Calculating required statistics for each station

gistfile1.txt

# Recalculating electric and classic bike counts as actual counts instead of rates
electric_bike_start_counts = df[df['rideable_type'] == 'electric_bike'].groupby('start_station_name')['ride_id'].count()
classic_bike_start_counts = df[df['rideable_type'] == 'classic_bike'].groupby('start_station_name')['ride_id'].count()

# Recalculating member and casual counts as actual counts instead of rates
member_counts = df[df['member_casual'] == 'member'].groupby('start_station_name')['ride_id'].count()
casual_counts = df[df['member_casual'] == 'casual'].groupby('start_station_name')['ride_id'].count()

# Total start and end counts for each station
start_counts = df.groupby('start_station_name')['ride_id'].count()
end_counts = df.groupby('end_station_name')['ride_id'].count()

# Average latitude and longitude for each start station
average_lat = df.groupby('start_station_name')['start_lat'].mean()
average_lng = df.groupby('start_station_name')['start_lng'].mean()

# Combining the recalculated counts into a single DataFrame
aggregated_data = pd.DataFrame({
    'Electric Bike Count': electric_bike_start_counts,
    'Classic Bike Count': classic_bike_start_counts,
    'Start Count': start_counts,
    'End Count': end_counts,
    'Member Count': member_counts,
    'Casual Count': casual_counts,
    'Average Latitude': average_lat,
    'Average Longitude': average_lng
})

# Filling NaN values with 0
aggregated_data = aggregated_data.fillna(0)

# Displaying the first few rows of the new aggregated data
aggregated_data