Sex

import pandas as pd

import warnings

warnings.filterwarnings('ignore')

train = pd.read_csv('data/train.csv')
test = pd.read_csv('data/test.csv')
gender_submission = pd.read_csv('data/gender_submission.csv')

train.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
PassengerId    891 non-null int64
Survived       891 non-null int64
Pclass         891 non-null int64
Name           891 non-null object
Sex            891 non-null object
Age            714 non-null float64
SibSp          891 non-null int64
Parch          891 non-null int64
Ticket         891 non-null object
Fare           891 non-null float64
Cabin          204 non-null object
Embarked       889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB

train['Sex_clean'] = train['Sex'].astype('category').cat.codes
test['Sex_clean'] = test['Sex'].astype('category').cat.codes

Embarked

train['Embarked'].isnull().sum()

2

test['Embarked'].isnull().sum()

0

train['Embarked'].value_counts()

S    644
C    168
Q     77
Name: Embarked, dtype: int64

train['Embarked'].fillna('S', inplace=True)

train['Embarked'].isnull().sum()

0

train['Embarked_clean'] = train['Embarked'].astype('category').cat.codes
test['Embarked_clean'] = test['Embarked'].astype('category').cat.codes

Family

train['Family'] = 1 + train['SibSp'] + train['Parch']
test['Family'] = 1 + test['SibSp'] + test['Parch']

train['Solo'] = (train['Family'] == 1)

test['Solo'] = (test['Family'] == 1)

## Fare

train['FareBin_4'] = pd.qcut(train['Fare'], 4)
test['FareBin_4'] = pd.qcut(test['Fare'], 4)

train.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked	Sex_clean	Embarked_clean	Family	Solo	FareBin_4
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S	1	2	2	False	(-0.001, 7.91]
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C	0	0	2	False	(31.0, 512.329]
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S	0	2	1	True	(7.91, 14.454]
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S	0	2	2	False	(31.0, 512.329]
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S	1	2	1	True	(7.91, 14.454]

pd.crosstab(train['FareBin_4'], train['Pclass'])

Pclass	1	2	3
FareBin_4
(-0.001, 7.91]	6	6	211
(7.91, 14.454]	0	86	138
(14.454, 31.0]	51	70	101
(31.0, 512.329]	159	22	41

Title

train['Title'] = train['Name'].str.extract(' ([A-Za-z]+)\.', expand=False)

test['Title'] = test['Name'].str.extract(' ([A-Za-z]+)\.', expand=False)

train['Title'] = train['Title'].replace(['Lady', 'Countess','Capt', 'Col','Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Other')

train['Title'].value_counts()

Mr        517
Miss      182
Mrs       125
Master     40
Other      23
Mlle        2
Mme         1
Ms          1
Name: Title, dtype: int64

train['Title'] = train['Title'].replace('Mlle', 'Miss')
train['Title'] = train['Title'].replace('Ms', 'Miss')
train['Title'] = train['Title'].replace('Mme', 'Mrs')

train['Title'].value_counts()

Mr        517
Miss      185
Mrs       126
Master     40
Other      23
Name: Title, dtype: int64

test['Title'] = test['Title'].replace(['Lady', 'Countess','Capt', 'Col','Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Other')

test['Title'] = test['Title'].replace('Mlle', 'Miss')
test['Title'] = test['Title'].replace('Ms', 'Miss')
test['Title'] = test['Title'].replace('Mme', 'Mrs')

test['Title'].value_counts()

Mr        240
Miss       79
Mrs        72
Master     21
Other       6
Name: Title, dtype: int64

train['Title_clean'] = train['Title'].astype('category').cat.codes
test['Title_clean'] = test['Title'].astype('category').cat.codes

Age

train["Age"].fillna(train.groupby("Title")["Age"].transform("median"), inplace=True)
test["Age"].fillna(test.groupby("Title")["Age"].transform("median"), inplace=True)

train.loc[ train['Age'] <= 16, 'Age_clean'] = 0
train.loc[(train['Age'] > 16) & (train['Age'] <= 26), 'Age_clean'] = 1
train.loc[(train['Age'] > 26) & (train['Age'] <= 36), 'Age_clean'] = 2
train.loc[(train['Age'] > 36) & (train['Age'] <= 62), 'Age_clean'] = 3
train.loc[ train['Age'] > 62, 'Age_clean'] = 4

test.loc[ test['Age'] <= 16, 'Age_clean'] = 0
test.loc[(test['Age'] > 16) & (test['Age'] <= 26), 'Age_clean'] = 1
test.loc[(test['Age'] > 26) & (test['Age'] <= 36), 'Age_clean'] = 2
test.loc[(test['Age'] > 36) & (test['Age'] <= 62), 'Age_clean'] = 3
test.loc[ test['Age'] > 62, 'Age_clean'] = 4

train.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked	Sex_clean	Embarked_clean	Family	Solo	FareBin_4	Title	Title_clean	Age_clean
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S	1	2	2	False	(-0.001, 7.91]	Mr	2	1.0
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C	0	0	2	False	(31.0, 512.329]	Mrs	3	3.0
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S	0	2	1	True	(7.91, 14.454]	Miss	1	1.0
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S	0	2	2	False	(31.0, 512.329]	Mrs	3	2.0
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S	1	2	1	True	(7.91, 14.454]	Mr	2	2.0

Fare

train["Fare"].fillna(train.groupby("Pclass")["Fare"].transform("median"), inplace=True)
test["Fare"].fillna(test.groupby("Pclass")["Fare"].transform("median"), inplace=True)

pd.qcut(train['Fare'], 4)

0       (-0.001, 7.91]
1      (31.0, 512.329]
2       (7.91, 14.454]
3      (31.0, 512.329]
4       (7.91, 14.454]
            ...       
886     (7.91, 14.454]
887     (14.454, 31.0]
888     (14.454, 31.0]
889     (14.454, 31.0]
890     (-0.001, 7.91]
Name: Fare, Length: 891, dtype: category
Categories (4, interval[float64]): [(-0.001, 7.91] < (7.91, 14.454] < (14.454, 31.0] < (31.0, 512.329]]

train.loc[ train['Fare'] <= 17, 'Fare_clean'] = 0
train.loc[(train['Fare'] > 17) & (train['Fare'] <= 30), 'Fare_clean'] = 1
train.loc[(train['Fare'] > 30) & (train['Fare'] <= 100), 'Fare_clean']   = 2
train.loc[ train['Fare'] > 100, 'Fare_clean'] = 3
train['Fare_clean'] = train['Fare_clean'].astype(int)

test.loc[ test['Fare'] <= 17, 'Fare_clean'] = 0
test.loc[(test['Fare'] > 17) & (test['Fare'] <= 30), 'Fare_clean'] = 1
test.loc[(test['Fare'] > 30) & (test['Fare'] <= 100), 'Fare_clean']   = 2
test.loc[ test['Fare'] > 100, 'Fare_clean'] = 3
test['Fare_clean'] = test['Fare_clean'].astype(int)

train.head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	...	Embarked	Sex_clean	Embarked_clean	Family	Solo	FareBin_4	Title	Title_clean	Age_clean	Fare_clean
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	...	S	1	2	2	False	(-0.001, 7.91]	Mr	2	1.0	0
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	...	C	0	0	2	False	(31.0, 512.329]	Mrs	3	3.0	2
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	...	S	0	2	1	True	(7.91, 14.454]	Miss	1	1.0	0
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	...	S	0	2	2	False	(31.0, 512.329]	Mrs	3	2.0	2
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	...	S	1	2	1	True	(7.91, 14.454]	Mr	2	2.0	0

5 rows × 21 columns

Cabin

train['Cabin'].str[:1].value_counts()

C    59
B    47
D    33
E    32
A    15
F    13
G     4
T     1
Name: Cabin, dtype: int64

mapping = {
    'A': 0,
    'B': 0.4,
    'C': 0.8,
    'D': 1.2,
    'E': 1.6,
    'F': 2.0,
    'G': 2.4,
    'T': 2.8
}

train['Cabin_clean'] = train['Cabin'].str[:1]

train['Cabin_clean'] = train['Cabin_clean'].map(mapping)

train[['Pclass', 'Cabin_clean']].head(10)

	Pclass	Cabin_clean
0	3	NaN
1	1	0.8
2	3	NaN
3	1	0.8
4	3	NaN
5	3	NaN
6	1	1.6
7	3	NaN
8	3	NaN
9	2	NaN

train.groupby('Pclass')['Cabin_clean'].median()

Pclass
1    0.8
2    1.8
3    2.0
Name: Cabin_clean, dtype: float64

train['Cabin_clean'].head(10)

0    NaN
1    0.8
2    NaN
3    0.8
4    NaN
5    NaN
6    1.6
7    NaN
8    NaN
9    NaN
Name: Cabin_clean, dtype: float64

train['Cabin_clean'] = train.groupby('Pclass')['Cabin_clean'].transform('median')

train['Cabin_clean'].head(10)

0    2.0
1    0.8
2    2.0
3    0.8
4    2.0
5    2.0
6    0.8
7    2.0
8    2.0
9    1.8
Name: Cabin_clean, dtype: float64

위와 같은 방법으로 할 경우 이미 자리 잡은 값들이 덮어 씌워짐
따라서 아래와 같은 방법으로 없는 값들만 채워줘야함 (fillna)

train['Cabin_clean'].fillna(train.groupby('Pclass')['Cabin_clean'].transform('median'), inplace=True)

train['Cabin_clean'].head(10)

0    2.0
1    0.8
2    2.0
3    0.8
4    2.0
5    2.0
6    0.8
7    2.0
8    2.0
9    1.8
Name: Cabin_clean, dtype: float64

test['Cabin_clean'] = test['Cabin'].str[:1]
test['Cabin_clean'] = test['Cabin_clean'].map(mapping)
test['Cabin_clean'].fillna(test.groupby('Pclass')['Cabin_clean'].transform('median'), inplace=True)

Feature & label

feature = [
    'Pclass',
    'SibSp',
    'Parch',
    'Sex_clean',
    'Embarked_clean',
    'Family',
    'Solo',
    'Title_clean',
    'Age_clean',
    'Fare_clean',
    'Cabin_clean'
]

label = [
    'Survived',
]

Model Selection

data = train[feature]
target = train[label]

from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score

k_fold = KFold(n_splits=10, shuffle=True, random_state=0) 

x_train, x_test, y_train, y_test = train_test_split(data, target, random_state=0)

from sklearn.ensemble import RandomForestClassifier
from lightgbm import LGBMClassifier
from xgboost import XGBClassifier

clf = RandomForestClassifier(n_estimators=170, max_depth=5, random_state=0)
cross_val_score(clf, data, target, cv=k_fold, scoring='accuracy', ).mean()

0.8305368289637952

clf = LGBMClassifier(n_estimators=150,
                    subsample=0.8,
                    colsample_bytree=0.8)
cross_val_score(clf, data, target, cv=k_fold, scoring='accuracy', ).mean()

0.8103245942571785

clf = LGBMClassifier(n_estimators=120,
                     max_depth=6,
                    subsample=0.8,
                    colsample_bytree=0.8, random_state=0)
cross_val_score(clf, data, target, cv=k_fold, scoring='accuracy', ).mean()

0.8226716604244695

clf = XGBClassifier(n_estimators=90,
                     max_depth=5,
                    subsample=0.8,
                    colsample_bytree=0.8, random_state=0)
cross_val_score(clf, data, target, cv=k_fold, scoring='accuracy', ).mean()

0.8226716604244695

Make Prediction

x_train = train[feature]
x_test = test[feature]
y_train = train[label]

clf.fit(x_train, y_train)

RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
                       max_depth=5, max_features='auto', max_leaf_nodes=None,
                       min_impurity_decrease=0.0, min_impurity_split=None,
                       min_samples_leaf=1, min_samples_split=2,
                       min_weight_fraction_leaf=0.0, n_estimators=170,
                       n_jobs=None, oob_score=False, random_state=0, verbose=0,
                       warm_start=False)

pred = clf.predict(x_test)

gender_submission['Survived'] = pred

gender_submission.to_csv('191111_random_forest.csv',index=False)

clf

RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
                       max_depth=5, max_features='auto', max_leaf_nodes=None,
                       min_impurity_decrease=0.0, min_impurity_split=None,
                       min_samples_leaf=1, min_samples_split=2,
                       min_weight_fraction_leaf=0.0, n_estimators=170,
                       n_jobs=None, oob_score=False, random_state=0, verbose=0,
                       warm_start=False)