. Plotting In Python

[5]:

123

import matplotlib.pyplot as plt
import pandas as pd

[2]:

12345678

# plotting simple line chart
import numpy as np

xpoints = np.array([0, 6])
ypoints = np.array([0, 250])

plt.plot(xpoints, ypoints)
plt.show()

[7]:

12

df=pd.read_csv('./data/fifa_eda.csv') # reading fifa data this file is saved in my current directory/data folder
df.head(1)

	ID	Name	Age	Nationality	Overall	Potential	Club	Value	Wage	Preferred Foot	International Reputation	Skill Moves	Position	Joined	Contract Valid Until	Height	Weight	Release Clause
0	158023	L. Messi	31	Argentina	94	94	FC Barcelona	110500.0	565.0	Left	5.0	4.0	RF	2004	2021-01-01	5.583333	159.0	226500.0

[9]:

123

x=df['Height']
y=df['Weight']
plt.scatter(x,y)

Out[9]:

<matplotlib.collections.PathCollection at 0x7fd54a16ac10>

[21]:

1234

# Plotting age wise average wage in line chart 
tmp_df=df.groupby(['Age'])['Wage'].mean().reset_index()
plt.plot(tmp_df['Age'],tmp_df['Wage'],marker='o',color='b')

Out[21]:

[<matplotlib.lines.Line2D at 0x7fd54c78d400>]

[22]:

12345678

# drawing multiple line charts
y1 = np.array([3, 8, 1, 10])
y2 = np.array([6, 2, 7, 11])

plt.plot(y1)
plt.plot(y2)

plt.show()

[25]:

1234567

# Plotting age wise average wage in line chart 
tmp_df=df.groupby(['Age'])['Wage'].mean().reset_index()
plt.plot(tmp_df['Age'],tmp_df['Wage'],marker='o',color='b')
plt.title("Age wise average wage")
plt.grid()
plt.xlabel('Age')
plt.ylabel('Avg Wage')

Out[25]:

Text(0, 0.5, 'Avg Wage')

[31]:

123456789

# Plotting age wise average wage in line chart 
tmp_df=df.groupby(['Age'])['Wage'].mean().reset_index()
plt.figure(figsize=(20,8))
plt.plot(tmp_df['Age'],tmp_df['Wage'],marker='o',color='b')

plt.title("Age wise average wage")
plt.grid()
plt.xlabel('Age')
plt.ylabel('Avg Wage')

Out[31]:

Text(0, 0.5, 'Avg Wage')

[36]:

12345678

plt.subplot(1,2,1)
tmp_df1=df.groupby(['Age'])['Wage'].mean().reset_index()
tmp_df2=df.groupby(['Age'])['Weight'].mean().reset_index()
plt.plot(tmp_df1['Age'],tmp_df1['Wage'])
plt.title("title1")
plt.subplot(1,2,2)
plt.plot(tmp_df2['Age'],tmp_df2['Weight'])
plt.title("title2")

Out[36]:

Text(0.5, 1.0, 'title2')

[37]:

123456789

# subplot with scatter
plt.subplot(1,2,1)
tmp_df1=df.groupby(['Age'])['Wage'].mean().reset_index()
tmp_df2=df.groupby(['Age'])['Weight'].mean().reset_index()
plt.scatter(tmp_df1['Age'],tmp_df1['Wage'])
plt.title("title1")
plt.subplot(1,2,2)
plt.scatter(tmp_df2['Age'],tmp_df2['Weight'])
plt.title("title2")

Out[37]:

Text(0.5, 1.0, 'title2')

[38]:

1234567891011

#day one, the age and speed of 13 cars:
x = np.array([5,7,8,7,2,17,2,9,4,11,12,9,6])
y = np.array([99,86,87,88,111,86,103,87,94,78,77,85,86])
plt.scatter(x, y)

#day two, the age and speed of 15 cars:
x = np.array([2,2,8,1,15,8,12,9,7,3,11,4,7,14,12])
y = np.array([100,105,84,105,90,99,90,95,94,100,79,112,91,80,85])
plt.scatter(x, y)

plt.show()

[43]:

123

# player position wise average wage
tmp_df=df.groupby(['Position'])['Wage'].mean().reset_index()
tmp_df.head()

	Position	Wage
0	CAM	10.218978
1	CB	7.700393
2	CDM	9.315401
3	CF	10.216216
4	CM	8.334767

[50]:

123

plt.figure(figsize=(20,8))
plt.bar(x=tmp_df['Position'],height=tmp_df['Wage'],color='b')

Out[50]:

[54]:

123

# histograme of age
plt.figure(figsize=(20,8))
plt.hist(df['Age'],bins=len(df['Age'].unique()))

Out[54]:

(array([4.200e+01, 2.890e+02, 7.320e+02, 1.024e+03, 1.240e+03, 1.423e+03, 1.340e+03, 1.332e+03, 1.358e+03, 1.319e+03, 1.387e+03, 1.162e+03, 1.101e+03, 9.590e+02, 9.170e+02, 7.070e+02, 5.740e+02, 4.080e+02, 4.040e+02, 1.960e+02, 1.270e+02, 8.200e+01, 3.700e+01, 2.500e+01, 1.300e+01, 5.000e+00, 1.000e+00, 0.000e+00, 3.000e+00]), array([16., 17., 18., 19., 20., 21., 22., 23., 24., 25., 26., 27., 28., 29., 30., 31., 32., 33., 34., 35., 36., 37., 38., 39., 40., 41., 42., 43., 44., 45.]), <BarContainer object of 29 artists>)

[55]:

1

import seaborn as sns

[58]:

12

plt.figure(figsize=(20,8))
sns.histplot(df['Age'],bins=len(df['Age'].unique()))

Out[58]:

<AxesSubplot:xlabel='Age', ylabel='Count'>

[ ]:

1