Portfolio Project 5 - Soccer Through the Ages

import pandas as pd
results = pd.read_csv("data/results.csv")
print(results.shape)
results.head(100)

import pandas as pd
import matplotlib.pyplot as plt

# Load the dataset
results = pd.read_csv("data/results.csv")

# Convert the 'date' column to datetime
results['date'] = pd.to_datetime(results['date'])

# Filter the dataset for games since 1960
results_since_1960 = results[results['date'].dt.year >= 1960]

# Calculate the number of wins for each country
home_wins = results_since_1960[results_since_1960['home_score'] > results_since_1960['away_score']]['home_team'].value_counts()
away_wins = results_since_1960[results_since_1960['away_score'] > results_since_1960['home_score']]['away_team'].value_counts()
total_wins = home_wins.add(away_wins, fill_value=0).sort_values(ascending=False)

# Get the top 15 countries with the most wins
top_15_winners = total_wins.head(15)

# Plot the results in a horizontal bar plot
plt.figure(figsize=(10, 8))
top_15_winners.plot(kind='barh', color='skyblue')
plt.xlabel('Number of Wins')
plt.ylabel('Country')
plt.title('Top 15 Countries with the Most Wins Since 1960')
plt.gca().invert_yaxis()  # Invert y-axis to have the country with the most wins at the top
plt.show()

import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px

# Load the data
goalscorers = pd.read_csv("data/goalscorers.csv")

# Ensure 'minute' column is of string type before extracting numerical values
goalscorers['minute'] = goalscorers['minute'].astype(str)

# Extract numerical values from the 'minute' column and convert to integers
goalscorers['minute'] = goalscorers['minute'].str.extract('(\d+)').dropna().astype(int)

# Calculate the total number of goals scored in each minute
goals_per_minute = goalscorers['minute'].value_counts().sort_index()

# Plot the results in a bar plot
plt.figure(figsize=(12, 6))
goals_per_minute.plot(kind='bar', color='skyblue')
plt.xlabel('Minute')
plt.ylabel('Number of Goals')
plt.title('Total Number of Goals Scored in Each Minute of the Game')
plt.show()

# Ensure 'date' column is of datetime type and extract year
goalscorers['date'] = pd.to_datetime(goalscorers['date'])
goalscorers['year'] = goalscorers['date'].dt.year

# Group by year and minute, and count the number of goals
goals_per_minute_yearly = goalscorers.groupby(['year', 'minute']).size().reset_index(name='goals')

# Create an animated Plotly plot to show how the distribution has changed over the years
fig = px.bar(
    goals_per_minute_yearly,
    x='minute',
    y='goals',
    animation_frame='year',
    range_y=[0, goals_per_minute_yearly['goals'].max()],
    labels={'minute': 'Minute', 'goals': 'Number of Goals'},
    title='Number of Goals Scored in Each Minute Over the Years'
)
fig.show()

import pandas as pd
import matplotlib.pyplot as plt

# Load the data
goalscorers = pd.read_csv("data/goalscorers.csv")

# Define hat tricks (3 or more goals in a single game)
hat_tricks = (
    goalscorers.groupby(['date', 'team', 'scorer'])
    .size()
    .reset_index(name='goals')
)
hat_tricks = hat_tricks[hat_tricks['goals'] >= 3]

# Count the number of hat tricks per player
hat_trick_counts = hat_tricks['scorer'].value_counts().head(10)

# Plot the top 10 players with the most hat tricks
plt.figure(figsize=(12, 6))
hat_trick_counts.plot(kind='bar', color='skyblue')
plt.title('Top 10 Players with the Most Hat Tricks')
plt.xlabel('Player')
plt.ylabel('Number of Hat Tricks')
plt.xticks(rotation=45)
plt.show()

import pandas as pd

# Load the results data
results = pd.read_csv("data/results.csv")

# Calculate the number of games won at home and away
home_wins = results[results['home_score'] > results['away_score']]['home_team'].value_counts()
away_wins = results[results['away_score'] > results['home_score']]['away_team'].value_counts()

# Calculate the total number of games played at home and away
home_games = results['home_team'].value_counts()
away_games = results['away_team'].value_counts()

# Calculate the proportion of games won at home and away
home_win_proportion = home_wins / home_games
away_win_proportion = away_wins / away_games

# Combine the proportions into a single DataFrame
win_proportions = pd.DataFrame({
    'Home Win Proportion': home_win_proportion,
    'Away Win Proportion': away_win_proportion
}).fillna(0)

# Calculate the difference between the proportions
win_proportions['Difference'] = win_proportions['Home Win Proportion'] - win_proportions['Away Win Proportion']

# Display the results
print(win_proportions)

import pandas as pd
import matplotlib.pyplot as plt

# Load the results data
results = pd.read_csv("data/results.csv")

# Calculate the number of games won at home and away
home_wins = (results['home_score'] > results['away_score']).sum()
away_wins = (results['away_score'] > results['home_score']).sum()

# Data for the pie chart
labels = ['Home Wins', 'Away Wins']
sizes = [home_wins, away_wins]
colors = ['#ff9999', '#66b3ff']
explode = (0.1, 0)  # explode the 1st slice (i.e., 'Home Wins')

# Plotting the pie chart
fig, ax = plt.subplots()
ax.pie(sizes, explode=explode, labels=labels, colors=colors, autopct='%1.1f%%',
       shadow=True, startangle=90)
ax.axis('equal')  # Equal aspect ratio ensures that pie is drawn as a circle.

plt.title('Proportion of Games Won by Home and Away Teams')
plt.show()

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

# Load the datasets
results = pd.read_csv("data/results.csv")
goalscorers = pd.read_csv("data/goalscorers.csv")
shootouts = pd.read_csv("data/shootouts.csv")

# Preprocess the data
results['home_win'] = (results['home_score'] > results['away_score']).astype(int)
results['away_win'] = (results['away_score'] > results['home_score']).astype(int)
results['draw'] = (results['home_score'] == results['away_score']).astype(int)

# Feature engineering
results['goal_difference'] = results['home_score'] - results['away_score']

# Select features and target
features = results[['home_team', 'away_team', 'goal_difference']]
target = results[['home_win', 'away_win', 'draw']]

# Encode categorical variables
features = pd.get_dummies(features, columns=['home_team', 'away_team'])

# Split the data
X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)

# Train the model
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Evaluate the model
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f"Model Accuracy: {accuracy:.2f}")

# Function to predict outcomes based on team draws
def predict_outcome(home_team, away_team):
    match_data = pd.DataFrame({
        'home_team': [home_team],
        'away_team': [away_team],
        'goal_difference': [0]  # Assuming no prior knowledge of goal difference
    })
    match_data = pd.get_dummies(match_data, columns=['home_team', 'away_team'])
    match_data = match_data.reindex(columns=X_train.columns, fill_value=0)
    
    prediction = model.predict(match_data)
    outcome = ['Home Win', 'Away Win', 'Draw']
    return outcome[np.argmax(prediction)]

# Example usage
home_team = 'TeamA'
away_team = 'TeamB'
predicted_outcome = predict_outcome(home_team, away_team)
print(f"Predicted Outcome for {home_team} vs {away_team}: {predicted_outcome}")