total rides for each station (both start and end)

gistfile1.txt

# Calculating total rides for each station (both start and end)
total_rides_per_station = df['start_station_name'].value_counts() + df['end_station_name'].value_counts()

# Sorting stations by total rides and selecting the top 20%
sorted_total_rides = total_rides_per_station.sort_values(ascending=False)
cumulative_percentage_total = sorted_total_rides.cumsum() / sorted_total_rides.sum()
top_20_total_stations = sorted_total_rides[cumulative_percentage_total <= 0.20]

# Separating the counts for start and end stations for the top 20%
top_20_start_counts = df['start_station_name'].value_counts().loc[top_20_total_stations.index]
top_20_end_counts = df['end_station_name'].value_counts().loc[top_20_total_stations.index]

# Plotting stacked bar chart
plt.figure(figsize=(15, 10))
top_20_start_counts.plot(kind='bar', color='skyblue', label='Start Station')
top_20_end_counts.plot(kind='bar', color='green', label='End Station', bottom=top_20_start_counts)

plt.title('Top 20% Stations by Total Rides (Start and End)')
plt.xlabel('Station Name')
plt.ylabel('Total Rides')
plt.xticks(rotation=90)
plt.legend()
plt.grid(axis='y')

plt.tight_layout()
plt.show()