params,
train_set=dtrain,
valid_sets=[dvalid],
early_stopping_rounds=50)
clf.save_model(
(save_path + '/model{}_{}.txt').format(i_fold,
int(time.time())))
with timer('fold {} predict'.format(i_fold)):
v_data = clf.predict(dvalid.data)
y_pre = one_hot2label_index(v_data)
sub_preds += clf.predict(test[feats])
write2file(test[ID], sub_preds, i_fold)
fold_importance_df = pd.DataFrame()
fold_importance_df["feature"] = feats
fold_importance_df["importance"] = clf.feature_importance(
importance_type='gain')
fold_importance_df["fold"] = i_fold + 1
feature_importance_df = pd.concat(
[feature_importance_df, fold_importance_df], axis=0)
f1 = f1_score(dvalid.label, y_pre, average='macro')
log.warn('Fold {} f1 : {} score {}'.format(i_fold + 1, f1, f1**2))
del clf, dtrain, dvalid
gc.collect()
display_importances(feature_importance_df)