1
00:00:00,300 --> 00:00:01,100
Hello my friends.

2
00:00:01,100 --> 00:00:01,966
Welcome back.

3
00:00:01,966 --> 00:00:05,400
Now let's learn together
how to import a data set.

4
00:00:05,533 --> 00:00:08,700
As a reminder, we're going to learn
how to import the following data.

5
00:00:08,700 --> 00:00:13,200
Set data dot CSV,
which is a very simple data set of,

6
00:00:13,200 --> 00:00:16,066
let's say a retail company
that is doing some analysis

7
00:00:16,066 --> 00:00:19,300
on which clients
purchased one of their products.

8
00:00:19,466 --> 00:00:24,533
So the rows in this data set correspond
to different customers of this employee.

9
00:00:24,766 --> 00:00:28,266
And for each of these customers,
we have the country they live in their

10
00:00:28,266 --> 00:00:32,566
age, their salary, and whether or not
they purchased the product.

11
00:00:32,600 --> 00:00:33,133
Okay.

12
00:00:33,133 --> 00:00:36,033
So we're going to learn
how to import that CSV

13
00:00:36,033 --> 00:00:39,166
on Python using,
of course, the pandas library.

14
00:00:39,300 --> 00:00:39,966
Here we go.

15
00:00:39,966 --> 00:00:42,933
So let's first create a new code cell.

16
00:00:42,933 --> 00:00:45,366
And now let's import this data set.

17
00:00:45,366 --> 00:00:48,500
So the first thing we have to do
is to create a new variable.

18
00:00:48,633 --> 00:00:51,733
And this variable will contain
exactly the data set.

19
00:00:52,100 --> 00:00:54,766
So I always like to choose simple names

20
00:00:54,766 --> 00:00:57,966
for my variables representing
well what we're creating.

21
00:00:57,966 --> 00:01:00,233
And therefore
since now we're importing the data set

22
00:01:00,233 --> 00:01:02,700
and we want to integrate the data
set in a variable.

23
00:01:02,700 --> 00:01:05,033
I'm going to call this variable data set.

24
00:01:05,033 --> 00:01:06,933
Okay. As simple as that.

25
00:01:06,933 --> 00:01:09,600
So this variable what will it be equal to.

26
00:01:09,600 --> 00:01:14,733
Well it will be equal to the output
of a certain function by pandas.

27
00:01:15,000 --> 00:01:17,966
And this certain function
will exactly read

28
00:01:17,966 --> 00:01:20,966
all the values of this data set

29
00:01:21,133 --> 00:01:23,933
and will create what we call a data frame.

30
00:01:23,933 --> 00:01:28,133
It's a certain format of data,
whether it is in Python or even R.

31
00:01:28,400 --> 00:01:31,200
So it will create a data frame
and it will contain

32
00:01:31,200 --> 00:01:35,100
exactly the same rows and columns
and values as what you see here.

33
00:01:35,133 --> 00:01:38,600
And this data frame
will be exactly this data set variable.

34
00:01:38,733 --> 00:01:39,500
All right.

35
00:01:39,500 --> 00:01:40,233
So there we go.

36
00:01:40,233 --> 00:01:43,733
In order to create this data frame
we're going to call a certain function

37
00:01:43,733 --> 00:01:47,766
by the pandas library
which is called read underscore CSV.

38
00:01:47,966 --> 00:01:49,933
And in this function we will only have to

39
00:01:49,933 --> 00:01:53,466
input the name of the data
set with the extension.

40
00:01:54,033 --> 00:01:58,333
So since we're about to call a function
of this, well,

41
00:01:58,333 --> 00:02:01,333
the first thing we have to do
is call dependance library.

42
00:02:01,533 --> 00:02:04,933
And therefore remember since we gave it
the shortcut named PG,

43
00:02:05,100 --> 00:02:08,100
in order to call it,
we need to add here PG.

44
00:02:08,233 --> 00:02:11,900
And then to call a function from a library
we need to add a dot.

45
00:02:11,900 --> 00:02:13,433
It's always done like that.

46
00:02:13,433 --> 00:02:16,433
And that's where you can call the function
you want to use.

47
00:02:16,533 --> 00:02:21,100
And as we said this function is named
read underscore CSV.

48
00:02:21,300 --> 00:02:24,666
And then you add some parenthesis
to enter the argument.

49
00:02:24,833 --> 00:02:26,133
So there we go. Let's do this.

50
00:02:26,133 --> 00:02:27,900
This will only what you will have to do

51
00:02:27,900 --> 00:02:30,733
when using this read underscore
CSV function.

52
00:02:30,733 --> 00:02:33,966
You have to input in quotes
the name of the data set.

53
00:02:34,266 --> 00:02:39,000
As a reminder, the name of the data set
is data with a capital D dot csv.

54
00:02:39,266 --> 00:02:40,066
So there we go.

55
00:02:40,066 --> 00:02:46,333
Data dot csv okay,
and this will create the data frame.

56
00:02:46,333 --> 00:02:48,700
You know
all the values inside this data set.

57
00:02:48,700 --> 00:02:52,766
And this data frame will be exactly
this data set variable okay.

58
00:02:53,166 --> 00:02:54,600
So that's the first step.

59
00:02:54,600 --> 00:02:56,766
But that's not enough to import data set.

60
00:02:56,766 --> 00:02:59,133
You know
as a first step of data preprocessing,

61
00:02:59,133 --> 00:03:03,233
the next thing that you have to do
is create two new entities.

62
00:03:03,266 --> 00:03:05,933
The first one is the matrix of features.

63
00:03:05,933 --> 00:03:08,933
And the second one
is the dependent variable vector.

64
00:03:08,966 --> 00:03:11,966
So let me show you exactly what they mean
and what they are

65
00:03:12,100 --> 00:03:15,300
in the data set right here okay.

66
00:03:15,800 --> 00:03:20,700
So I'm going to give you now a very first
important principle in machine learning.

67
00:03:21,166 --> 00:03:23,800
In any data set with which you're going

68
00:03:23,800 --> 00:03:27,066
to train a machine learning model,
you have the same entities

69
00:03:27,066 --> 00:03:30,600
which are the features
and the dependent variable vector.

70
00:03:30,933 --> 00:03:32,266
Can you guess here?

71
00:03:32,266 --> 00:03:35,266
What are the features
and what is the dependent variable?

72
00:03:35,533 --> 00:03:40,066
Well, very simply
the features are the columns

73
00:03:40,066 --> 00:03:43,466
with which you're going
to predict the dependent variable.

74
00:03:43,800 --> 00:03:46,900
And the dependent variable
of course is the last column.

75
00:03:46,900 --> 00:03:49,900
Because, you know,
this company would like to predict

76
00:03:49,933 --> 00:03:53,066
if some future customers
are going to purchase

77
00:03:53,066 --> 00:03:56,100
a certain product
based on these informations.

78
00:03:56,300 --> 00:04:01,033
So very simply, the features
or also called the independent variables,

79
00:04:01,333 --> 00:04:05,700
are the variables containing
some informations with which you can

80
00:04:05,700 --> 00:04:09,633
predict what you want to predict,
which is called the dependent variable.

81
00:04:10,033 --> 00:04:10,366
All right.

82
00:04:10,366 --> 00:04:14,100
So remember this very important principle
in any machine

83
00:04:14,100 --> 00:04:17,133
learning model that you're going to build
you're going to have separately

84
00:04:17,333 --> 00:04:20,966
the features usually
in the first columns of your data set.

85
00:04:21,333 --> 00:04:25,433
And the dependent variable, usually
in the last column of your data set,

86
00:04:25,566 --> 00:04:28,066
you will see that all the data sets
we will use in this course

87
00:04:28,066 --> 00:04:31,300
and most of the data sets
you'll use in your machine learning career

88
00:04:31,433 --> 00:04:35,200
will have the same format with first
the features you know in the first columns

89
00:04:35,366 --> 00:04:38,366
and the dependent variable vector
in the last column.

90
00:04:38,433 --> 00:04:39,333
Okay.

91
00:04:39,333 --> 00:04:42,666
And so right now what we want to create,
you know, the two entities,

92
00:04:42,666 --> 00:04:44,366
we want to create our first

93
00:04:44,366 --> 00:04:49,033
the matrix of features containing
separately these three columns here,

94
00:04:49,033 --> 00:04:51,266
you know, country age salary

95
00:04:51,266 --> 00:04:55,200
and separately we want to create
the dependent variable vector

96
00:04:55,266 --> 00:04:59,366
containing only this last column because
that's the column we want to predict.

97
00:04:59,700 --> 00:05:03,200
And that's exactly what
we always have to do in this first data

98
00:05:03,200 --> 00:05:04,000
preprocessing phase.

99
00:05:04,000 --> 00:05:05,133
So let's do this.

100
00:05:05,133 --> 00:05:07,066
Let's create these two entities.

101
00:05:07,066 --> 00:05:10,066
And we are going to call them x
for the matrix of features

102
00:05:10,200 --> 00:05:13,133
and y for the dependent variable vector.