生存情况信息统计分析

生存情况信息统计分析：

案例题目：查看数据信息，求平均年龄。求男女生存率，未成年人获救的概率。

数据来源：https://www.kaggle.com/c/titanic/data

# coding=utf-8
import numpy as np
import pandas as pd
#中文的话这样打开，不会出现Initializing from file failed这种错误
f=open("./data/train.csv")
titanic=pd.read_csv(f)
titanic.head(10)

	survived	sex	age	n_siblings_spouses	parch	fare	class	deck	embark_town	alone
0	0	male	22.0	1	0	7.2500	Third	unknown	Southampton	n
1	1	female	38.0	1	0	71.2833	First	C	Cherbourg	n
2	1	female	26.0	0	0	7.9250	Third	unknown	Southampton	y
3	1	female	35.0	1	0	53.1000	First	C	Southampton	n
4	0	male	28.0	0	0	8.4583	Third	unknown	Queenstown	y
5	0	male	2.0	3	1	21.0750	Third	unknown	Southampton	n
6	1	female	27.0	0	2	11.1333	Third	unknown	Southampton	n
7	1	female	14.0	1	0	30.0708	Second	unknown	Cherbourg	n
8	1	female	4.0	1	1	16.7000	Third	G	Southampton	n
9	0	male	20.0	0	0	8.0500	Third	unknown	Southampton	y

age = titanic["age"]
age_is_null = pd.isnull(age)#年龄是空值的布尔值
#如果不去除缺失值，就无法计算平均年龄
good_age = titanic["age"][age_is_null==False]
print(sum(good_age)/len(good_age)) #年龄的平均值
print(titanic["age"].mean()) #调用.mean()也可以直接计算年龄的平均值

29.631307814992027
29.631307814992027

titanicsur = titanic.pop('survived')
print(titanic.head())
print(titanicsur.head())
print(pd.concat([titanic, titanicsur], axis = 1).groupby('sex').survived.mean())

      sex   age  n_siblings_spouses  parch     fare  class     deck  \
0    male  22.0                   1      0   7.2500  Third  unknown   
1  female  38.0                   1      0  71.2833  First        C   
2  female  26.0                   0      0   7.9250  Third  unknown   
3  female  35.0                   1      0  53.1000  First        C   
4    male  28.0                   0      0   8.4583  Third  unknown   

   embark_town alone  
0  Southampton     n  
1    Cherbourg     n  
2  Southampton     y  
3  Southampton     n  
4   Queenstown     y  
0    0
1    1
2    1
3    1
4    0
Name: survived, dtype: int64
sex
female    0.778802
male      0.180488
Name: survived, dtype: float64

def generate_age_label(row):
    age = row["age"]
    if pd.isnull(age):
        return "unknown"
    elif age<18:
        return "minor"
    else:
        return "adult"
age_labels = titanic.apply(generate_age_label,axis=1)
titanic["age_labels"]=age_labels  #各个年龄段获救的概率
pd.concat([titanic, titanicsur], axis = 1).groupby('age_labels').survived.mean()

age_labels
adult    0.371841
minor    0.506849
Name: survived, dtype: float64