Verkennende data-analyse

Data Science begrijpen

Hadrien Lacroix

Content Developer at DataCamp

Wat is EDA?

Verkennende data-analyse:

  • De gegevens verkennen
  • Hypothesen formuleren
  • Kenmerken beoordelen
  • Visualiseren

photograph-of-john-tukey

Data Science begrijpen

Dataworkflow

data science workflow

Data Science begrijpen

We duiken er meteen in.

Dataset 1        Dataset 2        Dataset 3        Dataset 4        
|x    |y    |    |x    |y    |    |x    |y    |    |x    |y    |
|-----|-----|    |-----|-----|    |-----|-----|    |-----|-----|    
|10.0 |8.04 |    |10.0 |9.14 |    |10.0 |7.46 |    |8.0  |6.58 |
|8.0  |6.95 |    |8.0  |8.14 |    |8.0  |6.77 |    |8.0  |5.76 |
|13.0 |7.58 |    |13.0 |8.74 |    |13.0 |12.74|    |8.0  |7.71 |
|9.0  |8.81 |    |9.0  |8.77 |    |9.0  |7.11 |    |8.0  |8.84 |
|11.0 |8.33 |    |11.0 |9.26 |    |11.0 |7.81 |    |8.0  |8.47 |
|14.0 |9.96 |    |14.0 |8.10 |    |14.0 |8.84 |    |8.0  |7.04 |
|6.0  |7.24 |    |6.0  |6.13 |    |6.0  |6.08 |    |8.0  |5.25 |
|4.0  |4.26 |    |4.0  |3.10 |    |4.0  |5.39 |    |19.0 |12.50|
|12.0 |10.84|    |12.0 |9.13 |    |12.0 |8.15 |    |8.0  |5.56 |
|7.0  |4.82 |    |7.0  |7.26 |    |7.0  |6.42 |    |8.0  |7.91 |
|5.0  |5.68 |    |5.0  |4.74 |    |5.0  |5.73 |    |8.0  |6.89 |
Data Science begrijpen

Verrassing!

De vier datasets tonen:

  • identiek gemiddelde en variantie voor x
  • identiek gemiddelde en variantie voor y
  • identieke correlatiecoëfficiënt
  • identieke lineaire regressievergelijking

$$

Kort gezegd: ze lijken behoorlijk op elkaar

Data Science begrijpen

Kwartet van Anscombe

anscombe's quartet

Data Science begrijpen

anscombe's linear graph

Data Science begrijpen

anscombe's non-linear graph

Data Science begrijpen

anscombe's regression thrown off

Data Science begrijpen

anscombe's correlation thrown off

Data Science begrijpen

two-rockets-landing-at-the-same-time

Data Science begrijpen

Ken je gegevens

  • Vluchtnummer (getal)
  • Datum (datumtijd)
  • Tijd (UTC) (datumtijd)
  • Booster-versie (tekst)
  • Lanceerlocatie (tekst)
  • Lading (tekst)
  • Massa van de lading (kg) (getal)
  • Baan (tekst)
  • Klant (tekst)
  • Missieresultaat (tekst)
  • Landingsresultaat (tekst)
Data Science begrijpen

Bekijk je gegevens

Flight  Date         Time (UTC)  Booster Version  Launch Site     Payload
_______________________________________________________________________________________________________
1       2010-06-04   18:45:00    F9 v1.0 B0003    CCAFS LC-40    Dragon Spacecraft Qualification Unit
2       2010-12-08   15:43:00    F9 v1.0 B0004    CCAFS LC-40    Dragon demo flight C1, two CubeSats...
3       2012-05-22   7:44:00     F9 v1.0 B0005    CCAFS LC-40    Dragon demo flight C2+
4       2012-10-08   0:35:00     F9 v1.0 B0006    CCAFS LC-40    SpaceX CRS-1
5       2013-03-01   15:10:00    F9 v1.0 B0007    CCAFS LC-40    SpaceX CRS-2    

Payload Mass (kg)    Orbit     Customer         Mission Outcome  Landing Outcome
_______________________________________________________________________________________________________
NaN                  LEO       SpaceX           Success          Failure (parachute)
NaN                  LEO (ISS) NASA (COTS) NRO  Success          Failure (parachute)
525                  LEO (ISS) NASA (COTS)      Success          No attempt
500                  LEO (ISS) NASA (CRS)       Success          No attempt
677                  LEO (ISS) NASA (CRS)       Success          No attempt
Data Science begrijpen

Beschrijvende statistieken

        Flight  Date         Time (UTC)  Booster Version  Launch Site     Payload
_______________________________________________________________________________________________________
count   55     55            55          55               55              55
unique  55     55            53          51               4               55
top     6      2018-03-30    4:45:00     F9 v1.1          CCAFS LC-40     SES-9
freq    1      1             2           5                26              1

        Payload Mass (kg)    Orbit     Customer         Mission Outcome  Landing Outcome
_______________________________________________________________________________________________________
count   53                   55        55               55               55
unique  47                   8         28               2                12
top     9,600                GTO       NASA (CRS)       Success          No attempt
freq    5                    22        14               54               18
Data Science begrijpen

Visualiseer!

spacex_launch_count

Data Science begrijpen

Stel meer vragen!

space-x-launches-by-site

Data Science begrijpen

Stel meer vragen!

space-x-launches-by-outcome

Data Science begrijpen

Uitschieters

spacex-payload-mass-histogram

Data Science begrijpen

We gaan oefenen!

Data Science begrijpen

Preparing Video For Download...