In [2]:

    

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

# import data
data = pd.read_csv('train.csv')


    

In [3]:

    

print data.shape
data.head(1)


    

    




(891, 12)






    
Out[3]:






  

    

      

      
PassengerId
      
Survived
      
Pclass
      
Name
      
Sex
      
Age
      
SibSp
      
Parch
      
Ticket
      
Fare
      
Cabin
      
Embarked
    
  
  

    

      
0
      
 1
      
 0
      
 3
      
 Braund, Mr. Owen Harris
      
 male
      
 22
      
 1
      
 0
      
 A/5 21171
      
 7.25
      
 NaN
      
 S
    
  

In [4]:

    

data.rename(columns={'Survived' : 'survived', 'Pclass' : 'pass_class', 'Sex' : 'sex', 'Age' : 'age', 'SibSp' : 'horiz_rel', 'Parch' : 'vert_rel', 'Ticket' : 'ticket', 'Fare' : 'fare', 'Cabin' : 'cabin', 'Embarked' : 'embarked'}, inplace=True)


    

In [5]:

    

pd.value_counts(data.survived)


    

    
Out[5]:





0    549
1    342
dtype: int64

In [6]:

    

pd.value_counts(data.sex)


    

    
Out[6]:





male      577
female    314
dtype: int64

In [7]:

    

pd.crosstab(data.sex, data.survived)


    

    
Out[7]:






  

    

      
survived
      
0
      
1
    
    

      
sex
      

      

    
  
  

    

      
female
      
  81
      
 233
    
    

      
male
      
 468
      
 109
    
  

In [8]:

    

fem = data[data.sex == 'female']
fem_total = fem.sex.count()
fem_surv = fem[fem.survived == 1]
fem_surv_total = fem_surv.sex.count()
print str(round((fem_surv_total/(fem_total*1.0))*100, 2)) + "% of females survived"


    

    




74.2% of females survived

In [9]:

    

fem_surv.age.median()


    

    
Out[9]:





28.0

In [10]:

    

fem_surv.age.describe()


    

    
Out[10]:





count    197.000000
mean      28.847716
std       14.175073
min        0.750000
25%       19.000000
50%       28.000000
75%       38.000000
max       63.000000
dtype: float64

In [11]:

    

male = data[data.sex == 'male']
male_total = male.sex.count()
male_surv = male[male.survived == 1]
male_surv_total = male_surv.sex.count()
print str(round((male_surv_total/(male_total*1.0))*100, 2)) + "% of males survived"


    

    




18.89% of males survived

In [12]:

    

pd.crosstab(data.pass_class, data.survived)


    

    
Out[12]:






  

    

      
survived
      
0
      
1
    
    

      
pass_class
      

      

    
  
  

    

      
1
      
  80
      
 136
    
    

      
2
      
  97
      
  87
    
    

      
3
      
 372
      
 119
    
  

In [73]:

    

df = ['pass_class','horiz_rel','vert_rel','fare']
sns.pairplot(data, vars=df, hue='survived', size=2.5, diag_kind='kde')


    

    
Out[73]:





<seaborn.axisgrid.PairGrid at 0x11db0e990>






    

In [14]:

    

pd.crosstab(data.horiz_rel, data.survived)


    

    
Out[14]:






  

    

      
survived
      
0
      
1
    
    

      
horiz_rel
      

      

    
  
  

    

      
0
      
 398
      
 210
    
    

      
1
      
  97
      
 112
    
    

      
2
      
  15
      
  13
    
    

      
3
      
  12
      
   4
    
    

      
4
      
  15
      
   3
    
    

      
5
      
   5
      
   0
    
    

      
8
      
   7
      
   0
    
  

In [15]:

    

pd.crosstab(data.vert_rel, data.survived)


    

    
Out[15]:






  

    

      
survived
      
0
      
1
    
    

      
vert_rel
      

      

    
  
  

    

      
0
      
 445
      
 233
    
    

      
1
      
  53
      
  65
    
    

      
2
      
  40
      
  40
    
    

      
3
      
   2
      
   3
    
    

      
4
      
   4
      
   0
    
    

      
5
      
   4
      
   1
    
    

      
6
      
   1
      
   0
    
  

In [16]:

    

#pd.crosstab(data.ticket, data.survived)


    

In [17]:

    

#pd.crosstab(data.fare, data.survived)
data.fare.describe()


    

    
Out[17]:





count    891.000000
mean      32.204208
std       49.693429
min        0.000000
25%        7.910400
50%       14.454200
75%       31.000000
max      512.329200
dtype: float64

In [18]:

    

#pd.crosstab(data.cabin, data.survived)


    

In [19]:

    

pd.crosstab(data.embarked, data.survived)


    

    
Out[19]:






  

    

      
survived
      
0
      
1
    
    

      
embarked
      

      

    
  
  

    

      
C
      
  75
      
  93
    
    

      
Q
      
  47
      
  30
    
    

      
S
      
 427
      
 217
    
  

In [20]:

    

plt.scatter(survived.age, survived.fare, marker='o', color='b')
plt.scatter(died.age, died.fare, marker='x', color='r')
plt.xlabel('Age')
plt.ylabel('Fare')
plt.show()


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-20-15636cd6e130> in <module>()
----> 1 plt.scatter(survived.age, survived.fare, marker='o', color='b')
      2 plt.scatter(died.age, died.fare, marker='x', color='r')
      3 plt.xlabel('Age')
      4 plt.ylabel('Fare')
      5 plt.show()

NameError: name 'survived' is not defined

In [ ]:

    

lesst40surv = survived[survived.age < 40]
print len(lesst40surv)
greatt40surv = survived[survived.age > 40]
print len(greatt40surv)


    

In [ ]:

    

lesst40died = died[died.age < 40]
print len(lesst40died)
greatt40died = died[died.age > 40]
print len(greatt40died)


    

In [ ]:

    

lesst40surv = survived[survived.fare < 30]
print len(lesst40surv)
greatt40surv = survived[survived.fare > 30]
print len(greatt40surv)


    

In [ ]:

    

lesst40died = died[died.fare < 30]
print len(lesst40died)
greatt40died = died[died.fare > 30]
print len(greatt40died)