
import pandas as pd


train = pd.read_csv("data/titanic/train.csv")
test = pd.read_csv("data/titanic/test.csv")
sub = pd.read_csv("data/titanic/gender_submission.csv")


print(train.shape)
print(test.shape)
print(sub.shape)

(891, 12)
(418, 11)
(418, 2)


print(train.columns)
print(test.columns)

Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',
       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],
      dtype='object')
Index(['PassengerId', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch',
       'Ticket', 'Fare', 'Cabin', 'Embarked'],
      dtype='object')


train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   PassengerId  891 non-null    int64  
 1   Survived     891 non-null    int64  
 2   Pclass       891 non-null    int64  
 3   Name         891 non-null    object 
 4   Sex          891 non-null    object 
 5   Age          714 non-null    float64
 6   SibSp        891 non-null    int64  
 7   Parch        891 non-null    int64  
 8   Ticket       891 non-null    object 
 9   Fare         891 non-null    float64
 10  Cabin        204 non-null    object 
 11  Embarked     889 non-null    object 
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB


test.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 418 entries, 0 to 417
Data columns (total 11 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   PassengerId  418 non-null    int64  
 1   Pclass       418 non-null    int64  
 2   Name         418 non-null    object 
 3   Sex          418 non-null    object 
 4   Age          332 non-null    float64
 5   SibSp        418 non-null    int64  
 6   Parch        418 non-null    int64  
 7   Ticket       418 non-null    object 
 8   Fare         417 non-null    float64
 9   Cabin        91 non-null     object 
 10  Embarked     418 non-null    object 
dtypes: float64(2), int64(4), object(5)
memory usage: 36.0+ KB


train.isnull().sum()

PassengerId      0
Survived         0
Pclass           0
Name             0
Sex              0
Age            177
SibSp            0
Parch            0
Ticket           0
Fare             0
Cabin          687
Embarked         2
dtype: int64


test.isnull().sum()

PassengerId      0
Pclass           0
Name             0
Sex              0
Age             86
SibSp            0
Parch            0
Ticket           0
Fare             1
Cabin          327
Embarked         0
dtype: int64


train.describe()


test.describe()


train.describe(include=['O'])


test.describe(include=['O'])


from sklearn.neighbors import KNeighborsClassifier


# 데이터 준비 - 빠른 모델 생성을 위해 데이터 전처리가 불필요한 피처(변수)만 선택
# 'Survived'를 제외 (예측해야할 피처) , 
# 'Embarked', 'Sex'',Name', 'Ticket' => 문자포함
#  'Age' : 결측치가 있음
sel = ['PassengerId', 'Pclass', 'SibSp', 'Parch' ]

# 학습에 사용될 데이터 준비 X_train, y_train
X_train = train[sel]
y_train = train['Survived']

# 학습 후, 테스트에 사용될 피처 선택
X_test = test[sel]

X_train.shape, y_train.shape, X_test.shape

((891, 4), (891,), (418, 4))


# 모델 선택
model = KNeighborsClassifier()

# 학습
model.fit(X_train, y_train)

# 예측
pred = model.predict(X_test)
pred[:15]   # 예측한 값을 15개 정도 확인

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


# 제출
sub.columns

Index(['PassengerId', 'Survived'], dtype='object')


sub['Survived'] = pred
sub.to_csv("first_sub.csv", index=False)

구분	설명	값
Survival	생존 여부	Survival. 0 = No, 1 = Yes
Pclass	티켓의 클래스	Ticket class. 1 = 1st, 2 = 2nd, 3 = 3rd
Sex	성별(Sex)	남(male)/여(female)
Age	나이(Age in years.)
SibSp	함께 탑승한 형제와 배우자의 수 /siblings, spouses aboard the Titanic.
Parch	함께 탑승한 부모, 아이의 수	# of parents / children aboard the Titanic.
Ticket	티켓 번호(Ticket number)	(ex) CA 31352, A/5. 2151
Fare	탑승료(Passenger fare)
Cabin	객실 번호(Cabin number)
Embarked	탑승 항구(Port of Embarkation)	C = Cherbourg, Q = Queenstown, S = Southampton

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare
count	891.000000	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208
std	257.353842	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429
min	1.000000	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400
50%	446.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	668.500000	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000
max	891.000000	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200

	PassengerId	Pclass	Age	SibSp	Parch	Fare
count	418.000000	418.000000	332.000000	418.000000	418.000000	417.000000
mean	1100.500000	2.265550	30.272590	0.447368	0.392344	35.627188
std	120.810458	0.841838	14.181209	0.896760	0.981429	55.907576
min	892.000000	1.000000	0.170000	0.000000	0.000000	0.000000
25%	996.250000	1.000000	21.000000	0.000000	0.000000	7.895800
50%	1100.500000	3.000000	27.000000	0.000000	0.000000	14.454200
75%	1204.750000	3.000000	39.000000	1.000000	0.000000	31.500000
max	1309.000000	3.000000	76.000000	8.000000	9.000000	512.329200

	Name	Sex	Ticket	Cabin	Embarked
count	891	891	891	204	889
unique	891	2	681	147	3
top	Moore, Mr. Leonard Charles	male	1601	G6	S
freq	1	577	7	4	644

	Name	Sex	Ticket	Cabin	Embarked
count	418	418	418	91	418
unique	418	2	363	76	3
top	Ford, Mr. Arthur	male	PC 17608	B57 B59 B63 B66	S
freq	1	266	5	3	270

타이타닉 생존자 예측 대회¶

학습 목표¶

학습 내용¶

준비¶

Data Fields¶

데이터 셋 불러오기¶

1-2 데이터 탐색하기¶

1-3 모델 만들고 제출해 보기¶

제출 절차¶