График разброса панд по категориям и размеру точек

Вот код:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

earnings = pd.read_csv('earnings.csv', sep=';')
tips = pd.read_csv('tips.csv', sep=';')

print(earnings)

print(tips)

earnings['index'] = earnings.index

height, width = earnings.shape

cols = list(earnings.columns.values)

colors = ['r',  'g', 'b']

# Thanks for 
# https://stackoverflow.com/questions/43812911/adding-second-legend-to-scatter-plot
plt.rcParams["figure.subplot.right"] = 0.8

plt.figure(figsize=(8,4))

# get axis
ax = plt.gca()

# plot each column, each row will be in a different X coordinate, creating a category
for x in range(1, width-1):
    earnings.plot.scatter(x='index', y=cols[x], label=None, 
                          xticks=earnings.index, c=colors[x-1],
                          s=tips[cols[x]].multiply(10), linewidth=0, ax=ax)

# This second 'dummy' plot is to create the legend. If we use the one above, 
# [enter image description here][1]the circles in the legend might have different sizes
for x in range(1,width-1):
    earnings.loc[:1].plot.scatter([], [], label=cols[x], c=colors[x-1], s=30,
                                  linewidth=0, ax=ax)

# Label the X ticks with the categories' names
ax.set_xticklabels(earnings.loc[:,'DayOfWeek'])

ax.set_ylabel("Total Earnings")
ax.set_xlabel("Day of Week")


leg = plt.legend(title="Location", loc=(1.03,0))
ax.add_artist(leg)

# Create a second legent for the points' scale.
h = [plt.plot([],[], color="gray", marker="o", ms=i, ls="")[0] for i in range(1,10, 2)]
plt.legend(handles=h, labels=range(1,10, 2), loc=(1.03,0.5), title="Avg. Tip")

plt.show()

# See also:
# https://jakevdp.github.io/PythonDataScienceHandbook/04.06-customizing-legends.html

Результирующая цифра

Это тот вид сюжета, который подходит для грамматики графики.

import pandas as pd
from plotnine import *

# Create data
s1 = StringIO("""
       DayOfWeek  Hotel  Bar  Pool
    0     Sunday     41   32    15
    1     Monday     45   38    24
    2    Tuesday     42   32    27
    3  Wednesday     45   37    23
    4   Thursday     47   34    26
    5     Friday     43   30    19
    6   Saturday     48   30    28

""")

s2 = StringIO("""
   DayOfWeek  Hotel  Bar  Pool
0     Sunday      7    8     6
1     Monday      9    7     5
2    Tuesday      5    4     1
3  Wednesday      8    6     7
4   Thursday      4    5    10
5     Friday      3    1     1
6   Saturday     10    2     6
""")

# Read data
earnings = pd.read_csv(s1, sep="\s+")
tips = pd.read_csv(s2, sep="\s+")

# Make tidy data
kwargs = dict(value_vars=['Hotel', 'Bar', 'Pool'], id_vars=['DayOfWeek'], var_name='location')
days = ['Sunday', 'Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday']
earnings = pd.melt(earnings, value_name='earnings', **kwargs)
tips = pd.melt(tips,  value_name='tip', **kwargs)
df = pd.merge(earnings, tips, on=['DayOfWeek', 'location'])
df['DayOfWeek'] = pd.Categorical(df['DayOfWeek'], categories=days, ordered=True)

# Create plot
p = (ggplot(df)
     + geom_point(aes('DayOfWeek', 'earnings', color='location', size='tip'))
    )
print(p)