In [1]:

    

import pandas as pd
from pandas import Series, DataFrame


    

In [2]:

    

titanic_df = pd.read_csv('train.csv')


    

In [4]:

    

titanic_df.head()


    

    
Out[4]:






  

    

      

      
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 [5]:

    

titanic_df.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
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
dtypes: float64(2), int64(5), object(5)
memory usage: 83.6+ KB

In [6]:

    

import numpy as np


    

In [7]:

    

import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline


    

In [9]:

    

sns.factorplot('Sex',data=titanic_df,
kind='count')


    

    
Out[9]:





<seaborn.axisgrid.FacetGrid at 0x11a3da550>






    

In [11]:

    

sns.factorplot('Sex',data=titanic_df,hue='Pclass',kind='count')


    

    
Out[11]:





<seaborn.axisgrid.FacetGrid at 0x11a4dcb38>






    

In [13]:

    

sns.factorplot('Pclass',data=titanic_df,hue='Sex',kind='count')


    

    
Out[13]:





<seaborn.axisgrid.FacetGrid at 0x11a4ca208>






    

In [15]:

    

def male_female_child(passenger):
    age,sex = passenger
    
    if age < 16:
        return 'child'
    else:
        return sex


    

In [16]:

    

titanic_df['person'] = titanic_df[['Age', 'Sex']].apply(male_female_child,axis=1)


    

In [17]:

    

titanic_df[0:10]


    

    
Out[17]:






  

    

      

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

    

      
0
      
1
      
0
      
3
      
Braund, Mr. Owen Harris
      
male
      
22.0
      
1
      
0
      
A/5 21171
      
7.2500
      
NaN
      
S
      
male
    
    

      
1
      
2
      
1
      
1
      
Cumings, Mrs. John Bradley (Florence Briggs Th...
      
female
      
38.0
      
1
      
0
      
PC 17599
      
71.2833
      
C85
      
C
      
female
    
    

      
2
      
3
      
1
      
3
      
Heikkinen, Miss. Laina
      
female
      
26.0
      
0
      
0
      
STON/O2. 3101282
      
7.9250
      
NaN
      
S
      
female
    
    

      
3
      
4
      
1
      
1
      
Futrelle, Mrs. Jacques Heath (Lily May Peel)
      
female
      
35.0
      
1
      
0
      
113803
      
53.1000
      
C123
      
S
      
female
    
    

      
4
      
5
      
0
      
3
      
Allen, Mr. William Henry
      
male
      
35.0
      
0
      
0
      
373450
      
8.0500
      
NaN
      
S
      
male
    
    

      
5
      
6
      
0
      
3
      
Moran, Mr. James
      
male
      
NaN
      
0
      
0
      
330877
      
8.4583
      
NaN
      
Q
      
male
    
    

      
6
      
7
      
0
      
1
      
McCarthy, Mr. Timothy J
      
male
      
54.0
      
0
      
0
      
17463
      
51.8625
      
E46
      
S
      
male
    
    

      
7
      
8
      
0
      
3
      
Palsson, Master. Gosta Leonard
      
male
      
2.0
      
3
      
1
      
349909
      
21.0750
      
NaN
      
S
      
child
    
    

      
8
      
9
      
1
      
3
      
Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)
      
female
      
27.0
      
0
      
2
      
347742
      
11.1333
      
NaN
      
S
      
female
    
    

      
9
      
10
      
1
      
2
      
Nasser, Mrs. Nicholas (Adele Achem)
      
female
      
14.0
      
1
      
0
      
237736
      
30.0708
      
NaN
      
C
      
child
    
  

In [18]:

    

sns.factorplot('Pclass',data=titanic_df,hue='person',kind='count')


    

    
Out[18]:





<seaborn.axisgrid.FacetGrid at 0x11a89cd30>






    

In [19]:

    

titanic_df['Age'].hist(bins=70)


    

    
Out[19]:





<matplotlib.axes._subplots.AxesSubplot at 0x11abfa9b0>






    

In [20]:

    

titanic_df['Age'].mean()


    

    
Out[20]:





29.69911764705882

In [25]:

    

titanic_df['person'].value_counts()


    

    
Out[25]:





male      537
female    271
child      83
Name: person, dtype: int64

In [26]:

    

titanic_df['Sex'].value_counts()


    

    
Out[26]:





male      577
female    314
Name: Sex, dtype: int64

In [27]:

    

fig = sns.FacetGrid(titanic_df,hue='Sex',aspect=4)
fig.map(sns.kdeplot,'Age',shade=True)

oldest = titanic_df['Age'].max()

fig.set(xlim=(0,oldest))

fig.add_legend()


    

    




//anaconda/lib/python3.5/site-packages/statsmodels/nonparametric/kdetools.py:20: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
  y = X[:m/2+1] + np.r_[0,X[m/2+1:],0]*1j






    
Out[27]:





<seaborn.axisgrid.FacetGrid at 0x11adb8d68>






    

In [28]:

    

fig = sns.FacetGrid(titanic_df,hue='person',aspect=4)
fig.map(sns.kdeplot,'Age',shade=True)

oldest = titanic_df['Age'].max()

fig.set(xlim=(0,oldest))

fig.add_legend()


    

    




//anaconda/lib/python3.5/site-packages/statsmodels/nonparametric/kdetools.py:20: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
  y = X[:m/2+1] + np.r_[0,X[m/2+1:],0]*1j






    
Out[28]:





<seaborn.axisgrid.FacetGrid at 0x11aeaacc0>






    

In [29]:

    

fig = sns.FacetGrid(titanic_df,hue='Pclass',aspect=4)
fig.map(sns.kdeplot,'Age',shade=True)

oldest = titanic_df['Age'].max()

fig.set(xlim=(0,oldest))

fig.add_legend()


    

    




//anaconda/lib/python3.5/site-packages/statsmodels/nonparametric/kdetools.py:20: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
  y = X[:m/2+1] + np.r_[0,X[m/2+1:],0]*1j






    
Out[29]:





<seaborn.axisgrid.FacetGrid at 0x11b15a5c0>






    

In [30]:

    

titanic_df.head()


    

    
Out[30]:






  

    

      

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

    

      
0
      
1
      
0
      
3
      
Braund, Mr. Owen Harris
      
male
      
22.0
      
1
      
0
      
A/5 21171
      
7.2500
      
NaN
      
S
      
male
    
    

      
1
      
2
      
1
      
1
      
Cumings, Mrs. John Bradley (Florence Briggs Th...
      
female
      
38.0
      
1
      
0
      
PC 17599
      
71.2833
      
C85
      
C
      
female
    
    

      
2
      
3
      
1
      
3
      
Heikkinen, Miss. Laina
      
female
      
26.0
      
0
      
0
      
STON/O2. 3101282
      
7.9250
      
NaN
      
S
      
female
    
    

      
3
      
4
      
1
      
1
      
Futrelle, Mrs. Jacques Heath (Lily May Peel)
      
female
      
35.0
      
1
      
0
      
113803
      
53.1000
      
C123
      
S
      
female
    
    

      
4
      
5
      
0
      
3
      
Allen, Mr. William Henry
      
male
      
35.0
      
0
      
0
      
373450
      
8.0500
      
NaN
      
S
      
male
    
  

In [31]:

    

deck = titanic_df['Cabin'].dropna()


    

In [33]:

    

deck.head()


    

    
Out[33]:





1      C85
3     C123
6      E46
10      G6
11    C103
Name: Cabin, dtype: object

In [35]:

    

levels = []

for level in deck:
    levels.append(level[0])

cabin_df = DataFrame(levels)
cabin_df.columns = ['Cabin']
sns.factorplot('Cabin',data=cabin_df,palette='winter_d',kind='count')


    

    
Out[35]:





<seaborn.axisgrid.FacetGrid at 0x11b564438>






    

In [38]:

    

cabin_df = cabin_df[cabin_df.Cabin !='T']
sns.factorplot('Cabin',data=cabin_df,palette='summer',kind='count')


    

    
Out[38]:





<seaborn.axisgrid.FacetGrid at 0x11b5d4240>






    

In [39]:

    

titanic_df.head()


    

    
Out[39]:






  

    

      

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

    

      
0
      
1
      
0
      
3
      
Braund, Mr. Owen Harris
      
male
      
22.0
      
1
      
0
      
A/5 21171
      
7.2500
      
NaN
      
S
      
male
    
    

      
1
      
2
      
1
      
1
      
Cumings, Mrs. John Bradley (Florence Briggs Th...
      
female
      
38.0
      
1
      
0
      
PC 17599
      
71.2833
      
C85
      
C
      
female
    
    

      
2
      
3
      
1
      
3
      
Heikkinen, Miss. Laina
      
female
      
26.0
      
0
      
0
      
STON/O2. 3101282
      
7.9250
      
NaN
      
S
      
female
    
    

      
3
      
4
      
1
      
1
      
Futrelle, Mrs. Jacques Heath (Lily May Peel)
      
female
      
35.0
      
1
      
0
      
113803
      
53.1000
      
C123
      
S
      
female
    
    

      
4
      
5
      
0
      
3
      
Allen, Mr. William Henry
      
male
      
35.0
      
0
      
0
      
373450
      
8.0500
      
NaN
      
S
      
male
    
  

In [45]:

    

sns.factorplot('Embarked',data=titanic_df,hue='Pclass',kind='count',x_order=['C','Q','S'])


    

    




//anaconda/lib/python3.5/site-packages/seaborn/categorical.py:3367: UserWarning: The `x_order` parameter has been renamed `order`
  UserWarning)






    
Out[45]:





<seaborn.axisgrid.FacetGrid at 0x11ac21f28>






    

In [46]:

    

titanic_df.head()


    

    
Out[46]:






  

    

      

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

    

      
0
      
1
      
0
      
3
      
Braund, Mr. Owen Harris
      
male
      
22.0
      
1
      
0
      
A/5 21171
      
7.2500
      
NaN
      
S
      
male
    
    

      
1
      
2
      
1
      
1
      
Cumings, Mrs. John Bradley (Florence Briggs Th...
      
female
      
38.0
      
1
      
0
      
PC 17599
      
71.2833
      
C85
      
C
      
female
    
    

      
2
      
3
      
1
      
3
      
Heikkinen, Miss. Laina
      
female
      
26.0
      
0
      
0
      
STON/O2. 3101282
      
7.9250
      
NaN
      
S
      
female
    
    

      
3
      
4
      
1
      
1
      
Futrelle, Mrs. Jacques Heath (Lily May Peel)
      
female
      
35.0
      
1
      
0
      
113803
      
53.1000
      
C123
      
S
      
female
    
    

      
4
      
5
      
0
      
3
      
Allen, Mr. William Henry
      
male
      
35.0
      
0
      
0
      
373450
      
8.0500
      
NaN
      
S
      
male
    
  

In [47]:

    

titanic_df['Alone'] = titanic_df.SibSp + titanic_df.Parch


    

In [48]:

    

titanic_df['Alone']


    

    
Out[48]:





0       1
1       1
2       0
3       1
4       0
5       0
6       0
7       4
8       2
9       1
10      2
11      0
12      0
13      6
14      0
15      0
16      5
17      0
18      1
19      0
20      0
21      0
22      0
23      0
24      4
25      6
26      0
27      5
28      0
29      0
       ..
861     1
862     0
863    10
864     0
865     0
866     1
867     0
868     0
869     2
870     0
871     2
872     0
873     0
874     1
875     0
876     0
877     0
878     0
879     1
880     1
881     0
882     0
883     0
884     0
885     5
886     0
887     0
888     3
889     0
890     0
Name: Alone, dtype: int64

In [50]:

    

titanic_df['Alone'].loc[titanic_df['Alone'] >0] = 'With family' 

titanic_df['Alone'].loc[titanic_df['Alone'] == 0] = 'Alone'


    

    




---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-50-3a24223ab913> in <module>()
----> 1 titanic_df['Alone'].loc[titanic_df['Alone'] >0] = 'With family'
      2 
      3 titanic_df['Alone'].loc[titanic_df['Alone'] == 0] = 'Alone'

//anaconda/lib/python3.5/site-packages/pandas/core/ops.py in wrapper(self, other, axis)
    761                 other = np.asarray(other)
    762 
--> 763             res = na_op(values, other)
    764             if isscalar(res):
    765                 raise TypeError('Could not compare %s type with Series' %

//anaconda/lib/python3.5/site-packages/pandas/core/ops.py in na_op(x, y)
    681                     result = lib.vec_compare(x, y, op)
    682             else:
--> 683                 result = lib.scalar_compare(x, y, op)
    684         else:
    685 

pandas/lib.pyx in pandas.lib.scalar_compare (pandas/lib.c:14261)()

TypeError: unorderable types: str() > int()

In [52]:

    

titanic_df['Survivor'] = titanic_df.Survived.map({0:'no',1:'yes'})

sns.factorplot('Survivor', data=titanic_df,kind='count')


    

    
Out[52]:





<seaborn.axisgrid.FacetGrid at 0x11b92b9b0>






    

In [54]:

    

sns.factorplot('Pclass','Survived',hue='person',data=titanic_df)


    

    
Out[54]:





<seaborn.axisgrid.FacetGrid at 0x11bc86240>






    

In [56]:

    

sns.lmplot('Age','Survived',data=titanic_df)


    

    
Out[56]:





<seaborn.axisgrid.FacetGrid at 0x11bc0dd30>






    

In [58]:

    

sns.lmplot('Age','Survived',hue='Pclass'
,data=titanic_df)


    

    
Out[58]:





<seaborn.axisgrid.FacetGrid at 0x11c07cc18>






    

In [ ]: