Adjusting to select stations that make up the top 20% of all stations by count

gistfile1.txt

# Adjusting to select stations that make up the top 20% of all stations by count

# Sorting the station counts
sorted_start_stations = df['start_station_name'].value_counts().sort_values(ascending=False)
sorted_end_stations = df['end_station_name'].value_counts().sort_values(ascending=False)

# Calculating the cumulative percentage
cumulative_percentage_start = sorted_start_stations.cumsum() / sorted_start_stations.sum()
cumulative_percentage_end = sorted_end_stations.cumsum() / sorted_end_stations.sum()

# Filtering for top 20%
top_20_start_stations = sorted_start_stations[cumulative_percentage_start <= 0.20]
top_20_end_stations = sorted_end_stations[cumulative_percentage_end <= 0.20]

plt.figure(figsize=(15, 10))

# Plotting for start stations
plt.subplot(2, 1, 1)
top_20_start_stations.plot(kind='bar', color='skyblue')
plt.title('Top 20% of Start Stations by Count')
plt.xlabel('Station Name')
plt.ylabel('Frequency')
plt.xticks(rotation=90)
plt.grid(axis='y')

# Plotting for end stations
plt.subplot(2, 1, 2)
top_20_end_stations.plot(kind='bar', color='green')
plt.title('Top 20% of End Stations by Count')
plt.xlabel('Station Name')
plt.ylabel('Frequency')
plt.xticks(rotation=90)
plt.grid(axis='y')

plt.tight_layout()
plt.show()