In [1]:

    

import csv
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt


    

In [2]:

    

csv_file_object = csv.reader(open('Titanic/train.csv', 'r')) 
header = next(csv_file_object)

data=[] 

for row in csv_file_object:
    data.append(row)
data = np.array(data)


    

In [ ]:

    

#Matrices puras, sin nombres de columna
print(data)


    

In [ ]:

    

data[0:15,5]


    

In [ ]:

    

type(data[0::,5])


    

In [ ]:

    

#Problemas con valores faltantes
ages_onboard = data[0::,5].astype(np.float)


    

In [3]:

    

df = pd.read_csv('Titanic/train.csv', header=0)


    

In [ ]:

    

df


    

In [ ]:

    

type(df)


    

In [17]:

    

df.columns


    

    
Out[17]:





Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',
       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],
      dtype='object')

In [ ]:

    

df.dtypes #Inferencia de tipos de datos


    

In [ ]:

    

df.info()
#La mayoría de las columnas tiene sus valores completos


    

In [ ]:

    

df.describe()


    

In [ ]:

    

df['Age']


    

In [ ]:

    

type(df['Age'])


    

In [15]:

    

df['Age'][0:10]
#df['Age'].iloc[0:10]
#df[0:10]['Age']
#df.iloc[0:10]['Age']


    

    
Out[15]:





0    22.0
1    38.0
2    26.0
3    35.0
4    35.0
5     NaN
6    54.0
7     2.0
8    27.0
9    14.0
Name: Age, dtype: float64

In [ ]:

    

print("Media:", df['Age'].mean())
print("Mediana:", df['Age'].median())
print("Suma:", df['Age'].sum())


    

In [ ]:

    

df[ ['Sex', 'Pclass', 'Age'] ]


    

In [ ]:

    

df['Age'] > 60


    

In [ ]:

    

df[df['Age'] > 60]


    

In [ ]:

    

df[df['Age'] > 60][['Sex', 'Pclass', 'Age', 'Survived']]


    

In [19]:

    

df[(df['Age'] > 60) & (df['Sex'] == 'female')]


    

    
Out[19]:






  

    

      

      
PassengerId
      
Survived
      
Pclass
      
Name
      
Sex
      
Age
      
SibSp
      
Parch
      
Ticket
      
Fare
      
Cabin
      
Embarked
    
  
  

    

      
275
      
276
      
1
      
1
      
Andrews, Miss. Kornelia Theodosia
      
female
      
63.0
      
1
      
0
      
13502
      
77.9583
      
D7
      
S
    
    

      
483
      
484
      
1
      
3
      
Turkula, Mrs. (Hedwig)
      
female
      
63.0
      
0
      
0
      
4134
      
9.5875
      
NaN
      
S
    
    

      
829
      
830
      
1
      
1
      
Stone, Mrs. George Nelson (Martha Evelyn)
      
female
      
62.0
      
0
      
0
      
113572
      
80.0000
      
B28
      
NaN
    
  

In [ ]:

    

df[df['Age'].isnull()][['Sex', 'Pclass', 'Age']]


    

In [ ]:

    

import matplotlib.pyplot as plt
df['Age'].hist()
plt.show()


    

In [ ]:

    

df['Age'].hist(bins=16, range=(0,80), alpha = .5)
plt.show()


    

In [ ]:

    

df['Gender'] = df['Sex'].map( {'female': 0, 'male': 1} ).astype(int)
#df['Gender'] = df['Sex'].map( lambda x: 0 if x[0] == 'm' else 1 )


    

In [ ]:

    

df.head()


    

In [ ]:

    

df['Embarked'].unique()


    

In [ ]:

    

df['Embarked_N'] = df['Embarked'].map({'S':0, 'C':1, 'Q':2, np.nan: 3})


    

In [ ]:

    

df['Embarked_N'].unique()


    

In [ ]:

    

df['AgeNull'] = df['Age'].isnull()
df.loc[df['Age'].isnull(), 'Age'] = df['Age'].mean()


    

In [ ]:

    

df[df['AgeNull'] == 1]['Age']


    

In [ ]:

    

df['Embarked_N'].mode()


    

In [ ]:

    

type(df['Embarked_N'].mode())


    

In [ ]:

    

df.loc[df['Embarked_N'] == 3, 'Embarked_N'] = df['Embarked_N'].mode().iloc[0]


    

In [ ]:

    

df['Embarked_N'].unique()


    

In [10]:

    

total_mujeres = df[df['Sex'] == 'female'].shape[0]
mujeres_supervivientes = df[(df['Sex'] == 'female') & (df['Survived'] == 1)].shape[0]
print("Porcentaje de mujeres supervivientes:", mujeres_supervivientes / total_mujeres)

total_hombres = df[df['Sex'] == 'male'].shape[0]
hombres_supervivientes = df[(df['Sex'] == 'male') & (df['Survived'] == 1)].shape[0]
print("Porcentaje de hombres supervivientes:", hombres_supervivientes / total_hombres)


    

    




Porcentaje de mujeres supervivientes: 0.7420382165605095
Porcentaje de hombres supervivientes: 0.18890814558058924

In [ ]:

    

test = pd.read_csv('Titanic/test.csv')


    

In [ ]:

    

#Predecimos que sobrevivió si fue mujer y que murió si fue hombre
test['Survived'] = test['Sex'].map({'female': 1, 'male': 0})
test.to_csv('genderbasedpred.csv', 
            columns=['PassengerId', 'Survived'], 
            index=False)