In [2]:
import pandas as pd
train = pd.read_csv('data/train.csv')
train.head()
Out[2]:
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 [15]:
s_male = train.loc[(train['Sex'] == 'male') & (train['Survived'] == 1), 'PassengerId'].count()
d_male = train.loc[(train['Sex'] == 'male') & (train['Survived'] == 0), 'PassengerId'].count()
s_female = train.loc[(train['Sex'] == 'female') & (train['Survived'] == 1), 'PassengerId'].count()
d_female = train.loc[(train['Sex'] == 'female') & (train['Survived'] == 0), 'PassengerId'].count()
df = pd.DataFrame({'male':[d_male,s_male],'female':[d_female,s_female]},index=["Dead","Survived"])
df
Out[15]:
male female
Dead 468 81
Survived 109 233
In [ ]: