In [1]:

import pandas as pd
from matplotlib import pyplot as plt

In [2]:

plt.style.use('seaborn')
plt.rc('figure', figsize=(10, 8))

In [3]:

x = [5, 7, 8, 5, 6, 7, 9, 2, 3, 4, 4, 4, 2, 6, 3, 6, 8, 6, 4, 1]
y = [7, 4, 3, 9, 1, 3, 2, 5, 2, 4, 8, 7, 1, 6, 4, 9, 7, 7, 5, 1]

In [4]:

# s - size of dots
# c - color
# edgecolor - edges to the circles
# cmap - color map => https://matplotlib.org/3.1.0/tutorials/colors/colormaps.html

# plt.scatter(x,  y, s=100, c='green', marker='x')

# plt.scatter(x,  y, s=100, c='red', edgecolor='black', 
#             linewidth=1, alpha=0.75)


# color and size on a per mark basis
colors = [7, 5, 9, 7, 5, 7, 2, 5, 3, 7, 1, 2, 8, 1, 9, 2, 5, 6, 7, 5]
sizes = [209, 486, 381, 255, 191, 315, 185, 228, 174,
         538, 239, 394, 399, 153, 273, 293, 436, 501, 397, 539]


plt.scatter(x,  y, s=sizes, c=colors, cmap='Reds', edgecolor='black', 
            linewidth=1, alpha=0.75)
cbar = plt.colorbar()
cbar.set_label('Satisfaction level')


plt.tight_layout()

plt.show()

In [5]:

# EXAMPLE

In [6]:

data = pd.read_csv(r'examples/2019-05-31-data.csv')
data.head()

Out[6]:

	view_count	likes	ratio
0	8036001	324742	96.91
1	9378067	562589	98.19
2	2182066	273650	99.38
3	6525864	94698	96.25
4	9481284	582481	97.22

In [7]:

view_count = data['view_count']
likes = data['likes']
ratio = data['ratio']

In [8]:

plt.scatter(view_count,  likes, edgecolor='black', c=ratio,
            cmap='summer', linewidth=1, alpha=0.75)

cbar = plt.colorbar()
cbar.set_label('Like Dislike Ratio')


plt.xscale('log')
plt.yscale('log')
plt.title('Trending YouTube Videos')
plt.xlabel('View Count')
plt.ylabel('Total Likes')

plt.tight_layout()

plt.show()