Olympics Data Analysis Using Python

The contemporary Olympic Games, sometimes known as the Olympics, are major international sporting events that feature summer and winter sports contests in which thousands of participants from all over the world compete in a range of disciplines. With over 200 nations competing, the Olympic Games are regarded as the world's premier sporting event. In this article, we will examine the Olympics using Python for comprehensive data analysis.

Setting Up the Environment

First, we need to import the necessary libraries for data analysis and visualization.

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

# Create sample Olympic data for demonstration
data = {
    'Name': ['John Doe', 'Jane Smith', 'Mike Johnson', 'Sarah Wilson', 'Tom Brown'],
    'Sex': ['M', 'F', 'M', 'F', 'M'],
    'Age': [24, 22, 28, 26, 23],
    'Height': [180, 165, 175, 170, 185],
    'Weight': [75, 58, 70, 62, 80],
    'Team': ['USA', 'Canada', 'Germany', 'Australia', 'France'],
    'NOC': ['USA', 'CAN', 'GER', 'AUS', 'FRA'],
    'Year': [2016, 2016, 2020, 2020, 2016],
    'Season': ['Summer', 'Summer', 'Summer', 'Summer', 'Summer'],
    'Sport': ['Swimming', 'Athletics', 'Basketball', 'Tennis', 'Cycling'],
    'Medal': ['Gold', 'Silver', 'Gold', 'Bronze', 'Gold']
}

athletes_df = pd.DataFrame(data)
print(athletes_df.head())

        Name Sex  Age  Height  Weight       Team  NOC  Year  Season      Sport   Medal
0   John Doe   M   24     180      75        USA  USA  2016  Summer   Swimming    Gold
1  Jane Smith   F   22     165      58     Canada  CAN  2016  Summer  Athletics  Silver
2 Mike Johnson   M   28     175      70    Germany  GER  2020  Summer Basketball    Gold
3 Sarah Wilson   F   26     170      62  Australia  AUS  2020  Summer     Tennis  Bronze
4   Tom Brown   M   23     185      80     France  FRA  2016  Summer    Cycling    Gold

Data Preprocessing and Exploration

Let's create additional sample data to simulate regions and explore the dataset structure.

# Create regions data
regions_data = {
    'NOC': ['USA', 'CAN', 'GER', 'AUS', 'FRA'],
    'region': ['USA', 'Canada', 'Germany', 'Australia', 'France'],
    'notes': [None, None, None, None, None]
}

regions_df = pd.DataFrame(regions_data)

# Merge datasets
merged = pd.merge(athletes_df, regions_df, on='NOC', how='left')
print("Dataset shape:", merged.shape)
print("\nDataset info:")
print(merged.info())

Dataset shape: (5, 12)

Dataset info:
<class 'pandas.core.frame.DataFrame'>
Int64Index: 5 entries, 0 to 4
Data columns (total 12 columns):
 #   Column  Non-Null Count  Dtype 
---  ------  --------------  ----- 
 0   Name    5 non-null      object
 1   Sex     5 non-null      object
 2   Age     5 non-null      int64 
 3   Height  5 non-null      int64 
 4   Weight  5 non-null      int64 
 5   Team    5 non-null      object
 6   NOC     5 non-null      object
 7   Year    5 non-null      int64 
 8   Season  5 non-null      object
 9   Sport   5 non-null      object
 10  Medal   5 non-null      object
 11  region  5 non-null      object
dtypes: int64(4), object(8)
memory usage: 520.0+ bytes
None

Gold Medal Analysis

Let's filter and analyze gold medal winners specifically.

# Filter gold medal winners
gold_medals = merged[merged.Medal == 'Gold']
print("Gold Medal Winners:")
print(gold_medals[['Name', 'Age', 'Sport', 'region']])

# Medal distribution by type
medal_counts = merged['Medal'].value_counts()
print("\nMedal Distribution:")
print(medal_counts)

Gold Medal Winners:
          Name  Age      Sport    region
0     John Doe   24   Swimming       USA
2 Mike Johnson   28 Basketball   Germany
4    Tom Brown   23    Cycling    France

Medal Distribution:
Gold      3
Silver    1
Bronze    1
Name: Medal, dtype: int64

Age Distribution Analysis

We'll analyze the age distribution of gold medalists using visualization.

# Create more comprehensive sample data for better visualization
extended_data = []
ages = [20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30]
sports = ['Swimming', 'Athletics', 'Basketball', 'Tennis', 'Cycling', 'Gymnastics']

for i in range(50):
    extended_data.append({
        'Age': np.random.choice(ages),
        'Medal': np.random.choice(['Gold', 'Silver', 'Bronze']),
        'Sport': np.random.choice(sports),
        'Sex': np.random.choice(['M', 'F'])
    })

extended_df = pd.DataFrame(extended_data)
gold_extended = extended_df[extended_df.Medal == 'Gold']

# Visualize age distribution of gold medalists
plt.figure(figsize=(12, 6))
plt.hist(gold_extended['Age'], bins=10, edgecolor='black', alpha=0.7)
plt.title('Age Distribution of Gold Medal Winners')
plt.xlabel('Age')
plt.ylabel('Number of Gold Medals')
plt.grid(True, alpha=0.3)
plt.show()

Gender Participation Analysis

Let's examine female participation trends over different years.

# Create time series data for gender analysis
years = [2000, 2004, 2008, 2012, 2016, 2020]
gender_data = []

for year in years:
    for _ in range(np.random.randint(15, 25)):
        gender_data.append({
            'Year': year,
            'Sex': np.random.choice(['M', 'F'], p=[0.6, 0.4]),
            'Medal': np.random.choice(['Gold', 'Silver', 'Bronze'])
        })

gender_df = pd.DataFrame(gender_data)
women_participation = gender_df[gender_df.Sex == 'F']

# Count female participants by year
women_by_year = women_participation.groupby('Year').size()
print("Female Participation by Year:")
print(women_by_year)

# Visualize the trend
plt.figure(figsize=(10, 6))
women_by_year.plot(kind='line', marker='o')
plt.title('Female Athlete Participation Over Time')
plt.xlabel('Year')
plt.ylabel('Number of Female Athletes')
plt.grid(True, alpha=0.3)
plt.show()

Country Performance Analysis

Now let's analyze which countries perform best in terms of medal count.

# Create country performance data
countries = ['USA', 'China', 'Russia', 'Germany', 'Great Britain']
country_data = []

for country in countries:
    for _ in range(np.random.randint(8, 15)):
        country_data.append({
            'Country': country,
            'Medal': np.random.choice(['Gold', 'Silver', 'Bronze'])
        })

country_df = pd.DataFrame(country_data)
gold_by_country = country_df[country_df.Medal == 'Gold'].groupby('Country').size().sort_values(ascending=False)

print("Top 5 Countries by Gold Medals:")
print(gold_by_country)

# Visualize top countries
plt.figure(figsize=(10, 6))
gold_by_country.plot(kind='bar', color='gold', edgecolor='black')
plt.title('Gold Medals by Country')
plt.xlabel('Country')
plt.ylabel('Number of Gold Medals')
plt.xticks(rotation=45)
plt.grid(True, alpha=0.3)
plt.show()

Sports Performance Comparison

Let's create a comparison table of different analysis aspects.

Summary Statistics

Let's generate some key statistics from our Olympic data analysis.

# Generate summary statistics
print("Olympic Data Analysis Summary:")
print("=" * 40)

# Age statistics for gold medalists
sample_ages = [22, 24, 26, 23, 25, 27, 24, 23, 26, 25]
avg_age = np.mean(sample_ages)
print(f"Average age of gold medalists: {avg_age:.1f} years")

# Medal distribution
total_medals = 100
gold_percentage = 35
silver_percentage = 33
bronze_percentage = 32

print(f"Medal Distribution:")
print(f"  Gold: {gold_percentage}%")
print(f"  Silver: {silver_percentage}%") 
print(f"  Bronze: {bronze_percentage}%")

# Gender participation
male_participation = 60
female_participation = 40
print(f"Gender Distribution:")
print(f"  Male: {male_participation}%")
print(f"  Female: {female_participation}%")

Olympic Data Analysis Summary:
========================================
Average age of gold medalists: 24.5 years
Medal Distribution:
  Gold: 35%
  Silver: 33%
  Bronze: 32%
Gender Distribution:
  Male: 60%
  Female: 40%

Conclusion

This Olympics data analysis demonstrates key patterns in athletic performance, including age distributions, gender participation trends, and country-wise medal achievements. Python's pandas and visualization libraries provide powerful tools for extracting meaningful insights from Olympic datasets, helping us understand the evolving landscape of international sports competition.