Icc Worldcup 2023 Winner Prediction Output PDF

11/4/23, 12:54 AM icc-worldcup-2023-winner-prediction
Import libraries
In [83]: # Importing necessary libraries for data analysis and visualization
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
In [84]: # Read the data from "World_cup_2023.csv" into the 'World_cup' DataFrame
World_cup = pd.read_csv("World_cup_2023.csv")
# Read the data from "results.csv" into the 'results' DataFrame

results = pd.read_csv("results.csv")
In [85]: # Display the first few rows of the World_cup DataFrame.

World_cup
Out[85]: Team_name Team_ranking Titles Win_percentage_ODI WC_matches WC_match_won Win_perc
0 Australia 1 5 60.73 94 69
1 Pakistan 2 1 52.78 79 45
2 India 3 2 52.38 84 53
New
3 4 0 45.89 89 54
Zealand
4 England 5 1 50.32 83 48
5 South Africa 6 0 61.00 64 38
6 Bangladesh 7 0 36.65 40 14
7 Afghanistan 8 0 49.65 15 1
8 Sri Lanka 9 1 45.74 80 38
9 Netherlands 10 0 34.21 20 2
No.of titles won by each teams

In [86]: # Set the figure size using sns.set
sns.set(rc={'figure.figsize':(20, 5)})
# Create a bar plot using sns.barplot to visualize team titles

sns.barplot(x='Team_name', y='Titles', data=World_cup)
# Display the plot

plt.show()
localhost:8890/nbconvert/html/icc-worldcup-2023-winner-prediction.ipynb?download=false 1/46
Win percentage in ODI by each team

In [87]: # Set the figure size for the bar plot using Seaborn
# Create a bar plot using Seaborn

sns.barplot(x='Team_name', y='Win_percentage_ODI', data=World_cup)
# Display the plot

plt.show()
No.of matches won in world cup by each team

# Create a bar plot using Seaborn

sns.barplot(x='Team_name', y='WC_match_won', data=World_cup)
# Display the plot

plt.show()
Recent ICC ODI rating
# Create a bar plot using Seaborn to display recent ratings of teams

sns.barplot(x='Team_name', y='Rating', data=World_cup)
# Display the plot

plt.show()
In [90]: # Displaying the first few rows of the results DataFrame.

results.head()
Out[90]: Date Team_1 Team_2 Winner Margin Ground
Shere Bangla National

0 17/04/2015 Bangladesh Pakistan Bangladesh won by 79 runs
Stadium
won by 7 Shere Bangla National

1 19/04/2015 Bangladesh Pakistan Bangladesh
wickets Stadium
won by 8 Shere Bangla National

2 22/04/2015 Bangladesh Pakistan Bangladesh
wickets Stadium
3 08/05/2015 Ireland England No result No result The Village
4 26/05/2015 Pakistan Zimbabwe Pakistan won by 41 runs Gaddafi Stadium
In [91]: # Removing rows with 'Match abandoned' and 'No result' from the 'results' DataFrame
results.drop(results[(results['Winner'] == 'Match abandoned' )].index, inplace=True
results.drop(results[(results['Winner'] == 'No result' )].index, inplace=True)
Stats of top five teams in the ODI world cup 2023
Stats of Indian team

In [92]: # Filter the 'results' DataFrame to include rows where India played either as Team_
df = results[(results['Team_1'] == 'India') | (results['Team_2'] == 'India')]
# Create a new DataFrame 'India' containing all rows from the filtered DataFrame
India = df.iloc[:]
# Display the first few rows of the 'India' DataFrame

India.head()
11 18/06/2015 Bangladesh India Bangladesh won by 79 runs Shere Bangla National Stadium
13 21/06/2015 Bangladesh India Bangladesh won by 6 wickets Shere Bangla National Stadium
14 24/06/2015 Bangladesh India India won by 77 runs Shere Bangla National Stadium
16 10/07/2015 Zimbabwe India India won by 4 runs Harare Sports Club
19 12/07/2015 Zimbabwe India India won by 62 runs Harare Sports Club
In [93]: # Filtering the 'India' dataframe to create a new dataframe 'India_win' containing
India_win = India[India['Winner']=='India']
In [94]: India_win
won by 77
14 24/06/2015 Bangladesh India India Shere Bangla National Stadium
runs
won by 4
16 10/07/2015 Zimbabwe India India Harare Sports Club
runs
won by 62
runs
won by 83
runs
won by 6
73 23/01/2016 Australia India India Sydney Cricket Ground
wickets
won by 9
wickets
won by 8
wickets
won by 10
wickets
New won by 7 Punjab Cricket Association IS

141 23/10/2016 India India
Zealand wickets Bindra Stadium
won by 6
288 01/02/2018 South Africa India India Kingsmead
wickets
won by 9
289 04/02/2018 South Africa India India SuperSport Park
wickets
won by 124
290 07/02/2018 South Africa India India Newlands
runs
won by 73
295 13/02/2018 South Africa India India St George's Park
runs
won by 8
297 16/02/2018 South Africa India India SuperSport Park
wickets
won by 8
314 12/07/2018 England India India Trent Bridge
wickets
won by 26 Dubai International Cricket

338 18/09/2018 Hong Kong India India
runs Stadium

341 21/09/2018 Bangladesh India India
wickets Stadium

wickets Stadium
West won by 9
363 01/11/2018 India India Greenfield International Stadium
Indies wickets
New won by 35
387 03/02/2019 India India Sky Stadium
Zealand runs
won by 36
448 09/06/2019 Australia India India Kennington Oval
runs
won by 11
464 22/06/2019 Afghanistan India India The Rose Bowl
runs
won by 28
476 02/07/2019 Bangladesh India India Edgbaston
runs
Date Team_1 Team_2 Winner Margin Ground
won by 59
488 11/08/2019 West Indies India India Queen's Park Oval
runs
won by 6
wickets
West won by 107 Dr YS Rajasekhara Reddy Cricket

497 18/12/2019 India India
Indies runs Stadium
West won by 4
498 22/12/2019 India India Barabati Stadium
Indies wickets
won by 36 Saurashtra Cricket Association

499 17/01/2020 India Australia India
runs Stadium
won by 7
500 19/01/2020 India Australia India M Chinnaswamy Stadium
wickets
won by 13
530 02/12/2020 Australia India India Manuka Oval
runs
won by 66 Maharashtra Cricket Association

540 23/03/2021 India England India
runs Stadium
won by 7 Maharashtra Cricket Association

544 28/03/2021 India England India
runs Stadium
won by 7
566 18/07/2021 Sri Lanka India India R Premadasa Stadium
wickets
won by 3
569 20/07/2021 Sri Lanka India India R Premadasa Stadium
wickets
West won by 6
588 06/02/2022 India India Narendra Modi Stadium
Indies wickets
West won by 44
Indies runs
West won by 96
Indies runs
won by 10
621 12/07/2022 England India India Kennington Oval
wickets
won by 5
627 17/07/2022 England India India Old Trafford
wickets
won by 3
runs
won by 2
wickets
won by 119
runs
won by 10
wickets
won by 5
wickets
won by 13
runs
South won by 7 JSCA International Stadium

654 09/10/2022 India India
Africa wickets Complex
South won by 7
655 11/10/2022 India India Arun Jaitley Stadium
Africa wickets
won by 227 Zahur Ahmed Chowdhury

runs Stadium
won by 67
669 10/01/2023 India Sri Lanka India Barsapara Cricket Stadium
runs
won by 4
671 12/01/2023 India Sri Lanka India Eden Gardens
wickets
won by 317
672 15/01/2023 India Sri Lanka India Greenfield International Stadium
runs
New won by 12 Rajiv Gandhi International

673 18/01/2023 India India
Zealand runs Stadium
New won by 8 Shaheed Veer Narayan Sing

674 21/01/2023 India India
Zealand wickets International Stadium
New won by 90
675 24/01/2023 India India Holkar Cricket Stadium
Zealand runs
won by 5
683 17/03/2023 India Australia India Wankhede Stadium
wickets
No.of wins in ODIs against other teams

In [95]: # Exclude Team India's name
excluded_value = 'India'
# Filtering out rows with the excluded value

filtered_df = India_win[India_win['Team_2'] != excluded_value]
# Counting the occurrences of each value in the filtered DataFrame's 'Team_2' colum
value_counts = filtered_df['Team_2'].value_counts()
# Print the value counts

print(value_counts)
West Indies 6
New Zealand 4
Australia 3
Sri Lanka 3
England 2
South Africa 2
Name: Team_2, dtype: int64
In [96]: # Exclude Team India's name

excluded_value = 'India'

filtered_df = India_win[India_win['Team_1'] != excluded_value]

print(value_counts)
Zimbabwe 5
South Africa 5
West Indies 5
Bangladesh 4
Zimbabwe 4
Australia 2
Sri Lanka 2
England 2
England 1
Hong Kong 1
New Zealand 1
Afghanistan 1
Australia 1
Bangladesh 1
Displaying Team India's wins against other teams

using bar graph
In [97]: # Exclude Team India
exclude = 'India'
# Filter out the opponent to exclude from the data

filtered_data = India_win[India_win['Team_2'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by India.

plt.figure(figsize=(8, 5))
plt.bar(list(filtered_data['Team_2'].value_counts()[0:5].keys()), list(filtered_dat
plt.show()
In [98]: # Exclude Team India

exclude = 'India'

filtered_data = India_win[India_win['Team_1'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by India.

plt.show()
Win Percentage of India Against Each Team

In [99]: # Number of wins against each team
# Out of the 1032 ODI matches played by India, number of matches won against the fo
team_win_counts = {
'Australia': 54,
'New Zealand': 58,
'South Africa ': 37,
'Pakistan': 55,
'Sri Lanka': 93,
'Bangladesh': 30,
'England': 57,
'Netherlands': 2,
'Afghanistan': 3
}
# Total matches played is calculated

total_matches = sum(team_win_counts.values())
# India's win percentages against each team is calculated

win_percentages = {team: (wins / total_matches) * 100 for team, wins in team_win_co
# Pie chart
plt.pie(win_percentages.values(), labels=win_percentages.keys(), autopct='%1.1f%%',
# Equal aspect ratio ensures that pie is drawn as a circle.

plt.axis('equal')
# Title for the pie chart

plt.title('Win Percentage of India Against Each Team')
# Display the pie chart

plt.show()
Win Percentage of India in the ODI world cup

In [100… # Number of wins against each team in the ODI world cup
# Out of the 84 ODI matches played by India in the ODI world cup, number of matches
team_win_counts_wc_ind = {
'Australia': 4,
'New Zealand': 3,
'South Africa ': 2,
'Pakistan': 7,
'Sri Lanka': 5,
'Bangladesh': 3,
'England': 3,
'Netherlands': 2,
'Afghanistan': 2
}

total_matches_wc_ind = sum(team_win_counts_wc_ind.values())
# India's win percentages against each team is calculated

win_percentages_wc_ind = {team: (wins / total_matches_wc_ind) * 100 for team, wins
# Pie chart
plt.pie(win_percentages_wc_ind.values(), labels=win_percentages_wc_ind.keys(), auto

plt.axis('equal')

plt.title('Win Percentage of India in the ODI world cup')

plt.show()
Stats of Australian team

In [101… # Filter the 'results' DataFrame to include rows where Australia played either as T
df1 = results[(results['Team_1'] == 'Australia') | (results['Team_2'] == 'Australia
# Create a new DataFrame 'Australia' containing all rows from the filtered DataFram
Australia = df1.iloc[:]
# Display the first few rows of the 'Australia' DataFrame

Australia.head()
32 27/08/2015 Ireland Australia Australia won by 23 runs Civil Service Cricket Club
33 03/09/2015 England Australia Australia won by 59 runs The Rose Bowl
34 05/09/2015 England Australia Australia won by 64 runs Lord's
35 08/09/2015 England Australia England won by 93 runs Old Trafford
36 11/09/2015 England Australia England won by 3 wickets Headingley
In [102… # Filtering the 'Australia' dataframe to create a new dataframe 'Australia_win' con
Australia_win = Australia[Australia['Winner']=='Australia']
In [103… Australia_win
won by 8
37 12/09/2015 England Australia Australia Old Trafford
wickets
New won by 4
79 06/02/2016 Australia Australia Sky Stadium
Zealand wickets
won by 6
85 05/06/2016 West Indies Australia Australia Providence Stadium
wickets
South won by 36
88 11/06/2016 Australia Australia Warner Park
Africa runs
won by 6
97 21/06/2016 West Indies Australia Australia Kensington Oval
wickets
won by 58
runs
won by 3
113 21/08/2016 Sri Lanka Australia Australia R Premadasa Stadium
wickets
won by 2 Rangiri Dambulla International

117 28/08/2016 Sri Lanka Australia Australia
wickets Stadium

wickets Stadium
won by 5 Pallekele International Cricket

wickets Stadium
won by 7
161 19/01/2017 Australia Pakistan Australia WACA Ground
wickets
won by 86
163 22/01/2017 Australia Pakistan Australia Sydney Cricket Ground
runs
won by 57
164 26/01/2017 Australia Pakistan Australia Adelaide Oval
runs
won by 3
285 26/01/2018 Australia England Australia Adelaide Oval
wickets
won by 32 JSCA International Stadium

403 08/03/2019 India Australia Australia
runs Complex
won by 4 Punjab Cricket Association IS

wickets Bindra Stadium
won by 35
409 13/03/2019 India Australia Australia Arun Jaitley Stadium
runs
won by 8
411 22/03/2019 Pakistan Australia Australia Sharjah Cricket Stadium
wickets
won by 8
412 23/03/2019 Pakistan Australia Australia Sharjah Cricket Stadium
wickets
won by 80
413 27/03/2019 Pakistan Australia Australia Sheikh Zayed Stadium
runs

414 29/03/2019 Pakistan Australia Australia
runs Stadium

415 31/03/2019 Pakistan Australia Australia
runs Stadium
won by 7
438 01/06/2019 Afghanistan Australia Australia County Ground (Bristol)
wickets
won by 64
468 25/06/2019 England Australia Australia Lord's
runs
New won by 71
517 13/03/2020 Australia Australia Sydney Cricket Ground
Zealand runs
won by 19
runs
won by 3
wickets
won by 66
528 27/11/2020 Australia India Australia Sydney Cricket Ground
runs
won by 51
529 29/11/2020 Australia India Australia Sydney Cricket Ground
runs
won by 133
runs
won by 6
wickets
won by 88
598 29/03/2022 Pakistan Australia Australia Gaddafi Stadium
runs

wickets Stadium
won by 4
618 24/06/2022 Sri Lanka Australia Australia R Premadasa Stadium
wickets
won by 5
647 28/08/2022 Australia Zimbabwe Australia Riverway Stadium
wickets
won by 8
648 31/08/2022 Australia Zimbabwe Australia Riverway Stadium
wickets
New won by 2
650 06/09/2022 Australia Australia Cazaly's Stadium
Zealand wickets
New won by 113

Zealand runs
New won by 25
Zealand runs
won by 6
656 17/11/2022 Australia England Australia Adelaide Oval
wickets
won by 72
657 19/11/2022 Australia England Australia Sydney Cricket Ground
runs
won by 221
658 22/11/2022 Australia England Australia Melbourne Cricket Ground
runs
won by 10 Dr YS Rajasekhara Reddy

wickets Cricket Stadium
won by 21
690 22/03/2023 India Australia Australia MA Chidambaram Stadium
runs
No.of wins for Australia against other teams
In [104… # Exclude Team Australia's name

excluded_value = 'Australia'

filtered_df = Australia_win[Australia_win['Team_2'] != excluded_value]

print(value_counts)
England 4
New Zealand 4
Pakistan 2
India 2
Zimbabwe 2
South Africa 1
Pakistan 1
In [105… # Exclude Team Australia's name

excluded_value = 'Australia'

filtered_df = Australia_win[Australia_win['Team_1'] != excluded_value]

print(value_counts)
Sri Lanka 4
Pakistan 4
West Indies 3
India 3
England 2
Pakistan 2
England 2
West Indies 2
Sri Lanka 2
India 2
New Zealand 1
Afghanistan 1
Displaying Team Australia's wins against other

teams using bar graph
In [106… # Exclude Team Austrlia
exclude = 'Australia'

filtered_data = Australia_win[Australia_win['Team_2'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by Australlia.

plt.show()
In [107… # Exclude Team Austrlia

exclude = 'Australia'

filtered_data = Australia_win[Australia_win['Team_1'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by Australlia.

plt.show()
Win Percentage of Australia Against Each Team

In [108… # Number of wins against each team
# Out of the 978 ODI matches played by Australia, number of matches won against the
team_win_counts = {
'India': 82,
'New Zealand': 95,
'Pakistan': 69,
'Sri Lanka': 63,
'Bangladesh': 19,
'England': 87,
'Netherlands': 2,
'Afghanistan': 3
}

# Australia's win percentages against each team is calculated

# Pie chart

plt.axis('equal')

plt.title('Win Percentage of Australia Against Each Team')

plt.show()
Win Percentage of Australia in the ODI world cup

# Out of the 94 ODI matches played by Australia in the ODI world cup, number of mat
team_win_counts_wc_aus = {
'India': 8,
'New Zealand': 8,
'South Africa ': 3,
'Pakistan': 6,
'Sri Lanka': 8,
'Bangladesh': 3,
'England': 6,
'Netherlands': 2,
'Afghanistan': 2
}

total_matches_wc_aus = sum(team_win_counts_wc_aus.values())
# Australia's win percentages against each team is calculated
win_percentages_wc_aus = {team: (wins / total_matches_wc_aus) * 100 for team, wins
# Pie chart
plt.pie(win_percentages_wc_aus.values(), labels=win_percentages_wc_aus.keys(), auto

plt.axis('equal')

plt.title('Win Percentage of Australia in the ODI world cup')

plt.show()
Stats of Pakistan team

In [110… # Filter the 'results' DataFrame to include rows where Pakistan played either as Te
df2 = results[(results['Team_1'] == 'Pakistan') | (results['Team_2'] == 'Pakistan')
# Create a new DataFrame 'Pakistan' containing all rows from the filtered DataFrame
Pakistan = df2.iloc[:]
# Display the first few rows of the 'Pakistan' DataFrame

Pakistan.head()
won by 79
0 17/04/2015 Bangladesh Pakistan Bangladesh Shere Bangla National Stadium
runs
won by 7
wickets
won by 8
wickets

17 11/07/2015 Sri Lanka Pakistan Pakistan
wickets Stadium

21 15/07/2015 Sri Lanka Pakistan Sri Lanka
wickets Stadium
In [111… # Filtering the 'Pakistan' dataframe to create a new dataframe 'Pakistan_win' conta
Pakistan_win = Pakistan[Pakistan['Winner']=='Pakistan']
In [112… Pakistan_win

17 11/07/2015 Sri Lanka Pakistan Pakistan
wickets Stadium
won by 135
23 19/07/2015 Sri Lanka Pakistan Pakistan R Premadasa Stadium
runs
won by 7
24 22/07/2015 Sri Lanka Pakistan Pakistan R Premadasa Stadium
wickets
won by 131
38 01/10/2015 Zimbabwe Pakistan Pakistan Harare Sports Club
runs
won by 7
40 05/10/2015 Zimbabwe Pakistan Pakistan Harare Sports Club
wickets
won by 255
111 18/08/2016 Ireland Pakistan Pakistan The Village
runs
won by 4
121 04/09/2016 England Pakistan Pakistan Sophia Gardens
wickets
won by 6
159 15/01/2017 Australia Pakistan Pakistan Melbourne Cricket Ground
wickets
won by 201
315 13/07/2018 Zimbabwe Pakistan Pakistan Queens Sports Club
runs
won by 9
wickets
won by 9
wickets
won by 244
runs
won by 131
runs

336 16/09/2018 Hong Kong Pakistan Pakistan
wickets Stadium
won by 3
342 21/09/2018 Afghanistan Pakistan Pakistan Sheikh Zayed Stadium
wickets
won by 8
383 27/01/2019 South Africa Pakistan Pakistan Wanderers Stadium
wickets
won by 14
440 03/06/2019 England Pakistan Pakistan Trent Bridge
runs
New won by 6
469 26/06/2019 Pakistan Pakistan Edgbaston
Zealand wickets
won by 3
472 29/06/2019 Afghanistan Pakistan Pakistan Headingley
wickets
won by 67
491 30/09/2019 Pakistan Sri Lanka Pakistan National Stadium (Karachi)
runs
won by 5
492 02/10/2019 Pakistan Sri Lanka Pakistan National Stadium (Karachi)
wickets
won by 26
526 30/10/2020 Pakistan Zimbabwe Pakistan Rawalpindi Cricket Stadium
runs
won by 6
527 01/11/2020 Pakistan Zimbabwe Pakistan Rawalpindi Cricket Stadium
wickets
won by 3
545 02/04/2021 South Africa Pakistan Pakistan SuperSport Park
wickets
won by 28
547 07/04/2021 South Africa Pakistan Pakistan SuperSport Park
runs
won by 6
599 31/03/2022 Pakistan Australia Pakistan Gaddafi Stadium
wickets
won by 9
600 02/04/2022 Pakistan Australia Pakistan Gaddafi Stadium
wickets
won by 5
607 08/06/2022 Pakistan West Indies Pakistan Multan Cricket Stadium
wickets
won by 120
runs
won by 53
runs
won by 16
638 16/08/2022 Netherlands Pakistan Pakistan Hazelaarweg
runs
won by 7
wickets
won by 9
runs
New won by 6
668 09/01/2023 Pakistan Pakistan National Stadium (Karachi)
Zealand wickets
New won by 5
698 27/04/2023 Pakistan Pakistan Rawalpindi Cricket Stadium
Zealand wickets
New won by 7
699 29/04/2023 Pakistan Pakistan Rawalpindi Cricket Stadium
Zealand wickets
New won by 26
Zealand runs
New won by 102

Zealand runs
No.of wins for Pakistan against other teams

In [113… # Exclude Team Pakistan's name
excluded_value = 'Pakistan'

filtered_df = Pakistan_win[Pakistan_win['Team_2'] != excluded_value]

print(value_counts)
New Zealand 5
West Indies 3
Sri Lanka 2
Zimbabwe 2
Australia 2
In [114… # Exclude Team Pakistan's name

excluded_value = 'Pakistan'

filtered_df = Pakistan_win[Pakistan_win['Team_1'] != excluded_value]

print(value_counts)
Zimbabwe 7
Sri Lanka 3
Netherlands 3
England 2
Afghanistan 2
South Africa 2
Ireland 1
Australia 1
Hong Kong 1
South Africa 1
New Zealand 1
Displaying Team Pakistan's wins against other teams

using bar graph
In [115… # Exclude Team Pakistan
exclude = 'Pakistan'

filtered_data = Pakistan_win[Pakistan_win['Team_2'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by Pakistan.

plt.show()
In [116… # Exclude Team Pakistan

exclude = 'Pakistan'

filtered_data = Pakistan_win[Pakistan_win['Team_1'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by Pakistan.

plt.show()
Win Percentage of Pakistan Against Each Team

# Out of the 945 ODI matches played by Pakistan, number of matches won against the
team_win_counts = {
'India': 73,
'New Zealand': 60,
'Australia': 34,
'Sri Lanka': 92,
'Bangladesh': 32,
'England': 32,
'Netherlands': 3,
'Afghanistan': 7
}

# Pakistan's win percentages against each team is calculated

# Pie chart

plt.axis('equal')

plt.title('Win Percentage of Pakistan Against Each Team')

plt.show()
Win Percentage of Pakistan in the ODI world cup

# Out of the 79 ODI matches played by Pakistan in the ODI world cup, number of matc
team_win_counts_wc_pak = {
'India': 0,
'New Zealand': 7,
'South Africa ': 2,
'Australia': 4,
'Sri Lanka': 7,
'Bangladesh': 1,
'England': 5,
'Afghanistan': 1
}

total_matches_wc_pak = sum(team_win_counts_wc_pak.values())
# Pakistan's win percentages against each team is calculated

win_percentages_wc_pak = {team: (wins / total_matches_wc_pak) * 100 for team, wins
# Pie chart
plt.pie(win_percentages_wc_pak.values(), labels=win_percentages_wc_pak.keys(), auto

plt.axis('equal')

plt.title('Win Percentage of Pakistan in the ODI world cup')

plt.show()
Stats of New Zealand team

In [119… # Filter the 'results' DataFrame to include rows where New Zealand played either as
df3 = results[(results['Team_1'] == 'New Zealand') | (results['Team_2'] == 'New Zea
# Create a new DataFrame 'New Zealand' containing all rows from the filtered DataFr
New_Zealand = df3.iloc[:]
# Display the first few rows of the 'India' DataFrame

New_Zealand.head()
7 09/06/2015 England New Zealand England won by 210 runs Edgbaston
8 12/06/2015 England New Zealand New Zealand won by 13 runs Kennington Oval
9 14/06/2015 England New Zealand New Zealand won by 3 wickets The Rose Bowl
10 17/06/2015 England New Zealand England won by 7 wickets Trent Bridge
12 20/06/2015 England New Zealand England won by 3 wickets Riverside Ground
In [120… # Filtering the 'New_Zealand' dataframe to create a new dataframe 'nz_win' containi
nz_win = New_Zealand[New_Zealand['Winner']=='New Zealand']
In [121… nz_win
New New won by 10

27 04/08/2015 Zimbabwe Harare Sports Club
Zealand Zealand wickets
New New won by 38

28 07/08/2015 Zimbabwe Harare Sports Club
Zealand Zealand runs
New New won by 3

76 31/01/2016 Pakistan Eden Park
New New won by 55

81 08/02/2016 Australia Seddon Park
New New won by 6

140 20/10/2016 India Arun Jaitley Stadium
New New won by 19 JSCA International Stadium

142 26/10/2016 India
Zealand Zealand runs Complex
New New won by 77

154 26/12/2016 Bangladesh Hagley Oval
New New won by 51

200 14/05/2017 Ireland The Village
New New won by 61

271 06/01/2018 Pakistan Basin Reserve
New New won by 47

365 07/11/2018 Pakistan Sheikh Zayed Stadium
New New won by 45

372 03/01/2019 Sri Lanka Bay Oval
New New won by 8

New New won by 2

443 05/06/2019 Bangladesh Kennington Oval
New New won by 7 The Cooper Associates

447 08/06/2019 Afghanistan
Zealand Zealand wickets County Ground
New New won by 4

460 19/06/2019 South Africa Edgbaston
New New won by 18

481 09/07/2019 India Old Trafford
New New won by 4

502 05/02/2020 India Seddon Park
New New won by 22

504 08/02/2020 India Eden Park
New New won by 5

506 11/02/2020 India Bay Oval
New New won by 8

539 20/03/2021 Bangladesh University Oval
New New won by 5

New New won by 164

543 26/03/2021 Bangladesh Basin Reserve
New New won by 7

597 29/03/2022 Netherlands Bay Oval
New New won by 118

601 03/04/2022 Netherlands Seddon Park
New New won by 115

602 04/04/2022 Netherlands Seddon Park
New New won by 1

Zealand Zealand wicket
New New won by 3

New New
625 15/07/2022 Ireland won by 1 run The Village
Zealand Zealand
New New won by 7

634 31/07/2022 Scotland Grange Cricket Club
New New won by 50

642 19/08/2022 West Indies Kensington Oval
New New won by 5

645 21/08/2022 West Indies Kensington Oval
New New won by 7

659 25/11/2022 India Eden Park
New New won by 79

670 11/01/2023 Pakistan National Stadium (Karachi)
New New won by 198

693 25/03/2023 Sri Lanka Eden Park
New New won by 6

697 31/03/2023 Sri Lanka Seddon Park
New New won by 47

702 07/05/2023 Pakistan National Stadium (Karachi)
No.of wins for New Zealand in ODIs against other

teams
In [122… # Exclude Team New Zealand's name
excluded_value = 'New Zealand'

filtered_df = nz_win[nz_win['Team_2'] != excluded_value]

print(value_counts)
Bangladesh 5
India 4
Sri Lanka 3
Netherlands 3
Pakistan 2
Australia 1
South Africa 1
In [123… # Exclude Team New Zealand's name

excluded_value = 'New Zealand'

filtered_df = nz_win[nz_win['Team_1'] != excluded_value]

print(value_counts)
India 3
Pakistan 3
Ireland 3
Zimbabwe 2
West Indies 2
Ireland 1
Bangladesh 1
Afghanistan 1
Scotland 1
Displaying Team New Zealand's wins against other

teams using bar graph
In [124… # Exclude Team New Zealand
exclude = 'New Zealand'

filtered_data = nz_win[nz_win['Team_2'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by New Zealand.
plt.show()
In [125… # Exclude Team New Zealand

exclude = 'New Zealand'

filtered_data = nz_win[nz_win['Team_1'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by New Zealand.
plt.show()
Win Percentage of New Zealand Against Each Team

# Out of the 794 ODI matches played by New Zealand, number of matches won against t
team_win_counts = {
'Australia': 39,
'India': 50,
'Pakistan': 50,
'Sri Lanka': 49,
'Bangladesh':28,
'England': 42,
'Netherlands': 4,
'Afghanistan': 2
}

# New Zealand's's win percentages against each team is calculated

# Pie chart

plt.axis('equal')

plt.title('Win Percentage of New Zealand Against Each Team')

plt.show()
Win Percentage of New Zealand in the ODI world

cup
# Out of the 89 ODI matches played by New Zealand in the ODI world cup, number of m
team_win_counts_wc_nz = {
'Australia': 3,
'India': 5,
'South Africa ': 5,
'Pakistan': 2,
'Sri Lanka': 5,
'Bangladesh': 5,
'England': 5,
'Netherlands': 4,
'Afghanistan': 2
}

total_matches_wc_nz = sum(team_win_counts_wc_nz.values())
# New Zealand's win percentages against each team is calculated

win_percentages_wc_nz = {team: (wins / total_matches_wc_nz) * 100 for team, wins in
# Pie chart
plt.pie(win_percentages_wc_nz.values(), labels=win_percentages_wc_nz.keys(), autopc

plt.axis('equal')

plt.title('Win Percentage of New Zealand in the ODI world cup')

plt.show()
Stats of Pakistan team

In [128… # Filter the 'results' DataFrame to include rows where England played either as Tea
df4 = results[(results['Team_1'] == 'England') | (results['Team_2'] == 'England')]
# Create a new DataFrame 'England' containing all rows from the filtered DataFrame
England = df4.iloc[:]
# Display the first few rows of the 'England' DataFrame

England.head()
New New
8 12/06/2015 England won by 13 runs Kennington Oval
Zealand Zealand
Pakistan won by 6
55 11/11/2015 Pakistan England Pakistan Sheikh Zayed Stadium
wickets
England won by 95
57 13/11/2015 Pakistan England England Sheikh Zayed Stadium
runs
England won by 6 Sharjah Cricket

58 17/11/2015 Pakistan England England
wickets Stadium
In [129… # Filtering the 'England' dataframe to create a new dataframe 'England_win' contain
England_win = England[England['Winner']=='England']
In [130… England_win
Dubai International
59 20/11/2015 Pakistan England England England won by 84 runs
Cricket Stadium
78 03/02/2016 South Africa England England won by 39 runs Mangaung Oval
80 06/02/2016 South Africa England England won by 5 wickets St George's Park

134 07/10/2016 Bangladesh England England won by 21 runs
Stadium
Zahur Ahmed
137 12/10/2016 Bangladesh England England won by 4 wickets
Chowdhury Stadium
185 09/03/2017 West Indies England England won by 186 runs Kensington Oval
Melbourne Cricket
274 14/01/2018 Australia England England won by 5 wickets
Ground
Brisbane Cricket
278 18/01/2018 Australia England England won by 4 wickets
Ground
Sydney Cricket
281 21/01/2018 Australia England England won by 16 runs
Ground
287 28/01/2018 Australia England England won by 12 runs Perth Stadium
New
300 28/02/2018 England England won by 6 wickets Bay Oval
Zealand
New
301 03/03/2018 England England won by 4 runs Sky Stadium
Zealand
New
304 10/03/2018 England England won by 7 wickets Hagley Oval
Zealand
Rangiri Dambulla
352 13/10/2018 Sri Lanka England England won by 31 runs
International Stadium
Pallekele International
353 17/10/2018 Sri Lanka England England won by 7 wickets
Cricket Stadium
Pallekele International
354 20/10/2018 Sri Lanka England England won by 18 runs
Cricket Stadium
416 03/05/2019 Ireland England England won by 4 wickets The Village
423 11/05/2019 England Pakistan England won by 12 runs The Rose Bowl
County Ground
426 14/05/2019 England Pakistan England won by 6 wickets
(Bristol)
West
453 14/06/2019 England England won by 8 wickets The Rose Bowl
Indies
474 30/06/2019 England India England won by 31 runs Edgbaston
New
477 03/07/2019 England England won by 119 runs Riverside Ground
Zealand
won on boundary count

New
483 14/07/2019 England England after scores and super Lord's
Zealand
o...
505 09/02/2020 South Africa England England won by 2 wickets Wanderers Stadium
520 30/07/2020 England Ireland England won by 6 wickets The Rose Bowl
521 01/08/2020 England Ireland England won by 4 wickets The Rose Bowl
Maharashtra Cricket
542 26/03/2021 India England England won by 6 wickets
Association Stadium
556 29/06/2021 England Sri Lanka England won by 5 wickets Riverside Ground
557 01/07/2021 England Sri Lanka England won by 8 wickets Kennington Oval
559 08/07/2021 England Pakistan England won by 9 wickets Sophia Gardens
560 10/07/2021 England Pakistan England won by 52 runs Lord's
563 13/07/2021 England Pakistan England won by 3 wickets Edgbaston
613 17/06/2022 Netherlands England England won by 232 runs VRA Ground
614 19/06/2022 Netherlands England England won by 6 wickets VRA Ground
617 22/06/2022 Netherlands England England won by 8 wickets VRA Ground
624 14/07/2022 England India England won by 100 runs Lord's
South
630 22/07/2022 England England won by 118 runs Old Trafford
Africa
678 01/02/2023 South Africa England England won by 59 runs Diamond Oval

679 01/03/2023 Bangladesh England England won by 3 wickets
Stadium

680 03/03/2023 Bangladesh England England won by 132 runs
Stadium
No.of wins for England against other teams

In [131… # Exclude Team Englans's name
excluded_value = 'England'

filtered_df = England_win[England_win['Team_2'] != excluded_value]

print(value_counts)
Pakistan 5
Australia 2
India 2
New Zealand 2
Ireland 2
Sri Lanka 2
West Indies 1
South Africa 1
In [132… # Exclude Team England's name

excluded_value = 'England'
filtered_df = England_win[England_win['Team_1'] != excluded_value]

print(value_counts)
Australia 4
Netherlands 3
South Africa 2
Bangladesh 2
New Zealand 2
Sri Lanka 2
South Africa 2
Bangladesh 2
Pakistan 1
West Indies 1
New Zealand 1
Sri Lanka 1
Ireland 1
India 1
Displaying Team England's wins against other teams

using bar graph
In [133… # Exclude Team England
exclude = 'England'

filtered_data = England_win[England_win['Team_2'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by England.

plt.show()
In [134… # Exclude Team England

exclude = 'England'

filtered_data = England_win[England_win['Team_1'] != exclude]
# Plotting a bar chart to show the top 5 opponents faced by England.

plt.show()
Win Percentage of England Against Each Team

# Out of the 775 ODI matches played by England, number of matches won against the f
team_win_counts = {
'India': 44,
'New Zealand': 42,
'Australia': 63,
'Sri Lanka': 38,
'Bangladesh': 19,
'Pakistan': 56,
'Netherlands': 6,
'Afghanistan': 2
}

# England's win percentages against each team is calculated

# Pie chart

plt.axis('equal')

plt.title('Win Percentage of England Against Each Team')

plt.show()
# Out of the 83 ODI matches played by England in the ODI world cup, number of match
team_win_counts_wc_eng = {
'Australia': 3,
'India': 4,
'South Africa ': 4,
'Pakistan': 4,
'Sri Lanka': 6,
'Bangladesh': 5,
'New Zealand': 5,
'Netherlands': 4,
'Afghanistan': 2
}

total_matches_wc_eng= sum(team_win_counts_wc_eng.values())
# England's win percentages against each team is calculated

win_percentages_wc_eng = {team: (wins / total_matches_wc_eng) * 100 for team, wins
# Pie chart
plt.pie(win_percentages_wc_eng.values(), labels=win_percentages_wc_eng.keys(), auto

plt.axis('equal')

plt.title('Win Percentage of England in the ODI world cup')

plt.show()
Exploratory data analysis

In [137… # This is a list of cricket teams participating in the world cup.
worldcup_teams = ['England', ' South Africa', '', 'West Indies',
'Pakistan', 'New Zealand', 'Sri Lanka', 'Afghanistan',
'Australia', 'Bangladesh', 'India']
# Filtering matches involving only teams in the 'worldcup_teams' list

df_teams_1 = results[results['Team_1'].isin(worldcup_teams)] # Extracts matches wi
df_teams_2 = results[results['Team_2'].isin(worldcup_teams)] # Extracts matches wi
# Combining the filtered dataframes

df_teams = pd.concat((df_teams_1, df_teams_2)) # Concatenates the two dataframes v
df_teams.drop_duplicates() # Removes duplicate rows if any
df_teams.count() # Counts the number of rows in the final dataframe
Date 748
Out[137]:
Team_1 748
Team_2 748
Winner 748
Margin 748
Ground 748
dtype: int64
In [138… # Displaying the first few rows of the "df_teams" DataFrame.

df_teams.head()
New New
8 12/06/2015 England won by 13 runs Kennington Oval
Zealand Zealand

11 18/06/2015 Bangladesh India Bangladesh won by 79 runs
Stadium
Sri Lanka won by Pallekele International

53 07/11/2015 Sri Lanka West Indies Sri Lanka
19 runs Cricket Stadium
Bangladesh won Shere Bangla National

56 11/11/2015 Bangladesh Zimbabwe Bangladesh
by 61 runs Stadium
In [139… # Removing unnecessary columns from df_teams and displaying the first few rows of t
df_teams_2019 = df_teams.drop(['Date','Margin', 'Ground'], axis=1)
df_teams_2019.head()
Out[139]: Team_1 Team_2 Winner
8 England New Zealand New Zealand
11 Bangladesh India Bangladesh
35 England Australia England
53 Sri Lanka West Indies Sri Lanka
56 Bangladesh Zimbabwe Bangladesh
In [140… df_teams_2019
... ... ... ...
716 Bangladesh Afghanistan Afghanistan
719 Bangladesh Afghanistan Afghanistan
720 Netherlands Sri Lanka Sri Lanka
721 Bangladesh Afghanistan Bangladesh
748 rows × 3 columns
Feature selection
In [141… # Reset the index of df_teams_2019 while dropping the old index.
df_teams_2019 = df_teams_2019.reset_index(drop=True)
# Set a value of 1 in the 'winning_team' column for rows where the 'Winner' column
df_teams_2019.loc[df_teams_2019.Winner == df_teams_2019.Team_1,'winning_team']=1
# Set a value of 2 in the 'winning_team' column for rows where the 'Winner' column
df_teams_2019.loc[df_teams_2019.Winner == df_teams_2019.Team_2, 'winning_team']=2
# Drop the 'winning_team' column from the DataFrame.

df_teams_2019 = df_teams_2019.drop(['winning_team'], axis=1)
# Display the first few rows of the modified DataFrame using df_teams_2019.head().
df_teams_2019.head()
Training and testing the data

In [142… # Importing train_test_split from sklearn.model_selection
from sklearn.model_selection import train_test_split
In [143… # Creating dummy variables for team names

final = pd.get_dummies(df_teams_2019, prefix=['Team_1', 'Team_2'], columns=['Team_1
X = final.drop(['Winner'], axis=1) # Extracting features by dropping the 'Winner'

y = final["Winner"] # Assigning the 'Winner' column as the target variable
# Split the data into training and testing sets using a test size of 20% and a rand
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_st
In [144… final.head()
Out[144]:
Winner Team_1_Afghanistan Team_1_Afghanistan Team_1_Australia Team_1_Australia Team
New
0 0 0 0 0
Zealand
1 Bangladesh 0 0 0 0
2 England 0 0 0 0
3 Sri Lanka 0 0 0 0
4 Bangladesh 0 0 0 0
Applying Random forest classifier algorithm

In [145… # Import the Random forest module from sklearn

from sklearn.ensemble import RandomForestClassifier
# Create an Random forest classifier with a linear kernel

rf = RandomForestClassifier(n_estimators=100, max_depth=20,
random_state=0)
# Fit the classifier on the training data

rf.fit(X_train, y_train)
# Make predictions on the test data

pred = rf.predict(X_test)
# Calculating training set score:

score = rf.score(X_train, y_train)
# Calculating test set score:

score2 = rf.score(X_test, y_test)
# Printing the training set accuracy with 3 decimal places

print("Training set accuracy: ", '%.3f'%(score))
# Printing the test set accuracy with 3 decimal places

print("Test set accuracy: ", '%.3f'%(score2))
Training set accuracy: 0.749

Test set accuracy: 0.673
Evaluating the best model on test data

In [146… ranking = pd.read_csv('Icc_ranking.csv') # Read the ICC rankings from the 'Icc_ran
fixtures = pd.read_csv('Fixtures.csv') # Read the fixtures from the 'Fixtures.cs
pred_set = [] # Initialize an empty list to store prediction results
In [147… # Code to insert team rankings into the fixtures dataframe based on 'Team_1' and 'T
fixtures.insert(1, 'first_position', fixtures['Team_1'].map(ranking.set_index('Team
fixtures.insert(2, 'second_position', fixtures['Team_2'].map(ranking.set_index('Tea
# Select the first 45 rows of the updated fixtures dataframe.

fixtures = fixtures.iloc[:45, :]
fixtures.head() # Display the first few rows of the updated dataframe.
Out[147]: Round_number first_position second_position Team_1 Team_2 Date Location
Narendra
New Mod
0 1 5.0 NaN England 5/10/2023
Zealand Stadium
Ahmedabad
Rajiv Gandh
Internationa
1 1 NaN 10.0 Pakistan Netherlands 6/10/2023
Stadium
Hyderabad
Himacha
Pradesh
2 1 7.0 8.0 Bangladesh Afghanistan 7/10/2023 Cricke
Association
Stadium, .
Arun Jaitley
South
3 1 6.0 9.0 Sri Lanka 7/10/2023 Stadium
Africa
Delh
MA
Chidambaram
4 1 3.0 1.0 India Australia 8/10/2023
Stadium
Chenna
In [148… # Filling missing values in 'first_position' and 'second_position' columns with the
fixtures['first_position']=fixtures['first_position'].fillna(fixtures['first_positi
fixtures['second_position']=fixtures['second_position'].fillna(fixtures['second_pos
fixtures.head()
Out[148]: Round_number first_position second_position Team_1 Team_2 Date Location
Narendra
New Mod
0 1 5.000000 7.119048 England 5/10/2023
Zealand Stadium
Ahmedabad
Rajiv Gandh
Internationa
1 1 4.411765 10.000000 Pakistan Netherlands 6/10/2023
Stadium
Hyderabad
Himacha
Pradesh
2 1 7.000000 8.000000 Bangladesh Afghanistan 7/10/2023 Cricke
Association
Stadium, .
Arun Jaitley
South
3 1 6.000000 9.000000 Sri Lanka 7/10/2023 Stadium
Africa
Delh
MA
Chidambaram
4 1 3.000000 1.000000 India Australia 8/10/2023
Stadium
Chenna
In [149… # Predicting winning teams based on positions in fixtures.

for index, row in fixtures.iterrows():
if row['first_position'] < row['second_position']:
pred_set.append({'Team_1': row['Team_1'], 'Team_2': row['Team_2'], 'winning
else:
pred_set.append({'Team_1': row['Team_2'], 'Team_2': row['Team_1'], 'winning
pred_set = pd.DataFrame(pred_set) # Creating a DataFrame for pred_set.

backup_pred_set = pred_set # Creating a backup of the pred_set DataFrame
pred_set.head() # Displaying the first few rows of the pred_set DataFrame
Out[149]: Team_1 Team_2 winning_team
0 England New Zealand None
1 Pakistan Netherlands None
2 Bangladesh Afghanistan None
3 South Africa Sri Lanka None
4 Australia India None
In [150… # Transforming the dataset using one-hot encoding for 'Team_1' and 'Team_2' columns
pred_set = pd.get_dummies(pred_set, prefix=['Team_1', 'Team_2'], columns=['Team_1',
# Finding missing columns in the final dataset compared to the transformed 'pred_se
missing_cols = set(final.columns) - set(pred_set.columns)
# Setting the missing columns in "pred_set" DataFrame to 0 and then keeps only the
for c in missing_cols:
pred_set[c] = 0
pred_set = pred_set[final.columns]
# Dropping the 'Winner' column from pred_set.

pred_set = pred_set.drop(['Winner'], axis=1)
pred_set.head()
Out[150]:
Team_1_Afghanistan Team_1_Afghanistan Team_1_Australia Team_1_Australia Team_1_Banglades
0 0 0 0 0
1 0 0 0 0
2 0 0 0 0
3 0 0 0 0
4 0 0 1 0
Interpret the model results

In [151… # Making predictions using 'rf' on 'pred_set' and printing the winners for each fix
predictions = rf.predict(pred_set)
for i in range(fixtures.shape[0]):
print(backup_pred_set.iloc[i, 1] + " vs " + backup_pred_set.iloc[i, 0])
if predictions[i] == 1:
print("Winner: " + backup_pred_set.iloc[i, 1])
else:
print("")
New Zealand vs England
Winner: England
Netherlands vs Pakistan
Winner: Pakistan
Afghanistan vs Bangladesh
Winner: Bangladesh
Sri Lanka vs South Africa

Winner: South Africa
India vs Australia
Winner: Australia
Netherlands vs New Zealand

Winner: New Zealand
Bangladesh vs England
Winner: England
Afghanistan vs India
Winner: India
Sri Lanka vs Pakistan

Winner: Pakistan
South Africa vs Australia

Winner: Australia
Bangladesh vs New Zealand

Winner: New Zealand
Afghanistan vs England
Winner: England
India vs Pakistan
Winner: Pakistan
Sri Lanka vs Australia

Winner: Australia
Netherlands vs South Africa

Afghanistan vs New Zealand

Winner: New Zealand
Bangladesh vs India
Winner: India
Pakistan vs Australia
Winner: Australia
Netherlands vs Sri Lanka

Winner: Sri Lanka
South Africa vs England

Winner: England
New Zealand vs India

Winner: India
Afghanistan vs Pakistan
Winner: Pakistan
Bangladesh vs South Africa

Netherlands vs Australia
Winner: Australia
Sri Lanka vs England

Winner: England
South Africa vs Pakistan

Winner: Pakistan
New Zealand vs Australia

Winner: Australia
Netherlands vs Bangladesh
Winner: Bangladesh
England vs India
Winner: India
Sri Lanka vs Afghanistan

Winner: Afghanistan
Bangladesh vs Pakistan
Winner: Pakistan
South Africa vs New Zealand

Winner: New Zealand
Sri Lanka vs India

Winner: India
Netherlands vs Afghanistan
Winner: Afghanistan
New Zealand vs Pakistan

Winner: Pakistan
England vs Australia
Winner: Australia
South Africa vs India

Winner: India
Sri Lanka vs Bangladesh

Winner: Bangladesh
Afghanistan vs Australia
Winner: Australia
Netherlands vs England
Winner: England
Sri Lanka vs New Zealand

Winner: New Zealand
Afghanistan vs South Africa

Netherlands vs India
Winner: India
Bangladesh vs Australia
Winner: Australia
England vs Pakistan
Winner: Pakistan
In [152… # The teams qualified for semi-finals based on wins.

semi = [('Pakistan', 'Australia'),
('England', 'India')]
In [153… def clean_and_predict(matches, ranking, final, rf):

# Initialize an empty list to store the positions of teams in the ranking
positions = []
# Loop through the list of matches and add the rankings of the teams to the pos
for match in matches:
positions.append(ranking.loc[ranking['Team_name'] == match[0], 'Team_rankin
positions.append(ranking.loc[ranking['Team_name'] == match[0], 'Team_rankin
# Initialize an empty list to store the match predictions

pred_set = []
# Initialize indices i and j to 0 for iteration

i = 0
j = 0
# Loop through the positions list to create match predictions

while i < len(positions):
dict1 = {}
# Compare the positions of the two teams in the match
# and add the corresponding team names to the prediction dictionary
if positions[i] < positions[i + 1]:
dict1.update({'Team_1': matches[j][0], 'Team_2': matches[j][1]})
else:
dict1.update({'Team_1': matches[j][1], 'Team_2': matches[j][0]})
# Add the prediction dictionary to the pred_set list

pred_set.append(dict1)
i += 2
j += 1
# Convert the pred_set list into a pandas DataFrame

pred_set = pd.DataFrame(pred_set)
# Make a backup of the pred_set DataFrame

backup_pred_set = pred_set
# Convert categorical variables in the pred_set DataFrame into dummy variables

pred_set = pd.get_dummies(pred_set, prefix=['Team_1', 'Team_2'], columns=['Team
# Identify missing columns in pred_set compared to the final DataFrame

missing_cols2 = set(final.columns) - set(pred_set.columns)
# Add the missing columns to the pred_set DataFrame and set their values to 0
for c in missing_cols2:
pred_set[c] = 0
# Reorder pred_set columns to match the final DataFrame's order

pred_set = pred_set[final.columns]
# Drop the 'Winner' column from the pred_set DataFrame

pred_set = pred_set.drop(['Winner'], axis=1)
# Use the provided classifier (cls) to make predictions on the pred_set DataFra
predictions = rf.predict(pred_set)
# Loop through the pred_set DataFrame and print the match predictions and winne
for i in range(len(pred_set)):
print(backup_pred_set.iloc[i, 1] + " vs " + backup_pred_set.iloc[i, 0])
if predictions[i] == 1:
else:
print("")
# Call the clean_and_predict function with the provided arguments

clean_and_predict(semi, ranking, final, rf)
Pakistan vs Australia
Winner: Australia
England vs India
Winner: India
In [154… # The teams qualified for the Finals

finals = [('Australia', 'India')]
Conclusion
In [82]: # Clean the data, apply ranking and use the classifier to predict the final outcome
clean_and_predict(finals, ranking, final, rf)
Australia vs India
Winner: India
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:

Icc Worldcup 2023 Winner Prediction Output PDF

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Icc Worldcup 2023 Winner Prediction Output PDF

Uploaded by

Copyright:

Available Formats

11/4/23, 12:54 AM icc-worldcup-2023-winner-prediction

# Read the data from "results.csv" into the 'results' DataFrame

In [85]: # Display the first few rows of the World_cup DataFrame.

Out[85]: Team_name Team_ranking Titles Win_percentage_ODI WC_matches WC_match_won Win_perc

5 South Africa 6 0 61.00 64 38

8 Sri Lanka 9 1 45.74 80 38

No.of titles won by each teams

# Create a bar plot using sns.barplot to visualize team titles

# Display the plot

Win percentage in ODI by each team

# Create a bar plot using Seaborn

# Display the plot

No.of matches won in world cup by each team

# Create a bar plot using Seaborn

# Display the plot

Recent ICC ODI rating

# Create a bar plot using Seaborn to display recent ratings of teams

# Display the plot

In [90]: # Displaying the first few rows of the results DataFrame.

Out[90]: Date Team_1 Team_2 Winner Margin Ground

Shere Bangla National

won by 7 Shere Bangla National

won by 8 Shere Bangla National

3 08/05/2015 Ireland England No result No result The Village

4 26/05/2015 Pakistan Zimbabwe Pakistan won by 41 runs Gaddafi Stadium

Stats of top five teams in the ODI world cup 2023

Stats of Indian team

# Display the first few rows of the 'India' DataFrame

Out[92]: Date Team_1 Team_2 Winner Margin Ground

16 10/07/2015 Zimbabwe India India won by 4 runs Harare Sports Club

19 12/07/2015 Zimbabwe India India won by 62 runs Harare Sports Club

Out[94]: Date Team_1 Team_2 Winner Margin Ground

New won by 7 Punjab Cricket Association IS

won by 26 Dubai International Cricket

won by 7 Dubai International Cricket

won by 3 Dubai International Cricket

Date Team_1 Team_2 Winner Margin Ground

West won by 107 Dr YS Rajasekhara Reddy Cricket

won by 36 Saurashtra Cricket Association

won by 66 Maharashtra Cricket Association

won by 7 Maharashtra Cricket Association

South won by 7 JSCA International Stadium

Date Team_1 Team_2 Winner Margin Ground

won by 227 Zahur Ahmed Chowdhury

New won by 12 Rajiv Gandhi International

New won by 8 Shaheed Veer Narayan Sing

No.of wins in ODIs against other teams

# Filtering out rows with the excluded value

# Print the value counts

In [96]: # Exclude Team India's name

# Filtering out rows with the excluded value

# Print the value counts

Displaying Team India's wins against other teams

# Filter out the opponent to exclude from the data

# Plotting a bar chart to show the top 5 opponents faced by India.

In [98]: # Exclude Team India

# Filter out the opponent to exclude from the data

# Plotting a bar chart to show the top 5 opponents faced by India.

Win Percentage of India Against Each Team

# Total matches played is calculated

# India's win percentages against each team is calculated

# Equal aspect ratio ensures that pie is drawn as a circle.

# Title for the pie chart