Hello Jupyter!

Let's have a look at some tennis racket data and make observations about string patterns.

import pandas as pd
import matplotlib.pyplot as plt

rackets = pd.read_csv("./data/tennis-rackets.csv")

rackets.head(10)

	Model	Brand	Price	Mains	Crosses	Head Size (cm_sq)	Length (cm)	Strung Weight (g)
0	TFight 315 RS	Technifibre	229.0	16	19	632.26	68.58	332
1	Pure Strike 18x20 3rd Gen	Babolat	219.0	18	20	632.26	68.58	323
2	Pure Drive Plus 2021	Babolat	229.0	16	19	645.16	69.85	318
3	Pro Staff RF97 v13	Wilson	249.0	16	19	625.81	68.58	357
4	Triad Five	Wilson	169.0	16	20	664.51	69.22	283
5	Hyper Hammer 5.3 Stretch OS	Wilson	99.0	16	20	709.68	69.85	255
6	Graphene 360+ Instinct PWR	Head	189.0	16	19	741.93	70.36	244

Which 'cross' count is more frequent, 19 or 20?

rackets["Crosses"].value_counts().plot(kind="bar")

<AxesSubplot:>

A cross count of 19 seems to occur slightly more frequently. What is the most frequent stringing pattern if we compare both crosses and mains?

rackets.value_counts(["Mains", "Crosses"]).plot(kind="bar")

<AxesSubplot:xlabel='Mains,Crosses'>

16x19 seems to win by a significant margin, while 18x20 seems rather rare. Perhaps this is a result of our small sample size.