This is an example analysis of some bus data from Kingston's Open Data catalogue using Python.

# make plots appear inline in the notebook and load key libraries
import re
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style('white')

%matplotlib inline

# check out some available datasets
!ls /home/datasets/transit

agency.txt	    feed_info.txt  routes.txt  stops.txt       trips.txt
calendar_dates.txt  real-time	   shapes.txt  stop_times.txt

# load a dataset of all bus trips and take a look
trips = pd.read_csv('/home/datasets/transit/trips.txt')
trips.head()

	route_id	service_id	trip_id	trip_headsign	shape_id	block_id
0	12	189	866469:38369:5853	Highway 15	339	5853
1	501	188	864006:38371:4705	Express - Cataraqui Centre via Front/Bayridge	290	4705
2	2	223	859920:38372:5345	Division Street	345	5345
3	3	224	860985:38373:5365	Downtown via Queen Mary Rd	367	5365
4	10	192	864736:38374:5227	Cataraqui Centre	267	5227

# get the number of trips for each individual bus route
num_trips = trips.groupby('route_id').count()
num_trips = num_trips.sort_values('trip_id', ascending=False)

Now lets's make a bar plot of the most frequent bus routes. It looks like the 501/502 is the most frequent bus, with most other buses having the same amount of service:

num_trips['trip_id'].plot(kind='bar')

<matplotlib.axes._subplots.AxesSubplot at 0x7fdcef693940>