notebook.community

Edit and run



In [1]:

    
import pandas as pd
import numpy as np



In [2]:

    
train_df = pd.read_csv('/Users/williamgray/Library/Mobile Documents/com~apple~CloudDocs/Developer/KaggleTitanic/train.csv')
test_df = pd.read_csv('/Users/williamgray/Library/Mobile Documents/com~apple~CloudDocs/Developer/KaggleTitanic/test.csv')
combine = [train_df, test_df]



In [3]:

    
train_df.head()









    Out[3]:






  
    
      
      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 [4]:

    
test_df.head()









    Out[4]:






  
    
      
      PassengerId
      Pclass
      Name
      Sex
      Age
      SibSp
      Parch
      Ticket
      Fare
      Cabin
      Embarked
    
  
  
    
      0
      892
      3
      Kelly, Mr. James
      male
      34.5
      0
      0
      330911
      7.8292
      NaN
      Q
    
    
      1
      893
      3
      Wilkes, Mrs. James (Ellen Needs)
      female
      47.0
      1
      0
      363272
      7.0000
      NaN
      S
    
    
      2
      894
      2
      Myles, Mr. Thomas Francis
      male
      62.0
      0
      0
      240276
      9.6875
      NaN
      Q
    
    
      3
      895
      3
      Wirz, Mr. Albert
      male
      27.0
      0
      0
      315154
      8.6625
      NaN
      S
    
    
      4
      896
      3
      Hirvonen, Mrs. Alexander (Helga E Lindqvist)
      female
      22.0
      1
      1
      3101298
      12.2875
      NaN
      S



In [5]:

    
train_df.mean()









    Out[5]:





PassengerId    446.000000
Survived         0.383838
Pclass           2.308642
Age             29.699118
SibSp            0.523008
Parch            0.381594
Fare            32.204208
dtype: float64



In [6]:

    
test_df.mean()









    Out[6]:





PassengerId    1100.500000
Pclass            2.265550
Age              30.272590
SibSp             0.447368
Parch             0.392344
Fare             35.627188
dtype: float64



In [7]:

    
train_df.describe()









    Out[7]:






  
    
      
      PassengerId
      Survived
      Pclass
      Age
      SibSp
      Parch
      Fare
    
  
  
    
      count
      891.000000
      891.000000
      891.000000
      714.000000
      891.000000
      891.000000
      891.000000
    
    
      mean
      446.000000
      0.383838
      2.308642
      29.699118
      0.523008
      0.381594
      32.204208
    
    
      std
      257.353842
      0.486592
      0.836071
      14.526497
      1.102743
      0.806057
      49.693429
    
    
      min
      1.000000
      0.000000
      1.000000
      0.420000
      0.000000
      0.000000
      0.000000
    
    
      25%
      223.500000
      0.000000
      2.000000
      20.125000
      0.000000
      0.000000
      7.910400
    
    
      50%
      446.000000
      0.000000
      3.000000
      28.000000
      0.000000
      0.000000
      14.454200
    
    
      75%
      668.500000
      1.000000
      3.000000
      38.000000
      1.000000
      0.000000
      31.000000
    
    
      max
      891.000000
      1.000000
      3.000000
      80.000000
      8.000000
      6.000000
      512.329200



In [8]:

    
train_df[train_df['Survived'] == 1]









    Out[8]:






  
    
      
      PassengerId
      Survived
      Pclass
      Name
      Sex
      Age
      SibSp
      Parch
      Ticket
      Fare
      Cabin
      Embarked
    
  
  
    
      1
      2
      1
      1
      Cumings, Mrs. John Bradley (Florence Briggs Th...
      female
      38.00
      1
      0
      PC 17599
      71.2833
      C85
      C
    
    
      2
      3
      1
      3
      Heikkinen, Miss. Laina
      female
      26.00
      0
      0
      STON/O2. 3101282
      7.9250
      NaN
      S
    
    
      3
      4
      1
      1
      Futrelle, Mrs. Jacques Heath (Lily May Peel)
      female
      35.00
      1
      0
      113803
      53.1000
      C123
      S
    
    
      8
      9
      1
      3
      Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)
      female
      27.00
      0
      2
      347742
      11.1333
      NaN
      S
    
    
      9
      10
      1
      2
      Nasser, Mrs. Nicholas (Adele Achem)
      female
      14.00
      1
      0
      237736
      30.0708
      NaN
      C
    
    
      10
      11
      1
      3
      Sandstrom, Miss. Marguerite Rut
      female
      4.00
      1
      1
      PP 9549
      16.7000
      G6
      S
    
    
      11
      12
      1
      1
      Bonnell, Miss. Elizabeth
      female
      58.00
      0
      0
      113783
      26.5500
      C103
      S
    
    
      15
      16
      1
      2
      Hewlett, Mrs. (Mary D Kingcome)
      female
      55.00
      0
      0
      248706
      16.0000
      NaN
      S
    
    
      17
      18
      1
      2
      Williams, Mr. Charles Eugene
      male
      NaN
      0
      0
      244373
      13.0000
      NaN
      S
    
    
      19
      20
      1
      3
      Masselmani, Mrs. Fatima
      female
      NaN
      0
      0
      2649
      7.2250
      NaN
      C
    
    
      21
      22
      1
      2
      Beesley, Mr. Lawrence
      male
      34.00
      0
      0
      248698
      13.0000
      D56
      S
    
    
      22
      23
      1
      3
      McGowan, Miss. Anna "Annie"
      female
      15.00
      0
      0
      330923
      8.0292
      NaN
      Q
    
    
      23
      24
      1
      1
      Sloper, Mr. William Thompson
      male
      28.00
      0
      0
      113788
      35.5000
      A6
      S
    
    
      25
      26
      1
      3
      Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...
      female
      38.00
      1
      5
      347077
      31.3875
      NaN
      S
    
    
      28
      29
      1
      3
      O'Dwyer, Miss. Ellen "Nellie"
      female
      NaN
      0
      0
      330959
      7.8792
      NaN
      Q
    
    
      31
      32
      1
      1
      Spencer, Mrs. William Augustus (Marie Eugenie)
      female
      NaN
      1
      0
      PC 17569
      146.5208
      B78
      C
    
    
      32
      33
      1
      3
      Glynn, Miss. Mary Agatha
      female
      NaN
      0
      0
      335677
      7.7500
      NaN
      Q
    
    
      36
      37
      1
      3
      Mamee, Mr. Hanna
      male
      NaN
      0
      0
      2677
      7.2292
      NaN
      C
    
    
      39
      40
      1
      3
      Nicola-Yarred, Miss. Jamila
      female
      14.00
      1
      0
      2651
      11.2417
      NaN
      C
    
    
      43
      44
      1
      2
      Laroche, Miss. Simonne Marie Anne Andree
      female
      3.00
      1
      2
      SC/Paris 2123
      41.5792
      NaN
      C
    
    
      44
      45
      1
      3
      Devaney, Miss. Margaret Delia
      female
      19.00
      0
      0
      330958
      7.8792
      NaN
      Q
    
    
      47
      48
      1
      3
      O'Driscoll, Miss. Bridget
      female
      NaN
      0
      0
      14311
      7.7500
      NaN
      Q
    
    
      52
      53
      1
      1
      Harper, Mrs. Henry Sleeper (Myna Haxtun)
      female
      49.00
      1
      0
      PC 17572
      76.7292
      D33
      C
    
    
      53
      54
      1
      2
      Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkin...
      female
      29.00
      1
      0
      2926
      26.0000
      NaN
      S
    
    
      55
      56
      1
      1
      Woolner, Mr. Hugh
      male
      NaN
      0
      0
      19947
      35.5000
      C52
      S
    
    
      56
      57
      1
      2
      Rugg, Miss. Emily
      female
      21.00
      0
      0
      C.A. 31026
      10.5000
      NaN
      S
    
    
      58
      59
      1
      2
      West, Miss. Constance Mirium
      female
      5.00
      1
      2
      C.A. 34651
      27.7500
      NaN
      S
    
    
      61
      62
      1
      1
      Icard, Miss. Amelie
      female
      38.00
      0
      0
      113572
      80.0000
      B28
      NaN
    
    
      65
      66
      1
      3
      Moubarek, Master. Gerios
      male
      NaN
      1
      1
      2661
      15.2458
      NaN
      C
    
    
      66
      67
      1
      2
      Nye, Mrs. (Elizabeth Ramell)
      female
      29.00
      0
      0
      C.A. 29395
      10.5000
      F33
      S
    
    
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    
    
      809
      810
      1
      1
      Chambers, Mrs. Norman Campbell (Bertha Griggs)
      female
      33.00
      1
      0
      113806
      53.1000
      E8
      S
    
    
      820
      821
      1
      1
      Hays, Mrs. Charles Melville (Clara Jennings Gr...
      female
      52.00
      1
      1
      12749
      93.5000
      B69
      S
    
    
      821
      822
      1
      3
      Lulic, Mr. Nikola
      male
      27.00
      0
      0
      315098
      8.6625
      NaN
      S
    
    
      823
      824
      1
      3
      Moor, Mrs. (Beila)
      female
      27.00
      0
      1
      392096
      12.4750
      E121
      S
    
    
      827
      828
      1
      2
      Mallet, Master. Andre
      male
      1.00
      0
      2
      S.C./PARIS 2079
      37.0042
      NaN
      C
    
    
      828
      829
      1
      3
      McCormack, Mr. Thomas Joseph
      male
      NaN
      0
      0
      367228
      7.7500
      NaN
      Q
    
    
      829
      830
      1
      1
      Stone, Mrs. George Nelson (Martha Evelyn)
      female
      62.00
      0
      0
      113572
      80.0000
      B28
      NaN
    
    
      830
      831
      1
      3
      Yasbeck, Mrs. Antoni (Selini Alexander)
      female
      15.00
      1
      0
      2659
      14.4542
      NaN
      C
    
    
      831
      832
      1
      2
      Richards, Master. George Sibley
      male
      0.83
      1
      1
      29106
      18.7500
      NaN
      S
    
    
      835
      836
      1
      1
      Compton, Miss. Sara Rebecca
      female
      39.00
      1
      1
      PC 17756
      83.1583
      E49
      C
    
    
      838
      839
      1
      3
      Chip, Mr. Chang
      male
      32.00
      0
      0
      1601
      56.4958
      NaN
      S
    
    
      839
      840
      1
      1
      Marechal, Mr. Pierre
      male
      NaN
      0
      0
      11774
      29.7000
      C47
      C
    
    
      842
      843
      1
      1
      Serepeca, Miss. Augusta
      female
      30.00
      0
      0
      113798
      31.0000
      NaN
      C
    
    
      849
      850
      1
      1
      Goldenberg, Mrs. Samuel L (Edwiga Grabowska)
      female
      NaN
      1
      0
      17453
      89.1042
      C92
      C
    
    
      853
      854
      1
      1
      Lines, Miss. Mary Conover
      female
      16.00
      0
      1
      PC 17592
      39.4000
      D28
      S
    
    
      855
      856
      1
      3
      Aks, Mrs. Sam (Leah Rosen)
      female
      18.00
      0
      1
      392091
      9.3500
      NaN
      S
    
    
      856
      857
      1
      1
      Wick, Mrs. George Dennick (Mary Hitchcock)
      female
      45.00
      1
      1
      36928
      164.8667
      NaN
      S
    
    
      857
      858
      1
      1
      Daly, Mr. Peter Denis
      male
      51.00
      0
      0
      113055
      26.5500
      E17
      S
    
    
      858
      859
      1
      3
      Baclini, Mrs. Solomon (Latifa Qurban)
      female
      24.00
      0
      3
      2666
      19.2583
      NaN
      C
    
    
      862
      863
      1
      1
      Swift, Mrs. Frederick Joel (Margaret Welles Ba...
      female
      48.00
      0
      0
      17466
      25.9292
      D17
      S
    
    
      865
      866
      1
      2
      Bystrom, Mrs. (Karolina)
      female
      42.00
      0
      0
      236852
      13.0000
      NaN
      S
    
    
      866
      867
      1
      2
      Duran y More, Miss. Asuncion
      female
      27.00
      1
      0
      SC/PARIS 2149
      13.8583
      NaN
      C
    
    
      869
      870
      1
      3
      Johnson, Master. Harold Theodor
      male
      4.00
      1
      1
      347742
      11.1333
      NaN
      S
    
    
      871
      872
      1
      1
      Beckwith, Mrs. Richard Leonard (Sallie Monypeny)
      female
      47.00
      1
      1
      11751
      52.5542
      D35
      S
    
    
      874
      875
      1
      2
      Abelson, Mrs. Samuel (Hannah Wizosky)
      female
      28.00
      1
      0
      P/PP 3381
      24.0000
      NaN
      C
    
    
      875
      876
      1
      3
      Najib, Miss. Adele Kiamie "Jane"
      female
      15.00
      0
      0
      2667
      7.2250
      NaN
      C
    
    
      879
      880
      1
      1
      Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)
      female
      56.00
      0
      1
      11767
      83.1583
      C50
      C
    
    
      880
      881
      1
      2
      Shelley, Mrs. William (Imanita Parrish Hall)
      female
      25.00
      0
      1
      230433
      26.0000
      NaN
      S
    
    
      887
      888
      1
      1
      Graham, Miss. Margaret Edith
      female
      19.00
      0
      0
      112053
      30.0000
      B42
      S
    
    
      889
      890
      1
      1
      Behr, Mr. Karl Howell
      male
      26.00
      0
      0
      111369
      30.0000
      C148
      C
    
  

342 rows × 12 columns



In [9]:

    
train_df.describe(include=['O'])









    Out[9]:






  
    
      
      Name
      Sex
      Ticket
      Cabin
      Embarked
    
  
  
    
      count
      891
      891
      891
      204
      889
    
    
      unique
      891
      2
      681
      147
      3
    
    
      top
      Graham, Mr. George Edward
      male
      CA. 2343
      C23 C25 C27
      S
    
    
      freq
      1
      577
      7
      4
      644



In [17]:

    
train_df[['Pclass', 'Survived']].groupby('Pclass', as_index=False).mean().sort_values(by='Survived', ascending=False)



In [18]:

    
train_df[['Sex', 'Survived']].groupby('Sex', as_index=False).mean().sort_values(by='Survived', ascending=False)



In [19]:

    
import matplotlib.pyplot as plt



In [20]:

    
%matplotlib inline



In [21]:

    
# data analysis and wrangling
import pandas as pd
import numpy as np
import random as rnd

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

# machine learning
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier



In [28]:

    
g = sns.FacetGrid(train_df, col='Survived')
g.map(plt.hist, 'Age', bins=20)









    Out[28]:





<seaborn.axisgrid.FacetGrid at 0x118182d10>



In [31]:

    
grid = sns.FacetGrid(train_df, col='Survived', row='Pclass', size=2.2, aspect=1.6)
grid.map(plt.hist, 'Age', alpha=.5, bins=20)









    Out[31]:





<seaborn.axisgrid.FacetGrid at 0x1194f05d0>

grid = sns.FacetGrid(train_df, row='Embarked')



In [38]:

    
grid = sns.FacetGrid(train_df, row='Embarked', size=3, aspect=3)
grid.map(sns.pointplot, 'Pclass', 'Survived', 'Sex', palette='deep')
grid.add_legend();



In [41]:

    
grid = sns.FacetGrid(train_df, row='Embarked', col='Survived', size=3, aspect=2)
grid.map(sns.barplot, 'Sex', 'Fare', alpha=.5, ci=None)
grid.add_legend();



In [44]:

    
print('After ', train_df.shape, test_df.shape, combine[0].shape, combine[1].shape)









    



('After ', (891, 10), (418, 9), (891, 10), (418, 9))



In [45]:

    
train_df









    Out[45]:






  
    
      
      PassengerId
      Survived
      Pclass
      Name
      Sex
      Age
      SibSp
      Parch
      Fare
      Embarked
    
  
  
    
      0
      1
      0
      3
      Braund, Mr. Owen Harris
      male
      22.0
      1
      0
      7.2500
      S
    
    
      1
      2
      1
      1
      Cumings, Mrs. John Bradley (Florence Briggs Th...
      female
      38.0
      1
      0
      71.2833
      C
    
    
      2
      3
      1
      3
      Heikkinen, Miss. Laina
      female
      26.0
      0
      0
      7.9250
      S
    
    
      3
      4
      1
      1
      Futrelle, Mrs. Jacques Heath (Lily May Peel)
      female
      35.0
      1
      0
      53.1000
      S
    
    
      4
      5
      0
      3
      Allen, Mr. William Henry
      male
      35.0
      0
      0
      8.0500
      S
    
    
      5
      6
      0
      3
      Moran, Mr. James
      male
      NaN
      0
      0
      8.4583
      Q
    
    
      6
      7
      0
      1
      McCarthy, Mr. Timothy J
      male
      54.0
      0
      0
      51.8625
      S
    
    
      7
      8
      0
      3
      Palsson, Master. Gosta Leonard
      male
      2.0
      3
      1
      21.0750
      S
    
    
      8
      9
      1
      3
      Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)
      female
      27.0
      0
      2
      11.1333
      S
    
    
      9
      10
      1
      2
      Nasser, Mrs. Nicholas (Adele Achem)
      female
      14.0
      1
      0
      30.0708
      C
    
    
      10
      11
      1
      3
      Sandstrom, Miss. Marguerite Rut
      female
      4.0
      1
      1
      16.7000
      S
    
    
      11
      12
      1
      1
      Bonnell, Miss. Elizabeth
      female
      58.0
      0
      0
      26.5500
      S
    
    
      12
      13
      0
      3
      Saundercock, Mr. William Henry
      male
      20.0
      0
      0
      8.0500
      S
    
    
      13
      14
      0
      3
      Andersson, Mr. Anders Johan
      male
      39.0
      1
      5
      31.2750
      S
    
    
      14
      15
      0
      3
      Vestrom, Miss. Hulda Amanda Adolfina
      female
      14.0
      0
      0
      7.8542
      S
    
    
      15
      16
      1
      2
      Hewlett, Mrs. (Mary D Kingcome)
      female
      55.0
      0
      0
      16.0000
      S
    
    
      16
      17
      0
      3
      Rice, Master. Eugene
      male
      2.0
      4
      1
      29.1250
      Q
    
    
      17
      18
      1
      2
      Williams, Mr. Charles Eugene
      male
      NaN
      0
      0
      13.0000
      S
    
    
      18
      19
      0
      3
      Vander Planke, Mrs. Julius (Emelia Maria Vande...
      female
      31.0
      1
      0
      18.0000
      S
    
    
      19
      20
      1
      3
      Masselmani, Mrs. Fatima
      female
      NaN
      0
      0
      7.2250
      C
    
    
      20
      21
      0
      2
      Fynney, Mr. Joseph J
      male
      35.0
      0
      0
      26.0000
      S
    
    
      21
      22
      1
      2
      Beesley, Mr. Lawrence
      male
      34.0
      0
      0
      13.0000
      S
    
    
      22
      23
      1
      3
      McGowan, Miss. Anna "Annie"
      female
      15.0
      0
      0
      8.0292
      Q
    
    
      23
      24
      1
      1
      Sloper, Mr. William Thompson
      male
      28.0
      0
      0
      35.5000
      S
    
    
      24
      25
      0
      3
      Palsson, Miss. Torborg Danira
      female
      8.0
      3
      1
      21.0750
      S
    
    
      25
      26
      1
      3
      Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...
      female
      38.0
      1
      5
      31.3875
      S
    
    
      26
      27
      0
      3
      Emir, Mr. Farred Chehab
      male
      NaN
      0
      0
      7.2250
      C
    
    
      27
      28
      0
      1
      Fortune, Mr. Charles Alexander
      male
      19.0
      3
      2
      263.0000
      S
    
    
      28
      29
      1
      3
      O'Dwyer, Miss. Ellen "Nellie"
      female
      NaN
      0
      0
      7.8792
      Q
    
    
      29
      30
      0
      3
      Todoroff, Mr. Lalio
      male
      NaN
      0
      0
      7.8958
      S
    
    
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    
    
      861
      862
      0
      2
      Giles, Mr. Frederick Edward
      male
      21.0
      1
      0
      11.5000
      S
    
    
      862
      863
      1
      1
      Swift, Mrs. Frederick Joel (Margaret Welles Ba...
      female
      48.0
      0
      0
      25.9292
      S
    
    
      863
      864
      0
      3
      Sage, Miss. Dorothy Edith "Dolly"
      female
      NaN
      8
      2
      69.5500
      S
    
    
      864
      865
      0
      2
      Gill, Mr. John William
      male
      24.0
      0
      0
      13.0000
      S
    
    
      865
      866
      1
      2
      Bystrom, Mrs. (Karolina)
      female
      42.0
      0
      0
      13.0000
      S
    
    
      866
      867
      1
      2
      Duran y More, Miss. Asuncion
      female
      27.0
      1
      0
      13.8583
      C
    
    
      867
      868
      0
      1
      Roebling, Mr. Washington Augustus II
      male
      31.0
      0
      0
      50.4958
      S
    
    
      868
      869
      0
      3
      van Melkebeke, Mr. Philemon
      male
      NaN
      0
      0
      9.5000
      S
    
    
      869
      870
      1
      3
      Johnson, Master. Harold Theodor
      male
      4.0
      1
      1
      11.1333
      S
    
    
      870
      871
      0
      3
      Balkic, Mr. Cerin
      male
      26.0
      0
      0
      7.8958
      S
    
    
      871
      872
      1
      1
      Beckwith, Mrs. Richard Leonard (Sallie Monypeny)
      female
      47.0
      1
      1
      52.5542
      S
    
    
      872
      873
      0
      1
      Carlsson, Mr. Frans Olof
      male
      33.0
      0
      0
      5.0000
      S
    
    
      873
      874
      0
      3
      Vander Cruyssen, Mr. Victor
      male
      47.0
      0
      0
      9.0000
      S
    
    
      874
      875
      1
      2
      Abelson, Mrs. Samuel (Hannah Wizosky)
      female
      28.0
      1
      0
      24.0000
      C
    
    
      875
      876
      1
      3
      Najib, Miss. Adele Kiamie "Jane"
      female
      15.0
      0
      0
      7.2250
      C
    
    
      876
      877
      0
      3
      Gustafsson, Mr. Alfred Ossian
      male
      20.0
      0
      0
      9.8458
      S
    
    
      877
      878
      0
      3
      Petroff, Mr. Nedelio
      male
      19.0
      0
      0
      7.8958
      S
    
    
      878
      879
      0
      3
      Laleff, Mr. Kristo
      male
      NaN
      0
      0
      7.8958
      S
    
    
      879
      880
      1
      1
      Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)
      female
      56.0
      0
      1
      83.1583
      C
    
    
      880
      881
      1
      2
      Shelley, Mrs. William (Imanita Parrish Hall)
      female
      25.0
      0
      1
      26.0000
      S
    
    
      881
      882
      0
      3
      Markun, Mr. Johann
      male
      33.0
      0
      0
      7.8958
      S
    
    
      882
      883
      0
      3
      Dahlberg, Miss. Gerda Ulrika
      female
      22.0
      0
      0
      10.5167
      S
    
    
      883
      884
      0
      2
      Banfield, Mr. Frederick James
      male
      28.0
      0
      0
      10.5000
      S
    
    
      884
      885
      0
      3
      Sutehall, Mr. Henry Jr
      male
      25.0
      0
      0
      7.0500
      S
    
    
      885
      886
      0
      3
      Rice, Mrs. William (Margaret Norton)
      female
      39.0
      0
      5
      29.1250
      Q
    
    
      886
      887
      0
      2
      Montvila, Rev. Juozas
      male
      27.0
      0
      0
      13.0000
      S
    
    
      887
      888
      1
      1
      Graham, Miss. Margaret Edith
      female
      19.0
      0
      0
      30.0000
      S
    
    
      888
      889
      0
      3
      Johnston, Miss. Catherine Helen "Carrie"
      female
      NaN
      1
      2
      23.4500
      S
    
    
      889
      890
      1
      1
      Behr, Mr. Karl Howell
      male
      26.0
      0
      0
      30.0000
      C
    
    
      890
      891
      0
      3
      Dooley, Mr. Patrick
      male
      32.0
      0
      0
      7.7500
      Q
    
  

891 rows × 10 columns



In [71]:

    
for dataset in combine:
    dataset['Title'] = dataset.Name.str.extract(' ([A-Za-z]+)\.', expand=False)

pd.crosstab(train_df['Title'], train_df['Sex'])



In [72]:

    
for dataset in combine:
    dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',
                                                 'Don', 'Dr', 'Major', 'Rev', 'Sir', 
                                                 'Jonkheer', 'Dona'], 'Rare')
    dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')
    dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')
    dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')
    
train_df[['Title', 'Survived']].groupby('Title', as_index=False).mean().sort_values(by='Survived', ascending=False)



In [73]:

    
train_df['Title']









    Out[73]:





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



In [74]:

    
title_mapping = {'Mr':1, 'Miss':2, 'Mrs':3, 'Master':4, 'Rare':5}

for dataset in combine:
    dataset['Title'] = dataset['Title'].map(title_mapping)
    dataset['Title'] = dataset['Title'].fillna(0)
    
train_df.head()









    Out[74]:






  
    
      
      PassengerId
      Survived
      Pclass
      Name
      Sex
      Age
      SibSp
      Parch
      Fare
      Embarked
      Title
    
  
  
    
      0
      1
      0
      3
      Braund, Mr. Owen Harris
      male
      22.0
      1
      0
      7.2500
      S
      1
    
    
      1
      2
      1
      1
      Cumings, Mrs. John Bradley (Florence Briggs Th...
      female
      38.0
      1
      0
      71.2833
      C
      3
    
    
      2
      3
      1
      3
      Heikkinen, Miss. Laina
      female
      26.0
      0
      0
      7.9250
      S
      2
    
    
      3
      4
      1
      1
      Futrelle, Mrs. Jacques Heath (Lily May Peel)
      female
      35.0
      1
      0
      53.1000
      S
      3
    
    
      4
      5
      0
      3
      Allen, Mr. William Henry
      male
      35.0
      0
      0
      8.0500
      S
      1



In [75]:

    
train_df = train_df.drop(['PassengerId', 'Name'], axis=1)
test_df = test_df.drop('Name', axis=1)
combine = [train_df, test_df]
print(train_df.shape, test_df.shape)









    



((891, 9), (418, 9))



In [76]:

    
gender = {'female':1, 'male':0}
for dataset in combine:
    dataset['Sex'] = dataset['Sex'].map(gender).astype(int)
    
train_df.head()



In [ ]:

	Pclass	Survived
0	1	0.629630
1	2	0.472826
2	3	0.242363

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	373450	8.0500	NaN	S

	PassengerId	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	892	3	Kelly, Mr. James	male	34.5	0	0	330911	7.8292	NaN	Q
1	893	3	Wilkes, Mrs. James (Ellen Needs)	female	47.0	1	0	363272	7.0000	NaN	S
2	894	2	Myles, Mr. Thomas Francis	male	62.0	0	0	240276	9.6875	NaN	Q
3	895	3	Wirz, Mr. Albert	male	27.0	0	0	315154	8.6625	NaN	S
4	896	3	Hirvonen, Mrs. Alexander (Helga E Lindqvist)	female	22.0	1	1	3101298	12.2875	NaN	S

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare
count	891.000000	891.000000	891.000000	714.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	29.699118	0.523008	0.381594	32.204208
std	257.353842	0.486592	0.836071	14.526497	1.102743	0.806057	49.693429
min	1.000000	0.000000	1.000000	0.420000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	20.125000	0.000000	0.000000	7.910400
50%	446.000000	0.000000	3.000000	28.000000	0.000000	0.000000	14.454200
75%	668.500000	1.000000	3.000000	38.000000	1.000000	0.000000	31.000000
max	891.000000	1.000000	3.000000	80.000000	8.000000	6.000000	512.329200

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.00	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.00	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.00	1	0	113803	53.1000	C123	S
8	9	1	3	Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)	female	27.00	0	2	347742	11.1333	NaN	S
9	10	1	2	Nasser, Mrs. Nicholas (Adele Achem)	female	14.00	1	0	237736	30.0708	NaN	C
10	11	1	3	Sandstrom, Miss. Marguerite Rut	female	4.00	1	1	PP 9549	16.7000	G6	S
11	12	1	1	Bonnell, Miss. Elizabeth	female	58.00	0	0	113783	26.5500	C103	S
15	16	1	2	Hewlett, Mrs. (Mary D Kingcome)	female	55.00	0	0	248706	16.0000	NaN	S
17	18	1	2	Williams, Mr. Charles Eugene	male	NaN	0	0	244373	13.0000	NaN	S
19	20	1	3	Masselmani, Mrs. Fatima	female	NaN	0	0	2649	7.2250	NaN	C
21	22	1	2	Beesley, Mr. Lawrence	male	34.00	0	0	248698	13.0000	D56	S
22	23	1	3	McGowan, Miss. Anna "Annie"	female	15.00	0	0	330923	8.0292	NaN	Q
23	24	1	1	Sloper, Mr. William Thompson	male	28.00	0	0	113788	35.5000	A6	S
25	26	1	3	Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...	female	38.00	1	5	347077	31.3875	NaN	S
28	29	1	3	O'Dwyer, Miss. Ellen "Nellie"	female	NaN	0	0	330959	7.8792	NaN	Q
31	32	1	1	Spencer, Mrs. William Augustus (Marie Eugenie)	female	NaN	1	0	PC 17569	146.5208	B78	C
32	33	1	3	Glynn, Miss. Mary Agatha	female	NaN	0	0	335677	7.7500	NaN	Q
36	37	1	3	Mamee, Mr. Hanna	male	NaN	0	0	2677	7.2292	NaN	C
39	40	1	3	Nicola-Yarred, Miss. Jamila	female	14.00	1	0	2651	11.2417	NaN	C
43	44	1	2	Laroche, Miss. Simonne Marie Anne Andree	female	3.00	1	2	SC/Paris 2123	41.5792	NaN	C
44	45	1	3	Devaney, Miss. Margaret Delia	female	19.00	0	0	330958	7.8792	NaN	Q
47	48	1	3	O'Driscoll, Miss. Bridget	female	NaN	0	0	14311	7.7500	NaN	Q
52	53	1	1	Harper, Mrs. Henry Sleeper (Myna Haxtun)	female	49.00	1	0	PC 17572	76.7292	D33	C
53	54	1	2	Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkin...	female	29.00	1	0	2926	26.0000	NaN	S
55	56	1	1	Woolner, Mr. Hugh	male	NaN	0	0	19947	35.5000	C52	S
56	57	1	2	Rugg, Miss. Emily	female	21.00	0	0	C.A. 31026	10.5000	NaN	S
58	59	1	2	West, Miss. Constance Mirium	female	5.00	1	2	C.A. 34651	27.7500	NaN	S
61	62	1	1	Icard, Miss. Amelie	female	38.00	0	0	113572	80.0000	B28	NaN
65	66	1	3	Moubarek, Master. Gerios	male	NaN	1	1	2661	15.2458	NaN	C
66	67	1	2	Nye, Mrs. (Elizabeth Ramell)	female	29.00	0	0	C.A. 29395	10.5000	F33	S
...	...	...	...	...	...	...	...	...	...	...	...	...
809	810	1	1	Chambers, Mrs. Norman Campbell (Bertha Griggs)	female	33.00	1	0	113806	53.1000	E8	S
820	821	1	1	Hays, Mrs. Charles Melville (Clara Jennings Gr...	female	52.00	1	1	12749	93.5000	B69	S
821	822	1	3	Lulic, Mr. Nikola	male	27.00	0	0	315098	8.6625	NaN	S
823	824	1	3	Moor, Mrs. (Beila)	female	27.00	0	1	392096	12.4750	E121	S
827	828	1	2	Mallet, Master. Andre	male	1.00	0	2	S.C./PARIS 2079	37.0042	NaN	C
828	829	1	3	McCormack, Mr. Thomas Joseph	male	NaN	0	0	367228	7.7500	NaN	Q
829	830	1	1	Stone, Mrs. George Nelson (Martha Evelyn)	female	62.00	0	0	113572	80.0000	B28	NaN
830	831	1	3	Yasbeck, Mrs. Antoni (Selini Alexander)	female	15.00	1	0	2659	14.4542	NaN	C
831	832	1	2	Richards, Master. George Sibley	male	0.83	1	1	29106	18.7500	NaN	S
835	836	1	1	Compton, Miss. Sara Rebecca	female	39.00	1	1	PC 17756	83.1583	E49	C
838	839	1	3	Chip, Mr. Chang	male	32.00	0	0	1601	56.4958	NaN	S
839	840	1	1	Marechal, Mr. Pierre	male	NaN	0	0	11774	29.7000	C47	C
842	843	1	1	Serepeca, Miss. Augusta	female	30.00	0	0	113798	31.0000	NaN	C
849	850	1	1	Goldenberg, Mrs. Samuel L (Edwiga Grabowska)	female	NaN	1	0	17453	89.1042	C92	C
853	854	1	1	Lines, Miss. Mary Conover	female	16.00	0	1	PC 17592	39.4000	D28	S
855	856	1	3	Aks, Mrs. Sam (Leah Rosen)	female	18.00	0	1	392091	9.3500	NaN	S
856	857	1	1	Wick, Mrs. George Dennick (Mary Hitchcock)	female	45.00	1	1	36928	164.8667	NaN	S
857	858	1	1	Daly, Mr. Peter Denis	male	51.00	0	0	113055	26.5500	E17	S
858	859	1	3	Baclini, Mrs. Solomon (Latifa Qurban)	female	24.00	0	3	2666	19.2583	NaN	C
862	863	1	1	Swift, Mrs. Frederick Joel (Margaret Welles Ba...	female	48.00	0	0	17466	25.9292	D17	S
865	866	1	2	Bystrom, Mrs. (Karolina)	female	42.00	0	0	236852	13.0000	NaN	S
866	867	1	2	Duran y More, Miss. Asuncion	female	27.00	1	0	SC/PARIS 2149	13.8583	NaN	C
869	870	1	3	Johnson, Master. Harold Theodor	male	4.00	1	1	347742	11.1333	NaN	S
871	872	1	1	Beckwith, Mrs. Richard Leonard (Sallie Monypeny)	female	47.00	1	1	11751	52.5542	D35	S
874	875	1	2	Abelson, Mrs. Samuel (Hannah Wizosky)	female	28.00	1	0	P/PP 3381	24.0000	NaN	C
875	876	1	3	Najib, Miss. Adele Kiamie "Jane"	female	15.00	0	0	2667	7.2250	NaN	C
879	880	1	1	Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)	female	56.00	0	1	11767	83.1583	C50	C
880	881	1	2	Shelley, Mrs. William (Imanita Parrish Hall)	female	25.00	0	1	230433	26.0000	NaN	S
887	888	1	1	Graham, Miss. Margaret Edith	female	19.00	0	0	112053	30.0000	B42	S
889	890	1	1	Behr, Mr. Karl Howell	male	26.00	0	0	111369	30.0000	C148	C

	Name	Sex	Ticket	Cabin	Embarked
count	891	891	891	204	889
unique	891	2	681	147	3
top	Graham, Mr. George Edward	male	CA. 2343	C23 C25 C27	S
freq	1	577	7	4	644

Sex	female	male
Title
Capt	0	1
Col	0	2
Countess	1	0
Don	0	1
Dr	1	6
Jonkheer	0	1
Lady	1	0
Major	0	2
Master	0	40
Miss	182	0
Mlle	2	0
Mme	1	0
Mr	0	517
Mrs	125	0
Ms	1	0
Rev	0	6
Sir	0	1

	Title	Survived
3	Mrs	0.793651
1	Miss	0.702703
0	Master	0.575000
4	Rare	0.347826
2	Mr	0.156673