Kaggle入门——泰坦尼克号生还者预测

时间:2021-05-09 05:16:53

前言

  这个是Kaggle比赛中泰坦尼克号生存率的分析。强烈建议在做这个比赛的时候,再看一遍电源《泰坦尼克号》,可能会给你一些启发,比如妇女儿童先上船等。所以是否获救其实并非随机,而是基于一些背景有先后顺序的。

1,背景介绍

  1912年4月15日,载着1316号乘客和891名船员的豪华巨轮泰坦尼克号在首次航行期间撞上冰山后沉没,2224名乘客和机组人员中有1502人遇难。沉船导致大量伤亡的原因之一是没有足够的救生艇给乘客和船员。虽然幸存下来有一些运气因素,但有一些人比其他人更有可能生存,比如妇女,儿童和上层阶级。在本文中将对哪些人可能生存作出分析,特别是运用Python和机器学习的相关模型工具来预测哪些乘客幸免于难,最后提交结果。

  其中训练和测试数据是一些乘客的个人信息以及存活状况,要尝试根据它生成合适的模型并预测其他人的存活状况。这是一个二分类的问题。

2,数据文件说明

  从Kaggle泰坦尼克号项目页面下载数据:https://www.kaggle.com/c/titanic

  下面是问题的背景页:

Kaggle入门——泰坦尼克号生还者预测

  下面是可下载Data的页面

Kaggle入门——泰坦尼克号生还者预测

  下面是forum页面,我们会从中学到各种数据处理/建模想法:

Kaggle入门——泰坦尼克号生还者预测

Kaggle入门——泰坦尼克号生还者预测

3,数据变量说明

  每个乘客有12个属性,其中PassengerID在这里只起到索引作用,而Survived是我们要预测的目标,因此我们要处理的数据总共有10个变量。

Kaggle入门——泰坦尼克号生还者预测

  对于上述变量的说明:

  1. PassengerID(ID)
  2. Survived(存活与否)
  3. Pclass(客舱等级,在当时的英国阶级分层比较严重,较为重要)
  4. Name(姓名,可提取出更多信息)
  5. Sex(性别,较为重要)
  6. Age(年龄,较为重要)
  7. Parch(直系亲友,是指父母,孩子,其中1表示有一个,依次类推)
  8. SibSp(旁系,是指兄弟姐妹)
  9. Ticket(票编号,这个是个玄学问题)
  10. Fare(票价,可能票价贵的获救几率大)
  11. Cabin(客舱编号)
  12. Embarked(上船的港口编号,是指从不同的港口上船)

4,评估方法

  将从基础的方法开始学习,然后预测结果,最后将准确率最高的模型预测的结果提交到Kaggle上,查看自己的结果如何。

5,完整代码,请移步小编的GitHub

  传送门:请点击我

  如果点不开,复制这个地址:https://github.com/LeBron-Jian/Kaggle-learn

数据预处理

  数据的质量决定模型能达到的上限、所以对数据的预处理无比重要。机器学习的算法模型是用来挖掘数据中潜在模式的,但是若数据太过复杂,潜在的模式就很难找到,更糟糕的是,我们所收集的数据的特征和我们想预测的标签之间并没有太大关联,这时候这个特征就像噪音一样只会干扰我们的模型做出准确的预测。所以说,我们要对拿到手的数据集进行分析,并看看各个特征到底会不会显著影响到我们要预测的标签值。

1,总体预览

  在Data下的我们的 train.csv 和 test.csv 两个文件分别存着官方给出的训练和测试数据。

train.info()

Kaggle入门——泰坦尼克号生还者预测

  从数据中发现,总数为891个,那还有特征是有空值的,Cabin甚至只有一点数据(不着急,这里我们先看看)。而且有些数据是数值型的,一些是文本型的,还有一些是类目性的。这些我们用下面函数是看不到的。

res = all_data.describe()

Kaggle入门——泰坦尼克号生还者预测

  describe() 函数时查看数据的描述统计信息,只查看数值型数据,字符串型的数据,如姓名(name),客舱号(Cabin)等不可显示。

  而上面信息告诉我们,大概有 0.383838的人最终获救了,平均乘客年龄大概是29.88岁等等。。

2,数据初步分析

  每个乘客都有这么多属性,那我们咋知道哪些属性更有用,而又应该怎么用他们呢?说实话这会我也不知道,但是我们要知道,对数据的认识是非常重要的!所以我们要深入的看我们的数据,后面就会写到如何分析数据。

  为什么要这样分析数据,我们可以先看看这个文章https://zhuanlan.zhihu.com/p/26663761。一个泰坦尼克号的生还者写下的回忆录,我这里粘贴几个重要的:

  注意:面对沉船灾难,妇女和儿童先上救生艇,当然也有例外,不过很少。

Kaggle入门——泰坦尼克号生还者预测

Kaggle入门——泰坦尼克号生还者预测

Kaggle入门——泰坦尼克号生还者预测

Kaggle入门——泰坦尼克号生还者预测

  这次分析分析以下几个方面:

  • 1,性别与幸存率的关系
  • 2,乘客社会等级与幸存率的关系
  • 3,携带配偶及兄弟姐妹与幸存率的关系
  • 4,携带父母及子女与幸存率的关系
  • 5,年龄与幸存率的关系
  • 6,登港港口与幸存率的关系
  • 7,称呼(从姓名中提取乘客的称呼)与幸存率的关系
  • 8,家庭总人数与幸存率的关系
  • 9,不同船舱的乘客与幸存率的关系

  (这些分析参考博客:https://www.jianshu.com/p/e79a8c41cb1a)

  首先,我们看看得到的数据中,幸存的人与死亡人数的比重:

    res = train['Survived'].value_counts()
print(res)
'''
0 549
1 342
Name: Survived, dtype: int64 '''

2.1 性别与生存率的关系

  我们从上面知道,让妇女儿童上船,那么女性的幸存率到底如何呢?我们看图:

    sns.barplot(x='Sex', y='Survived', data=train)

  图如下:

Kaggle入门——泰坦尼克号生还者预测

  我们可以看到,确实是女性幸存率远高于男性,那么性别Sex是一个很重要的特征。

2.2  乘客等级与生存率的关系

sns.barplot(x='Pclass', y='Survived', data=train)

  图如下:

Kaggle入门——泰坦尼克号生还者预测

  我们发现,乘客社会等级越高,幸存率越高,所以Pclass这个特征也比较重要。

2.3  携带配偶及兄弟姐妹与生存率的关系

sns.barplot(x='SibSp', y='Survived', data=train)

  图如下:

Kaggle入门——泰坦尼克号生还者预测

  只能说:携带的配偶与兄弟姐妹适中的乘客幸存率更高,可能带个配偶幸存率最高。

2.4 携带父母与子女与生存率的关系

sns.barplot(x='Parch', y='Survived', data=train)

  图如下:

Kaggle入门——泰坦尼克号生还者预测

  好像也是父母与子女适中的乘客幸存率更高。

2.5  年龄与幸存率的关系

    facet = sns.FacetGrid(train, hue='Survived', aspect=2)
facet.map(sns.kdeplot, 'Age', shade=True)
facet.set(xlim=(0, train['Age'].max()))
facet.add_legend()
plt.xlabel('Age')
plt.ylabel('density')

  图如下:

  Kaggle入门——泰坦尼克号生还者预测

  从不同生还情况的密度图可以看出,在年龄15岁的左侧,生还率有明显差别,密度图非交叉区域面积非常大,但在其他年龄段,则差别不是很明显,认为是随机所致,因此可以考虑将年龄偏小的区域分离出来。

2.6  登港港口与幸存率的关系

登船港口(Embarked):

  • 出发地点:S = 英国南安普顿Southampton
  • 途径地点1:C = 法国 瑟堡市Cherbourg
  • 途径地点2:Q = 爱尔兰 昆士敦Queenstown

  我们先按照登港港口与幸存率的关系画图,代码如下:

sns.countplot('Embarked',hue='Survived',data=train)

图如下:

Kaggle入门——泰坦尼克号生还者预测

  我们发现C地的生存率更高,这个应该保存为模型特征,最后我们再筛选嘛。

2.7  不同称呼与幸存率的关系

  每个人都有自己的名字,而且每个名字都是独一无二的,名字和幸存与否看起来并没有直接关联,那怎么利用这个特征呢?有用的信息就隐藏在称呼当中,比如上面我们提到过女生优先,所以称呼为Mrs和 Miss 的就比称呼为Mr 的的更可能幸存,于是我们需要从Name中拿到其称呼并建立新的特征列Title。

  我们注意在每一个name 中,有一个非常显著的特点:乘客头衔每个名字当中都包含了具体的称谓或者说是头衔,将这部分信息提取出来后可以作为非常有用的一个新变量,可以帮助我们进行预测。

  例如:

Braund, Mr. Owen Harris
Heikkinen, Miss. Laina
Oliva y Ocana, Dona. Fermina
Peter, Master. Michael J

  定义函数,从名字中获取头衔。

all_data['Title'] = all_data.Name.apply(lambda name: name.split(',')[1].split('.')[0].strip())

  如果上面代码看不懂,可以看下面这个:

    # get all the titles and print how often each one occurs
titles = all_data['Name'].apply(get_title)
print(pd.value_counts(titles)) # A function to get the title from a name
def get_title(name):
# use a regular expression to search for a title
title_search = re.search('([A-Za-z]+)\.', name)
# if the title exists, extract and return it
if title_search:
return title_search.group(1)
return ''

  我们可以看看称呼的种类和数量:

all_data.Title.value_counts()

out:
Mr 757
Miss 260
Mrs 197
Master 61
Rev 8
Dr 8
Col 4
Mlle 2
Ms 2
Major 2
Capt 1
Lady 1
Jonkheer 1
Don 1
Dona 1
the Countess 1
Mme 1
Sir 1
Name: Title, dtype: int64

  我们将定义以下几种头衔类型

  1. Officer*官员
  2. Royalty王室(皇室)
  3. Mr已婚男士
  4. Mrs已婚妇女
  5. Miss年轻未婚女子
  6. Master有技能的人/教师

  大类可以分为六个:Mr,Miss,Mrs,Master,Royalty,Officer,姓名中头衔字符串与定义头衔类型的分类代码如下:

    all_data = pd.concat([train, test], ignore_index=True)
all_data['Title'] = all_data['Name'].apply(lambda x:x.split(',')[1].split('.')[0].strip())
Title_Dict = {}
Title_Dict.update(dict.fromkeys(['Capt', 'Col', 'Major', 'Dr', 'Rev'], 'Officer'))
Title_Dict.update(dict.fromkeys(['Don', 'Sir', 'the Countess', 'Dona', 'Lady'], 'Royalty'))
Title_Dict.update(dict.fromkeys(['Mme', 'Ms', 'Mrs'], 'Mrs'))
Title_Dict.update(dict.fromkeys(['Mlle', 'Miss'], 'Miss'))
Title_Dict.update(dict.fromkeys(['Mr'], 'Mr'))
Title_Dict.update(dict.fromkeys(['Master','Jonkheer'], 'Master')) all_data['Title'] = all_data['Title'].map(Title_Dict)
sns.barplot(x="Title", y="Survived", data=all_data)

  上面的pandas不会使用,也可以使用下面代码:

# map each title to an integer some titles are very rare
# and are compressed into the same codes as other titles
title_mapping = {
'Mr': 1,
'Miss': 2,
'Mrs': 3,
'Master': 4,
'Rev': 5,
'Dr': 6,
'Col': 7,
'Mlle': 8,
'Ms': 9,
'Major': 10,
'Don': 11,
'Countess': 12,
'Mme': 13,
'Jonkheer ': 14,
'Sir': 15,
'Dona': 16,
'Capt': 17,
'Lady': 18,
}
for k, v in title_mapping.items():
titles[titles == k] = v
# print(k, v)
all_data['Title'] = titles

  至于如何分类,就看自己的想法了,我这里只是将所有的称呼表示出来,你可以自己分。我按照上面的分类:

    title_mapping = {
'Mr': 2,
'Miss': 3,
'Mrs': 4,
'Master': 1,
'Rev': 5,
'Dr': 5,
'Col': 5,
'Mlle': 3,
'Ms': 4,
'Major': 6,
'Don': 5,
'Countess': 5,
'Mme': 4,
'Jonkheer ': 1,
'Sir': 5,
'Dona': 5,
'Capt': 6,
'Lady': 5,
}

  图如下:

Kaggle入门——泰坦尼克号生还者预测

2.8  家庭总人数与幸存率的关系

  我们新增FamilyLabel特征,这个特征等于父母儿童+配偶兄弟姐妹+1,在文中就是 FamilyLabel=Parch+SibSp+1,然后将FamilySize分为三类:

all_data['FamilySize']=all_data['SibSp']+all_data['Parch']+1
sns.barplot(x="FamilySize", y="Survived", data=all_data)

  图如下:

Kaggle入门——泰坦尼克号生还者预测

家庭类别:

  • 小家庭Family_Single:家庭人数=1
  • 中等家庭Family_Small: 2<=家庭人数<=4
  • 大家庭Family_Large: 家庭人数>=5

  我们按照生存率将FamilySize分为三类,构成FamilyLabel特征:

def Fam_label(s):
if (s >= 2) & (s <= 4):
return 2
elif ((s > 4) & (s <= 7)) | (s == 1):
return 1
elif (s > 7):
return 0 all_data['FamilySize'] = all_data['SibSp'] + all_data['Parch'] + 1
all_data['FamilyLabel']=all_data['FamilySize'].apply(Fam_label)
sns.barplot(x="FamilyLabel", y="Survived", data=all_data)

  结果图如下:

Kaggle入门——泰坦尼克号生还者预测

  也可以提取名字长度的特征:

    # generating a familysize column  是指所有的家庭成员
all_data['FamilySize'] = all_data['SibSp'] + all_data['Parch'] # the .apply method generates a new series
all_data['NameLength'] = all_data['Name'].apply(lambda x: len(x))

  最后我们选择是否使用这些特征。

2.9 不同船舱的乘客与幸存率的关系

  船舱号(Cabin)里面数据总数是295,缺失了1309-295=1014,缺失率=1014/1309=77.5%,缺失比较大。这注定是个棘手的问题。

  当然船舱的数据并不是很多,但是乘客位于不同船舱,也就意味着身份不同,所以我们新增Deck特征,先把Cabin空白的填充为“Unknown”,再提取Cabin中的首字母构成乘客的甲板号。

    all_data['Cabin'] = all_data['Cabin'].fillna('Unknown')
all_data['Deck'] = all_data['Cabin'].str.get(0)
sns.barplot(x="Deck", y="Survived", data=all_data)

  图如下:

Kaggle入门——泰坦尼克号生还者预测

2.10  与二到四人共票号的乘客与幸存率的关系

  新增了一个特征叫做 TicketGroup特征,这个特征是统计每个乘客的共票号数。代码如下:

    Ticket_Count = dict(all_data['Ticket'].value_counts())
all_data['TicketGroup'] = all_data['Ticket'].apply(lambda x: Ticket_Count[x])
sns.barplot(x='TicketGroup', y='Survived', data=all_data)

  图如下:

Kaggle入门——泰坦尼克号生还者预测

  把生存率按照TicketGroup 分为三类:

    Ticket_Count = dict(all_data['Ticket'].value_counts())
all_data['TicketGroup'] = all_data['Ticket'].apply(lambda x: Ticket_Count[x])
all_data['TicketGroup'] = all_data['TicketGroup'].apply(Ticket_Label)
sns.barplot(x='TicketGroup', y='Survived', data=all_data) def Ticket_Label(s):
if (s >= 2) & (s <= 4):
return 2
elif ((s > 4) & (s <= 8)) | (s == 1):
return 1
elif (s > 8):
return 0

  图如下:

Kaggle入门——泰坦尼克号生还者预测

3,数据清洗

3.1 缺失值填充

  上面我们从整体分析的时候,也发现了有着不少的缺失值,缺失量也有比较大的,所以我们如何填充缺失值,这是个问题。

  很多机器学习算法为了训练模型,要求所传入的特征中不能有空值。一般做如下处理:

1,如果是数值类型,用平均值取代  .fillna(.mean())

2,如果是分类数据,用最常见的类别取代 .value_counts() + fillna.()

3,使用模型预测缺失值,例如KNN

  具体可以参考我的博客:

Python机器学习笔记:使用sklearn做特征工程和数据挖掘

  我们首先看看那些变量都有缺失值:

  下面这个是train的数据,总共数据有891个,那么在训练的数据集中 Age,Cabin, Embarked 有缺失值。

Kaggle入门——泰坦尼克号生还者预测

  下面这个是test的数据,总共有418个数据,其中Age, Fare, Cabin 有缺失值。

Kaggle入门——泰坦尼克号生还者预测

  这里对Age的缺失值处理方法是采用平均值:

traindata['Age'] = traindata['Age'].fillna(traindata['Age'].median())

test['Age'] = test['Age'].fillna(test['Age'].median())

  当然平均值可能有些不妥,我百度,也有说按照称呼对Age的缺失值进行补全了,(上面我们不是对姓名做了处理:2.7 不同称呼与幸存率之间的关系),因为Miss用于未婚女子,通常其年龄比较小,Mrs则表示太太,夫人,一般年龄较大,因此利用称呼中隐含的信息去推断其年龄是比较合理的,下面可以根据title进行分组并对Age进行补全。

    train = pd.read_csv(trainfile)
test = pd.read_csv(testfile)
all_data = pd.concat([train, test], ignore_index=True)
all_data['Title'] = all_data['Name'].apply(lambda x:x.split(',')[1].split('.')[0].strip())
Title_Dict = {}
Title_Dict.update(dict.fromkeys(['Capt', 'Col', 'Major', 'Dr', 'Rev'], 'Officer'))
Title_Dict.update(dict.fromkeys(['Don', 'Sir', 'the Countess', 'Dona', 'Lady'], 'Royalty'))
Title_Dict.update(dict.fromkeys(['Mme', 'Ms', 'Mrs'], 'Mrs'))
Title_Dict.update(dict.fromkeys(['Mlle', 'Miss'], 'Miss'))
Title_Dict.update(dict.fromkeys(['Mr'], 'Mr'))
Title_Dict.update(dict.fromkeys(['Master','Jonkheer'], 'Master')) all_data['Title'] = all_data['Title'].map(Title_Dict)
# sns.barplot(x="Title", y="Survived", data=all_data)
grouped = all_data.groupby(['Title'])
median = grouped.Age.median()
print(median) Title
Master 4.5
Miss 22.0
Mr 29.0
Mrs 35.0
Officer 49.5
Royalty 40.0
Name: Age, dtype: float64

  可以看到,不同称呼的乘客其年龄的中位数有显著差异,因此我们只需要按称呼对缺失值进行补全即可,这里使用中位数(平均数也是可以的,在这个问题当中两者差异不大,而中位数看起来更整洁一些)。

  代码如下:

    all_data['Title'] = all_data['Title'].map(Title_Dict)
# sns.barplot(x="Title", y="Survived", data=all_data)
grouped = all_data.groupby(['Title'])
median = grouped.Age.median()
for i in range(len(all_data['Age'])):
if pd.isnull(all_data['Age'][i]):
all_data['Age'][i] = median[all_data['Title'][i]]

  我们可以查看一下 all_data.info()

Kaggle入门——泰坦尼克号生还者预测

  Age的缺失值已经补全了,下面我们对Cabin,Embarked 以及Fare进行补全。

  而Embarked 缺失值只有两个,对结果影响不大,所以我们这里将缺失值补全为登船港口人数最多的港口(这里其实应用的是先验概率最大原则)。从结果来看(上面分析过),S地的登船人数最多,所以我们将缺失值填充为最频繁出现的值,S=英国安南普顿Southampton。

all_data['Embarked'] = all_data['Embarked'].fillna('S')

  上面我们也提到过Cabin缺失数值比较多,所以我们把船舱号(Cabin)的缺失值填充为U,表示未知(Unknown)。

    # 缺失数据比较多,船舱号(Cabin)缺失值填充为U,表示未知(Uknow)
all_data['Cabin'] = all_data['Cabin'].fillna('U')

  Fare只有一个缺失值,所以我们可以用票价Fare的平均值补全。

all_data['Fare'] = all_data['Fare'].fillna(all_data.Fare.median())

  至此,我们的缺失值就补全了,check一下:

Kaggle入门——泰坦尼克号生还者预测

  完整代码如下:

def load_dataset(trainfile, testfile):
train = pd.read_csv(trainfile)
test = pd.read_csv(testfile)
# print(test.info())
all_data = pd.concat([train, test], ignore_index=True) titles = all_data['Name'].apply(get_title)
# print(pd.value_counts(titles))
# map each title to an integer some titles are very rare
# and are compressed into the same codes as other titles
title_mapping = {
'Mr': 2,
'Miss': 3,
'Mrs': 4,
'Master': 1,
'Rev': 5,
'Dr': 5,
'Col': 5,
'Mlle': 3,
'Ms': 4,
'Major': 6,
'Don': 5,
'Countess': 5,
'Mme': 4,
'Jonkheer': 1,
'Sir': 5,
'Dona': 5,
'Capt': 6,
'Lady': 5,
}
for k, v in title_mapping.items():
titles[titles == k] = v
# print(k, v)
all_data['Title'] = titles grouped = all_data.groupby(['Title'])
median = grouped.Age.median()
for i in range(len(all_data['Age'])):
if pd.isnull(all_data['Age'][i]):
all_data['Age'][i] = median[all_data['Title'][i]]
# print(all_data['Age']) # generating a familysize column 是指所有的家庭成员
all_data['FamilySize'] = all_data['SibSp'] + all_data['Parch'] # the .apply method generates a new series
all_data['NameLength'] = all_data['Name'].apply(lambda x: len(x))
# print(all_data['NameLength']) all_data['Embarked'] = all_data['Embarked'].fillna('S')
# 缺失数据比较多,船舱号(Cabin)缺失值填充为U,表示未知(Uknow)
all_data['Cabin'] = all_data['Cabin'].fillna('U')
all_data['Fare'] = all_data['Fare'].fillna(all_data.Fare.median()) all_data.loc[all_data['Embarked'] == 'S', 'Embarked'] = 0
all_data.loc[all_data['Embarked'] == 'C', 'Embarked'] = 1
all_data.loc[all_data['Embarked'] == 'Q', 'Embarked'] = 2 all_data.loc[all_data['Sex'] == 'male', 'Sex'] = 0
all_data.loc[all_data['Sex'] == 'female', 'Sex'] = 1 traindata, testdata = all_data[:891], all_data[891:]
# print(traindata.shape, testdata.shape, all_data.shape) # (891, 15) (418, 15) (1309, 15)
traindata, trainlabel = traindata.drop('Survived', axis=1), traindata['Survived'] # train.pop('Survived')
testdata = testdata
corrDf = all_data.corr()
'''
查看各个特征与生成情况(Survived)的相关系数,
ascending=False表示按降序排列
'''
res = corrDf['Survived'].sort_values(ascending=False)
print(res)
return traindata, trainlabel, testdata # A function to get the title from a name
def get_title(name):
# use a regular expression to search for a title
title_search = re.search('([A-Za-z]+)\.', name)
# if the title exists, extract and return it
if title_search:
return title_search.group(1)
return ''

  OK,下一步,我们就需要进行特征工程对补全后的特征做进一步处理。

3.2 特征处理

  当补全数据后,我们查看了数据类型,总共有三种数据类型。有整形 int, 有浮点型 float, 有object。我们需要用数值替代类别。有些动作我们前面已经做过了,但是这里总体再过一遍。

  • 1,乘客性别(Sex):男性male,女性 female  male=0,female=1
  • 2,登船港口(Embarked):S,C,Q        S=0, C=1, Q=2
  • 3,乘客姓名(Name):我们分为六类(具体见前面2.7  不同称呼与幸存率的关系

  代码如下(其实上面都有):

all_data.loc[all_data['Embarked'] == 'S', 'Embarked'] = 0
all_data.loc[all_data['Embarked'] == 'C', 'Embarked'] = 1
all_data.loc[all_data['Embarked'] == 'Q', 'Embarked'] = 2 all_data.loc[all_data['Sex'] == 'male', 'Sex'] = 0
all_data.loc[all_data['Sex'] == 'female', 'Sex'] = 1 titles = all_data['Name'].apply(get_title)
# print(pd.value_counts(titles))
# map each title to an integer some titles are very rare
# and are compressed into the same codes as other titles
title_mapping = {
'Mr': 2,
'Miss': 3,
'Mrs': 4,
'Master': 1,
'Rev': 5,
'Dr': 5,
'Col': 5,
'Mlle': 3,
'Ms': 4,
'Major': 6,
'Don': 5,
'Countess': 5,
'Mme': 4,
'Jonkheer': 1,
'Sir': 5,
'Dona': 5,
'Capt': 6,
'Lady': 5,
}
for k, v in title_mapping.items():
titles[titles == k] = v
# print(k, v)
all_data['Title'] = titles

4,特征提取

  一般来说,一个比较真实的项目,也就是说数据挖掘工程需要建立特征工程,我们需要看看如何提取新的特征,使得我们的准确率更高。这个怎么说呢,其实我们上面对数据分析了那么多,肯定是有原因的。下面一一阐述。

4.1 随机森林寻找重要特征

  上面我们将数据缺失值填充完后,然后进行了概述,总共有14个特征,1个结果(Survived),其中四个特征是object类型,我们去掉,剩下了10个特征,我们做重要特征提取

Kaggle入门——泰坦尼克号生还者预测

  我们使用上面五个比较重要的特征:Pclass,Sex,Fare,Title, NameLength 做随机森林模型训练。

def random_forestclassifier_train(traindata, trainlabel, testdata):
# predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked', 'FamilySize', 'Title', 'NameLength']
predictors =['Pclass', 'Sex', 'Fare', 'Title', 'NameLength', ]
traindata, testdata = traindata[predictors], testdata[predictors]
# print(traindata.shape, trainlabel.shape, testdata.shape) # (891, 7) (891,) (418, 7)
# print(testdata.info())
trainSet, testSet, trainlabel, testlabel = train_test_split(traindata, trainlabel,
test_size=0.2, random_state=12345)
# initialize our algorithm class
clf = RandomForestClassifier(random_state=1, n_estimators=100,
min_samples_split=4, min_samples_leaf=2)
# training the algorithm using the predictors and target
clf.fit(trainSet, trainlabel)
test_accuracy = clf.score(testSet, testlabel) * 100
print("正确率为 %s%%" % test_accuracy) # 正确率为 80.44692737430168%

 准确率还没有不提取特征的高。。。。这就有点尴尬哈。

4.2 相关系数法

  相关系数法:计算各个特征的相关系数

    # 相关性矩阵
corrDf = all_data.corr()
'''
查看各个特征与生成情况(Survived)的相关系数,
ascending=False表示按降序排列
'''
res = corrDf['Survived'].sort_values(ascending=False)
print(res)

  结果如下:

Kaggle入门——泰坦尼克号生还者预测

   我们使用上面六个正相关的特征:Sex,NameLength, Fare,Embarked,Parch, FamiySize, 做随机森林模型训练。

def random_forestclassifier_train(traindata, trainlabel, testdata):
# predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked', 'FamilySize', 'Title', 'NameLength']
predictors = ['Sex', 'Fare', 'Embarked', 'NameLength', 'Parch', 'FamilySize']
traindata, testdata = traindata[predictors], testdata[predictors]
# print(traindata.shape, trainlabel.shape, testdata.shape) # (891, 7) (891,) (418, 7)
# print(testdata.info())
trainSet, testSet, trainlabel, testlabel = train_test_split(traindata, trainlabel,
test_size=0.2, random_state=12345)
# initialize our algorithm class
clf = RandomForestClassifier(random_state=1, n_estimators=100,
min_samples_split=4, min_samples_leaf=2)
# training the algorithm using the predictors and target
clf.fit(trainSet, trainlabel)
test_accuracy = clf.score(testSet, testlabel) * 100
print("正确率为 %s%%" % test_accuracy) # 正确率为 81.56424581005587%

  相比于上个随机森林,效果好了不少,准确率提高了1个百分点。

4.3 尝试用所有特征做随机森林模型训练

def random_forestclassifier_train(traindata, trainlabel, testdata):
predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked', 'FamilySize', 'Title', 'NameLength'] traindata, testdata = traindata[predictors], testdata[predictors]
# print(traindata.shape, trainlabel.shape, testdata.shape) # (891, 7) (891,) (418, 7)
# print(testdata.info())
trainSet, testSet, trainlabel, testlabel = train_test_split(traindata, trainlabel,
test_size=0.2, random_state=12345)
# initialize our algorithm class
clf = RandomForestClassifier(random_state=1, n_estimators=100,
min_samples_split=4, min_samples_leaf=2)
# training the algorithm using the predictors and target
clf.fit(trainSet, trainlabel)
test_accuracy = clf.score(testSet, testlabel) * 100
print("正确率为 %s%%" % test_accuracy) # 正确率为 83.79888268156425%

  准确率进一步提高,这次提高了两个百分点。

  这可能是目前效果最好的吧。。。。。。

  所以下一步进行集成学习各种尝试,然后调参。。。。。。over

模型训练及其结果展示

1,线性回归模型

  这里展示两种线性回归的方式,但是不知道为什么我的线性回归模型准确率低的可怕,都没有蒙的多,只有37.63003367180264%。具体原因不知道,希望细心的网友帮我发现。

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import warnings
import seaborn as sns
from sklearn.linear_model import LinearRegression, LogisticRegression
from sklearn.model_selection import KFold, train_test_split
from sklearn.ensemble import RandomForestClassifier warnings.filterwarnings('ignore') def load_dataset(trainfile, testfile):
train = pd.read_csv(trainfile)
test = pd.read_csv(testfile)
train['Age'] = train['Age'].fillna(train['Age'].median())
test['Age'] = test['Age'].fillna(test['Age'].median())
# replace all the occurences of male with the number 0
train.loc[train['Sex'] == 'male', 'Sex'] = 0
train.loc[train['Sex'] == 'female', 'Sex'] = 1
test.loc[test['Sex'] == 'male', 'Sex'] = 0
test.loc[test['Sex'] == 'female', 'Sex'] = 1
# .fillna() 为数据填充函数 用括号里面的东西填充
train['Embarked'] = train['Embarked'].fillna('S')
train.loc[train['Embarked'] == 'S', 'Embarked'] = 0
train.loc[train['Embarked'] == 'C', 'Embarked'] = 1
train.loc[train['Embarked'] == 'Q', 'Embarked'] = 2
test['Embarked'] = test['Embarked'].fillna('S')
test.loc[test['Embarked'] == 'S', 'Embarked'] = 0
test.loc[test['Embarked'] == 'C', 'Embarked'] = 1
test.loc[test['Embarked'] == 'Q', 'Embarked'] = 2
test['Fare'] = test['Fare'].fillna(test['Fare'].median())
traindata, trainlabel = train.drop('Survived', axis=1), train['Survived'] # train.pop('Survived')
testdata = test
print(traindata.shape, trainlabel.shape, testdata.shape)
# (891, 11) (891,) (418, 11)
return traindata, trainlabel, testdata def linear_regression_test(traindata, trainlabel, testdata):
traindata = pd.read_csv(trainfile)
test = pd.read_csv(testfile)
traindata['Age'] = traindata['Age'].fillna(traindata['Age'].median())
test['Age'] = test['Age'].fillna(test['Age'].median())
# replace all the occurences of male with the number 0
traindata.loc[traindata['Sex'] == 'male', 'Sex'] = 0
traindata.loc[traindata['Sex'] == 'female', 'Sex'] = 1
# .fillna() 为数据填充函数 用括号里面的东西填充
traindata['Embarked'] = traindata['Embarked'].fillna('S')
traindata.loc[traindata['Embarked'] == 'S', 'Embarked'] = 0
traindata.loc[traindata['Embarked'] == 'C', 'Embarked'] = 1
traindata.loc[traindata['Embarked'] == 'Q', 'Embarked'] = 2
# the columns we'll use to predict the target
all_variables = ['PassengerID', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch',
'Ticket', 'Fare', 'Cabin', 'Embarked']
predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
# traindata, testdata = traindata[predictors], testdata[predictors]
alg = LinearRegression()
kf = KFold(n_splits=3, random_state=1)
predictions = []
for train_index, test_index in kf.split(traindata):
# print(train_index, test_index)
train_predictors = (traindata[predictors].iloc[train_index, :])
train_target = traindata['Survived'].iloc[train_index]
alg.fit(train_predictors, train_target)
test_predictions = alg.predict(traindata[predictors].iloc[test_index, :])
predictions.append(test_predictions)
# print(type(predictions))
predictions = np.concatenate(predictions, axis=0) #<class 'numpy.ndarray'>
# print(type(predictions))
predictions[predictions > 0.5] = 1
predictions[predictions < 0.5] = 1
accuracy = sum(predictions[predictions == traindata['Survived']]/len(predictions))
print(accuracy) # 0.3838383838383825 def linear_regression_train(traindata, trainlabel, testdata):
# the columns we'll use to predict the target
all_variables = ['PassengerID', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch',
'Ticket', 'Fare', 'Cabin', 'Embarked']
predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
traindata, testdata = traindata[predictors], testdata[predictors]
print(traindata.shape, trainlabel.shape, testdata.shape) # (891, 7) (891,) (418, 7)
print(testdata.info())
trainSet, testSet, trainlabel, testlabel = train_test_split(traindata, trainlabel,
test_size=0.2, random_state=12345)
# initialize our algorithm class
clf = LinearRegression()
# training the algorithm using the predictors and target
clf.fit(trainSet, trainlabel)
test_accuracy = clf.score(testSet, testlabel) * 100
print("正确率为 %s%%" % test_accuracy) # 正确率为 37.63003367180264%
# res = clf.predict(testdata) if __name__ == '__main__':
trainfile = 'data/titanic_train.csv'
testfile = 'data/test.csv'
traindata, trainlabel, testdata = load_dataset(trainfile, testfile)
# print(traindata.shape[1]) # 11
linear_regression_train(traindata, trainlabel, testdata)
# linear_regression_test(traindata, trainlabel, testdata)

2,逻辑回归模型

  逻辑回归也是只选择了几个比较全的特征,准确率还好,达到了: 81.56424581005587%。代码如下:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import warnings
import seaborn as sns
from sklearn.linear_model import LinearRegression, LogisticRegression
from sklearn.model_selection import KFold, train_test_split
from sklearn.ensemble import RandomForestClassifier warnings.filterwarnings('ignore') def load_dataset(trainfile, testfile):
train = pd.read_csv(trainfile)
test = pd.read_csv(testfile)
train['Age'] = train['Age'].fillna(train['Age'].median())
test['Age'] = test['Age'].fillna(test['Age'].median())
# replace all the occurences of male with the number 0
train.loc[train['Sex'] == 'male', 'Sex'] = 0
train.loc[train['Sex'] == 'female', 'Sex'] = 1
test.loc[test['Sex'] == 'male', 'Sex'] = 0
test.loc[test['Sex'] == 'female', 'Sex'] = 1
# .fillna() 为数据填充函数 用括号里面的东西填充
train['Embarked'] = train['Embarked'].fillna('S')
train.loc[train['Embarked'] == 'S', 'Embarked'] = 0
train.loc[train['Embarked'] == 'C', 'Embarked'] = 1
train.loc[train['Embarked'] == 'Q', 'Embarked'] = 2
test['Embarked'] = test['Embarked'].fillna('S')
test.loc[test['Embarked'] == 'S', 'Embarked'] = 0
test.loc[test['Embarked'] == 'C', 'Embarked'] = 1
test.loc[test['Embarked'] == 'Q', 'Embarked'] = 2
test['Fare'] = test['Fare'].fillna(test['Fare'].median())
traindata, trainlabel = train.drop('Survived', axis=1), train['Survived'] # train.pop('Survived')
testdata = test
print(traindata.shape, trainlabel.shape, testdata.shape)
# (891, 11) (891,) (418, 11)
return traindata, trainlabel, testdata def logistic_regression_train(traindata, trainlabel, testdata):
# the columns we'll use to predict the target
all_variables = ['PassengerID', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch',
'Ticket', 'Fare', 'Cabin', 'Embarked']
predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
traindata, testdata = traindata[predictors], testdata[predictors]
# print(traindata.shape, trainlabel.shape, testdata.shape) # (891, 7) (891,) (418, 7)
# print(testdata.info())
trainSet, testSet, trainlabel, testlabel = train_test_split(traindata, trainlabel,
test_size=0.2, random_state=12345)
# initialize our algorithm class
clf = LogisticRegression()
# training the algorithm using the predictors and target
clf.fit(trainSet, trainlabel)
test_accuracy = clf.score(testSet, testlabel) * 100
print("正确率为 %s%%" % test_accuracy) # 正确率为 81.56424581005587%
# res = clf.predict(testdata) if __name__ == '__main__':
trainfile = 'data/titanic_train.csv'
testfile = 'data/test.csv'
traindata, trainlabel, testdata = load_dataset(trainfile, testfile)
logistic_regression_train(traindata, trainlabel, testdata)

3,随机森林模型

  我们依旧选择和上面相同的特征,使用随机森林来做,准确率为:81.56424581005587%。效果还行,不过也只是和逻辑回归一样,代码如下:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import warnings
import seaborn as sns
from sklearn.linear_model import LinearRegression, LogisticRegression
from sklearn.model_selection import KFold, train_test_split
from sklearn.ensemble import RandomForestClassifier warnings.filterwarnings('ignore') def load_dataset(trainfile, testfile):
train = pd.read_csv(trainfile)
test = pd.read_csv(testfile)
train['Age'] = train['Age'].fillna(train['Age'].median())
test['Age'] = test['Age'].fillna(test['Age'].median())
# replace all the occurences of male with the number 0
train.loc[train['Sex'] == 'male', 'Sex'] = 0
train.loc[train['Sex'] == 'female', 'Sex'] = 1
test.loc[test['Sex'] == 'male', 'Sex'] = 0
test.loc[test['Sex'] == 'female', 'Sex'] = 1
# .fillna() 为数据填充函数 用括号里面的东西填充
train['Embarked'] = train['Embarked'].fillna('S')
train.loc[train['Embarked'] == 'S', 'Embarked'] = 0
train.loc[train['Embarked'] == 'C', 'Embarked'] = 1
train.loc[train['Embarked'] == 'Q', 'Embarked'] = 2
test['Embarked'] = test['Embarked'].fillna('S')
test.loc[test['Embarked'] == 'S', 'Embarked'] = 0
test.loc[test['Embarked'] == 'C', 'Embarked'] = 1
test.loc[test['Embarked'] == 'Q', 'Embarked'] = 2
test['Fare'] = test['Fare'].fillna(test['Fare'].median())
traindata, trainlabel = train.drop('Survived', axis=1), train['Survived'] # train.pop('Survived')
testdata = test
print(traindata.shape, trainlabel.shape, testdata.shape)
# (891, 11) (891,) (418, 11)
return traindata, trainlabel, testdata def random_forestclassifier_train(traindata, trainlabel, testdata):
predictors = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
traindata, testdata = traindata[predictors], testdata[predictors]
# print(traindata.shape, trainlabel.shape, testdata.shape) # (891, 7) (891,) (418, 7)
# print(testdata.info())
trainSet, testSet, trainlabel, testlabel = train_test_split(traindata, trainlabel,
test_size=0.2, random_state=12345)
# initialize our algorithm class
clf = RandomForestClassifier(random_state=1, n_estimators=100,
min_samples_split=4, min_samples_leaf=2)
# training the algorithm using the predictors and target
clf.fit(trainSet, trainlabel)
test_accuracy = clf.score(testSet, testlabel) * 100
print("正确率为 %s%%" % test_accuracy) # 正确率为 81.56424581005587% if __name__ == '__main__':
trainfile = 'data/titanic_train.csv'
testfile = 'data/test.csv'
traindata, trainlabel, testdata = load_dataset(trainfile, testfile)
random_forestclassifier_train(traindata, trainlabel, testdata)

4,集成学习模型

  这里简单的集成GradientBoostingClassifier和LogisticRegression 两种算法。

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import warnings
import seaborn as sns
from sklearn.linear_model import LinearRegression, LogisticRegression
from sklearn.model_selection import KFold, train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_selection import SelectKBest, f_classif
from sklearn.ensemble import GradientBoostingClassifier
import re warnings.filterwarnings('ignore') # A function to get the title from a name
def get_title(name):
# use a regular expression to search for a title
title_search = re.search('([A-Za-z]+)\.', name)
# if the title exists, extract and return it
if title_search:
return title_search.group(1)
return '' def load_dataset(trainfile, testfile):
train = pd.read_csv(trainfile)
test = pd.read_csv(testfile)
train['Age'] = train['Age'].fillna(train['Age'].median())
test['Age'] = test['Age'].fillna(test['Age'].median())
# replace all the occurences of male with the number 0
train.loc[train['Sex'] == 'male', 'Sex'] = 0
train.loc[train['Sex'] == 'female', 'Sex'] = 1
test.loc[test['Sex'] == 'male', 'Sex'] = 0
test.loc[test['Sex'] == 'female', 'Sex'] = 1
# .fillna() 为数据填充函数 用括号里面的东西填充
train['Embarked'] = train['Embarked'].fillna('S')
train.loc[train['Embarked'] == 'S', 'Embarked'] = 0
train.loc[train['Embarked'] == 'C', 'Embarked'] = 1
train.loc[train['Embarked'] == 'Q', 'Embarked'] = 2
test['Embarked'] = test['Embarked'].fillna('S')
test.loc[test['Embarked'] == 'S', 'Embarked'] = 0
test.loc[test['Embarked'] == 'C', 'Embarked'] = 1
test.loc[test['Embarked'] == 'Q', 'Embarked'] = 2
test['Fare'] = test['Fare'].fillna(test['Fare'].median())
# generating a familysize column 是指所有的家庭成员
train['FamilySize'] = train['SibSp'] + train['Parch']
test['FamilySize'] = test['SibSp'] + test['Parch'] # the .apply method generates a new series
train['NameLength'] = train['Name'].apply(lambda x: len(x))
test['NameLength'] = test['Name'].apply(lambda x: len(x)) titles_train = train['Name'].apply(get_title)
titles_test = test['Name'].apply(get_title)
title_mapping = {
'Mr': 1,
'Miss': 2,
'Mrs': 3,
'Master': 4,
'Rev': 6,
'Dr': 5,
'Col': 7,
'Mlle': 8,
'Ms': 2,
'Major': 7,
'Don': 9,
'Countess': 10,
'Mme': 8,
'Jonkheer': 10,
'Sir': 9,
'Dona': 9,
'Capt': 7,
'Lady': 10,
}
for k, v in title_mapping.items():
titles_train[titles_train == k] = v
train['Title'] = titles_train
for k, v in title_mapping.items():
titles_test[titles_test == k] = v
test['Title'] = titles_test
# print(pd.value_counts(titles_train))
traindata, trainlabel = train.drop('Survived', axis=1), train['Survived'] # train.pop('Survived')
testdata = test
print(traindata.shape, trainlabel.shape, testdata.shape)
# (891, 11) (891,) (418, 11)
return traindata, trainlabel, testdata def emsemble_model_train(traindata, trainlabel, testdata):
# the algorithms we want to ensemble
# we're using the more linear predictors for the logistic regression,
# and everything with the gradient boosting classifier
algorithms = [
[GradientBoostingClassifier(random_state=1, n_estimators=25, max_depth=3),
['Pclass', 'Sex', 'Fare', 'FamilySize', 'Title', 'Age', 'Embarked', ]],
[LogisticRegression(random_state=1),
['Pclass', 'Sex', 'Fare', 'FamilySize', 'Title', 'Age', 'Embarked', ]]
]
# initialize the cross validation folds
kf = KFold(n_splits=3, random_state=1)
predictions = []
for train_index, test_index in kf.split(traindata):
# print(train_index, test_index)
full_test_predictions = []
for alg, predictors in algorithms:
train_predictors = (traindata[predictors].iloc[train_index, :])
train_target = trainlabel.iloc[train_index]
alg.fit(train_predictors, train_target)
test_predictions = alg.predict(traindata[predictors].iloc[test_index, :])
full_test_predictions.append(test_predictions)
# use a simple ensembling scheme
test_predictions = (full_test_predictions[0] + full_test_predictions[1]) / 2
test_predictions[test_predictions <= 0.5] = 0
test_predictions[test_predictions >= 0.5] = 1
predictions.append(test_predictions)
predictions = np.concatenate(predictions, axis=0)
# compute accuracy bu comparing to the training data
accuracy = sum(predictions[predictions == trainlabel]) / len(predictions)
print(accuracy) def emsemble_model_train(traindata, trainlabel, testdata):
# the algorithms we want to ensemble
# we're using the more linear predictors for the logistic regression,
# and everything with the gradient boosting classifier
predictors = ['Pclass', 'Sex', 'Fare', 'FamilySize', 'Title', 'Age', 'Embarked', ]
traindata, testdata = traindata[predictors], testdata[predictors]
trainSet, testSet, trainlabel, testlabel = train_test_split(traindata, trainlabel,
test_size=0.2, random_state=12345)
# initialize our algorithm class
clf1 = GradientBoostingClassifier(random_state=1, n_estimators=25, max_depth=3)
clf2 = LogisticRegression(random_state=1)
# training the algorithm using the predictors and target
clf1.fit(trainSet, trainlabel)
clf2.fit(trainSet, trainlabel)
test_accuracy1 = clf1.score(testSet, testlabel) * 100
test_accuracy2 = clf2.score(testSet, testlabel) * 100
print(test_accuracy1, test_accuracy2) # 78.77094972067039 80.44692737430168
print("正确率为 %s%%" % ((test_accuracy1+test_accuracy2)/2)) # 正确率为 79.60893854748603% if __name__ == '__main__':
trainfile = 'data/titanic_train.csv'
testfile = 'data/test.csv'
traindata, trainlabel, testdata = load_dataset(trainfile, testfile)
emsemble_model_train(traindata, trainlabel, testdata)

  当然,对于集成学习中,集成集中算法,也可以使用赋予权重比的方式。具体可以参考:

Python机器学习笔记 集成学习总结

  这里不再多赘述。

  我的GitHub地址:https://github.com/LeBron-Jian/Kaggle-learn

参考文献:

https://www.jianshu.com/p/ee91d8880bbd

https://www.jianshu.com/p/e79a8c41cb1a

https://www.cnblogs.com/python-1807/p/10645170.html

https://blog.csdn.net/han_xiaoyang/article/details/49797143