Kaggle - Titanic -1

續前 : Kaggle

Ref: http://www.jianshu.com/p/32def2294ae6


繼續研究各欄位


1. 分析各欄位

info()

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

--

PassengerId: 是 int, 值為 index +1

--

Survived : 0 / 1

--

Pclass : 1 - 頭等艙, 2 - 商務艙, 3 - 經濟艙

--

Name : 姓名,  我取 last name (, 前 )

須注意 string 輸入到 random forest classifier 會有型態的錯誤, 需要轉換 

可用 

• LabelEncoder : turn your string into incremental value
• OneHotEncoder : use One-of-K algorithm to transform your String into integer

先用 LabelEncoder 來試試. 

-- 

Age : 

想說用 random forest 來預測 Age, 但準確度並不高. （<0.1), 

改用原範例 平均值先

之後可能 Age 得想個好的關聯圖.. 

--

Ticket : 一樣用 LabelEncoder

--

Cabin : 很多 NaN, 也許下一版找個好的方法

Embarked : 

這兩欄先去除

--

程式 :  github

---

結果 : 增加 0.01

Todo:

https://www.kaggle.com/c/titanic/details/further-reading-watching

Further Reading / Watching

Want more? Here are some links to some tutorial pages that might interest you!

• triangleinequality's Complete Guide to improving your score with a great section on Feature Engineering
• agconti's iPython Tutorial which touches upon other machine learning methods to try
• Getting Started with Pandas exercise, more advanced one that uses a completely different dataset
• Getting Into Shape for Competitive Data Science (Video)
• Kaggle wiki of Data Science Tutorials