상관분석 코드

아래코드를 사용하면 상관 분석이 가능하다

colormap = plt.cm.magma
plt.figure(figsize=(16,12))
plt.title('Pearson correlation of continuous features', y=1.05, size=15)
sns.heatmap(train_float.corr(),linewidths=0.1,vmax=1.0, square=True, 
            cmap=colormap, linecolor='white', annot=True)

 

#train_int = train_int.drop(["id", "target"], axis=1)
# colormap = plt.cm.bone
# plt.figure(figsize=(21,16))
# plt.title('Pearson correlation of categorical features', y=1.05, size=15)
# sns.heatmap(train_cat.corr(),linewidths=0.1,vmax=1.0, square=True, cmap=colormap, linecolor='white', annot=False)
data = [
    go.Heatmap(
        z= train_int.corr().values,
        x=train_int.columns.values,
        y=train_int.columns.values,
        colorscale='Viridis',
        reversescale = False,
        text = True ,
        opacity = 1.0 )
]

layout = go.Layout(
    title='Pearson Correlation of Integer-type features',
    xaxis = dict(ticks='', nticks=36),
    yaxis = dict(ticks='' ),
    width = 900, height = 700)

fig = go.Figure(data=data, layout=layout)
py.iplot(fig, filename='labelled-heatmap')

빨간색으로 상관관계 시각화

 

def corr_heatmap(var):
    correlations = trainset[var].corr()

    # Create color map ranging between two colors
    cmap = sns.diverging_palette(50, 10, as_cmap=True)

    fig, ax = plt.subplots(figsize=(10,10))
    sns.heatmap(correlations, cmap=cmap, vmax=1.0, center=0, fmt='.2f',
                square=True, linewidths=.5, annot=True, cbar_kws={"shrink": .75})
    plt.show();
    
var = metadata[(metadata.type == 'real') & (metadata.preserve)].index
corr_heatmap(var)