Olympic data-based analysis using Python

 import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

df = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-07-27/olympics.csv')

print(df.head())

medal_counts = df.groupby('team')['medal'].count().reset_index()

medal_counts = medal_counts.sort_values(by='medal', ascending=False).head(10)

print(medal_counts)

top_countries = medal_counts['team'].head(5)

df_top_countries = df[df['team'].isin(top_countries)]

medals_by_year = df_top_countries.groupby(['year', 'team'])['medal'].count().reset_index()

# Plot: Medals Over Time for Top 5 Countries

plt.figure(figsize=(14, 8))

sns.lineplot(data=medals_by_year, x='year', y='medal', hue='team')

plt.title('Medals Over Time for Top 5 Countries')

plt.xlabel('Year')

plt.ylabel('Number of Medals')

plt.legend(title='Country')

plt.show()

# What is the distribution of medals by sport?

medals_by_sport = df.groupby('sport')['medal'].count().reset_index()

medals_by_sport = medals_by_sport.sort_values(by='medal', ascending=False).head(10)

# Plot: Top 10 Sports by Number of Medals

plt.figure(figsize=(14, 8))

sns.barplot(data=medals_by_sport, x='medal', y='sport', palette='viridis')

plt.title('Top 10 Sports by Number of Medals')

plt.xlabel('Number of Medals')

plt.ylabel('Sport')

plt.show()

#clcoding.com