In [1]:

    

# https://www.kaggle.com/omarelgabry/a-journey-through-titanic


    

In [2]:

    

# Imports

# pandas
import pandas as pd
from pandas import Series, DataFrame

# numpy, matplotlib, seaborn
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style('whitegrid')
%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


    

In [3]:

    

# get titanic & test csv files as a DataFrame
titanic_df = pd.read_csv('input/train.csv')
test_df = pd.read_csv('input/test.csv')

# preview the data
titanic_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]:

    

titanic_df.info()
print("--------------------------")
test_df.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
PassengerId    891 non-null int64
Survived       891 non-null int64
Pclass         891 non-null int64
Name           891 non-null object
Sex            891 non-null object
Age            714 non-null float64
SibSp          891 non-null int64
Parch          891 non-null int64
Ticket         891 non-null object
Fare           891 non-null float64
Cabin          204 non-null object
Embarked       889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.6+ KB
--------------------------
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 418 entries, 0 to 417
Data columns (total 11 columns):
PassengerId    418 non-null int64
Pclass         418 non-null int64
Name           418 non-null object
Sex            418 non-null object
Age            332 non-null float64
SibSp          418 non-null int64
Parch          418 non-null int64
Ticket         418 non-null object
Fare           417 non-null float64
Cabin          91 non-null object
Embarked       418 non-null object
dtypes: float64(2), int64(4), object(5)
memory usage: 36.0+ KB

In [5]:

    

# drop unnecessary columns, these columns won't be useful 
# in analysis and prediction
titanic_df = titanic_df.drop(['PassengerId', 'Name', 'Ticket'], axis=1)
test_df = test_df.drop(['Name', 'Ticket'], axis=1)


    

In [6]:

    

# Embarked

# only in titanic_df, fill the two missing values 
# with the most occurred value, Which is 'S'
titanic_df["Embarked"] = titanic_df["Embarked"].fillna("S")

# plot
sns.factorplot('Embarked', 'Survived', data=titanic_df, size=4, aspect=3)
fig, (axis1, axis2, axis3) = plt.subplots(1, 3, figsize=(15,5))

sns.factorplot('Embarked', data=titanic_df, kind='count', 
               order=['S', 'C', 'Q'], ax=axis1)
sns.factorplot('Survived', hue='Embarked', data=titanic_df, kind='count', 
               order=[1,0], ax=axis2)
sns.countplot(x='Embarked', data=titanic_df, ax=axis1)
sns.countplot(x='Survived', hur='Embarked', data=titanic_df, order=[1, 0],
             ax=axis2)

# group by embarked, and get the mean for suvived passengers 
# for each value in Embarked
embark_perc = titanic_df[["Embarked", "Survived"]].groupby(
    ['Embarked', as_index=False]).mean()
sns.barplot(x='Embarked', y='Survived', data=embark_perc, 
            order=['S', 'C', 'Q'], ax=axis3)

# Either to consider Embarked column in predictions,
# and remove "S" dummy variable,
# and leave "C" & "Q", since they seem to have a good rate for Survival.
# OR, don't create dummy variables for Embarked column, just drop it,
# because logically, Embarked doesn't seem to be useful in prediction.


    

    




  File "<ipython-input-6-54e16572b8a2>", line 22
    ['Embarked', as_index=False]).mean()
                         ^
SyntaxError: invalid syntax

In [ ]: