如何使 Python LightGBM 代码接受列表

Question

I am using the folllowing code:

import numpy as np

from sklearn.model_selection import train_test_split

import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.metrics import mean_squared_error,roc_auc_score,precision_score
pd.options.display.max_columns = 999
import lightgbm as lgb

def load_csv(filepath):
    data =  []
    col = []
    checkcol = False
    with open(filepath) as f:
        for val in f.readlines():
            val = val.replace("\n","")
            val = val.split(',')
            if checkcol is False:
                col = val
                checkcol = True
            else:
                data.append(val)
    df = pd.DataFrame(data=data, columns=col)
    return df

heart=load_csv(r'C:\Users\PC\Documents\Essay\heart.csv')

df=heart[['chol','cp']]
Y=heart['sex']

sc=StandardScaler()
sc.fit(df)
X=pd.DataFrame(sc.fit_transform(df))

X_train,X_test,y_train,y_test=train_test_split(X,Y,test_size=0.3,random_state=0)


d_train=lgb.Dataset(X_train, label=y_train)

params={}
params['learning_rate']=0.03
params['boosting_type']='gbdt' #GradientBoostingDecisionTree
params['objective']='binary' #Binary target feature
params['metric']='binary_logloss' #metric for binary classification
params['max_depth']=10


clf=lgb.train(params,d_train,100)

Only to get the error message:

ValueError: Series.dtypes must be int, float or bool

I know that this is becuase of my choice of Y, but i have also tried with arrays and nested lists here which still fails.

Answer 1

Using labelencoder would allow to convert your column to the expected format:

from sklearn import preprocessing

encoder = preprocessing.LabelEncoder()
encoder.fit(df['sex'])
encoder.transform(df['sex']) 

This will yield a list of zeros and ones which you can feed into your learning algorithm:

array([1, 0, 0, 0, 1])