import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
import plotly.graph_objects as go
import plotly.express as px
import warnings
from plotly.offline import init_notebook_mode
init_notebook_mode(connected=True)
warnings.filterwarnings('ignore')

sns.set_style("darkgrid")

data=pd.read_csv('C:/Users/Ambuj nayan mishra/Downloads/Most Wickets in Test Cricket .csv')

Quick Access Link:

1. Most wicket taker bowler respect to country:

2. Most wicket taker player:

3. Most Matches played by player:

4. Number of Balls throw by bowler:

5. Most Economical bowler:

6. Most 5 and 10 wickets in a match:

7. Matches vs wickets:

8. Balls vs wicket:

9. Total wickets Country Wise:

10. Conclusion: </div>

1. Most wicket taker bowler respect to country:

f,ax=plt.subplots(1,1,figsize=(25,10))
sns.countplot(x='Country ',data=data,palette ='bright',order=data['Country '].value_counts().index,saturation=0.95)
for container in ax.containers:
    ax.bar_label(container,color='black',size=20)

# Use `hole` to create a donut-like pie chart
fig = go.Figure(data=[go.Pie(labels=['Sri Lanka ', 'Australia ', 'England ', 'India ', 'West Indies','South Africa', 'New Zealand ', 'Pakistan ', 'Zimbabwe','Bangladesh '], values=data['Country '].value_counts(), hole=.3)])
fig.show()    
    

data['Country '].value_counts()

Australia       18
England         15
India           11
South Africa     9
West Indies      8
New Zealand      7
Pakistan         7
Sri Lanka        3
Zimbabwe         1
Bangladesh       1
Name: Country , dtype: int64

Group_data=data.groupby('Country ')
Group_data.get_group('Australia ')

	Rank	Player	Country	Matches	Innings	Balls	Runs	Wickets	Average	Econ	SR	5	10
1	2	S Warne	Australia	145	273	40705	17995	708	25.41	2.65	57.4	37	10
4	5	GD McGrath	Australia	124	243	29248	12186	563	21.64	2.49	51.9	29	3
12	13	NM Lyon	Australia	108	204	27983	13732	427	32.15	2.94	65.5	19	3
23	24	DK Lillee	Australia	70	132	18467	8493	355	23.92	2.75	52.0	23	7
28	29	MG Johnson	Australia	73	140	16001	8891	313	28.40	3.33	51.1	12	3
31	32	B Lee	Australia	76	150	16531	9554	310	30.81	3.46	53.3	10	0
38	39	CJ McDermott	Australia	71	124	16586	8332	291	28.63	3.01	56.9	14	2
39	40	MA Starc	Australia	69	133	14104	7786	282	27.60	3.31	50.0	13	2
43	44	JN Gillespie	Australia	71	137	14234	6770	259	26.13	2.85	54.9	8	0
47	48	R Benaud	Australia	63	116	19108	6704	248	27.03	2.10	77.0	16	1
49	50	GD McKenzie	Australia	60	113	17681	7328	246	29.78	2.48	71.8	16	3
63	64	RR Lindwall	Australia	61	113	13650	5251	228	23.03	2.30	59.8	12	0
67	68	PM Siddle	Australia	67	126	13907	6777	221	30.66	2.92	62.9	8	0
69	70	CV Grimmett	Australia	37	67	14513	5231	216	24.21	2.16	67.1	21	7
71	72	JR Hazlewood	Australia	57	107	12235	5573	215	25.92	2.73	56.9	9	0
74	75	MG Hughes	Australia	53	97	12285	6017	212	28.38	2.93	57.9	7	1
75	76	SCG MacGill	Australia	44	85	11237	6038	208	29.02	3.22	54.0	12	2
79	80	JR Thomson	Australia	51	90	10535	5601	200	28.00	3.18	52.6	8	0

2. Most wicket taker player:

Group_data['Player '].head(2).values

array(['M Muralidaran ', 'S Warne', 'JM Anderson ', 'A Kumble ',
       'GD McGrath', 'SCJ Broad', 'CA Walsh ', 'R Ashwin ', 'DW Steyn ',
       'HMRKB Herath ', 'Sir RJ Hadlee', 'SM Pollock ', 'Wasim Akram ',
       'CEL Ambrose', 'Waqar Younis ', 'DL Vettori', 'HH Streak ',
       'Shakib Al Hasan '], dtype=object)

Group_data['Wickets '].head(2).values

array([800, 708, 640, 619, 563, 537, 519, 442, 439, 433, 431, 421, 414,
       405, 373, 362, 216, 215], dtype=int64)

df = px.data.tips()
fig = px.bar(Group_data, x=Group_data['Player '].head(2).values, y=Group_data['Wickets '].head(2).values,
             color=Group_data['Wickets '].head(2),
             labels={'y':'Wickets','x':'Player'}, height=600)
fig.update_traces(textfont_size=12, textangle=0, textposition="outside", cliponaxis=False)
fig.show()

df = px.data.tips()
fig = px.bar(Group_data, x=Group_data['Wickets '].head(1).values, y=Group_data['Player '].head(1).values, color=Group_data['Country '].head(1).values, orientation='h',
             height=600,labels={'y':'Players','x':'Wickets'})
fig.show()

fig = go.Figure(go.Funnel(
    y = data['Player '].values,
    x = data['Wickets '].values))

fig.show()

Observation:- Most wicket taker bowler is M. Muralidaran.

Observation:-Second wicket taker bowler is S. Warne.

Group_data['Matches'].max().sort_values(ascending=False)

Country 
England         169
South Africa    166
Australia       145
Sri Lanka       133
India           132
West Indies     132
New Zealand     113
Pakistan        104
Zimbabwe         65
Bangladesh       59
Name: Matches, dtype: int64

3. Most Matches played by player:

Group_data['Matches'].head(2).values

array([133, 145, 169, 132, 124, 152, 132,  86,  93,  93,  86, 108, 104,
        98,  87, 113,  65,  59], dtype=int64)

#Group_data['Matches'].max().sort_values(ascending=False)
Group_data['Player '].head(2).values

array(['M Muralidaran ', 'S Warne', 'JM Anderson ', 'A Kumble ',
       'GD McGrath', 'SCJ Broad', 'CA Walsh ', 'R Ashwin ', 'DW Steyn ',
       'HMRKB Herath ', 'Sir RJ Hadlee', 'SM Pollock ', 'Wasim Akram ',
       'CEL Ambrose', 'Waqar Younis ', 'DL Vettori', 'HH Streak ',
       'Shakib Al Hasan '], dtype=object)

df = px.data.tips()
fig = px.bar(Group_data, x=Group_data['Player '].head(1).values, y=Group_data['Matches'].head(1).values,
             color=Group_data['Matches'].head(1),labels={'x':'Players','y':'Matches'},height=600,color_continuous_scale=px.colors.sequential.Inferno)
fig.show()

Observation:- Most matches played player JM Anderson

4. Number of Balls throw by bowler:

f,ax=plt.subplots(1,1,figsize=(30,16))
sns.barplot(x=Group_data['Player '].head(2).values, y=Group_data['Balls '].head(2).values,palette = 'bright',saturation=0.95)
for container in ax.containers:
    ax.bar_label(container,color='black',size=20)

Observation:- Most Balls throw by bowler is M. Muralidaran

5. Most Economical bowler:

df = px.data.tips()
fig = px.bar(Group_data, x=Group_data['Player '].head(1).values, y=Group_data['Econ'].head(1).values,
             color=Group_data['Econ'].head(1),
             labels={'y':'Economical','x':'Player'}, height=600,color_continuous_scale=px.colors.sequential.Magenta)
fig.show()

Observation:- Most Economical bowler is M. Muralidaran.

6. Most 5 and 10 wickets in a match:

df = px.data.tips()
fig = px.bar(Group_data, y=Group_data['Player '].head(2).values, x=Group_data['5'].head(2).values,
             color=Group_data['5'].head(2),
             labels={'x':'5 Wickets','y':'Player'}, height=600,color_continuous_scale=px.colors.sequential.Jet)
fig.show()

df = px.data.tips()
fig = px.bar(Group_data, x=Group_data['Player '].head(2).values, y=Group_data['10'].head(2).values,
             color=Group_data['10'].head(2),
             labels={'y':'10 Wickets','x':'Player'}, height=600,color_continuous_scale=px.colors.sequential.Blackbody)
fig.show()

Observation:- Most 5 and 10 wickets taken in a match by M. Muralidaran.

7. Matches vs wickets:

df = px.data.iris()
fig = px.scatter(data, x='Matches', y='Wickets ', size='Wickets ',color='Wickets ')
fig.show()

f,ax=plt.subplots(1,1,figsize=(18,10))
#sns.scatterplot(data["Matches"], data["Wickets "],hue=data['Country '])
sns.lineplot(data['Matches'],data['Wickets '], hue =data["Country "])

<AxesSubplot:xlabel='Matches', ylabel='Wickets '>

fig = px.scatter(data, x="Matches", y="Wickets ", trendline="ols",
                 labels={"Matches": "Matches",
                         "Wickets ": "Wickets"})
fig.update_layout(title_text='Relationship between Matches and Wickets',
                  title_x=0.5, title_font=dict(size=20))
fig.data[1].line.color = 'red'
fig.show()

Observation:- As you can see whosoever played more matches he gets more wickets.

8. Balls vs wicket:

df = px.data.gapminder()
fig = px.line(data, x='Balls ', y='Wickets ', color='Player ', markers=True)
fig.show()

px.defaults.color_continuous_scale = px.colors.sequential.Blackbody
df = px.data.iris()
fig = px.scatter(data, x='Balls ', y='Wickets ', size='Wickets ',color='Wickets ',color_continuous_scale=px.colors.sequential.Jet)
fig.show()

9. Total wickets Country Wise:

df = px.data.tips()
fig = px.ecdf(data, x="Matches", y='Wickets ',color='Country ',ecdfnorm=None)
fig.show()

df = px.data.gapminder()
fig = px.sunburst(data, path=['Country ','Player ','Matches', 'Wickets '], values='Wickets ',
                  color='Wickets ', hover_data=['Player '],height=800)
fig.show()

10. Conclusion:

Eleven years ago, Muttiah Muralitharan became the first and till now the only man to have picked up 800 wickets in Test cricket. While the saying goes that records are meant to be broken, this particular achievement of Murali may be a feat too high for anyone to achieve.