Все функции должны быть в диапазоне [0, 9] или [-10, 0] ⇐ Python

[Anonymous]

У меня есть следующий код:
df = load_data()
pd.set_option('display.max_columns', None)
df.dtypes

intBillID object
chBillChargeCode object
chBillNo object
chOriginalBillNo object
sdBillDate datetime64[ns]
sdDueDate datetime64[ns]
sdDatePaidCancelled datetime64[ns]
sdBillCancelledDate object
totalDaysToPay int64
paidInDays int64
paidOnTime int64
chBillStatus object
chBillType object
chDebtorCode object
chBillGroupCode int64
dcTotFeeBilledAmt float64
dcFinalBillExpAmt float64
dcTotProgBillAmt float64
dcTotProgBillExpAmt float64
dcReceiveBillAmt float64
dcTotWipHours float64
dcTotWipTargetAmt float64
vcReason object
OperatingUnit object
BusinessUnit object
LosCode object
dcTotNetBillAmt float64
dtype: object

Тогда у меня есть это:
# Separate features and labels
X, y = df[['totalDaysToPay', 'paidOnTime','dcTotFeeBilledAmt','dcFinalBillExpAmt','dcTotProgBillAmt', 'dcTotProgBillExpAmt','dcTotProgBillExpAmt','dcReceiveBillAmt','dcTotWipHours','dcTotWipTargetAmt']].values, df['paidInDays'].values
print('Features:',X[:10], '\nLabels:', y[:10], sep='\n')

затем я разделяю X, Y
из sklearn.model_selection import train_test_split
# Split data 70%-30% into training set and test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=0)

print ('Training Set: %d rows\nTest Set: %d rows' % (X_train.shape[0], X_test.shape[0]))

Затем я хочу преобразовать числовые и категориальные функции:
# Train the model
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.linear_model import LinearRegression
import numpy as np
from sklearn.ensemble import GradientBoostingRegressor

# Define preprocessing for numeric columns (scale them)
numeric_features = [8,9,10,11,12,13,15,16,17,18,19,20,21,26]
numeric_transformer = Pipeline(steps=[
('scaler', StandardScaler())])

# Define preprocessing for categorical features (encode them)
categorical_features = [1,23,24,25]
categorical_transformer = Pipeline(steps=[
('onehot', OneHotEncoder(handle_unknown='ignore'))])

# Combine preprocessing steps
preprocessor = ColumnTransformer(
transformers=[
('num', numeric_transformer, numeric_features),
('cat', categorical_transformer, categorical_features)])

# Create preprocessing and training pipeline
pipeline = Pipeline(steps=[('preprocessor', preprocessor),
('regressor', GradientBoostingRegressor())])

# fit the pipeline to train a linear regression model on the training set
model = pipeline.fit(X_train, (y_train))
print (model)

Однако я получаю эту ошибку:
ValueError: all features must be in [0, 9] or [-10, 0]


Подробнее здесь: https://stackoverflow.com/questions/657 ... -9-or-10-0