134: The Greatest Data Analyst of All Time (John Snow)

Avery: 00:00:00

Today I'm going to tell you the story of one of the earliest and one of

2

: 00:00:03

the greatest data analysts of all time.

3

: 00:00:05

It's a story that had such a big

impact on my life that I actually

4

: 00:00:08

named my consulting company, Snow

Data Science, after this guy.

5

: 00:00:12

His name is John Snow.

6

: 00:00:14

And no, not the guy from Game of

Thrones, but an English physician

7

: 00:00:17

from the mid 1800s who saved a

country from a deadly outbreak of

8

: 00:00:21

cholera using only data analytics.

9

: 00:00:24

London, 1854, and there's a terrifying

disease sweeping the streets.

10

: 00:00:28

Cholera.

11

: 00:00:29

People are dropping like flies

and no one really knows why.

12

: 00:00:32

In fact, over 500 people had died in

this small area in the last 10 days.

13

: 00:00:37

At the time, most people believed that

cholera was spread through the air via

14

: 00:00:40

bad smells and what's called bad air.

15

: 00:00:43

Some people even believed that cholera

was really only coming out of the

16

: 00:00:46

cemeteries from people who had already

previously passed of the disease.

17

: 00:00:49

Basically, no one knew what was

going on in the disease world.

18

: 00:00:52

No one knew how people were getting

sick, They just knew that people were

19

: 00:00:55

getting sick at an alarming rate.

20

: 00:00:57

And with that knowledge, 75 percent of

that part of the city, Soho, fled due

21

: 00:01:02

to fear of contracting the disease.

22

: 00:01:04

Dr.

23

: 00:01:05

Jon Snow was determined to

figure out why these people were

24

: 00:01:08

getting sick and how to fix it.

25

: 00:01:09

You see, Jon was a doctor, and

he had this crazy idea that maybe

26

: 00:01:13

cholera wasn't spread through the

air, but rather through water.

27

: 00:01:17

And to us, that sounds pretty simple.

28

: 00:01:18

But at the time, it was

a revolutionary idea.

29

: 00:01:21

But no one would believe him.

30

: 00:01:23

So he knew he needed data to prove it.

31

: 00:01:25

So John hit the streets.

32

: 00:01:26

He started talking to people

who had gotten sick and asked

33

: 00:01:29

them a series of questions.

34

: 00:01:30

One of which was crucially,

Where are you getting your water?

35

: 00:01:34

And after interviewing dozens

of folks, he looked at his notes

36

: 00:01:37

and realized many had mentioned

getting water from the same well.

37

: 00:01:40

Which was the pump down on Broad Street.

38

: 00:01:43

A curious note, but nothing concrete.

39

: 00:01:45

John realized he needed more.

40

: 00:01:47

And here's where Snow did

something revolutionary and

41

: 00:01:50

thought like a data analyst.

42

: 00:01:51

He created a map of the streets of London

and plotted every cholera case on it.

43

: 00:01:56

Each water pump was highlighted

with a simple black circle, and each

44

: 00:01:59

case of cholera was indicated by a

simple black line stacked on top of

45

: 00:02:03

the other one to represent multiple

contractions at the same residence.

46

: 00:02:06

After constructing the graph, he found

that most of the deaths clustered around

47

: 00:02:10

one pump, the pump on Broad Street.

48

: 00:02:13

This gave him the data driven evidence

that maybe the disease was indeed in

49

: 00:02:17

the water, specifically at that pump.

50

: 00:02:19

This wasn't just a cool visualization that

he made, it was data analytics in action.

51

: 00:02:24

Armed with his data evidence,

he headed to the local officials

52

: 00:02:27

and presented his theory.

53

: 00:02:28

He showed them his map and asked them to

remove the handle of the pump which would

54

: 00:02:32

literally shut water down to that area.

55

: 00:02:34

The government obliged

and shut the pump down.

56

: 00:02:37

And guess what?

57

: 00:02:38

The cholera outbreak

slowed nearly immediately.

58

: 00:02:41

People stopped getting sick.

59

: 00:02:43

People stopped dying.

60

: 00:02:44

And the population of

London returned to the city.

61

: 00:02:46

This analysis didn't only save

lives, it actually changed

62

: 00:02:50

public health care forever.

63

: 00:02:51

Jon Snow's work is considered

one of the earliest examples

64

: 00:02:54

of data analytics in the UK.

65

: 00:02:55

and is still referred to

in pandemics or outbreaks.

66

: 00:02:58

Here are three simple ways that you and

I can be great analysts like Jon Snow.

67

: 00:03:03

Number one, visualize our data.

68

: 00:03:05

We as humans are not very

good at remembering numbers.

69

: 00:03:08

We can only really take a

look at 10 numbers at a time.

70

: 00:03:11

If you don't believe me, try to memorize a

telephone number in less than 10 seconds,

71

: 00:03:15

and if you can, you're above average.

72

: 00:03:18

If you don't believe me,

just try to remember this.

73

: 00:03:20

Number 8 0 1 5 7 2 2 7 7 8 4 3 2 1 7.

74

: 00:03:26

Go ahead and try to repeat that

in the comments down below.

75

: 00:03:28

If you get it, you're above average.

76

: 00:03:30

We as humans are just not good

at dealing with numbers, but

77

: 00:03:33

we are good at visualizing.

78

: 00:03:35

Our eyes are extremely powerful, and

so instead of trying to just understand

79

: 00:03:39

data inside of a notebook or instead

of a spreadsheet, when we visualize

80

: 00:03:42

data, that helps us understand it

better, and that was the key to success.

81

: 00:03:45

To John, figuring out what

was causing this disease.

82

: 00:03:48

Number two, we can storytell with data.

83

: 00:03:51

Notice that John didn't go to the

government and just, you know, show them

84

: 00:03:54

the map or just tell them the theory.

85

: 00:03:56

He combined the two.

86

: 00:03:57

He told a story.

87

: 00:03:59

In fact, they actually asked, well,

what is happening with this green

88

: 00:04:03

area right here and this green

area right here that you see on

89

: 00:04:06

the map, they're not getting sick.

90

: 00:04:08

Why are they not getting sick?

91

: 00:04:09

Even though they're really close

to this well, and he actually

92

: 00:04:12

went and interviewed those people

and found out that one was a bar.

93

: 00:04:15

And they said, quote, no

one drinks water here.

94

: 00:04:18

So those people were actually saved

from cholera by only drinking beer.

95

: 00:04:22

And the second one was actually

a prison where they actually have

96

: 00:04:24

their own well inside of the prison.

97

: 00:04:27

So he was able to illustrate the

full story with the data that was

98

: 00:04:30

able to convince the government

that this was the cause, even though

99

: 00:04:33

everyone thought it was in the air,

that it was actually in the water.

100

: 00:04:36

And number three, another

thing that Jon Snow did very

101

: 00:04:39

well is explain the outliers.

102

: 00:04:40

If you look at the map, you'll

notice that towards the bottom

103

: 00:04:43

and even some other places.

104

: 00:04:44

There are outliers.

105

: 00:04:45

There are people who contracted

cholera that were not close to

106

: 00:04:48

this pump and not using this pump.

107

: 00:04:50

This would actually hurt his

hypothesis, and he knew that.

108

: 00:04:53

So he actually went to those areas to talk

with those people and found out that many

109

: 00:04:57

of them had relatives or they had recently

visited that pump just a couple days ago.

110

: 00:05:02

So the outliers did not

hurt his case, they actually

111

: 00:05:04

ended up supporting his case.

112

: 00:05:06

If you want to be a great analyst

like Jon Snow, go ahead and hit

113

: 00:05:09

subscribe to get future episodes

that will help you get there.

Share Episode

Shownotes

Transcripts

Follow

Links

Chapters

Video

More from YouTube