amazon.py

n_best = 20

top_authors = df.Author.value_counts().nlargest(n_best)
no_dup = df.drop_duplicates('Name') # removes all rows with duplicate book names

fig, ax = plt.subplots(1, 3, figsize=(11,10), sharey=True)

color = sns.color_palette("hls", n_best)

ax[0].hlines(y=top_authors.index , xmin=0, xmax=top_authors.values, color=color, linestyles='dashed')
ax[0].plot(top_authors.values, top_authors.index, 'go', markersize=9)
ax[0].set_xlabel('Number of appearences')
ax[0].set_xticks(np.arange(top_authors.values.max()+1))
ax[0].set_yticklabels(top_authors.index, fontweight='semibold')
ax[0].set_title('Appearences')

book_count = []
total_reviews = []
for name, col in zip(top_authors.index, color):
    book_count.append(len(no_dup[no_dup.Author == name]['Name']))
    total_reviews.append(no_dup[no_dup.Author == name]['Reviews'].sum()/1000)
ax[1].hlines(y=top_authors.index , xmin=0, xmax=book_count, color=color, linestyles='dashed')
ax[1].plot(book_count, top_authors.index, 'go', markersize=9)
ax[1].set_xlabel('Number of unique books')
ax[1].set_xticks(np.arange(max(book_count)+1))
ax[1].set_title('Unique books')

ax[2].barh(y=top_authors.index, width=total_reviews, color=color, edgecolor='black', height=0.7)
for name, val in zip(top_authors.index, total_reviews):
    ax[2].text(val+2, name, val)
ax[2].set_xlabel("Total Reviews (in 1000's)")
ax[2].set_title('Total reviews')

#plt.suptitle('Top 20 best selling Authors (from 2009 to 2019) details', fontsize=15)
plt.show()