notebook.community

Edit and run



In [1]:

    
import pandas as pd
from pandas import Series, DataFrame



In [2]:

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



In [4]:

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



In [7]:

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









    Out[7]:





<seaborn.axisgrid.FacetGrid at 0x119ff6fd0>



In [8]:

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









    Out[8]:





<seaborn.axisgrid.FacetGrid at 0x117ad7ed0>



In [9]:

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









    Out[9]:





<seaborn.axisgrid.FacetGrid at 0x11a932850>



In [11]:

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



In [12]:

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



In [13]:

    
titanic_df[0:10]









    Out[13]:






  
    
      
      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 [14]:

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









    Out[14]:





<seaborn.axisgrid.FacetGrid at 0x11ab01790>



In [16]:

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









    Out[16]:





<matplotlib.axes._subplots.AxesSubplot at 0x11aed3610>



In [17]:

    
titanic_df['Age'].mean()









    Out[17]:





29.69911764705882



In [18]:

    
titanic_df['person'].value_counts()









    Out[18]:





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



In [19]:

    
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()









    Out[19]:





<seaborn.axisgrid.FacetGrid at 0x11b022990>



In [21]:

    
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()









    Out[21]:





<seaborn.axisgrid.FacetGrid at 0x11b9e1350>



In [23]:

    
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()









    Out[23]:





<seaborn.axisgrid.FacetGrid at 0x11b9e1d90>



In [24]:

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



In [25]:

    
levels = []

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



In [26]:

    
levels









    Out[26]:





['C',
 'C',
 'E',
 'G',
 'C',
 'D',
 'A',
 'C',
 'B',
 'D',
 'B',
 'C',
 'B',
 'C',
 'F',
 'F',
 'C',
 'E',
 'A',
 'D',
 'D',
 'C',
 'B',
 'E',
 'D',
 'F',
 'D',
 'C',
 'B',
 'F',
 'C',
 'E',
 'B',
 'A',
 'C',
 'F',
 'A',
 'F',
 'B',
 'B',
 'G',
 'A',
 'D',
 'D',
 'C',
 'C',
 'C',
 'D',
 'G',
 'C',
 'B',
 'E',
 'B',
 'C',
 'C',
 'C',
 'D',
 'A',
 'B',
 'D',
 'C',
 'C',
 'B',
 'E',
 'C',
 'C',
 'E',
 'C',
 'B',
 'C',
 'E',
 'C',
 'D',
 'B',
 'C',
 'C',
 'C',
 'E',
 'T',
 'F',
 'C',
 'F',
 'C',
 'E',
 'D',
 'B',
 'E',
 'C',
 'B',
 'D',
 'G',
 'C',
 'E',
 'C',
 'E',
 'B',
 'C',
 'A',
 'C',
 'C',
 'C',
 'E',
 'D',
 'E',
 'E',
 'D',
 'A',
 'B',
 'C',
 'B',
 'C',
 'D',
 'C',
 'B',
 'C',
 'E',
 'D',
 'F',
 'B',
 'B',
 'C',
 'B',
 'B',
 'B',
 'C',
 'C',
 'A',
 'E',
 'C',
 'E',
 'E',
 'C',
 'A',
 'E',
 'B',
 'D',
 'A',
 'C',
 'F',
 'D',
 'D',
 'D',
 'A',
 'B',
 'B',
 'D',
 'A',
 'D',
 'E',
 'C',
 'B',
 'B',
 'D',
 'B',
 'B',
 'C',
 'F',
 'C',
 'E',
 'E',
 'C',
 'C',
 'C',
 'F',
 'C',
 'E',
 'E',
 'B',
 'B',
 'D',
 'C',
 'B',
 'B',
 'D',
 'E',
 'B',
 'B',
 'D',
 'E',
 'F',
 'B',
 'B',
 'D',
 'B',
 'D',
 'B',
 'A',
 'E',
 'B',
 'B',
 'E',
 'B',
 'E',
 'C',
 'C',
 'D',
 'E',
 'D',
 'A',
 'D',
 'B',
 'C',
 'B',
 'C']



In [27]:

    
cabin_df = DataFrame(levels)



In [29]:

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









    Out[29]:





<seaborn.axisgrid.FacetGrid at 0x11c0bba90>



In [30]:

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









    Out[30]:





<seaborn.axisgrid.FacetGrid at 0x11bb06950>



In [33]:

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









    Out[33]:





<seaborn.axisgrid.FacetGrid at 0x11c74cad0>



In [34]:

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



In [35]:

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









    



/Users/andymeyers/anaconda/lib/python2.7/site-packages/pandas/core/indexing.py:132: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  self._setitem_with_indexer(indexer, value)



In [38]:

    
sns.factorplot('Alone', data=titanic_df, palette = 'Blues', kind='count')









    Out[38]:





<seaborn.axisgrid.FacetGrid at 0x11c8a5450>



In [39]:

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

sns.factorplot('Survivor', data=titanic_df, palette = 'Set1', kind='count')









    Out[39]:





<seaborn.axisgrid.FacetGrid at 0x11b506790>



In [41]:

    
sns.factorplot('Pclass', 'Survived', data=titanic_df, palette = 'Set1')









    Out[41]:





<seaborn.axisgrid.FacetGrid at 0x11c09cad0>



In [42]:

    
sns.factorplot('Sex', 'Survived', data=titanic_df, palette = 'Set1')









    Out[42]:





<seaborn.axisgrid.FacetGrid at 0x11cb21490>



In [44]:

    
sns.factorplot('Pclass', 'Survived', data=titanic_df, palette = 'Set1', hue='person')









    Out[44]:





<seaborn.axisgrid.FacetGrid at 0x11d37d190>



In [45]:

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









    Out[45]:





<seaborn.axisgrid.FacetGrid at 0x11d453390>



In [46]:

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









    Out[46]:





<seaborn.axisgrid.FacetGrid at 0x11d85d710>



In [47]:

    
generations = [10, 20, 30, 40, 50, 60, 70, 80]
sns.lmplot('Age', 'Survived', data=titanic_df, hue='Pclass', x_bins=generations)









    Out[47]:





<seaborn.axisgrid.FacetGrid at 0x11d85d050>



In [48]:

    
sns.lmplot('Age', 'Survived', data=titanic_df, hue='Sex', x_bins=generations)









    Out[48]:





<seaborn.axisgrid.FacetGrid at 0x11dafb650>



In [49]:

    
sns.lmplot('Age', 'Survived', data=titanic_df, hue='Alone', x_bins=generations)









    Out[49]:





<seaborn.axisgrid.FacetGrid at 0x11d0bebd0>



In [52]:

    
sns.factorplot('Pclass', 'Survived', data=titanic_df, palette = 'Set1', hue='Alone')









    Out[52]:





<seaborn.axisgrid.FacetGrid at 0x11e716850>



In [53]:

    
sns.factorplot('Sex', 'Survived', data=titanic_df, palette = 'Set1', hue='Alone')









    Out[53]:





<seaborn.axisgrid.FacetGrid at 0x11f277750>



In [ ]:

	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