Apply to Titanic Dataset



In [4]:

    
import pandas as pd
import numpy as np

% matplotlib inline
from matplotlib import pyplot as plt

Load data



In [5]:

    
df = pd.read_csv('../data/titanic_exercise.csv')
df.head()









    Out[5]:






  
    
      
      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

Task: Clean outliers, duplicates and missing values



In [6]:

    
# Your code here:

	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