T2-1

안녕하세요 캐글 T2-1을 푸는 도중 도저히 에러를 해결할 수 없어 질문드립니다!ㅠㅠ코드는 가장 아래에 있습니다

1. 데이터가 3개 주어지고 결측치가 있는 경우 제가 짠 코드와 같이 결측치를 채우면 될까요?

2. 에러는 아래와 같이 나타납니다. test 데이터에 ‘Ali', 'Mr Ahmed'가 없다는 뜻같은데 무엇이 문제이고 어떻게 해결해야 좋을까요?ㅠㅠ

에러메시지, 코드:

KeyError                                  Traceback (most recent call last)
/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_label.py in _encode_python(values, uniques, encode)
     65         try:
---> 66             encoded = np.array([table[v] for v in values])
     67         except KeyError as e:

/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_label.py in <listcomp>(.0)
     65         try:
---> 66             encoded = np.array([table[v] for v in values])
     67         except KeyError as e:

KeyError: 'Ali, Mr. Ahmed'

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
/tmp/ipykernel_20/403961971.py in <module>
     53      le = LabelEncoder()
     54      X_train[col] = le.fit_transform(X_train[col])
---> 55      X_test[col] = le.transform(X_test[col])

/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_label.py in transform(self, y)
    275             return np.array([])
    276 
--> 277         _, y = _encode(y, uniques=self.classes_, encode=True)
    278         return y
    279 

/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_label.py in _encode(values, uniques, encode, check_unknown)
    111     if values.dtype == object:
    112         try:
--> 113             res = _encode_python(values, uniques, encode)
    114         except TypeError:
    115             types = sorted(t.__qualname__

/opt/conda/lib/python3.7/site-packages/sklearn/preprocessing/_label.py in _encode_python(values, uniques, encode)
     67         except KeyError as e:
     68             raise ValueError("y contains previously unseen labels: %s"
---> 69                              % str(e))
     70         return uniques, encoded
     71     else:

ValueError: y contains previously unseen labels: 'Ali, Mr. Ahmed'

# 시험환경 세팅 (코드 변경 X)
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split

def exam_data_load(df, target, id_name="", null_name=""):
    if id_name == "":
        df = df.reset_index().rename(columns={"index": "id"})
        id_name = 'id'
    else:
        id_name = id_name
    
    if null_name != "":
        df[df == null_name] = np.nan
    
    X_train, X_test = train_test_split(df, test_size=0.2, random_state=2021)
    
    y_train = X_train[[id_name, target]]
    X_train = X_train.drop(columns=[target])

    
    y_test = X_test[[id_name, target]]
    X_test = X_test.drop(columns=[target])
    return X_train, X_test, y_train, y_test 
    
df = pd.read_csv("../input/titanic/train.csv")
X_train, X_test, y_train, y_test = exam_data_load(df, target='Survived', id_name='PassengerId')

X_train.shape, X_test.shape, y_train.shape, y_test.shape



import pandas as pd

df = pd.concat([X_train,y_train['Survived']], axis = 1)
    
df['Age'] = df['Age'].fillna(df['Age'].median())
X_test['Age'] = X_test['Age'].fillna(df['Age'].median())

df['Cabin'] = df['Cabin'].fillna('N')
X_test['Cabin'] = X_test['Cabin'].fillna('N')

df['Embarked'] = df['Embarked'].fillna('S')
X_test['Embarked'] = X_test['Embarked'].fillna('S')

#print(df.isnull().sum())
#print(X_test.isnull().sum())
print(df.info())
print(X_test)
cols = ['Name','Sex', 'Ticket', 'Cabin', 'Embarked']
from sklearn.preprocessing import LabelEncoder
for col in cols:
     le = LabelEncoder()
     X_train[col] = le.fit_transform(X_train[col])
     X_test[col] = le.transform(X_test[col])