Parvisa korrelationer

Dimensionsreduktion i Python

Jeroen Boeye

Head of Machine Learning, Faktion

Parvisa korrelationer

sns.pairplot(ansur, hue="gender")

ansur pairplot

Parvisa korrelationer

sns.pairplot(ansur, hue="gender")

ansur pairplot annotated

Korrelationskoefficient

extreme correlations

Korrelationskoefficient

scrambled correlations

Korrelationsmatris

weights_df.corr()

korrelationsmatris ansur

Korrelationsmatris

weights_df.corr()

korrelationsmatris ansur dubbletter

Korrelationsmatris

weights_df.corr()

korrelationsmatris ansur dubbletter 2

Korrelationsmatris

weights_df.corr()

korrelationsmatris ansur diagonal

Visualisera korrelationsmatrisen

cmap = sns.diverging_palette(h_neg=10, 
                             h_pos=240, 
                             as_cmap=True)

sns.heatmap(weights_df.corr(), center=0, 
            cmap=cmap, linewidths=1, 
            annot=True, fmt=".2f")

korrelationsmatris visualiserad

Visualisera korrelationsmatrisen

corr = weights_df.corr()

mask = np.triu(np.ones_like(corr, dtype=bool))

array([[ True,  True,  True],
       [False,  True,  True],
       [False, False,  True]])

Visualisera korrelationsmatrisen

sns.heatmap(weights_df.corr(), mask=mask, 
            center=0, cmap=cmap, linewidths=1, 
            annot=True, fmt=".2f")

vikt vs. längd korrelationer maskerade

Visualisera korrelationsmatrisen

ansur urval korrelationer

Nu kör vi en övning!

Dimensionsreduktion i Python