lda_1.py

# assign each vector the cluster withwhich it is most associated
df_avg['cluster'] = np.argmax(lda.transform(df_avg), axis=1)

#chart the different clusters

fig, axs = plt.subplots(3, 1, sharex=True, sharey=True)

df_avg.iloc[:,:-1].loc[df_avg.cluster == 0].mean().plot.bar(ax=axs[0])
axs[0].set_title('Category - 0 (Evening/Night)')

df_avg.iloc[:,:-1].loc[df_avg.cluster == 1].mean().plot.bar(ax=axs[1])
axs[1].set_title('Category - 1 (Normal Day)')

df_avg.iloc[:,:-1].loc[df_avg.cluster == 2].mean().plot.bar(ax=axs[2])
axs[2].set_title('Category - 2 (Late Night/Early Morning)')

for ax in axs.flat:
    ax.set(xlabel='hours', ylabel='views')