In [28]:

    

import pandas as pd

import matplotlib as plt
%matplotlib inline


    

In [2]:

    

df = pd.read_csv('../titanicdeath/static/X_train.csv')


    

In [3]:

    

df.head()


    

    
Out[3]:






  

    

      

      
Pclass
      
Sex
      
Age
      
Fare
      
Embarked
      
Title
      
IsAlone
      
Age*Class
    
  
  

    

      
0
      
3
      
0
      
1
      
0
      
0
      
1
      
0
      
3
    
    

      
1
      
1
      
1
      
2
      
3
      
1
      
3
      
0
      
2
    
    

      
2
      
3
      
1
      
1
      
1
      
0
      
2
      
1
      
3
    
    

      
3
      
1
      
1
      
2
      
3
      
0
      
3
      
0
      
2
    
    

      
4
      
3
      
0
      
2
      
1
      
0
      
1
      
1
      
6
    
  

In [4]:

    

embarked_dist = df['Embarked'].value_counts()


    

In [5]:

    

embarked_dist


    

    
Out[5]:





0    646
1    168
2     77
Name: Embarked, dtype: int64

In [6]:

    

embarked_dist[0]/sum(embarked_dist)


    

    
Out[6]:





0.72502805836139173

In [7]:

    

embarked_dist[1]/sum(embarked_dist)


    

    
Out[7]:





0.18855218855218855

In [8]:

    

embarked_dist[2]/sum(embarked_dist)


    

    
Out[8]:





0.086419753086419748

In [9]:

    

# this is the code we should use to sample from the exsiting distribution of embarkation ports
df['Embarked'].sample(1).values[0]


    

    
Out[9]:





1

In [10]:

    

# graph the titles and sexes of those titles
cross = pd.crosstab(df['Title'], df['Sex'])
cross


    

    
Out[10]:






  

    

      
Sex
      
0
      
1
    
    

      
Title
      

      

    
  
  

    

      
1
      
517
      
0
    
    

      
2
      
0
      
185
    
    

      
3
      
0
      
126
    
    

      
4
      
40
      
0
    
    

      
5
      
20
      
3
    
  

In [11]:

    

df['Title'][df['Sex'] == 0].sample()


    

    
Out[11]:





287    1
Name: Title, dtype: int64

In [12]:

    

cross[0]


    

    
Out[12]:





Title
1    517
2      0
3      0
4     40
5     20
Name: 0, dtype: int64

In [13]:

    

cross[1]


    

    
Out[13]:





Title
1      0
2    185
3    126
4      0
5      3
Name: 1, dtype: int64

In [14]:

    

cross[0].sample(1)


    

    
Out[14]:





Title
1    517
Name: 0, dtype: int64

In [15]:

    

cross[1].sample(1).values[0]


    

    
Out[15]:





185

In [16]:

    

cross_fare = pd.crosstab(df['Pclass'], df['Fare'])
cross_fare


    

    
Out[16]:






  

    

      
Fare
      
0
      
1
      
2
      
3
    
    

      
Pclass
      

      

      

      

    
  
  

    

      
1
      
6
      
0
      
51
      
159
    
    

      
2
      
6
      
86
      
70
      
22
    
    

      
3
      
211
      
131
      
108
      
41
    
  

In [17]:

    

cross_fare[0]


    

    
Out[17]:





Pclass
1      6
2      6
3    211
Name: 0, dtype: int64

In [18]:

    

cross_fare[1]


    

    
Out[18]:





Pclass
1      0
2     86
3    131
Name: 1, dtype: int64

In [19]:

    

cross_fare[2]


    

    
Out[19]:





Pclass
1     51
2     70
3    108
Name: 2, dtype: int64

In [20]:

    

cross_fare[3]


    

    
Out[20]:





Pclass
1    159
2     22
3     41
Name: 3, dtype: int64

In [21]:

    

df['Fare'][df['Pclass'] == 1].sample(1)


    

    
Out[21]:





194    2
Name: Fare, dtype: int64

In [23]:

    

# get a distribution of parents/grandparents
# load in original data

orig_train = pd.read_csv('../titanicdeath/static/train.csv')
orig_test = pd.read_csv('../titanicdeath/static/test.csv')


    

In [25]:

    

orig_train.head()


    

    
Out[25]:






  

    

      

      
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
    
  

In [31]:

    

# number of parents and children
orig_train['Parch'].describe()


    

    
Out[31]:





count    891.000000
mean       0.381594
std        0.806057
min        0.000000
25%        0.000000
50%        0.000000
75%        0.000000
max        6.000000
Name: Parch, dtype: float64

In [ ]:

    

# so the mean number of spouses is ~ 0.4 or half a person
# so what we want to do in our code is sample from this dist.