Scatter Plot and Regression plot with "tips" dataset from seaborn package

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
plt.style.use(['dark_background'])
import seaborn as sns
sns.set(color_codes = True)

to place and size the graph to desired size and location

• fig = plt.gcf()
• fig.set_size_inches(8,6)
• plt.legend(bbox_to_anchor = (1,1))

t = sns.load_dataset('tips')

t.head(2)

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3

sns.scatterplot(x='tip', y='total_bill', data = t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975d668890>

sns.scatterplot(x='total_bill', y='tip', data = t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975d668b10>

the above plot conveys that tip is proportional to bill amount, apart from some outliners

t.head(2)

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3

sns.scatterplot(x='tip', y='smoker', data = t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975d06aed0>

t.groupby(t['smoker']).count()

	total_bill	tip	sex	day	time	size
smoker
Yes	93	93	93	93	93	93
No	151	151	151	151	151	151

t.head(2)

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3

sns.scatterplot(x='total_bill', y='size', data=t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975b1d8610>

size = t.groupby(['size']).count()

size

	total_bill	tip	sex	smoker	day	time
size
1	4	4	4	4	4	4
2	156	156	156	156	156	156
3	38	38	38	38	38	38
4	37	37	37	37	37	37
5	5	5	5	5	5	5
6	4	4	4	4	4	4

sns.scatterplot(x='tip', y='size', data=t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975b0fcb90>

t.info(); t.describe()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 244 entries, 0 to 243
Data columns (total 7 columns):
 #   Column      Non-Null Count  Dtype   
---  ------      --------------  -----   
 0   total_bill  244 non-null    float64 
 1   tip         244 non-null    float64 
 2   sex         244 non-null    category
 3   smoker      244 non-null    category
 4   day         244 non-null    category
 5   time        244 non-null    category
 6   size        244 non-null    int64   
dtypes: category(4), float64(2), int64(1)
memory usage: 7.4 KB

	total_bill	tip	size
count	244.000000	244.000000	244.000000
mean	19.785943	2.998279	2.569672
std	8.902412	1.383638	0.951100
min	3.070000	1.000000	1.000000
25%	13.347500	2.000000	2.000000
50%	17.795000	2.900000	2.000000
75%	24.127500	3.562500	3.000000
max	50.810000	10.000000	6.000000

t.head(1)

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2

sns.scatterplot(x='total_bill', y='tip', hue='smoker', data=t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975b08c2d0>

sns.scatterplot(x='total_bill', y='tip', data = t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975b0f0890>

t['frac_tip'] = t['tip']/t['total_bill']

t.head(2)

	total_bill	tip	sex	smoker	day	time	size	frac_tip
0	16.99	1.01	Female	No	Sun	Dinner	2	0.059447
1	10.34	1.66	Male	No	Sun	Dinner	3	0.160542

sns.scatterplot(x='total_bill', y='frac_tip', data = t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975ac14850>

t['tTipFrac'] = (t['tip'] + t['total_bill']) / t['total_bill']

t.head(2)

	total_bill	tip	sex	smoker	day	time	size	frac_tip	tTipFrac
0	16.99	1.01	Female	No	Sun	Dinner	2	0.059447	1.059447
1	10.34	1.66	Male	No	Sun	Dinner	3	0.160542	1.160542

sns.scatterplot(x = "total_bill", y = 'tTipFrac', data = t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975aa2f490>

t.head()

	total_bill	tip	sex	smoker	day	time	size	frac_tip	tTipFrac
0	16.99	1.01	Female	No	Sun	Dinner	2	0.059447	1.059447
1	10.34	1.66	Male	No	Sun	Dinner	3	0.160542	1.160542
2	21.01	3.50	Male	No	Sun	Dinner	3	0.166587	1.166587
3	23.68	3.31	Male	No	Sun	Dinner	2	0.139780	1.139780
4	24.59	3.61	Female	No	Sun	Dinner	4	0.146808	1.146808

t.drop('tTipFrac', inplace = True, axis=1)

t.head()

	total_bill	tip	sex	smoker	day	time	size	frac_tip
0	16.99	1.01	Female	No	Sun	Dinner	2	0.059447
1	10.34	1.66	Male	No	Sun	Dinner	3	0.160542
2	21.01	3.50	Male	No	Sun	Dinner	3	0.166587
3	23.68	3.31	Male	No	Sun	Dinner	2	0.139780
4	24.59	3.61	Female	No	Sun	Dinner	4	0.146808

sns.scatterplot(x = "total_bill", y = 'tip', data = t, hue = 'time')

<matplotlib.axes._subplots.AxesSubplot at 0x7f975af4bdd0>

sns.scatterplot(x = "total_bill", y = 'tip', data = t, hue = 'sex')

<matplotlib.axes._subplots.AxesSubplot at 0x7f975a958590>

sns.scatterplot(x = "total_bill", y = 'tip', data = t, hue = 'smoker')

<matplotlib.axes._subplots.AxesSubplot at 0x7f975a990210>

sns.scatterplot(x = "total_bill", y = 'tip', data = t, hue = 'day')

<matplotlib.axes._subplots.AxesSubplot at 0x7f975aa2fc90>

sns.scatterplot(x = "total_bill", y = 'tip', data = t, hue = 'size')

<matplotlib.axes._subplots.AxesSubplot at 0x7f975a808810>

sns.scatterplot(x = "total_bill", y = 'tip', data = t, hue = 'time', style='sex')

<matplotlib.axes._subplots.AxesSubplot at 0x7f975a1ba150>

fig = plt.gcf()
fig.set_size_inches(15, 6)
sns.scatterplot(x = "total_bill", y = 'tip', data = t, hue = 'time', style='sex', size='size')
plt.legend(bbox_to_anchor=(1, 1))

<matplotlib.legend.Legend at 0x7f9759ee3550>

sns.regplot(x = "total_bill", y = 'tip', data = t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f9759edc050>

t.head(2)

	total_bill	tip	sex	smoker	day	time	size	frac_tip
0	16.99	1.01	Female	No	Sun	Dinner	2	0.059447
1	10.34	1.66	Male	No	Sun	Dinner	3	0.160542

sns.regplot(x = "total_bill", y = 'frac_tip', data = t)

<matplotlib.axes._subplots.AxesSubplot at 0x7f975a0c2450>

sns.regplot(x = "total_bill", y = 'tip', data = t, marker="+")

<matplotlib.axes._subplots.AxesSubplot at 0x7f975a5f91d0>

sns.regplot(x = "total_bill", y = 'tip', data = t, marker=".")

<matplotlib.axes._subplots.AxesSubplot at 0x7f9759fde150>

d = sns.load_dataset('diamonds')

sns.scatterplot('x', 'price', data = d.sample(1000))

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

<matplotlib.axes._subplots.AxesSubplot at 0x7f9759c55550>

sns.regplot('x', 'price', data = d.sample(1000))

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

<matplotlib.axes._subplots.AxesSubplot at 0x7f9759c9ee10>

sns.regplot('x', 'price', data = d.sample(1000), order=2)

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

<matplotlib.axes._subplots.AxesSubplot at 0x7f9759b8f650>

ds = d.sample(1000)

fig = plt.gcf()
fig.set_size_inches(15, 6)
sns.regplot('x', 'price', data = ds, order = 2, marker="+")
plt.legend(bbox_to_anchor=(1, 1))

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
No handles with labels found to put in legend.

<matplotlib.legend.Legend at 0x7f97599c1c90>

fig = plt.gcf()
fig.set_size_inches(15, 6)
sns.regplot('x', 'price', data = ds, order=2)
plt.legend(bbox_to_anchor=(1, 1))

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
No handles with labels found to put in legend.

<matplotlib.legend.Legend at 0x7f97599d3850>

fig = plt.gcf()
fig.set_size_inches(15, 6)
sns.regplot('x', 'price', data = d, order=2)
plt.legend(bbox_to_anchor=(1, 1))

/usr/local/lib/python3.7/dist-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning
No handles with labels found to put in legend.

<matplotlib.legend.Legend at 0x7f975998f710>

ds = sns.load_dataset("tips")
g = sns.FacetGrid(ds, col="time")

g = sns.FacetGrid(ds, col="time")
g.map(sns.histplot, "tip")

<seaborn.axisgrid.FacetGrid at 0x7f9759ce6a50>

g = sns.FacetGrid(ds, col="sex", hue="smoker")
g.map(sns.scatterplot, "total_bill", "tip", alpha=.7)
g.add_legend()

<seaborn.axisgrid.FacetGrid at 0x7f9759b74f10>

g = sns.FacetGrid(ds, col="smoker", row='time')
g.map(sns.scatterplot, "total_bill", "tip", alpha=.7)
g.add_legend()

<seaborn.axisgrid.FacetGrid at 0x7f9756a724d0>

g = sns.FacetGrid(ds, col="day", height=5, aspect=.7)
g.map(sns.barplot, "sex", "total_bill", order=["Male", "Female"])

<seaborn.axisgrid.FacetGrid at 0x7f9756436ad0>

sns.lmplot(x="size", y="tip", data=ds, x_estimator=np.mean);

from mpl_toolkits.mplot3d import Axes3D

fig = plt.figure()
ax = fig.add_subplot(111, projection = '3d')

x = t['tip']
y = t['total_bill']
z = t['size']

ax.set_xlabel("tip")
ax.set_ylabel("total bill")
ax.set_zlabel("size")

ax.scatter(x, y, z)

plt.show()

!pip install nbconvert

%shell jupyter nbconvert --to html /content/testfile.ipynb