part 3
sns.distplot(df_train['age'][df_train['sex']=='male'])
sns.distplot(df_train['age'][df_train['sex']=='female'])
sns.lmplot('age', 'survived', hue='sex', data=df_train)
sns.factorplot('age', kind='count', hue='survived', data=df_train)
sns.factorplot('age', kind='count', hue='survived', data=df_train[df_train['age'] < 6])
sns.factorplot('age', kind='count', hue='survived', data=df_train[df_train['age'] >70])
sns.factorplot('embarked', kind='count', hue='survived', data=df_train)
sns.factorplot('cabin', kind='count', hue='survived', data=df_train)
sns.lmplot('sibsp', 'survived', hue='sex', data=df_train)
sns.lmplot('parch', 'survived', hue='sex', data=df_train)
df_train['family_size'] = df_train['sibsp'] + df_train['parch']
df_train.head()
df_temp = df_train[['pclass', 'sex','age','sibsp', 'parch', 'fare']]
df_temp.head()
# sex 컬럼을 범주형에서 수치형으로 변환한다.
df_temp['sex'] = df_temp['sex'].map({'female':0, 'male':1})
df_temp.head()
df_temp.info()
