泰坦尼克号代码分析

读入训练数据

import numpy as np
import pandas as pd 
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer

train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')

train.head()

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

test.head()

	PassengerId	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	892	3	Kelly, Mr. James	male	34.5	0	0	330911	7.8292	NaN	Q
1	893	3	Wilkes, Mrs. James (Ellen Needs)	female	47.0	1	0	363272	7.0000	NaN	S
2	894	2	Myles, Mr. Thomas Francis	male	62.0	0	0	240276	9.6875	NaN	Q
3	895	3	Wirz, Mr. Albert	male	27.0	0	0	315154	8.6625	NaN	S
4	896	3	Hirvonen, Mrs. Alexander (Helga E Lindqvist)	female	22.0	1	1	3101298	12.2875	NaN	S

g_sub = pd.read_csv('gender_submission.csv')
g_sub.info()

特征含义：

PassengerId：乘客编号（无意义）
Survived：是否存活（1-存活，0-未存活），目标特征
Pclass：船舱等级（1、2、3等舱）
SibSp：堂兄弟姐妹个数
Parch：直系亲属个数
Embarked：登船港口

看一看数据的基本信息

RangeIndex: 418 entries, 0 to 417
Data columns (total 2 columns):
# Column Non-Null Count Dtype
— ------ -------------- -----
0 PassengerId 418 non-null int64
1 Survived 418 non-null int64
dtypes: int64(2)
memory usage: 6.7 KB

g_sub.head()

	PassengerId	Survived
0	892	0
1	893	1
2	894	0
3	895	0
4	896	1

union = train.append(test, ignore_index=True)
union.info()

RangeIndex: 1309 entries, 0 to 1308
Data columns (total 12 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   PassengerId  1309 non-null   int64  
 1   Survived     891 non-null    float64
 2   Pclass       1309 non-null   int64  
 3   Name         1309 non-null   object 
 4   Sex          1309 non-null   object 
 5   Age          1046 non-null   float64
 6   SibSp        1309 non-null   int64  
 7   Parch        1309 non-null   int64  
 8   Ticket       1309 non-null   object 
 9   Fare         1308 non-null   float64
 10  Cabin        295 non-null    object 
 11  Embarked     1307 non-null   object 
dtypes: float64(3), int64(4), object(5)
memory usage: 122.8+ KB

我们发现：

乘客总数（记录数）：1309
特征总数：11
缺失：年龄、船舱编号、登船港口

union.describe()

看一看数据的基本统计值

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare
count	1309.000000	891.000000	1309.000000	1046.000000	1309.000000	1309.000000	1308.000000
mean	655.000000	0.383838	2.294882	29.881138	0.498854	0.385027	33.295479
std	378.020061	0.486592	0.837836	14.413493	1.041658	0.865560	51.758668
min	1.000000	0.000000	1.000000	0.170000	0.000000	0.000000	0.000000
25%	328.000000	0.000000	2.000000	21.000000	0.000000	0.000000	7.895800
50%	655.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	982.000000	1.000000	3.000000	39.000000	1.000000	0.000000	31.275000
max	1309.000000	1.000000	3.000000	80.000000	8.000000	9.000000	512.329200

我们可以看出：

平均年龄29.8岁，说明乘客青壮年居多
存活率38.4%
2、3等舱乘客比一等舱要多很多

union['Age'].fillna(union['Age'].median(), inplace=True)
union['Fare'].fillna(union['Fare'].mean(), inplace=True)
union = union.drop(['Name', 'Cabin'], axis=1)

union['Embarked'].value_counts()

对于登船港口的处理，我们采取最频繁的值填充

S    914
C    270
Q    123
Name: Embarked, dtype: int64

我们用最多的“s”来填充缺少的登船港口

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

union.info()

RangeIndex: 1309 entries, 0 to 1308
Data columns (total 10 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   PassengerId  1309 non-null   int64  
 1   Survived     891 non-null    float64
 2   Pclass       1309 non-null   int64  
 3   Sex          1309 non-null   object 
 4   Age          1309 non-null   float64
 5   SibSp        1309 non-null   int64  
 6   Parch        1309 non-null   int64  
 7   Ticket       1309 non-null   object 
 8   Fare         1309 non-null   float64
 9   Embarked     1309 non-null   object 
dtypes: float64(3), int64(4), object(3)
memory usage: 102.4+ KB

union.head()

	PassengerId	Survived	Pclass	Sex	Age	SibSp	Parch	Ticket	Fare	Embarked
0	1	0.0	3	male	22.0	1	0	A/5 21171	7.2500	S
1	2	1.0	1	female	38.0	1	0	PC 17599	71.2833	C
2	3	1.0	3	female	26.0	0	0	STON/O2. 3101282	7.9250	S
3	4	1.0	1	female	35.0	1	0	113803	53.1000	S
4	5	0.0	3	male	35.0	0	0	373450	8.0500	S

经过处理之后，发现已经没有缺失值，简单的数据预处理告一段落

train = union.loc[0:890]
test = union.loc[891:]

把合并的数据集重新拆开

x_train = train.drop(['Survived','Ticket'], axis=1)
x_test = test.drop(['Survived','Ticket'], axis=1)
y_train = train['Survived']
y_test = test['Survived']

将其分为训练集的特征值，测试集的特征值，训练集的目标值和测试集的目标值

dict = DictVectorizer(sparse=False)
X_train = dict.fit_transform(x_train.to_dict(orient='record'))
X_test = dict.transform(x_test.to_dict(orient='record'))
dict.get_feature_names()

调用 fit transform（X）
与tranform（X）

['Age',
 'Embarked=C',
 'Embarked=Q',
 'Embarked=S',
 'Fare',
 'Parch',
 'PassengerId',
 'Pclass',
 'Sex=female',
 'Sex=male',
 'SibSp']

X_train

array([[22.,  0.,  0., ...,  0.,  1.,  1.],
       [38.,  1.,  0., ...,  1.,  0.,  1.],
       [26.,  0.,  0., ...,  1.,  0.,  0.],
       ...,
       [28.,  0.,  0., ...,  1.,  0.,  1.],
       [26.,  1.,  0., ...,  0.,  1.,  0.],
       [32.,  0.,  1., ...,  0.,  1.,  0.]])

from sklearn.tree import DecisionTreeClassifier

导入库sklearn.tree.DecisionTreeClassifier()

dec = DecisionTreeClassifier(max_depth=5)
dec.fit(X_train, y_train)

DecisionTreeClassifier(max_depth=5)

y_predict = dec.predict(X_test).astype(np.int64)

y_predict

array([0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 0,
       1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 0, 1,
       1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,
       1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1,
       1, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0,
       0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1,
       0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1,
       0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1,
       1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1,
       0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1, 0,
       1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1,
       1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1,
       0, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0,
       0, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1,
       1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0,
       1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 0,
       0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0,
       1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1,
       0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0],
      dtype=int64)

id = test['PassengerId']
sub = {
     'PassengerId': id, 'Survived': y_predict}
submission = pd.DataFrame(sub)
submission.to_csv("sub.csv", index=False)

submission

	PassengerId	Survived
891	892	0
892	893	0
893	894	0
894	895	0
895	896	1
...	...	...
1304	1305	0
1305	1306	1
1306	1307	0
1307	1308	0
1308	1309	0

418 rows × 2 columns