lightgbm.basic.LightGBMError: Unknown boosting typeというエラーが出てしまう

Question

自作データセットを用いて機械学習モデルを使いとりあえず動かしてみようと思いLightGBM手法を使い実行してみたところ下記のエラーが出てきました。

Traceback (most recent call last):
  File "face3.py", line 87, in <module>
    reg.fit(X_train, y_train)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\sklearn\multioutput.py", line 182, in fit
    for i in range(y.shape[1]))
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\joblib\parallel.py", line 1041, in __call__
    if self.dispatch_one_batch(iterator):
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\joblib\parallel.py", line 859, in dispatch_one_batch
    self._dispatch(tasks)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\joblib\parallel.py", line 777, in _dispatch
    job = self._backend.apply_async(batch, callback=cb)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\joblib\_parallel_backends.py", line 208, in apply_async
    result = ImmediateResult(func)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\joblib\_parallel_backends.py", line 572, in __init__
    self.results = batch()
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\joblib\parallel.py", line 263, in __call__
    for func, args, kwargs in self.items]
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\joblib\parallel.py", line 263, in <listcomp>
    for func, args, kwargs in self.items]
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\sklearn\utils\fixes.py", line 222, in __call__
    return self.function(*args, **kwargs)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\sklearn\multioutput.py", line 41, in _fit_estimator
    estimator.fit(X, y, **fit_params)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\lightgbm\sklearn.py", line 822, in fit
    categorical_feature=categorical_feature, callbacks=callbacks, init_model=init_model)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\lightgbm\sklearn.py", line 688, in fit
    callbacks=callbacks, init_model=init_model)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\lightgbm\engine.py", line 228, in train
    booster = Booster(params=params, train_set=train_set)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\lightgbm\basic.py", line 2229, in __init__
    train_set.construct()
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\lightgbm\basic.py", line 1472, in construct
    categorical_feature=self.categorical_feature, params=self.params)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\lightgbm\basic.py", line 1270, in _lazy_init
    self.__init_from_np2d(data, params_str, ref_dataset)
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\lightgbm\basic.py", line 1320, in __init_from_np2d
    ctypes.byref(self.handle)))
  File "C:\Users\shota\anaconda3\envs\env2\lib\site-packages\lightgbm\basic.py", line 110, in _safe_call
    raise LightGBMError(_LIB.LGBM_GetLastError().decode('utf-8'))
lightgbm.basic.LightGBMError: Unknown boosting type {'gender':

途中までの出力

[LightGBM] [Warning] Unknown parameter: 2.864}},{'gender':
[LightGBM] [Warning] Unknown parameter: 99.415,
[LightGBM] [Warning] Unknown parameter: 0.354}},{'gender':
[LightGBM] [Warning] Unknown parameter: 90.221,
[LightGBM] [Warning] Unknown parameter: 97.022,

実行したコード

import pandas as pd
import json
import codecs
import numpy as np
from sklearn import svm, metrics, model_selection
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=1)

df = pd.read_csv('emotion.csv')

with open("Emotion.json") as f:
    data = json.load(f)

res1 = []
for d in data:
    res1.append(d['gender'])
res2 = []
for e in data:
    res2.append(d['age'])

res3 = []
for f in data:
    res3.append(d['emotion'])

#print(res1)
#print(res2)
#print(res3)
#df = data[0]
#DF = df["emotion"].keys()
#print(DF)
#print(df)
#print(type(df))



print("データセットのキー（特徴量名）の確認==>:\n", df.keys())
print('dataframeの行数・列数の確認==>\n', df.shape)


# dataframe各列の欠損値でないデータ数、データ型を確認
df.info()

# 数値ではない型の要素の抽出
#objectlist = df[['特徴量名を入れる']][df['特徴量名を入れる'].apply(lambda s:pd.to_numeric(s, errors='coerce')).isnull()]
#objectlist

import sklearn
facemotion = sklearn.utils.Bunch()

# 'Score'(幸福スコア)を目的変数'target'とする
facemotion['target'] = df[['anger', 'disgust', 'fear', 'happiness', 'neutral',
       'sadness', 'surprise']]

# 説明変数を'data'に入れる
facemotion['data'] = df.loc[:, ['anger', 'disgust', 'fear', 'happiness', 'neutral',
       'sadness', 'surprise']]



# 特徴量の名前も入れておくと、グラフの凡例等に使えます（無くても可）
#facemotion['feature_names'] = ['anger', 'disgust', 'fear', 'happiness', 'neutral', 'sadness', 'surprise']

# 訓練セットとテストセットに分割
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(
    facemotion['data'], facemotion['target'], random_state=0)


#X_train, X_test, y_train, y_test = \
#model_selection.train_test_split(facemotion['data'], facemotion['target'], random_state=0)


print("X_train shape:", X_train.shape)
print("X_test shape:", X_test.shape)





from sklearn.multioutput import MultiOutputRegressor
import lightgbm as lgb


reg = MultiOutputRegressor(lgb.LGBMRegressor(data, n_estimators=500))

reg.fit(X_train, y_train)




"""

# データを学習し、予測
clf = svm.SVC()
clf.fit(X_train, y_train)
pre = clf.predict(X_test)

# 正解率を求める
ac_score = metrics.accuracy_score(y_test, pre)
print("正解率 =", ac_score)



# 未知のデータを予測
newdata = np.array([[5.8,2.6,4.0,1.2]])
print("newdata.shape: {}".format(newdata.shape))

knn.fit(X_train, y_train)

prediction = knn.predict(newdata)
print("Predicted target name: {}".format(prediction))

"""

エラー内容を検索してみても回答が得られず、ここに投稿させていただきました。
何か解決方法があれば教えていただきたいです。

Answer 1

LGBMRegressor(data, n_estimators=500)というコードにおいて、LGBMRegressorの使い方が間違っています。すくなくとも、LGBMRegressor(n_estimators=500)にすることで、エラーは無くなると思いますので、試してみてください。

LGBMRegressorの引数は、パラメータリストを入れるところであり、データを入れるところではありません。特に、最初のパラメータはboosting_type='gbdt'とデフォルト設定されていますが、質問者様がdataを代入したため、JSONの中身がパラメータboosting_typeだと判断されて、Unknown boosting typeというエラーがでたものと思います。