0

我收到错误“NameError: name 'y_train' is not defined”。我在这里复制了 CatBoost 示例中的代码：https ://towardsdatascience.com/catboost-vs-light-gbm-vs-xgboost-5f93620723db

我搜索了类似的问题，发现表明该变量只能在函数中使用，但由于我没有创建函数，因此列出的解决方案不适用...

cat_features_index = [c for c in train.columns if c not in ['ID_code', 'target']]

def auc(m, train, test): 
    return (metrics.roc_auc_score(y_train,m.predict_proba(train)[:,1]),
                            metrics.roc_auc_score(y_test,m.predict_proba(test)[:,1]))

params = {'depth': [4, 7, 10],
          'learning_rate' : [0.03, 0.1, 0.15],
         'l2_leaf_reg': [1,4,9],
         'iterations': [300]}
cb = cb.CatBoostClassifier()
cb_model = GridSearchCV(cb, params, scoring="roc_auc", cv = 3)
cb_model.fit(train, y_train)

# With Categorical features
clf = cb.CatBoostClassifier(eval_metric="AUC", depth=10, iterations= 500, l2_leaf_reg= 9, learning_rate= 0.15)

错误信息如下：

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-13-f261cd049b40> in <module>()
     11 cb = cb.CatBoostClassifier()
     12 cb_model = GridSearchCV(cb, params, scoring="roc_auc", cv = 3)
---> 13 cb_model.fit(train, y_train)
     14 
     15 # With Categorical features

NameError: name 'y_train' is not defined
4

1 回答 1

0

你需要这个：

import pandas as pd, numpy as np, time
from sklearn.model_selection import train_test_split
import catboost as cb


data = pd.read_csv("flights.csv")
data = data.sample(frac = 0.1, random_state=10)

data = data[["MONTH","DAY","DAY_OF_WEEK","AIRLINE","FLIGHT_NUMBER","DESTINATION_AIRPORT",
                 "ORIGIN_AIRPORT","AIR_TIME", "DEPARTURE_TIME","DISTANCE","ARRIVAL_DELAY"]]
data.dropna(inplace=True)

data["ARRIVAL_DELAY"] = (data["ARRIVAL_DELAY"]>10)*1

cols = ["AIRLINE","FLIGHT_NUMBER","DESTINATION_AIRPORT","ORIGIN_AIRPORT"]
for item in cols:
    data[item] = data[item].astype("category").cat.codes +1

train, test, y_train, y_test = train_test_split(data.drop(["ARRIVAL_DELAY"], axis=1), data["ARRIVAL_DELAY"],
                                                random_state=10, test_size=0.25)

# Now you have defined train, test, y_train, y_test

cat_features_index = [0,1,2,3,4,5,6]

def auc(m, train, test): 
    return (metrics.roc_auc_score(y_train,m.predict_proba(train)[:,1]),
                            metrics.roc_auc_score(y_test,m.predict_proba(test)[:,1]))

params = {'depth': [4, 7, 10],
          'learning_rate' : [0.03, 0.1, 0.15],
         'l2_leaf_reg': [1,4,9],
         'iterations': [300]}
cb = cb.CatBoostClassifier()
cb_model = GridSearchCV(cb, params, scoring="roc_auc", cv = 3)
cb_model.fit(train, y_train)

With Categorical features
clf = cb.CatBoostClassifier(eval_metric="AUC", depth=10, iterations= 500, l2_leaf_reg= 9, learning_rate= 0.15)
clf.fit(train,y_train)
auc(clf, train, test)

With Categorical features
clf = cb.CatBoostClassifier(eval_metric="AUC",one_hot_max_size=31, \
                            depth=10, iterations= 500, l2_leaf_reg= 9, learning_rate= 0.15)
clf.fit(train,y_train, cat_features= cat_features_index)
auc(clf, train, test)
于 2019-11-16T00:22:28.470 回答