Titanic [EDA] 타이타닉 탐색적 분석

data['Age_band']=0
data.loc[(data['Age']>16) &(data['Age']<=32) , 'Age_band'] = 1
data.loc[(data['Age']>32) &(data['Age']<=48) , 'Age_band'] = 2
data.loc[(data['Age']>48) &(data['Age']<=64) , 'Age_band'] = 3
data.loc[data['Age']>64, 'Age_band'] = 4
 
data['Age_band'].value_counts().to_frame().style.background_gradient(cmap='summer')

--- numeric describe

train_df.describe()

--- object describe

train_df.describe(include=['O'])

--- info

train_df.info()
print('_'*40)
test_df.info()

--- > Correlation between The Features

sns.heatmap(data.corr(), annot=True, cmap='RdYlGn', linewidths=0.2) 
fig=plt.gcf()
fig.set_size_inches(10,8)
plt.show()

Filling NaN

sns.heatmap(data.corr(), annot=True, cmap='RdYlGn', linewidths=0.2) 
fig=plt.gcf()
fig.set_size_inches(10,8)
plt.show()

Pivoting

train_df[['Pclass', 'Survived']].groupby(['Pclass'],as_index=False).mean().sort_values(by='Survived', ascending=False)

Visualizing

g = sns.FacetGrid(train_df, col='Survived')
g.map(plt.hist, 'Age', bins=20)

---> Distritution by class

# grid = sns.FacetGrid(train_df, col='Pclass', hue='Survived')
grid = sns.FacetGrid(train_df, col='Survived', row='Pclass', size=2.2, aspect=1.6)
grid.map(plt.hist, 'Age', alpha=.5, bins=20)
grid.add_legend();

g = sns.pairplot(train[[u'Survived', u'Pclass', u'Sex', u'Age', u'Parch', u'Fare', u'Embarked',
       u'FamilySize', u'Title']], hue='Survived', palette = 'seismic',size=1.2,diag_kind = 'kde',diag_kws=dict(shade=True),plot_kws=dict(s=10) )
g.set(xticklabels=[])