Garimpagem de Dados

Aula 4 - Exercídio de Classificação com kNN

13/10/2017

Equipe:

Sayonara Santos Araújo
Lailson Azevedo do Rego

Resolução



In [2]:

    
import numpy as np
from sklearn import datasets
from sklearn.neighbors import DistanceMetric
from collections import Counter
from operator import itemgetter



In [3]:

    
class KNNClassifier(object):
    def __init__(self):
        self.train_data = None
        self.train_labels = None
    
    #Recebe os dados de treino
    def fit(self, train_d, train_l):
        self.train_data = train_d
        self.train_labels = train_l
    
    ##1. (Atualizada) função que mede a distância euclidiana 
    def euc_distance(self, a, b):
        dist = DistanceMetric.get_metric('euclidean')
        return dist.pairwise([a], [b]) #np.linalg.norm(a-b)

    ##2. Função que seleciona os k vizinhos mais próximos (k > 1)
    def get_neighbors(self, k, test_instance):
        distances = []
        for i in range(len(self.train_data)):
            dist = self.euc_distance(test_instance, self.train_data[i])
            distances.append((self.train_data[i], dist, self.train_labels[i]))
        distances.sort(key=itemgetter(1))
        neighbors = distances[:k]
        #print('Instancia testada: ',test_instance,'\nVizinhos: ',neighbors,'\n')
        return neighbors
    
    ##3.Função que recebe os k vizinhos mais próximos e determina a classe correta    
    def vote(self, neighbors):
        class_counter = Counter()
        for neighbor in neighbors:
            class_counter[neighbor[2]] += 1
        return class_counter.most_common(1)[0][0]
    
    def predict(self, k, test_data):
        votes = []
        for i in range(len(test_data)):
            neighbors = self.get_neighbors(k, test_data[i])
            v = self.vote(neighbors)
            votes.append(v)
        return votes



In [4]:

    
#Carrega o dataset
import pandas as pd
dataset = pd.read_csv('train_sayonara.csv')
dataset









    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
    
    
      5
      6
      0
      3
      Moran, Mr. James
      male
      NaN
      0
      0
      330877
      8.4583
      NaN
      Q
    
    
      6
      7
      0
      1
      McCarthy, Mr. Timothy J
      male
      54.0
      0
      0
      17463
      51.8625
      E46
      S
    
    
      7
      8
      0
      3
      Palsson, Master. Gosta Leonard
      male
      2.0
      3
      1
      349909
      21.0750
      NaN
      S
    
    
      8
      9
      1
      3
      Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)
      female
      27.0
      0
      2
      347742
      11.1333
      NaN
      S
    
    
      9
      10
      1
      2
      Nasser, Mrs. Nicholas (Adele Achem)
      female
      14.0
      1
      0
      237736
      30.0708
      NaN
      C
    
    
      10
      11
      1
      3
      Sandstrom, Miss. Marguerite Rut
      female
      4.0
      1
      1
      PP 9549
      16.7000
      G6
      S
    
    
      11
      12
      1
      1
      Bonnell, Miss. Elizabeth
      female
      58.0
      0
      0
      113783
      26.5500
      C103
      S
    
    
      12
      13
      0
      3
      Saundercock, Mr. William Henry
      male
      20.0
      0
      0
      A/5. 2151
      8.0500
      NaN
      S
    
    
      13
      14
      0
      3
      Andersson, Mr. Anders Johan
      male
      39.0
      1
      5
      347082
      31.2750
      NaN
      S
    
    
      14
      15
      0
      3
      Vestrom, Miss. Hulda Amanda Adolfina
      female
      14.0
      0
      0
      350406
      7.8542
      NaN
      S
    
    
      15
      16
      1
      2
      Hewlett, Mrs. (Mary D Kingcome)
      female
      55.0
      0
      0
      248706
      16.0000
      NaN
      S
    
    
      16
      17
      0
      3
      Rice, Master. Eugene
      male
      2.0
      4
      1
      382652
      29.1250
      NaN
      Q
    
    
      17
      18
      1
      2
      Williams, Mr. Charles Eugene
      male
      NaN
      0
      0
      244373
      13.0000
      NaN
      S
    
    
      18
      19
      0
      3
      Vander Planke, Mrs. Julius (Emelia Maria Vande...
      female
      31.0
      1
      0
      345763
      18.0000
      NaN
      S
    
    
      19
      20
      1
      3
      Masselmani, Mrs. Fatima
      female
      NaN
      0
      0
      2649
      7.2250
      NaN
      C
    
    
      20
      21
      0
      2
      Fynney, Mr. Joseph J
      male
      35.0
      0
      0
      239865
      26.0000
      NaN
      S
    
    
      21
      22
      1
      2
      Beesley, Mr. Lawrence
      male
      34.0
      0
      0
      248698
      13.0000
      D56
      S
    
    
      22
      23
      1
      3
      McGowan, Miss. Anna "Annie"
      female
      15.0
      0
      0
      330923
      8.0292
      NaN
      Q
    
    
      23
      24
      1
      1
      Sloper, Mr. William Thompson
      male
      28.0
      0
      0
      113788
      35.5000
      A6
      S
    
    
      24
      25
      0
      3
      Palsson, Miss. Torborg Danira
      female
      8.0
      3
      1
      349909
      21.0750
      NaN
      S
    
    
      25
      26
      1
      3
      Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...
      female
      38.0
      1
      5
      347077
      31.3875
      NaN
      S
    
    
      26
      27
      0
      3
      Emir, Mr. Farred Chehab
      male
      NaN
      0
      0
      2631
      7.2250
      NaN
      C
    
    
      27
      28
      0
      1
      Fortune, Mr. Charles Alexander
      male
      19.0
      3
      2
      19950
      263.0000
      C23 C25 C27
      S
    
    
      28
      29
      1
      3
      O'Dwyer, Miss. Ellen "Nellie"
      female
      NaN
      0
      0
      330959
      7.8792
      NaN
      Q
    
    
      29
      30
      0
      3
      Todoroff, Mr. Lalio
      male
      NaN
      0
      0
      349216
      7.8958
      NaN
      S
    
    
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    
    
      861
      862
      0
      2
      Giles, Mr. Frederick Edward
      male
      21.0
      1
      0
      28134
      11.5000
      NaN
      S
    
    
      862
      863
      1
      1
      Swift, Mrs. Frederick Joel (Margaret Welles Ba...
      female
      48.0
      0
      0
      17466
      25.9292
      D17
      S
    
    
      863
      864
      0
      3
      Sage, Miss. Dorothy Edith "Dolly"
      female
      NaN
      8
      2
      CA. 2343
      69.5500
      NaN
      S
    
    
      864
      865
      0
      2
      Gill, Mr. John William
      male
      24.0
      0
      0
      233866
      13.0000
      NaN
      S
    
    
      865
      866
      1
      2
      Bystrom, Mrs. (Karolina)
      female
      42.0
      0
      0
      236852
      13.0000
      NaN
      S
    
    
      866
      867
      1
      2
      Duran y More, Miss. Asuncion
      female
      27.0
      1
      0
      SC/PARIS 2149
      13.8583
      NaN
      C
    
    
      867
      868
      0
      1
      Roebling, Mr. Washington Augustus II
      male
      31.0
      0
      0
      PC 17590
      50.4958
      A24
      S
    
    
      868
      869
      0
      3
      van Melkebeke, Mr. Philemon
      male
      NaN
      0
      0
      345777
      9.5000
      NaN
      S
    
    
      869
      870
      1
      3
      Johnson, Master. Harold Theodor
      male
      4.0
      1
      1
      347742
      11.1333
      NaN
      S
    
    
      870
      871
      0
      3
      Balkic, Mr. Cerin
      male
      26.0
      0
      0
      349248
      7.8958
      NaN
      S
    
    
      871
      872
      1
      1
      Beckwith, Mrs. Richard Leonard (Sallie Monypeny)
      female
      47.0
      1
      1
      11751
      52.5542
      D35
      S
    
    
      872
      873
      0
      1
      Carlsson, Mr. Frans Olof
      male
      33.0
      0
      0
      695
      5.0000
      B51 B53 B55
      S
    
    
      873
      874
      0
      3
      Vander Cruyssen, Mr. Victor
      male
      47.0
      0
      0
      345765
      9.0000
      NaN
      S
    
    
      874
      875
      1
      2
      Abelson, Mrs. Samuel (Hannah Wizosky)
      female
      28.0
      1
      0
      P/PP 3381
      24.0000
      NaN
      C
    
    
      875
      876
      1
      3
      Najib, Miss. Adele Kiamie "Jane"
      female
      15.0
      0
      0
      2667
      7.2250
      NaN
      C
    
    
      876
      877
      0
      3
      Gustafsson, Mr. Alfred Ossian
      male
      20.0
      0
      0
      7534
      9.8458
      NaN
      S
    
    
      877
      878
      0
      3
      Petroff, Mr. Nedelio
      male
      19.0
      0
      0
      349212
      7.8958
      NaN
      S
    
    
      878
      879
      0
      3
      Laleff, Mr. Kristo
      male
      NaN
      0
      0
      349217
      7.8958
      NaN
      S
    
    
      879
      880
      1
      1
      Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)
      female
      56.0
      0
      1
      11767
      83.1583
      C50
      C
    
    
      880
      881
      1
      2
      Shelley, Mrs. William (Imanita Parrish Hall)
      female
      25.0
      0
      1
      230433
      26.0000
      NaN
      S
    
    
      881
      882
      0
      3
      Markun, Mr. Johann
      male
      33.0
      0
      0
      349257
      7.8958
      NaN
      S
    
    
      882
      883
      0
      3
      Dahlberg, Miss. Gerda Ulrika
      female
      22.0
      0
      0
      7552
      10.5167
      NaN
      S
    
    
      883
      884
      0
      2
      Banfield, Mr. Frederick James
      male
      28.0
      0
      0
      C.A./SOTON 34068
      10.5000
      NaN
      S
    
    
      884
      885
      0
      3
      Sutehall, Mr. Henry Jr
      male
      25.0
      0
      0
      SOTON/OQ 392076
      7.0500
      NaN
      S
    
    
      885
      886
      0
      3
      Rice, Mrs. William (Margaret Norton)
      female
      39.0
      0
      5
      382652
      29.1250
      NaN
      Q
    
    
      886
      887
      0
      2
      Montvila, Rev. Juozas
      male
      27.0
      0
      0
      211536
      13.0000
      NaN
      S
    
    
      887
      888
      1
      1
      Graham, Miss. Margaret Edith
      female
      19.0
      0
      0
      112053
      30.0000
      B42
      S
    
    
      888
      889
      0
      3
      Johnston, Miss. Catherine Helen "Carrie"
      female
      NaN
      1
      2
      W./C. 6607
      23.4500
      NaN
      S
    
    
      889
      890
      1
      1
      Behr, Mr. Karl Howell
      male
      26.0
      0
      0
      111369
      30.0000
      C148
      C
    
    
      890
      891
      0
      3
      Dooley, Mr. Patrick
      male
      32.0
      0
      0
      370376
      7.7500
      NaN
      Q
    
  

891 rows × 12 columns



In [9]:

    
#Dados faltantes em Age e Cabin
# Então, na idades faltantes, atribui a média das idades
dataset.Age = dataset.Age.fillna(dataset.Age.mean())

# Nos dados das cabines faltantes, subistitui por SC   (Remover ou preencher?)
#dataset = dataset.dropna(axis=0, how="any")
dataset.Cabin = dataset.Cabin.fillna('SC')



In [10]:

    
##4. Transforma dados categóricos em numéricos (?)
cate = ['Name','Sex','SibSp','Parch','Ticket','Fare','Cabin','Embarked']
datasetc=dataset
for c in cate:
    datasetc[c] = dataset[c].astype('category')
    datasetc[c] = datasetc[c].cat.codes
#dataset.dtypes
datasetc









    Out[10]:







  
    
      
      PassengerId
      Survived
      Pclass
      Name
      Sex
      Age
      SibSp
      Parch
      Ticket
      Fare
      Cabin
      Embarked
    
  
  
    
      0
      1
      0
      3
      108
      1
      22.000000
      1
      0
      523
      18
      146
      2
    
    
      1
      2
      1
      1
      190
      0
      38.000000
      1
      0
      596
      207
      81
      0
    
    
      2
      3
      1
      3
      353
      0
      26.000000
      0
      0
      669
      41
      146
      2
    
    
      3
      4
      1
      1
      272
      0
      35.000000
      1
      0
      49
      189
      55
      2
    
    
      4
      5
      0
      3
      15
      1
      35.000000
      0
      0
      472
      43
      146
      2
    
    
      5
      6
      0
      3
      554
      1
      29.699118
      0
      0
      275
      51
      146
      1
    
    
      6
      7
      0
      1
      515
      1
      54.000000
      0
      0
      85
      186
      129
      2
    
    
      7
      8
      0
      3
      624
      1
      2.000000
      3
      1
      395
      124
      146
      2
    
    
      8
      9
      1
      3
      412
      0
      27.000000
      0
      2
      344
      74
      146
      2
    
    
      9
      10
      1
      2
      576
      0
      14.000000
      1
      0
      132
      154
      146
      0
    
    
      10
      11
      1
      3
      727
      0
      4.000000
      1
      1
      616
      110
      145
      2
    
    
      11
      12
      1
      1
      95
      0
      58.000000
      0
      0
      38
      143
      49
      2
    
    
      12
      13
      0
      3
      729
      1
      20.000000
      0
      0
      535
      43
      146
      2
    
    
      13
      14
      0
      3
      28
      1
      39.000000
      1
      5
      333
      158
      146
      2
    
    
      14
      15
      0
      3
      840
      0
      14.000000
      0
      0
      413
      36
      146
      2
    
    
      15
      16
      1
      2
      359
      0
      55.000000
      0
      0
      153
      108
      146
      2
    
    
      16
      17
      0
      3
      682
      1
      2.000000
      4
      1
      480
      151
      146
      1
    
    
      17
      18
      1
      2
      867
      1
      29.699118
      0
      0
      151
      85
      146
      2
    
    
      18
      19
      0
      3
      839
      0
      31.000000
      1
      0
      301
      113
      146
      2
    
    
      19
      20
      1
      3
      512
      0
      29.699118
      0
      0
      184
      16
      146
      0
    
    
      20
      21
      0
      2
      273
      1
      35.000000
      0
      0
      139
      138
      146
      2
    
    
      21
      22
      1
      2
      80
      1
      34.000000
      0
      0
      152
      85
      111
      2
    
    
      22
      23
      1
      3
      523
      0
      15.000000
      0
      0
      278
      42
      146
      1
    
    
      23
      24
      1
      1
      765
      1
      28.000000
      0
      0
      42
      168
      13
      2
    
    
      24
      25
      0
      3
      626
      0
      8.000000
      3
      1
      395
      124
      146
      2
    
    
      25
      26
      1
      3
      44
      0
      38.000000
      1
      5
      329
      159
      146
      2
    
    
      26
      27
      0
      3
      240
      1
      29.699118
      0
      0
      179
      16
      146
      0
    
    
      27
      28
      0
      1
      260
      1
      19.000000
      3
      2
      95
      246
      63
      2
    
    
      28
      29
      1
      3
      605
      0
      29.699118
      0
      0
      283
      38
      146
      1
    
    
      29
      30
      0
      3
      813
      1
      29.699118
      0
      0
      362
      40
      146
      2
    
    
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    
    
      861
      862
      0
      2
      283
      1
      21.000000
      1
      0
      221
      76
      146
      2
    
    
      862
      863
      1
      1
      797
      0
      48.000000
      0
      0
      88
      137
      94
      2
    
    
      863
      864
      0
      3
      718
      0
      29.699118
      6
      2
      568
      205
      146
      2
    
    
      864
      865
      0
      2
      285
      1
      24.000000
      0
      0
      120
      85
      146
      2
    
    
      865
      866
      1
      2
      122
      0
      42.000000
      0
      0
      126
      85
      146
      2
    
    
      866
      867
      1
      2
      230
      0
      27.000000
      1
      0
      632
      89
      146
      0
    
    
      867
      868
      0
      1
      696
      1
      31.000000
      0
      0
      590
      184
      6
      2
    
    
      868
      869
      0
      3
      890
      1
      29.699118
      0
      0
      309
      64
      146
      2
    
    
      869
      870
      1
      3
      407
      1
      4.000000
      1
      1
      344
      74
      146
      2
    
    
      870
      871
      0
      3
      59
      1
      26.000000
      0
      0
      387
      40
      146
      2
    
    
      871
      872
      1
      1
      79
      0
      47.000000
      1
      1
      54
      188
      102
      2
    
    
      872
      873
      0
      1
      139
      1
      33.000000
      0
      0
      502
      2
      34
      2
    
    
      873
      874
      0
      3
      836
      1
      47.000000
      0
      0
      303
      58
      146
      2
    
    
      874
      875
      1
      2
      4
      0
      28.000000
      1
      0
      575
      132
      146
      0
    
    
      875
      876
      1
      3
      571
      0
      15.000000
      0
      0
      195
      16
      146
      0
    
    
      876
      877
      0
      3
      311
      1
      20.000000
      0
      0
      504
      69
      146
      2
    
    
      877
      878
      0
      3
      657
      1
      19.000000
      0
      0
      358
      40
      146
      2
    
    
      878
      879
      0
      3
      451
      1
      29.699118
      0
      0
      363
      40
      146
      2
    
    
      879
      880
      1
      1
      668
      0
      56.000000
      0
      1
      59
      221
      70
      0
    
    
      880
      881
      1
      2
      739
      0
      25.000000
      0
      1
      115
      138
      146
      2
    
    
      881
      882
      0
      3
      510
      1
      33.000000
      0
      0
      394
      40
      146
      2
    
    
      882
      883
      0
      3
      193
      0
      22.000000
      0
      0
      508
      73
      146
      2
    
    
      883
      884
      0
      2
      61
      1
      28.000000
      0
      0
      565
      72
      146
      2
    
    
      884
      885
      0
      3
      793
      1
      25.000000
      0
      0
      650
      12
      146
      2
    
    
      885
      886
      0
      3
      684
      0
      39.000000
      0
      5
      480
      151
      146
      1
    
    
      886
      887
      0
      2
      548
      1
      27.000000
      0
      0
      101
      85
      146
      2
    
    
      887
      888
      1
      1
      303
      0
      19.000000
      0
      0
      14
      153
      30
      2
    
    
      888
      889
      0
      3
      413
      0
      29.699118
      1
      2
      675
      131
      146
      2
    
    
      889
      890
      1
      1
      81
      1
      26.000000
      0
      0
      8
      153
      60
      0
    
    
      890
      891
      0
      3
      220
      1
      32.000000
      0
      0
      466
      30
      146
      1
    
  

891 rows × 12 columns



In [11]:

    
##5. Normaliza os atributos numéricos
from sklearn import preprocessing
min_max_scaler = preprocessing.MinMaxScaler()
dataset_scaled = min_max_scaler.fit_transform(dataset)
datasetn = pd.DataFrame(dataset_scaled)
datasetn.columns = ['PassengerId','Survived','Pclass','Name','Sex','Age','SibSp','Parch','Ticket','Fare','Cabin','Embarked']
datasetn









    Out[11]:







  
    
      
      PassengerId
      Survived
      Pclass
      Name
      Sex
      Age
      SibSp
      Parch
      Ticket
      Fare
      Cabin
      Embarked
    
  
  
    
      0
      0.000000
      0.0
      1.0
      0.121348
      1.0
      0.271174
      0.166667
      0.000000
      0.769118
      0.072874
      0.993197
      1.000000
    
    
      1
      0.001124
      1.0
      0.0
      0.213483
      0.0
      0.472229
      0.166667
      0.000000
      0.876471
      0.838057
      0.551020
      0.333333
    
    
      2
      0.002247
      1.0
      1.0
      0.396629
      0.0
      0.321438
      0.000000
      0.000000
      0.983824
      0.165992
      0.993197
      1.000000
    
    
      3
      0.003371
      1.0
      0.0
      0.305618
      0.0
      0.434531
      0.166667
      0.000000
      0.072059
      0.765182
      0.374150
      1.000000
    
    
      4
      0.004494
      0.0
      1.0
      0.016854
      1.0
      0.434531
      0.000000
      0.000000
      0.694118
      0.174089
      0.993197
      1.000000
    
    
      5
      0.005618
      0.0
      1.0
      0.622472
      1.0
      0.367921
      0.000000
      0.000000
      0.404412
      0.206478
      0.993197
      0.666667
    
    
      6
      0.006742
      0.0
      0.0
      0.578652
      1.0
      0.673285
      0.000000
      0.000000
      0.125000
      0.753036
      0.877551
      1.000000
    
    
      7
      0.007865
      0.0
      1.0
      0.701124
      1.0
      0.019854
      0.500000
      0.166667
      0.580882
      0.502024
      0.993197
      1.000000
    
    
      8
      0.008989
      1.0
      1.0
      0.462921
      0.0
      0.334004
      0.000000
      0.333333
      0.505882
      0.299595
      0.993197
      1.000000
    
    
      9
      0.010112
      1.0
      0.5
      0.647191
      0.0
      0.170646
      0.166667
      0.000000
      0.194118
      0.623482
      0.993197
      0.333333
    
    
      10
      0.011236
      1.0
      1.0
      0.816854
      0.0
      0.044986
      0.166667
      0.166667
      0.905882
      0.445344
      0.986395
      1.000000
    
    
      11
      0.012360
      1.0
      0.0
      0.106742
      0.0
      0.723549
      0.000000
      0.000000
      0.055882
      0.578947
      0.333333
      1.000000
    
    
      12
      0.013483
      0.0
      1.0
      0.819101
      1.0
      0.246042
      0.000000
      0.000000
      0.786765
      0.174089
      0.993197
      1.000000
    
    
      13
      0.014607
      0.0
      1.0
      0.031461
      1.0
      0.484795
      0.166667
      0.833333
      0.489706
      0.639676
      0.993197
      1.000000
    
    
      14
      0.015730
      0.0
      1.0
      0.943820
      0.0
      0.170646
      0.000000
      0.000000
      0.607353
      0.145749
      0.993197
      1.000000
    
    
      15
      0.016854
      1.0
      0.5
      0.403371
      0.0
      0.685851
      0.000000
      0.000000
      0.225000
      0.437247
      0.993197
      1.000000
    
    
      16
      0.017978
      0.0
      1.0
      0.766292
      1.0
      0.019854
      0.666667
      0.166667
      0.705882
      0.611336
      0.993197
      0.666667
    
    
      17
      0.019101
      1.0
      0.5
      0.974157
      1.0
      0.367921
      0.000000
      0.000000
      0.222059
      0.344130
      0.993197
      1.000000
    
    
      18
      0.020225
      0.0
      1.0
      0.942697
      0.0
      0.384267
      0.166667
      0.000000
      0.442647
      0.457490
      0.993197
      1.000000
    
    
      19
      0.021348
      1.0
      1.0
      0.575281
      0.0
      0.367921
      0.000000
      0.000000
      0.270588
      0.064777
      0.993197
      0.333333
    
    
      20
      0.022472
      0.0
      0.5
      0.306742
      1.0
      0.434531
      0.000000
      0.000000
      0.204412
      0.558704
      0.993197
      1.000000
    
    
      21
      0.023596
      1.0
      0.5
      0.089888
      1.0
      0.421965
      0.000000
      0.000000
      0.223529
      0.344130
      0.755102
      1.000000
    
    
      22
      0.024719
      1.0
      1.0
      0.587640
      0.0
      0.183212
      0.000000
      0.000000
      0.408824
      0.170040
      0.993197
      0.666667
    
    
      23
      0.025843
      1.0
      0.0
      0.859551
      1.0
      0.346569
      0.000000
      0.000000
      0.061765
      0.680162
      0.088435
      1.000000
    
    
      24
      0.026966
      0.0
      1.0
      0.703371
      0.0
      0.095250
      0.500000
      0.166667
      0.580882
      0.502024
      0.993197
      1.000000
    
    
      25
      0.028090
      1.0
      1.0
      0.049438
      0.0
      0.472229
      0.166667
      0.833333
      0.483824
      0.643725
      0.993197
      1.000000
    
    
      26
      0.029213
      0.0
      1.0
      0.269663
      1.0
      0.367921
      0.000000
      0.000000
      0.263235
      0.064777
      0.993197
      0.333333
    
    
      27
      0.030337
      0.0
      0.0
      0.292135
      1.0
      0.233476
      0.500000
      0.333333
      0.139706
      0.995951
      0.428571
      1.000000
    
    
      28
      0.031461
      1.0
      1.0
      0.679775
      0.0
      0.367921
      0.000000
      0.000000
      0.416176
      0.153846
      0.993197
      0.666667
    
    
      29
      0.032584
      0.0
      1.0
      0.913483
      1.0
      0.367921
      0.000000
      0.000000
      0.532353
      0.161943
      0.993197
      1.000000
    
    
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    
    
      861
      0.967416
      0.0
      0.5
      0.317978
      1.0
      0.258608
      0.166667
      0.000000
      0.325000
      0.307692
      0.993197
      1.000000
    
    
      862
      0.968539
      1.0
      0.0
      0.895506
      0.0
      0.597889
      0.000000
      0.000000
      0.129412
      0.554656
      0.639456
      1.000000
    
    
      863
      0.969663
      0.0
      1.0
      0.806742
      0.0
      0.367921
      1.000000
      0.333333
      0.835294
      0.829960
      0.993197
      1.000000
    
    
      864
      0.970787
      0.0
      0.5
      0.320225
      1.0
      0.296306
      0.000000
      0.000000
      0.176471
      0.344130
      0.993197
      1.000000
    
    
      865
      0.971910
      1.0
      0.5
      0.137079
      0.0
      0.522493
      0.000000
      0.000000
      0.185294
      0.344130
      0.993197
      1.000000
    
    
      866
      0.973034
      1.0
      0.5
      0.258427
      0.0
      0.334004
      0.166667
      0.000000
      0.929412
      0.360324
      0.993197
      0.333333
    
    
      867
      0.974157
      0.0
      0.0
      0.782022
      1.0
      0.384267
      0.000000
      0.000000
      0.867647
      0.744939
      0.040816
      1.000000
    
    
      868
      0.975281
      0.0
      1.0
      1.000000
      1.0
      0.367921
      0.000000
      0.000000
      0.454412
      0.259109
      0.993197
      1.000000
    
    
      869
      0.976404
      1.0
      1.0
      0.457303
      1.0
      0.044986
      0.166667
      0.166667
      0.505882
      0.299595
      0.993197
      1.000000
    
    
      870
      0.977528
      0.0
      1.0
      0.066292
      1.0
      0.321438
      0.000000
      0.000000
      0.569118
      0.161943
      0.993197
      1.000000
    
    
      871
      0.978652
      1.0
      0.0
      0.088764
      0.0
      0.585323
      0.166667
      0.166667
      0.079412
      0.761134
      0.693878
      1.000000
    
    
      872
      0.979775
      0.0
      0.0
      0.156180
      1.0
      0.409399
      0.000000
      0.000000
      0.738235
      0.008097
      0.231293
      1.000000
    
    
      873
      0.980899
      0.0
      1.0
      0.939326
      1.0
      0.585323
      0.000000
      0.000000
      0.445588
      0.234818
      0.993197
      1.000000
    
    
      874
      0.982022
      1.0
      0.5
      0.004494
      0.0
      0.346569
      0.166667
      0.000000
      0.845588
      0.534413
      0.993197
      0.333333
    
    
      875
      0.983146
      1.0
      1.0
      0.641573
      0.0
      0.183212
      0.000000
      0.000000
      0.286765
      0.064777
      0.993197
      0.333333
    
    
      876
      0.984270
      0.0
      1.0
      0.349438
      1.0
      0.246042
      0.000000
      0.000000
      0.741176
      0.279352
      0.993197
      1.000000
    
    
      877
      0.985393
      0.0
      1.0
      0.738202
      1.0
      0.233476
      0.000000
      0.000000
      0.526471
      0.161943
      0.993197
      1.000000
    
    
      878
      0.986517
      0.0
      1.0
      0.506742
      1.0
      0.367921
      0.000000
      0.000000
      0.533824
      0.161943
      0.993197
      1.000000
    
    
      879
      0.987640
      1.0
      0.0
      0.750562
      0.0
      0.698417
      0.000000
      0.166667
      0.086765
      0.894737
      0.476190
      0.333333
    
    
      880
      0.988764
      1.0
      0.5
      0.830337
      0.0
      0.308872
      0.000000
      0.166667
      0.169118
      0.558704
      0.993197
      1.000000
    
    
      881
      0.989888
      0.0
      1.0
      0.573034
      1.0
      0.409399
      0.000000
      0.000000
      0.579412
      0.161943
      0.993197
      1.000000
    
    
      882
      0.991011
      0.0
      1.0
      0.216854
      0.0
      0.271174
      0.000000
      0.000000
      0.747059
      0.295547
      0.993197
      1.000000
    
    
      883
      0.992135
      0.0
      0.5
      0.068539
      1.0
      0.346569
      0.000000
      0.000000
      0.830882
      0.291498
      0.993197
      1.000000
    
    
      884
      0.993258
      0.0
      1.0
      0.891011
      1.0
      0.308872
      0.000000
      0.000000
      0.955882
      0.048583
      0.993197
      1.000000
    
    
      885
      0.994382
      0.0
      1.0
      0.768539
      0.0
      0.484795
      0.000000
      0.833333
      0.705882
      0.611336
      0.993197
      0.666667
    
    
      886
      0.995506
      0.0
      0.5
      0.615730
      1.0
      0.334004
      0.000000
      0.000000
      0.148529
      0.344130
      0.993197
      1.000000
    
    
      887
      0.996629
      1.0
      0.0
      0.340449
      0.0
      0.233476
      0.000000
      0.000000
      0.020588
      0.619433
      0.204082
      1.000000
    
    
      888
      0.997753
      0.0
      1.0
      0.464045
      0.0
      0.367921
      0.166667
      0.333333
      0.992647
      0.530364
      0.993197
      1.000000
    
    
      889
      0.998876
      1.0
      0.0
      0.091011
      1.0
      0.321438
      0.000000
      0.000000
      0.011765
      0.619433
      0.408163
      0.333333
    
    
      890
      1.000000
      0.0
      1.0
      0.247191
      1.0
      0.396833
      0.000000
      0.000000
      0.685294
      0.121457
      0.993197
      0.666667
    
  

891 rows × 12 columns



In [12]:

    
##6. Seleciona as features baseada na correlação 
datasetn.corr()









    Out[12]:







  
    
      
      PassengerId
      Survived
      Pclass
      Name
      Sex
      Age
      SibSp
      Parch
      Ticket
      Fare
      Cabin
      Embarked
    
  
  
    
      PassengerId
      1.000000
      -0.005007
      -0.035144
      -0.038559
      0.042939
      0.033207
      -0.065229
      -0.001652
      -0.056554
      -0.006390
      -0.035197
      0.012985
    
    
      Survived
      -0.005007
      1.000000
      -0.338481
      -0.057343
      -0.543351
      -0.069809
      -0.026385
      0.081629
      -0.164549
      0.333943
      -0.253658
      -0.176509
    
    
      Pclass
      -0.035144
      -0.338481
      1.000000
      0.052831
      0.131900
      -0.331339
      0.078141
      0.018443
      0.319869
      -0.724119
      0.682176
      0.173511
    
    
      Name
      -0.038559
      -0.057343
      0.052831
      1.000000
      0.020314
      0.057466
      -0.035535
      -0.049105
      0.047348
      -0.053846
      0.062119
      -0.010633
    
    
      Sex
      0.042939
      -0.543351
      0.131900
      0.020314
      1.000000
      0.084153
      -0.123164
      -0.245489
      0.059372
      -0.265389
      0.095991
      0.118492
    
    
      Age
      0.033207
      -0.069809
      -0.331339
      0.057466
      0.084153
      1.000000
      -0.254997
      -0.179191
      -0.068848
      0.110296
      -0.234912
      -0.039610
    
    
      SibSp
      -0.065229
      -0.026385
      0.078141
      -0.035535
      -0.123164
      -0.254997
      1.000000
      0.423338
      0.069238
      0.368688
      0.040687
      0.069165
    
    
      Parch
      -0.001652
      0.081629
      0.018443
      -0.049105
      -0.245489
      -0.179191
      0.423338
      1.000000
      0.020003
      0.361243
      -0.028179
      0.043351
    
    
      Ticket
      -0.056554
      -0.164549
      0.319869
      0.047348
      0.059372
      -0.068848
      0.069238
      0.020003
      1.000000
      -0.168153
      0.243082
      0.011146
    
    
      Fare
      -0.006390
      0.333943
      -0.724119
      -0.053846
      -0.265389
      0.110296
      0.368688
      0.361243
      -0.168153
      1.000000
      -0.538549
      -0.169849
    
    
      Cabin
      -0.035197
      -0.253658
      0.682176
      0.062119
      0.095991
      -0.234912
      0.040687
      -0.028179
      0.243082
      -0.538549
      1.000000
      0.226137
    
    
      Embarked
      0.012985
      -0.176509
      0.173511
      -0.010633
      0.118492
      -0.039610
      0.069165
      0.043351
      0.011146
      -0.169849
      0.226137
      1.000000



In [13]:

    
'''
Baseando-se com na correlação dos atributos com Survived, serão selecionados os atributos com correlação acima de 0.3 
  Correlação com Survived:
   Forte/Moderada: Pclass, Sex, Fare
   Fraca: Passengerid, SibSp, Embarked, Age, Name, Parch, Ticket, Fare, Cabin
'''

#Elimina os atributos irrelevantes para predição
datasetd = datasetn.drop(['PassengerId','SibSp','Embarked','Age','Name','Parch','Ticket','Cabin'], axis=1)
#datasetd



In [14]:

    
##7. Separa o dataset em treino (75%) / teste (25%) / validação (10% do treino)

# Separa o atributo Survived (saída) dos outros (entrada)
y = datasetd.Survived.values
X = datasetd.drop('Survived', axis=1).values

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)
X_train, X_validation, y_train, y_validation = train_test_split(X_train, y_train, test_size=0.1)



In [15]:

    
##8. Executa o classificador para 30 k's, pulando de 4 em 4
from sklearn import metrics
a_accuracy = []
ks = []
for k in range(3,30,4):
    knn = KNNClassifier()
    knn.fit(X_train, y_train)
    result = knn.predict(k, X_test)
    accuracy = metrics.accuracy_score(result,y_test)
    a_accuracy.append(accuracy)
    ks.append(k)



In [16]:

    
%matplotlib inline
import matplotlib.pyplot as plt
plt.scatter(ks, a_accuracy, marker='o');
plt.grid()
plt.title('Relação da acurácia com a quantidade de vizinhos')
plt.xlabel('k')
plt.ylabel(u'Acurácia')









    Out[16]:





Text(0,0.5,'Acurácia')



In [17]:

    
##9. Executa o classificar para o melhor k
# encontra melhor acuracia
index, best_accuracy = max(enumerate(a_accuracy))
print('Melhor acurácia: ',best_accuracy,' | Index:',index,
     '\nMelhor k: ',ks[index])









    



Melhor acurácia:  0.834080717489  | Index: 6 
Melhor k:  27



In [18]:

    
knn_best = KNNClassifier()
knn_best.fit(X_train, y_train)
result = knn.predict(ks[index], X_validation)
accuracy = metrics.accuracy_score(result,y_validation)
print('{0:f}'.format(accuracy))



In [19]:

    
from sklearn.metrics import classification_report
print(classification_report(y_validation, result, target_names=['Survived', 'Not Survived']))









    



              precision    recall  f1-score   support

    Survived       0.80      0.98      0.88        41
Not Survived       0.94      0.62      0.74        26

 avg / total       0.85      0.84      0.83        67



In [ ]:



In [ ]:

	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
5	6	0	3	Moran, Mr. James	male	NaN	0	0	330877	8.4583	NaN	Q
6	7	0	1	McCarthy, Mr. Timothy J	male	54.0	0	0	17463	51.8625	E46	S
7	8	0	3	Palsson, Master. Gosta Leonard	male	2.0	3	1	349909	21.0750	NaN	S
8	9	1	3	Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)	female	27.0	0	2	347742	11.1333	NaN	S
9	10	1	2	Nasser, Mrs. Nicholas (Adele Achem)	female	14.0	1	0	237736	30.0708	NaN	C
10	11	1	3	Sandstrom, Miss. Marguerite Rut	female	4.0	1	1	PP 9549	16.7000	G6	S
11	12	1	1	Bonnell, Miss. Elizabeth	female	58.0	0	0	113783	26.5500	C103	S
12	13	0	3	Saundercock, Mr. William Henry	male	20.0	0	0	A/5. 2151	8.0500	NaN	S
13	14	0	3	Andersson, Mr. Anders Johan	male	39.0	1	5	347082	31.2750	NaN	S
14	15	0	3	Vestrom, Miss. Hulda Amanda Adolfina	female	14.0	0	0	350406	7.8542	NaN	S
15	16	1	2	Hewlett, Mrs. (Mary D Kingcome)	female	55.0	0	0	248706	16.0000	NaN	S
16	17	0	3	Rice, Master. Eugene	male	2.0	4	1	382652	29.1250	NaN	Q
17	18	1	2	Williams, Mr. Charles Eugene	male	NaN	0	0	244373	13.0000	NaN	S
18	19	0	3	Vander Planke, Mrs. Julius (Emelia Maria Vande...	female	31.0	1	0	345763	18.0000	NaN	S
19	20	1	3	Masselmani, Mrs. Fatima	female	NaN	0	0	2649	7.2250	NaN	C
20	21	0	2	Fynney, Mr. Joseph J	male	35.0	0	0	239865	26.0000	NaN	S
21	22	1	2	Beesley, Mr. Lawrence	male	34.0	0	0	248698	13.0000	D56	S
22	23	1	3	McGowan, Miss. Anna "Annie"	female	15.0	0	0	330923	8.0292	NaN	Q
23	24	1	1	Sloper, Mr. William Thompson	male	28.0	0	0	113788	35.5000	A6	S
24	25	0	3	Palsson, Miss. Torborg Danira	female	8.0	3	1	349909	21.0750	NaN	S
25	26	1	3	Asplund, Mrs. Carl Oscar (Selma Augusta Emilia...	female	38.0	1	5	347077	31.3875	NaN	S
26	27	0	3	Emir, Mr. Farred Chehab	male	NaN	0	0	2631	7.2250	NaN	C
27	28	0	1	Fortune, Mr. Charles Alexander	male	19.0	3	2	19950	263.0000	C23 C25 C27	S
28	29	1	3	O'Dwyer, Miss. Ellen "Nellie"	female	NaN	0	0	330959	7.8792	NaN	Q
29	30	0	3	Todoroff, Mr. Lalio	male	NaN	0	0	349216	7.8958	NaN	S
...	...	...	...	...	...	...	...	...	...	...	...	...
861	862	0	2	Giles, Mr. Frederick Edward	male	21.0	1	0	28134	11.5000	NaN	S
862	863	1	1	Swift, Mrs. Frederick Joel (Margaret Welles Ba...	female	48.0	0	0	17466	25.9292	D17	S
863	864	0	3	Sage, Miss. Dorothy Edith "Dolly"	female	NaN	8	2	CA. 2343	69.5500	NaN	S
864	865	0	2	Gill, Mr. John William	male	24.0	0	0	233866	13.0000	NaN	S
865	866	1	2	Bystrom, Mrs. (Karolina)	female	42.0	0	0	236852	13.0000	NaN	S
866	867	1	2	Duran y More, Miss. Asuncion	female	27.0	1	0	SC/PARIS 2149	13.8583	NaN	C
867	868	0	1	Roebling, Mr. Washington Augustus II	male	31.0	0	0	PC 17590	50.4958	A24	S
868	869	0	3	van Melkebeke, Mr. Philemon	male	NaN	0	0	345777	9.5000	NaN	S
869	870	1	3	Johnson, Master. Harold Theodor	male	4.0	1	1	347742	11.1333	NaN	S
870	871	0	3	Balkic, Mr. Cerin	male	26.0	0	0	349248	7.8958	NaN	S
871	872	1	1	Beckwith, Mrs. Richard Leonard (Sallie Monypeny)	female	47.0	1	1	11751	52.5542	D35	S
872	873	0	1	Carlsson, Mr. Frans Olof	male	33.0	0	0	695	5.0000	B51 B53 B55	S
873	874	0	3	Vander Cruyssen, Mr. Victor	male	47.0	0	0	345765	9.0000	NaN	S
874	875	1	2	Abelson, Mrs. Samuel (Hannah Wizosky)	female	28.0	1	0	P/PP 3381	24.0000	NaN	C
875	876	1	3	Najib, Miss. Adele Kiamie "Jane"	female	15.0	0	0	2667	7.2250	NaN	C
876	877	0	3	Gustafsson, Mr. Alfred Ossian	male	20.0	0	0	7534	9.8458	NaN	S
877	878	0	3	Petroff, Mr. Nedelio	male	19.0	0	0	349212	7.8958	NaN	S
878	879	0	3	Laleff, Mr. Kristo	male	NaN	0	0	349217	7.8958	NaN	S
879	880	1	1	Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)	female	56.0	0	1	11767	83.1583	C50	C
880	881	1	2	Shelley, Mrs. William (Imanita Parrish Hall)	female	25.0	0	1	230433	26.0000	NaN	S
881	882	0	3	Markun, Mr. Johann	male	33.0	0	0	349257	7.8958	NaN	S
882	883	0	3	Dahlberg, Miss. Gerda Ulrika	female	22.0	0	0	7552	10.5167	NaN	S
883	884	0	2	Banfield, Mr. Frederick James	male	28.0	0	0	C.A./SOTON 34068	10.5000	NaN	S
884	885	0	3	Sutehall, Mr. Henry Jr	male	25.0	0	0	SOTON/OQ 392076	7.0500	NaN	S
885	886	0	3	Rice, Mrs. William (Margaret Norton)	female	39.0	0	5	382652	29.1250	NaN	Q
886	887	0	2	Montvila, Rev. Juozas	male	27.0	0	0	211536	13.0000	NaN	S
887	888	1	1	Graham, Miss. Margaret Edith	female	19.0	0	0	112053	30.0000	B42	S
888	889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	NaN	1	2	W./C. 6607	23.4500	NaN	S
889	890	1	1	Behr, Mr. Karl Howell	male	26.0	0	0	111369	30.0000	C148	C
890	891	0	3	Dooley, Mr. Patrick	male	32.0	0	0	370376	7.7500	NaN	Q

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	108	1	22.000000	1	0	523	18	146	2
1	2	1	1	190	0	38.000000	1	0	596	207	81	0
2	3	1	3	353	0	26.000000	0	0	669	41	146	2
3	4	1	1	272	0	35.000000	1	0	49	189	55	2
4	5	0	3	15	1	35.000000	0	0	472	43	146	2
5	6	0	3	554	1	29.699118	0	0	275	51	146	1
6	7	0	1	515	1	54.000000	0	0	85	186	129	2
7	8	0	3	624	1	2.000000	3	1	395	124	146	2
8	9	1	3	412	0	27.000000	0	2	344	74	146	2
9	10	1	2	576	0	14.000000	1	0	132	154	146	0
10	11	1	3	727	0	4.000000	1	1	616	110	145	2
11	12	1	1	95	0	58.000000	0	0	38	143	49	2
12	13	0	3	729	1	20.000000	0	0	535	43	146	2
13	14	0	3	28	1	39.000000	1	5	333	158	146	2
14	15	0	3	840	0	14.000000	0	0	413	36	146	2
15	16	1	2	359	0	55.000000	0	0	153	108	146	2
16	17	0	3	682	1	2.000000	4	1	480	151	146	1
17	18	1	2	867	1	29.699118	0	0	151	85	146	2
18	19	0	3	839	0	31.000000	1	0	301	113	146	2
19	20	1	3	512	0	29.699118	0	0	184	16	146	0
20	21	0	2	273	1	35.000000	0	0	139	138	146	2
21	22	1	2	80	1	34.000000	0	0	152	85	111	2
22	23	1	3	523	0	15.000000	0	0	278	42	146	1
23	24	1	1	765	1	28.000000	0	0	42	168	13	2
24	25	0	3	626	0	8.000000	3	1	395	124	146	2
25	26	1	3	44	0	38.000000	1	5	329	159	146	2
26	27	0	3	240	1	29.699118	0	0	179	16	146	0
27	28	0	1	260	1	19.000000	3	2	95	246	63	2
28	29	1	3	605	0	29.699118	0	0	283	38	146	1
29	30	0	3	813	1	29.699118	0	0	362	40	146	2
...	...	...	...	...	...	...	...	...	...	...	...	...
861	862	0	2	283	1	21.000000	1	0	221	76	146	2
862	863	1	1	797	0	48.000000	0	0	88	137	94	2
863	864	0	3	718	0	29.699118	6	2	568	205	146	2
864	865	0	2	285	1	24.000000	0	0	120	85	146	2
865	866	1	2	122	0	42.000000	0	0	126	85	146	2
866	867	1	2	230	0	27.000000	1	0	632	89	146	0
867	868	0	1	696	1	31.000000	0	0	590	184	6	2
868	869	0	3	890	1	29.699118	0	0	309	64	146	2
869	870	1	3	407	1	4.000000	1	1	344	74	146	2
870	871	0	3	59	1	26.000000	0	0	387	40	146	2
871	872	1	1	79	0	47.000000	1	1	54	188	102	2
872	873	0	1	139	1	33.000000	0	0	502	2	34	2
873	874	0	3	836	1	47.000000	0	0	303	58	146	2
874	875	1	2	4	0	28.000000	1	0	575	132	146	0
875	876	1	3	571	0	15.000000	0	0	195	16	146	0
876	877	0	3	311	1	20.000000	0	0	504	69	146	2
877	878	0	3	657	1	19.000000	0	0	358	40	146	2
878	879	0	3	451	1	29.699118	0	0	363	40	146	2
879	880	1	1	668	0	56.000000	0	1	59	221	70	0
880	881	1	2	739	0	25.000000	0	1	115	138	146	2
881	882	0	3	510	1	33.000000	0	0	394	40	146	2
882	883	0	3	193	0	22.000000	0	0	508	73	146	2
883	884	0	2	61	1	28.000000	0	0	565	72	146	2
884	885	0	3	793	1	25.000000	0	0	650	12	146	2
885	886	0	3	684	0	39.000000	0	5	480	151	146	1
886	887	0	2	548	1	27.000000	0	0	101	85	146	2
887	888	1	1	303	0	19.000000	0	0	14	153	30	2
888	889	0	3	413	0	29.699118	1	2	675	131	146	2
889	890	1	1	81	1	26.000000	0	0	8	153	60	0
890	891	0	3	220	1	32.000000	0	0	466	30	146	1

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	0.000000	0.0	1.0	0.121348	1.0	0.271174	0.166667	0.000000	0.769118	0.072874	0.993197	1.000000
1	0.001124	1.0	0.0	0.213483	0.0	0.472229	0.166667	0.000000	0.876471	0.838057	0.551020	0.333333
2	0.002247	1.0	1.0	0.396629	0.0	0.321438	0.000000	0.000000	0.983824	0.165992	0.993197	1.000000
3	0.003371	1.0	0.0	0.305618	0.0	0.434531	0.166667	0.000000	0.072059	0.765182	0.374150	1.000000
4	0.004494	0.0	1.0	0.016854	1.0	0.434531	0.000000	0.000000	0.694118	0.174089	0.993197	1.000000
5	0.005618	0.0	1.0	0.622472	1.0	0.367921	0.000000	0.000000	0.404412	0.206478	0.993197	0.666667
6	0.006742	0.0	0.0	0.578652	1.0	0.673285	0.000000	0.000000	0.125000	0.753036	0.877551	1.000000
7	0.007865	0.0	1.0	0.701124	1.0	0.019854	0.500000	0.166667	0.580882	0.502024	0.993197	1.000000
8	0.008989	1.0	1.0	0.462921	0.0	0.334004	0.000000	0.333333	0.505882	0.299595	0.993197	1.000000
9	0.010112	1.0	0.5	0.647191	0.0	0.170646	0.166667	0.000000	0.194118	0.623482	0.993197	0.333333
10	0.011236	1.0	1.0	0.816854	0.0	0.044986	0.166667	0.166667	0.905882	0.445344	0.986395	1.000000
11	0.012360	1.0	0.0	0.106742	0.0	0.723549	0.000000	0.000000	0.055882	0.578947	0.333333	1.000000
12	0.013483	0.0	1.0	0.819101	1.0	0.246042	0.000000	0.000000	0.786765	0.174089	0.993197	1.000000
13	0.014607	0.0	1.0	0.031461	1.0	0.484795	0.166667	0.833333	0.489706	0.639676	0.993197	1.000000
14	0.015730	0.0	1.0	0.943820	0.0	0.170646	0.000000	0.000000	0.607353	0.145749	0.993197	1.000000
15	0.016854	1.0	0.5	0.403371	0.0	0.685851	0.000000	0.000000	0.225000	0.437247	0.993197	1.000000
16	0.017978	0.0	1.0	0.766292	1.0	0.019854	0.666667	0.166667	0.705882	0.611336	0.993197	0.666667
17	0.019101	1.0	0.5	0.974157	1.0	0.367921	0.000000	0.000000	0.222059	0.344130	0.993197	1.000000
18	0.020225	0.0	1.0	0.942697	0.0	0.384267	0.166667	0.000000	0.442647	0.457490	0.993197	1.000000
19	0.021348	1.0	1.0	0.575281	0.0	0.367921	0.000000	0.000000	0.270588	0.064777	0.993197	0.333333
20	0.022472	0.0	0.5	0.306742	1.0	0.434531	0.000000	0.000000	0.204412	0.558704	0.993197	1.000000
21	0.023596	1.0	0.5	0.089888	1.0	0.421965	0.000000	0.000000	0.223529	0.344130	0.755102	1.000000
22	0.024719	1.0	1.0	0.587640	0.0	0.183212	0.000000	0.000000	0.408824	0.170040	0.993197	0.666667
23	0.025843	1.0	0.0	0.859551	1.0	0.346569	0.000000	0.000000	0.061765	0.680162	0.088435	1.000000
24	0.026966	0.0	1.0	0.703371	0.0	0.095250	0.500000	0.166667	0.580882	0.502024	0.993197	1.000000
25	0.028090	1.0	1.0	0.049438	0.0	0.472229	0.166667	0.833333	0.483824	0.643725	0.993197	1.000000
26	0.029213	0.0	1.0	0.269663	1.0	0.367921	0.000000	0.000000	0.263235	0.064777	0.993197	0.333333
27	0.030337	0.0	0.0	0.292135	1.0	0.233476	0.500000	0.333333	0.139706	0.995951	0.428571	1.000000
28	0.031461	1.0	1.0	0.679775	0.0	0.367921	0.000000	0.000000	0.416176	0.153846	0.993197	0.666667
29	0.032584	0.0	1.0	0.913483	1.0	0.367921	0.000000	0.000000	0.532353	0.161943	0.993197	1.000000
...	...	...	...	...	...	...	...	...	...	...	...	...
861	0.967416	0.0	0.5	0.317978	1.0	0.258608	0.166667	0.000000	0.325000	0.307692	0.993197	1.000000
862	0.968539	1.0	0.0	0.895506	0.0	0.597889	0.000000	0.000000	0.129412	0.554656	0.639456	1.000000
863	0.969663	0.0	1.0	0.806742	0.0	0.367921	1.000000	0.333333	0.835294	0.829960	0.993197	1.000000
864	0.970787	0.0	0.5	0.320225	1.0	0.296306	0.000000	0.000000	0.176471	0.344130	0.993197	1.000000
865	0.971910	1.0	0.5	0.137079	0.0	0.522493	0.000000	0.000000	0.185294	0.344130	0.993197	1.000000
866	0.973034	1.0	0.5	0.258427	0.0	0.334004	0.166667	0.000000	0.929412	0.360324	0.993197	0.333333
867	0.974157	0.0	0.0	0.782022	1.0	0.384267	0.000000	0.000000	0.867647	0.744939	0.040816	1.000000
868	0.975281	0.0	1.0	1.000000	1.0	0.367921	0.000000	0.000000	0.454412	0.259109	0.993197	1.000000
869	0.976404	1.0	1.0	0.457303	1.0	0.044986	0.166667	0.166667	0.505882	0.299595	0.993197	1.000000
870	0.977528	0.0	1.0	0.066292	1.0	0.321438	0.000000	0.000000	0.569118	0.161943	0.993197	1.000000
871	0.978652	1.0	0.0	0.088764	0.0	0.585323	0.166667	0.166667	0.079412	0.761134	0.693878	1.000000
872	0.979775	0.0	0.0	0.156180	1.0	0.409399	0.000000	0.000000	0.738235	0.008097	0.231293	1.000000
873	0.980899	0.0	1.0	0.939326	1.0	0.585323	0.000000	0.000000	0.445588	0.234818	0.993197	1.000000
874	0.982022	1.0	0.5	0.004494	0.0	0.346569	0.166667	0.000000	0.845588	0.534413	0.993197	0.333333
875	0.983146	1.0	1.0	0.641573	0.0	0.183212	0.000000	0.000000	0.286765	0.064777	0.993197	0.333333
876	0.984270	0.0	1.0	0.349438	1.0	0.246042	0.000000	0.000000	0.741176	0.279352	0.993197	1.000000
877	0.985393	0.0	1.0	0.738202	1.0	0.233476	0.000000	0.000000	0.526471	0.161943	0.993197	1.000000
878	0.986517	0.0	1.0	0.506742	1.0	0.367921	0.000000	0.000000	0.533824	0.161943	0.993197	1.000000
879	0.987640	1.0	0.0	0.750562	0.0	0.698417	0.000000	0.166667	0.086765	0.894737	0.476190	0.333333
880	0.988764	1.0	0.5	0.830337	0.0	0.308872	0.000000	0.166667	0.169118	0.558704	0.993197	1.000000
881	0.989888	0.0	1.0	0.573034	1.0	0.409399	0.000000	0.000000	0.579412	0.161943	0.993197	1.000000
882	0.991011	0.0	1.0	0.216854	0.0	0.271174	0.000000	0.000000	0.747059	0.295547	0.993197	1.000000
883	0.992135	0.0	0.5	0.068539	1.0	0.346569	0.000000	0.000000	0.830882	0.291498	0.993197	1.000000
884	0.993258	0.0	1.0	0.891011	1.0	0.308872	0.000000	0.000000	0.955882	0.048583	0.993197	1.000000
885	0.994382	0.0	1.0	0.768539	0.0	0.484795	0.000000	0.833333	0.705882	0.611336	0.993197	0.666667
886	0.995506	0.0	0.5	0.615730	1.0	0.334004	0.000000	0.000000	0.148529	0.344130	0.993197	1.000000
887	0.996629	1.0	0.0	0.340449	0.0	0.233476	0.000000	0.000000	0.020588	0.619433	0.204082	1.000000
888	0.997753	0.0	1.0	0.464045	0.0	0.367921	0.166667	0.333333	0.992647	0.530364	0.993197	1.000000
889	0.998876	1.0	0.0	0.091011	1.0	0.321438	0.000000	0.000000	0.011765	0.619433	0.408163	0.333333
890	1.000000	0.0	1.0	0.247191	1.0	0.396833	0.000000	0.000000	0.685294	0.121457	0.993197	0.666667

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
PassengerId	1.000000	-0.005007	-0.035144	-0.038559	0.042939	0.033207	-0.065229	-0.001652	-0.056554	-0.006390	-0.035197	0.012985
Survived	-0.005007	1.000000	-0.338481	-0.057343	-0.543351	-0.069809	-0.026385	0.081629	-0.164549	0.333943	-0.253658	-0.176509
Pclass	-0.035144	-0.338481	1.000000	0.052831	0.131900	-0.331339	0.078141	0.018443	0.319869	-0.724119	0.682176	0.173511
Name	-0.038559	-0.057343	0.052831	1.000000	0.020314	0.057466	-0.035535	-0.049105	0.047348	-0.053846	0.062119	-0.010633
Sex	0.042939	-0.543351	0.131900	0.020314	1.000000	0.084153	-0.123164	-0.245489	0.059372	-0.265389	0.095991	0.118492
Age	0.033207	-0.069809	-0.331339	0.057466	0.084153	1.000000	-0.254997	-0.179191	-0.068848	0.110296	-0.234912	-0.039610
SibSp	-0.065229	-0.026385	0.078141	-0.035535	-0.123164	-0.254997	1.000000	0.423338	0.069238	0.368688	0.040687	0.069165
Parch	-0.001652	0.081629	0.018443	-0.049105	-0.245489	-0.179191	0.423338	1.000000	0.020003	0.361243	-0.028179	0.043351
Ticket	-0.056554	-0.164549	0.319869	0.047348	0.059372	-0.068848	0.069238	0.020003	1.000000	-0.168153	0.243082	0.011146
Fare	-0.006390	0.333943	-0.724119	-0.053846	-0.265389	0.110296	0.368688	0.361243	-0.168153	1.000000	-0.538549	-0.169849
Cabin	-0.035197	-0.253658	0.682176	0.062119	0.095991	-0.234912	0.040687	-0.028179	0.243082	-0.538549	1.000000	0.226137
Embarked	0.012985	-0.176509	0.173511	-0.010633	0.118492	-0.039610	0.069165	0.043351	0.011146	-0.169849	0.226137	1.000000