09_semisupervised - LightGBMError: Do not support special JSON characters in feature name.

Just trying to execute the code as is and I'm getting the following error: trainingScores = [] cvScores = [] predictionsBasedOnKFolds = pd.DataFrame(data=[], index=y_train.index, \ columns=['prediction'])

for train_index, cv_index in k_fold.split(np.zeros(len(X_train)), \ y_train.ravel()): X_train_fold, X_cv_fold = X_train.iloc[train_index,:], \ X_train.iloc[cv_index,:] y_train_fold, y_cv_fold = y_train.iloc[train_index], \ y_train.iloc[cv_index]

lgb_train = lgb.Dataset(X_train_fold, y_train_fold)
lgb_eval = lgb.Dataset(X_cv_fold, y_cv_fold, reference=lgb_train)
gbm = lgb.train(params_lightGB, lgb_train, num_boost_round=2000,
               valid_sets=lgb_eval, early_stopping_rounds=200)

loglossTraining = log_loss(y_train_fold, gbm.predict(X_train_fold, \
                            num_iteration=gbm.best_iteration))
trainingScores.append(loglossTraining)

predictionsBasedOnKFolds.loc[X_cv_fold.index,'prediction'] = \
    gbm.predict(X_cv_fold, num_iteration=gbm.best_iteration) 
loglossCV = log_loss(y_cv_fold, \
    predictionsBasedOnKFolds.loc[X_cv_fold.index,'prediction'])
cvScores.append(loglossCV)

print('Training Log Loss: ', loglossTraining)
print('CV Log Loss: ', loglossCV)

loglossLightGBMGradientBoosting = log_loss(y_train, \ predictionsBasedOnKFolds.loc[:,'prediction']) print('LightGBM Gradient Boosting Log Loss: ', \ loglossLightGBMGradientBoosting)

LightGBMError Traceback (most recent call last)

in 14 lgb_eval = lgb.Dataset(X_cv_fold, y_cv_fold, reference=lgb_train) 15 gbm = lgb.train(params_lightGB, lgb_train, num_boost_round=2000, ---> 16 valid_sets=lgb_eval, early_stopping_rounds=200) 17 18 loglossTraining = log_loss(y_train_fold, gbm.predict(X_train_fold, \ ~/.local/lib/python3.6/site-packages/lightgbm/engine.py in train(params, train_set, num_boost_round, valid_sets, valid_names, fobj, feval, init_model, feature_name, categorical_feature, early_stopping_rounds, evals_result, verbose_eval, learning_rates, keep_training_booster, callbacks) 226 # construct booster 227 try: --> 228 booster = Booster(params=params, train_set=train_set) 229 if is_valid_contain_train: 230 booster.set_train_data_name(train_data_name) ~/.local/lib/python3.6/site-packages/lightgbm/basic.py in __init__(self, params, train_set, model_file, model_str, silent) 1712 self.handle = ctypes.c_void_p() 1713 _safe_call(_LIB.LGBM_BoosterCreate( -> 1714 train_set.construct().handle, 1715 c_str(params_str), 1716 ctypes.byref(self.handle))) ~/.local/lib/python3.6/site-packages/lightgbm/basic.py in construct(self) 1083 init_score=self.init_score, predictor=self._predictor, 1084 silent=self.silent, feature_name=self.feature_name, -> 1085 categorical_feature=self.categorical_feature, params=self.params) 1086 if self.free_raw_data: 1087 self.data = None ~/.local/lib/python3.6/site-packages/lightgbm/basic.py in _lazy_init(self, data, label, reference, weight, group, init_score, predictor, silent, feature_name, categorical_feature, params) 913 raise TypeError('Wrong predictor type {}'.format(type(predictor).__name__)) 914 # set feature names --> 915 return self.set_feature_name(feature_name) 916 917 def __init_from_np2d(self, mat, params_str, ref_dataset): ~/.local/lib/python3.6/site-packages/lightgbm/basic.py in set_feature_name(self, feature_name) 1366 self.handle, 1367 c_array(ctypes.c_char_p, c_feature_name), -> 1368 ctypes.c_int(len(feature_name)))) 1369 return self 1370 ~/.local/lib/python3.6/site-packages/lightgbm/basic.py in _safe_call(ret) 43 """ 44 if ret != 0: ---> 45 raise LightGBMError(decode_string(_LIB.LGBM_GetLastError())) 46 47 LightGBMError: Do not support special JSON characters in feature name.

aapatel09 / handson-unsupervised-learning

09_semisupervised - LightGBMError: Do not support special JSON characters in feature name. #8