nycflights13 package

import seaborn as sns
import pandas as pd
import plotly.express as px

The `nycflights13` package

The nycflights13 python package gives quick access to several dataframes related to flights, airports, airlines and weather data out of New York in 2013. Useful to illustrate how to aggregate, enrich and merge dataframes to create meaningful visualizations.

from nycflights13 import flights, airports, airlines, planes, weather
flights.head()

	year	month	day	dep_time	sched_dep_time	dep_delay	arr_time	sched_arr_time	arr_delay	carrier	flight	tailnum	origin	dest	air_time	distance	hour	minute	time_hour
0	2013	1	1	517.0	515	2.0	830.0	819	11.0	UA	1545	N14228	EWR	IAH	227.0	1400	5	15	2013-01-01T10:00:00Z
1	2013	1	1	533.0	529	4.0	850.0	830	20.0	UA	1714	N24211	LGA	IAH	227.0	1416	5	29	2013-01-01T10:00:00Z
2	2013	1	1	542.0	540	2.0	923.0	850	33.0	AA	1141	N619AA	JFK	MIA	160.0	1089	5	40	2013-01-01T10:00:00Z
3	2013	1	1	544.0	545	-1.0	1004.0	1022	-18.0	B6	725	N804JB	JFK	BQN	183.0	1576	5	45	2013-01-01T10:00:00Z
4	2013	1	1	554.0	600	-6.0	812.0	837	-25.0	DL	461	N668DN	LGA	ATL	116.0	762	6	0	2013-01-01T11:00:00Z

airports.head()

	faa	name	lat	lon	alt	tz	dst	tzone
0	04G	Lansdowne Airport	41.130472	-80.619583	1044	-5	A	America/New_York
1	06A	Moton Field Municipal Airport	32.460572	-85.680028	264	-6	A	America/Chicago
2	06C	Schaumburg Regional	41.989341	-88.101243	801	-6	A	America/Chicago
3	06N	Randall Airport	41.431912	-74.391561	523	-5	A	America/New_York
4	09J	Jekyll Island Airport	31.074472	-81.427778	11	-5	A	America/New_York

planes.head()

	tailnum	year	type	manufacturer	model	engines	seats	speed	engine
0	N10156	2004.0	Fixed wing multi engine	EMBRAER	EMB-145XR	2	55	NaN	Turbo-fan
1	N102UW	1998.0	Fixed wing multi engine	AIRBUS INDUSTRIE	A320-214	2	182	NaN	Turbo-fan
2	N103US	1999.0	Fixed wing multi engine	AIRBUS INDUSTRIE	A320-214	2	182	NaN	Turbo-fan
3	N104UW	1999.0	Fixed wing multi engine	AIRBUS INDUSTRIE	A320-214	2	182	NaN	Turbo-fan
4	N10575	2002.0	Fixed wing multi engine	EMBRAER	EMB-145LR	2	55	NaN	Turbo-fan

airlines.head()

	carrier	name
0	9E	Endeavor Air Inc.
1	AA	American Airlines Inc.
2	AS	Alaska Airlines Inc.
3	B6	JetBlue Airways
4	DL	Delta Air Lines Inc.

weather.head()

	origin	year	month	day	hour	temp	dewp	humid	wind_dir	wind_speed	wind_gust	pressure	visib	time_hour
0	EWR	2013	1	1	1	39.02	26.06	59.37	270.0	10.35702	NaN	1012.0	10.0	2013-01-01T06:00:00Z
1	EWR	2013	1	1	2	39.02	26.96	61.63	250.0	8.05546	NaN	1012.3	10.0	2013-01-01T07:00:00Z
2	EWR	2013	1	1	3	39.02	28.04	64.43	240.0	11.50780	NaN	1012.5	10.0	2013-01-01T08:00:00Z
3	EWR	2013	1	1	4	39.92	28.04	62.21	250.0	12.65858	NaN	1012.2	10.0	2013-01-01T09:00:00Z
4	EWR	2013	1	1	5	39.02	28.04	64.43	260.0	12.65858	NaN	1011.9	10.0	2013-01-01T10:00:00Z

Illustration: counting the number of flights per airport

# count number of flights per airport
series_number_of_flights = flights[['dest']].groupby('dest').size()
series_number_of_flights.name = 'Count flights'
series_number_of_flights

dest
ABQ      254
ACK      265
ALB      439
ANC        8
ATL    17215
       ...  
TPA     7466
TUL      315
TVC      101
TYS      631
XNA     1036
Name: Count flights, Length: 105, dtype: int64

airports_with_flight_counts = airports.merge(series_number_of_flights,
                                            left_on='faa',
                                            right_index=True)
airports_with_flight_counts

	faa	name	lat	lon	alt	tz	dst	tzone	Count flights
87	ABQ	Albuquerque International Sunport	35.040222	-106.609194	5355	-7	A	America/Denver	254
91	ACK	Nantucket Mem	41.253053	-70.060181	48	-5	A	America/New_York	265
118	ALB	Albany Intl	42.748267	-73.801692	285	-5	A	America/New_York	439
128	ANC	Ted Stevens Anchorage Intl	61.174361	-149.996361	152	-9	A	America/Anchorage	8
153	ATL	Hartsfield Jackson Atlanta Intl	33.636719	-84.428067	1026	-5	A	America/New_York	17215
...	...	...	...	...	...	...	...	...	...
1327	TPA	Tampa Intl	27.975472	-82.533250	26	-5	A	America/New_York	7466
1334	TUL	Tulsa Intl	36.198389	-95.888111	677	-6	A	America/Chicago	315
1337	TVC	Cherry Capital Airport	44.741445	-85.582235	624	-5	A	America/New_York	101
1347	TYS	Mc Ghee Tyson	35.810972	-83.994028	981	-5	A	America/New_York	631
1430	XNA	NW Arkansas Regional	36.281869	-94.306811	1287	-6	A	America/Chicago	1036

101 rows × 9 columns

# SFO and LAX (large airport)
airports_with_flight_counts.query('faa == "LAX" or faa == "SFO"')

	faa	name	lat	lon	alt	tz	dst	tzone	Count flights
770	LAX	Los Angeles Intl	33.942536	-118.408075	126	-8	A	America/Los_Angeles	16174
1216	SFO	San Francisco Intl	37.618972	-122.374889	13	-8	A	America/Los_Angeles	13331

Mean delay per airport

series_airport_with_mean_delay = flights[['dest', 'dep_delay']].groupby('dest').mean()
series_airport_with_mean_delay.name = 'delay'
series_airport_with_mean_delay.head()

	dep_delay
dest
ABQ	13.740157
ACK	6.456604
ALB	23.620525
ANC	12.875000
ATL	12.509824

Mean delay and number of fliths, on a map

airports_with_flight_counts_with_delays = airports.merge(
    series_number_of_flights,
    left_on='faa',
    right_index=True
).merge(
        series_airport_with_mean_delay,
        left_on='faa',
        right_index=True
)
airports_with_flight_counts_with_delays.query('faa == "LAX" or faa == "SFO"')

	faa	name	lat	lon	alt	tz	dst	tzone	Count flights	dep_delay
770	LAX	Los Angeles Intl	33.942536	-118.408075	126	-8	A	America/Los_Angeles	16174	9.401344
1216	SFO	San Francisco Intl	37.618972	-122.374889	13	-8	A	America/Los_Angeles	13331	12.866289

fig = px.scatter_geo(airports_with_flight_counts_with_delays,
                     lat='lat', lon='lon',
                     hover_name="name",
                     fitbounds="locations",
                     size='Count flights',
                     color='dep_delay'
                    )
fig.show()

The nycflights13 package

Illustration: counting the number of flights per airport

Mean delay per airport

Mean delay and number of fliths, on a map

The `nycflights13` package