1
00:00:01,920 --> 00:00:04,680
great so I think we can start since the

2
00:00:04,680 --> 00:00:07,859
meeting is recorded So if everyone uh

3
00:00:07,859 --> 00:00:11,160
jump jumps in later can can watch the

4
00:00:11,160 --> 00:00:12,420
recording

5
00:00:12,420 --> 00:00:15,780
so hi everyone and welcome to these

6
00:00:15,780 --> 00:00:18,000
um Cloud skill challenge study session

7
00:00:18,000 --> 00:00:20,880
around a create classification models

8
00:00:20,880 --> 00:00:24,000
with Azure machine learning designer

9
00:00:24,000 --> 00:00:27,240
so today I'm thrilled to be here with

10
00:00:27,240 --> 00:00:29,820
John uh John do my introduce briefly

11
00:00:29,820 --> 00:00:31,619
yourself

12
00:00:31,619 --> 00:00:34,160
uh thank you Carlotta hello everyone

13
00:00:34,160 --> 00:00:38,160
Welcome to our Workshop today I hope

14
00:00:38,160 --> 00:00:40,559
that you are all excited for it I am

15
00:00:40,559 --> 00:00:43,140
John Aziz a gold Microsoft learn student

16
00:00:43,140 --> 00:00:47,460
ambassador and I will be here with uh

17
00:00:47,460 --> 00:00:50,760
Carlota to like do the Practical part

18
00:00:50,760 --> 00:00:53,820
about this module of the cloud skills

19
00:00:53,820 --> 00:00:57,000
challenge thank you for having me

20
00:00:57,000 --> 00:00:59,219
perfect thanks John so for those who

21
00:00:59,219 --> 00:01:03,440
don't know me I'm kellota

22
00:01:03,440 --> 00:01:06,479
based in Italy and focus it on AI

23
00:01:06,479 --> 00:01:08,760
machine learning Technologies and about

24
00:01:08,760 --> 00:01:11,900
the use in education

25
00:01:12,060 --> 00:01:13,200
um so

26
00:01:13,200 --> 00:01:15,000
um these Cloud skill challenge study

27
00:01:15,000 --> 00:01:17,580
session is based on a learn module a

28
00:01:17,580 --> 00:01:21,540
dedicated learn module I sent to you uh

29
00:01:21,540 --> 00:01:23,939
the link to this module uh in the chat

30
00:01:23,939 --> 00:01:25,619
in a way that you can follow along the

31
00:01:25,619 --> 00:01:28,680
model if you want or just have a look at

32
00:01:28,680 --> 00:01:33,000
the module later at your own pace

33
00:01:33,000 --> 00:01:33,780
um

34
00:01:33,780 --> 00:01:37,020
so before starting I would also like to

35
00:01:37,020 --> 00:01:40,619
remember to remember you uh the code of

36
00:01:40,619 --> 00:01:43,439
conduct and guidelines of our student

37
00:01:43,439 --> 00:01:47,640
Masters community so please during this

38
00:01:47,640 --> 00:01:51,000
meeting be respectful and inclusive and

39
00:01:51,000 --> 00:01:53,579
be friendly open and with coming and

40
00:01:53,579 --> 00:01:56,159
respectful of other each other

41
00:01:56,159 --> 00:01:57,720
differences

42
00:01:57,720 --> 00:02:01,200
if you want to learn more about the code

43
00:02:01,200 --> 00:02:03,540
of content you can use this link in the

44
00:02:03,540 --> 00:02:08,880
deck again.ms slash s-a-c-o-c

45
00:02:09,660 --> 00:02:12,420
and now we are

46
00:02:12,420 --> 00:02:15,420
um we are ready to to start our session

47
00:02:15,420 --> 00:02:18,959
so as we mentioned it we are going to

48
00:02:18,959 --> 00:02:21,780
focus on classification models and Azure

49
00:02:21,780 --> 00:02:24,900
ml uh today so first of all we are going

50
00:02:24,900 --> 00:02:28,920
to um identify uh the kind of

51
00:02:28,920 --> 00:02:31,080
um of scenarios in which you should

52
00:02:31,080 --> 00:02:33,900
choose to use a classification model

53
00:02:33,900 --> 00:02:36,660
we're going to introduce Azure machine

54
00:02:36,660 --> 00:02:39,060
learning and Azure machine designer

55
00:02:39,060 --> 00:02:41,879
we're going to understand uh which are

56
00:02:41,879 --> 00:02:43,680
the steps to follow to create a

57
00:02:43,680 --> 00:02:46,200
classification model in Azure mesh

58
00:02:46,200 --> 00:02:48,599
learning and then John will

59
00:02:48,599 --> 00:02:49,500
um

60
00:02:49,500 --> 00:02:52,379
lead an amazing demo about training and

61
00:02:52,379 --> 00:02:54,300
Publishing a classification model in

62
00:02:54,300 --> 00:02:57,000
Azure ml designer

63
00:02:57,000 --> 00:02:59,819
so let's start from the beginning let's

64
00:02:59,819 --> 00:03:02,640
start from identifying classification

65
00:03:02,640 --> 00:03:05,220
machine learning scenarios

66
00:03:05,220 --> 00:03:07,640
so first of all what is classification

67
00:03:07,640 --> 00:03:09,959
classification is a form of machine

68
00:03:09,959 --> 00:03:12,120
learning that is used to predict which

69
00:03:12,120 --> 00:03:15,599
category or class an item belongs to for

70
00:03:15,599 --> 00:03:17,340
example we might want to develop a

71
00:03:17,340 --> 00:03:19,800
classifier able to identify if an

72
00:03:19,800 --> 00:03:22,200
Incoming Email should be filtered or not

73
00:03:22,200 --> 00:03:25,080
according to the style the center the

74
00:03:25,080 --> 00:03:28,140
length of the email Etc in this case the

75
00:03:28,140 --> 00:03:30,060
characteristics of the email are the

76
00:03:30,060 --> 00:03:31,080
features

77
00:03:31,080 --> 00:03:34,200
and the label is a classification of

78
00:03:34,200 --> 00:03:38,099
either a zero or one representing a Spam

79
00:03:38,099 --> 00:03:40,860
or non-spam for the including email so

80
00:03:40,860 --> 00:03:42,360
this is an example of a binary

81
00:03:42,360 --> 00:03:44,400
classifier if you want to assign

82
00:03:44,400 --> 00:03:46,260
multiple categories to the incoming

83
00:03:46,260 --> 00:03:48,959
email like work letters love letters

84
00:03:48,959 --> 00:03:52,080
complaints or other categories in this

85
00:03:52,080 --> 00:03:54,000
case a binary classifier is not longer

86
00:03:54,000 --> 00:03:55,739
enough and we should develop a

87
00:03:55,739 --> 00:03:58,319
multi-class classifier so classification

88
00:03:58,319 --> 00:04:00,599
is an example of what is called

89
00:04:00,599 --> 00:04:02,519
supervised machine learning

90
00:04:02,519 --> 00:04:05,280
in which you train a model using data

91
00:04:05,280 --> 00:04:07,080
that includes both the features and

92
00:04:07,080 --> 00:04:08,879
known values for label

93
00:04:08,879 --> 00:04:11,099
so that the model learns to fit the

94
00:04:11,099 --> 00:04:13,560
feature combinations to the label then

95
00:04:13,560 --> 00:04:15,420
after training has been completed you

96
00:04:15,420 --> 00:04:17,040
can use the train model to predict

97
00:04:17,040 --> 00:04:19,500
labels for new items for for which the

98
00:04:19,500 --> 00:04:22,320
label is unknown

99
00:04:22,320 --> 00:04:25,440
but let's see some examples of scenarios

100
00:04:25,440 --> 00:04:27,120
for classification machine learning

101
00:04:27,120 --> 00:04:29,160
models so we already mentioned an

102
00:04:29,160 --> 00:04:31,020
example of a solution in which we would

103
00:04:31,020 --> 00:04:33,660
need a classifier but let's explore

104
00:04:33,660 --> 00:04:35,699
other scenarios for classification in

105
00:04:35,699 --> 00:04:37,979
other Industries for example you can use

106
00:04:37,979 --> 00:04:40,380
a classification model for a health

107
00:04:40,380 --> 00:04:43,680
clinic scenario and use clinical data to

108
00:04:43,680 --> 00:04:45,720
predict whether patient will become sick

109
00:04:45,720 --> 00:04:47,060
or not

110
00:04:47,060 --> 00:04:49,680
uh you can use

111
00:04:49,680 --> 00:04:51,740
um

112
00:05:03,780 --> 00:05:07,860
oh sorry so when I became muted it's a

113
00:05:07,860 --> 00:05:11,940
long time or you can use you can use uh

114
00:05:11,940 --> 00:05:13,560
some models for classification for

115
00:05:13,560 --> 00:05:16,919
example you can use you're saying this

116
00:05:16,919 --> 00:05:21,199
uh so I I was I was

117
00:05:21,660 --> 00:05:24,180
this one like you you have been muted

118
00:05:24,180 --> 00:05:27,060
for uh one second okay okay perfect

119
00:05:27,060 --> 00:05:30,419
perfect uh yeah I was talking sorry for

120
00:05:30,419 --> 00:05:34,560
that so I was talking about the possible

121
00:05:34,560 --> 00:05:37,320
you can use a classification model like

122
00:05:37,320 --> 00:05:39,660
have Clinic scenario Financial scenario

123
00:05:39,660 --> 00:05:41,699
or other third one is business type of

124
00:05:41,699 --> 00:05:44,100
scenario you can use characteristics or

125
00:05:44,100 --> 00:05:45,900
small business to predict if a new

126
00:05:45,900 --> 00:05:47,880
Venture will will succeed or not for

127
00:05:47,880 --> 00:05:49,560
example and these are all types of

128
00:05:49,560 --> 00:05:52,160
binary classification

129
00:05:52,160 --> 00:05:55,199
uh but today we are also going to talk

130
00:05:55,199 --> 00:05:57,240
about Azure machine learning so let's

131
00:05:57,240 --> 00:05:58,139
see

132
00:05:58,139 --> 00:06:00,660
um what is azure Mash learning so

133
00:06:00,660 --> 00:06:02,160
training and deploying an effective

134
00:06:02,160 --> 00:06:04,199
machine learning model involves a lot of

135
00:06:04,199 --> 00:06:06,539
work much of it time consuming and

136
00:06:06,539 --> 00:06:08,880
resource intensive so Azure machine

137
00:06:08,880 --> 00:06:11,039
learning is a cloud-based service that

138
00:06:11,039 --> 00:06:12,780
helps simplify some of the tasks it

139
00:06:12,780 --> 00:06:15,720
takes to prepare data train a model and

140
00:06:15,720 --> 00:06:18,060
also deploy it as a predictive service

141
00:06:18,060 --> 00:06:20,220
so it helps that the scientists increase

142
00:06:20,220 --> 00:06:22,380
their efficiency by automating many of

143
00:06:22,380 --> 00:06:24,660
the time consuming tasks Associated to

144
00:06:24,660 --> 00:06:27,539
creating and training a model

145
00:06:27,539 --> 00:06:29,520
and it enables them also to use

146
00:06:29,520 --> 00:06:31,740
cloud-based compute resources that scale

147
00:06:31,740 --> 00:06:33,720
effectively to handle large volumes of

148
00:06:33,720 --> 00:06:36,300
data while incurring costs only when

149
00:06:36,300 --> 00:06:38,699
actually used

150
00:06:38,699 --> 00:06:41,220
to use Azure machine learning you

151
00:06:41,220 --> 00:06:43,199
fasting fast you need to create a

152
00:06:43,199 --> 00:06:44,940
workspace resource in your Azure

153
00:06:44,940 --> 00:06:47,520
subscription and you can then use these

154
00:06:47,520 --> 00:06:50,220
workspace to manage data compute

155
00:06:50,220 --> 00:06:52,440
resources code models and other

156
00:06:52,440 --> 00:06:55,139
artifacts after you have created an

157
00:06:55,139 --> 00:06:56,819
Azure machine learning workspace you can

158
00:06:56,819 --> 00:06:58,560
develop Solutions with the Azure machine

159
00:06:58,560 --> 00:07:00,840
learning service either with developer

160
00:07:00,840 --> 00:07:02,580
tools or the Azure machine Learning

161
00:07:02,580 --> 00:07:04,380
Studio web portal

162
00:07:04,380 --> 00:07:06,360
in particular International Learning

163
00:07:06,360 --> 00:07:07,800
Studio is a web portal for machine

164
00:07:07,800 --> 00:07:09,720
learning Solutions in Azure and it

165
00:07:09,720 --> 00:07:11,639
includes a wide range of features and

166
00:07:11,639 --> 00:07:13,800
capabilities that help data scientists

167
00:07:13,800 --> 00:07:16,259
prepare data train models publish

168
00:07:16,259 --> 00:07:18,479
Predictive Services and monitor also

169
00:07:18,479 --> 00:07:19,680
their usage

170
00:07:19,680 --> 00:07:22,139
so to begin using the web portal you

171
00:07:22,139 --> 00:07:23,880
need to assign the workspace you created

172
00:07:23,880 --> 00:07:26,819
in the Azure portal to the Azure machine

173
00:07:26,819 --> 00:07:29,419
Learning Studio

174
00:07:29,520 --> 00:07:31,800
as its core Azure Mash learning is a

175
00:07:31,800 --> 00:07:33,720
service for training and managing

176
00:07:33,720 --> 00:07:36,000
machine learning models for which you

177
00:07:36,000 --> 00:07:38,220
need compute resources on which to run

178
00:07:38,220 --> 00:07:39,919
the training process

179
00:07:39,919 --> 00:07:44,280
compute targets are um one of the main

180
00:07:44,280 --> 00:07:46,740
basic concept of azure Mash learning

181
00:07:46,740 --> 00:07:48,780
they are cloud-based resources on which

182
00:07:48,780 --> 00:07:50,639
you can run model training and AD

183
00:07:50,639 --> 00:07:53,220
exploration processes

184
00:07:53,220 --> 00:07:54,780
so initial machine Learning Studio you

185
00:07:54,780 --> 00:07:56,759
can manage the compute targets for your

186
00:07:56,759 --> 00:07:58,740
data science activities and there are

187
00:07:58,740 --> 00:08:03,240
four kinds of of compute targets you can

188
00:08:03,240 --> 00:08:05,940
create we have the computer instances

189
00:08:05,940 --> 00:08:09,539
which are vital machine set up for

190
00:08:09,539 --> 00:08:10,979
running machine learning code during

191
00:08:10,979 --> 00:08:13,319
development so they are not designed for

192
00:08:13,319 --> 00:08:14,460
production

193
00:08:14,460 --> 00:08:17,099
then we have compute clusters which are

194
00:08:17,099 --> 00:08:19,800
a set of virtual machines that can scale

195
00:08:19,800 --> 00:08:22,199
up automatically based on traffic

196
00:08:22,199 --> 00:08:24,599
we have inference clusters which are

197
00:08:24,599 --> 00:08:26,699
similar to compute clusters but they are

198
00:08:26,699 --> 00:08:29,340
designed for deployment so they are a

199
00:08:29,340 --> 00:08:31,979
deployment targets for Predictive

200
00:08:31,979 --> 00:08:35,820
Services that use train models

201
00:08:35,820 --> 00:08:38,339
and finally we have attached compute

202
00:08:38,339 --> 00:08:41,339
which are any compute Target that you

203
00:08:41,339 --> 00:08:44,159
manage yourself outside of azramel like

204
00:08:44,159 --> 00:08:46,560
for example virtual machines or Azure

205
00:08:46,560 --> 00:08:49,700
databricks clusters

206
00:08:49,980 --> 00:08:52,800
so we talked about Azure machine

207
00:08:52,800 --> 00:08:54,300
learning but we also mentioned it

208
00:08:54,300 --> 00:08:55,500
mentioned Azure machine learning

209
00:08:55,500 --> 00:08:57,540
designer what is azure machine learning

210
00:08:57,540 --> 00:09:00,120
designer so initial machine Learning

211
00:09:00,120 --> 00:09:02,880
Studio there are several ways to author

212
00:09:02,880 --> 00:09:04,560
classification machine learning models

213
00:09:04,560 --> 00:09:08,100
one way is to use a visual interface and

214
00:09:08,100 --> 00:09:10,260
this visual interface is called designer

215
00:09:10,260 --> 00:09:13,140
and you can use it to train test and

216
00:09:13,140 --> 00:09:15,540
also deploy machine learning models and

217
00:09:15,540 --> 00:09:17,940
the drag and drop interface makes use of

218
00:09:17,940 --> 00:09:20,279
clearly defined inputs and outputs that

219
00:09:20,279 --> 00:09:22,680
can be shared reused and also Version

220
00:09:22,680 --> 00:09:23,880
Control

221
00:09:23,880 --> 00:09:25,920
and using the designer you can identify

222
00:09:25,920 --> 00:09:28,080
the building blocks or components needed

223
00:09:28,080 --> 00:09:30,839
for your model place and connect them on

224
00:09:30,839 --> 00:09:33,120
your canvas and run a machine learning

225
00:09:33,120 --> 00:09:35,300
job

226
00:09:35,399 --> 00:09:36,779
so

227
00:09:36,779 --> 00:09:39,120
um each designer project so each project

228
00:09:39,120 --> 00:09:42,360
in the designer is known as a pipeline

229
00:09:42,360 --> 00:09:45,600
and in the design we have a left panel

230
00:09:45,600 --> 00:09:48,360
for navigation and a canvas on your

231
00:09:48,360 --> 00:09:50,640
right hand side in which you build your

232
00:09:50,640 --> 00:09:53,940
pipeline visually so pipelines let you

233
00:09:53,940 --> 00:09:56,100
organize manage and reuse complex

234
00:09:56,100 --> 00:09:58,260
machine learning workflows across

235
00:09:58,260 --> 00:10:00,480
projects and users

236
00:10:00,480 --> 00:10:03,000
a pipeline starts with the data set from

237
00:10:03,000 --> 00:10:04,140
which you want to train the model

238
00:10:04,140 --> 00:10:05,880
because all begins with data when

239
00:10:05,880 --> 00:10:07,380
talking about data science and machine

240
00:10:07,380 --> 00:10:09,540
learning and each time you run a

241
00:10:09,540 --> 00:10:10,980
pipeline the configuration of the

242
00:10:10,980 --> 00:10:12,959
pipeline and its results are stored in

243
00:10:12,959 --> 00:10:17,339
your workspace as a pipeline job

244
00:10:17,339 --> 00:10:21,959
so the second main concept of azure

245
00:10:21,959 --> 00:10:25,080
machine learning is a component so going

246
00:10:25,080 --> 00:10:28,440
hierarchically from the pipeline we can

247
00:10:28,440 --> 00:10:30,540
say that each building block of a

248
00:10:30,540 --> 00:10:33,920
pipeline is called a component

249
00:10:33,920 --> 00:10:36,959
learning component encapsulate one step

250
00:10:36,959 --> 00:10:39,420
in a machine learning pipeline so it's a

251
00:10:39,420 --> 00:10:41,640
reusable piece of code with inputs and

252
00:10:41,640 --> 00:10:44,100
outputs something very similar to a

253
00:10:44,100 --> 00:10:46,500
function in any programming language

254
00:10:46,500 --> 00:10:48,899
and in a pipeline project you can access

255
00:10:48,899 --> 00:10:51,480
data assets and components from the left

256
00:10:51,480 --> 00:10:52,700
panels

257
00:10:52,700 --> 00:10:56,279
asset Library tab as you can see

258
00:10:56,279 --> 00:11:00,200
um here in the screenshot in the deck

259
00:11:00,300 --> 00:11:03,360
so you can create data assets on using

260
00:11:03,360 --> 00:11:08,339
an adoc page called Data Page and a data

261
00:11:08,339 --> 00:11:11,160
set is a reference to a data source

262
00:11:11,160 --> 00:11:12,480
location

263
00:11:12,480 --> 00:11:15,720
so this data source location could be a

264
00:11:15,720 --> 00:11:18,779
local file a data store a web file or

265
00:11:18,779 --> 00:11:21,660
even an age group open that set

266
00:11:21,660 --> 00:11:23,880
and these data assets will appear along

267
00:11:23,880 --> 00:11:26,459
with standard sample data set in the

268
00:11:26,459 --> 00:11:30,019
designers asset Library

269
00:11:30,839 --> 00:11:31,560
um

270
00:11:31,560 --> 00:11:36,959
and another basic concept of azure ml is

271
00:11:36,959 --> 00:11:38,880
azure machine learning jobs

272
00:11:38,880 --> 00:11:43,519
so basically when you submit a pipeline

273
00:11:43,519 --> 00:11:47,040
you create a job which will run all the

274
00:11:47,040 --> 00:11:49,920
steps in your pipeline so a job execute

275
00:11:49,920 --> 00:11:52,800
a task against a specified compute

276
00:11:52,800 --> 00:11:53,760
Target

277
00:11:53,760 --> 00:11:56,640
jobs enable systematic tracking for your

278
00:11:56,640 --> 00:11:58,560
machine learning experimentation in

279
00:11:58,560 --> 00:11:59,880
Azure ml

280
00:11:59,880 --> 00:12:02,399
and once a job is created azramel

281
00:12:02,399 --> 00:12:05,459
maintains a run record uh for for the

282
00:12:05,459 --> 00:12:07,640
job

283
00:12:08,399 --> 00:12:12,180
um but let's move to the classification

284
00:12:12,180 --> 00:12:14,040
steps so

285
00:12:14,040 --> 00:12:17,160
um let's introduce uh how to create a

286
00:12:17,160 --> 00:12:21,360
classification model in Azure ml but you

287
00:12:21,360 --> 00:12:23,640
will see it in more details in a

288
00:12:23,640 --> 00:12:26,339
handsome demo that John will will guide

289
00:12:26,339 --> 00:12:29,459
through in a few minutes

290
00:12:29,459 --> 00:12:32,220
so you can think of the steps to train

291
00:12:32,220 --> 00:12:33,720
and evaluate a classification machine

292
00:12:33,720 --> 00:12:36,660
learning model as four main steps so

293
00:12:36,660 --> 00:12:38,459
first of all you need to prepare your

294
00:12:38,459 --> 00:12:41,100
data so you need to identify the

295
00:12:41,100 --> 00:12:43,139
features and the label in your data set

296
00:12:43,139 --> 00:12:46,139
you need to pre-process so you need to

297
00:12:46,139 --> 00:12:48,839
clean and transform the data as needed

298
00:12:48,839 --> 00:12:51,120
then the second step of course is

299
00:12:51,120 --> 00:12:52,740
training the model

300
00:12:52,740 --> 00:12:54,600
and for training the model you need to

301
00:12:54,600 --> 00:12:57,060
split the data into two groups a

302
00:12:57,060 --> 00:12:59,519
training and a validation set

303
00:12:59,519 --> 00:13:01,320
then you train a machine learning model

304
00:13:01,320 --> 00:13:03,540
using the training data set and you test

305
00:13:03,540 --> 00:13:05,040
the machine learning model for

306
00:13:05,040 --> 00:13:07,019
performance using the validation data

307
00:13:07,019 --> 00:13:08,100
set

308
00:13:08,100 --> 00:13:12,180
the third step is performance evaluation

309
00:13:12,180 --> 00:13:14,519
um which means comparing how close the

310
00:13:14,519 --> 00:13:16,139
model's predictions are to the known

311
00:13:16,139 --> 00:13:20,519
labels and these lead us to compute some

312
00:13:20,519 --> 00:13:23,279
evaluation performance metrics

313
00:13:23,279 --> 00:13:25,740
and then finally

314
00:13:25,740 --> 00:13:29,880
um so these three steps are not

315
00:13:29,880 --> 00:13:33,000
um not performed uh every time in a

316
00:13:33,000 --> 00:13:35,459
linear manner it's more an iterative

317
00:13:35,459 --> 00:13:39,420
process but once you obtain you achieve

318
00:13:39,420 --> 00:13:42,959
a a performance with which you are

319
00:13:42,959 --> 00:13:45,779
satisfied so you are ready to let's say

320
00:13:45,779 --> 00:13:48,660
go into production and you can deploy

321
00:13:48,660 --> 00:13:51,920
your train model as a predictive service

322
00:13:51,920 --> 00:13:55,980
into a real-time uh to a real-time

323
00:13:55,980 --> 00:13:58,019
endpoint and to do so you need to

324
00:13:58,019 --> 00:14:00,240
convert the training pipeline into a

325
00:14:00,240 --> 00:14:02,820
real-time inference Pipeline and then

326
00:14:02,820 --> 00:14:04,260
you can deploy the model as an

327
00:14:04,260 --> 00:14:06,779
application on a server or device so

328
00:14:06,779 --> 00:14:11,420
that others can consume this model

329
00:14:11,459 --> 00:14:14,279
so let's start with the first step which

330
00:14:14,279 --> 00:14:17,700
is prepaid data reward data can contain

331
00:14:17,700 --> 00:14:19,920
many different issues that can affect

332
00:14:19,920 --> 00:14:22,320
the utility of the data and our

333
00:14:22,320 --> 00:14:24,959
interpretation of the results so also

334
00:14:24,959 --> 00:14:26,579
the machine learning model that you

335
00:14:26,579 --> 00:14:29,399
train using this data for example real

336
00:14:29,399 --> 00:14:31,440
world data can be affected by a bed

337
00:14:31,440 --> 00:14:34,079
recording or a bad measurement and it

338
00:14:34,079 --> 00:14:36,480
can also contain missing values for some

339
00:14:36,480 --> 00:14:38,880
parameters and Azure machine learning

340
00:14:38,880 --> 00:14:40,860
designer has several pre-built

341
00:14:40,860 --> 00:14:43,019
components that can be used to prepaid

342
00:14:43,019 --> 00:14:46,079
data for training these components

343
00:14:46,079 --> 00:14:48,300
enable you to clean data normalize

344
00:14:48,300 --> 00:14:52,940
features join tables and and more

345
00:14:53,000 --> 00:14:57,120
let's come to uh training so to train a

346
00:14:57,120 --> 00:14:59,220
classification model you need a data set

347
00:14:59,220 --> 00:15:02,160
that includes historical features so the

348
00:15:02,160 --> 00:15:03,899
characteristics of the entity for which

349
00:15:03,899 --> 00:15:06,899
one to make a prediction and known label

350
00:15:06,899 --> 00:15:09,779
values the label is the class indicator

351
00:15:09,779 --> 00:15:11,820
we want to train a model to predict it

352
00:15:11,820 --> 00:15:13,920
and it's common practice to train a

353
00:15:13,920 --> 00:15:16,199
model using a subset of the data while

354
00:15:16,199 --> 00:15:18,300
holding back some data with which to

355
00:15:18,300 --> 00:15:20,760
test the train model and this enables

356
00:15:20,760 --> 00:15:22,440
you to compare the labels that the model

357
00:15:22,440 --> 00:15:25,380
predicts with the actual known labels in

358
00:15:25,380 --> 00:15:27,420
the original data set

359
00:15:27,420 --> 00:15:29,880
this operation can be performed in the

360
00:15:29,880 --> 00:15:32,100
designer using the split data component

361
00:15:32,100 --> 00:15:34,740
as shown by the screenshot here in the

362
00:15:34,740 --> 00:15:36,660
in the deck

363
00:15:36,660 --> 00:15:39,540
there's also another component that you

364
00:15:39,540 --> 00:15:40,980
should use which is the score model

365
00:15:40,980 --> 00:15:43,139
component to generate the predicted

366
00:15:43,139 --> 00:15:45,360
class label value using the validation

367
00:15:45,360 --> 00:15:48,060
data as input so once you connect all

368
00:15:48,060 --> 00:15:49,800
these components

369
00:15:49,800 --> 00:15:52,440
um the component specifying the the

370
00:15:52,440 --> 00:15:54,959
model we are going to use the split data

371
00:15:54,959 --> 00:15:57,060
component the trained model component

372
00:15:57,060 --> 00:16:00,300
and the score model component you want

373
00:16:00,300 --> 00:16:02,639
to run an a new experiment in the

374
00:16:02,639 --> 00:16:05,760
initial map which will use the data set

375
00:16:05,760 --> 00:16:09,600
on the canvas to train and score a model

376
00:16:09,600 --> 00:16:12,000
after training a model it is important

377
00:16:12,000 --> 00:16:14,639
we say to evaluate its performance to

378
00:16:14,639 --> 00:16:17,060
understand how bad how how good sorry

379
00:16:17,060 --> 00:16:20,760
our model is performing

380
00:16:20,760 --> 00:16:22,680
and there are many performance metrics

381
00:16:22,680 --> 00:16:24,600
and methodologies for evaluating how

382
00:16:24,600 --> 00:16:27,000
well a model makes predictions the

383
00:16:27,000 --> 00:16:29,160
component to use to perform evaluation

384
00:16:29,160 --> 00:16:32,220
in Azure ml designer is called as

385
00:16:32,220 --> 00:16:35,060
intuitive as it is evaluate model

386
00:16:35,060 --> 00:16:38,339
once the job of training and evaluation

387
00:16:38,339 --> 00:16:40,740
of the model is completed you can review

388
00:16:40,740 --> 00:16:42,959
evaluation metrics on the completed job

389
00:16:42,959 --> 00:16:45,860
Page by right clicking on the component

390
00:16:45,860 --> 00:16:48,480
in the evaluation results you can also

391
00:16:48,480 --> 00:16:51,000
find the so-called confusion Matrix that

392
00:16:51,000 --> 00:16:53,399
you can see here in the right side of of

393
00:16:53,399 --> 00:16:55,079
this deck

394
00:16:55,079 --> 00:16:57,420
a confusion Matrix shows cases where

395
00:16:57,420 --> 00:16:59,220
both the predicted and actual values

396
00:16:59,220 --> 00:17:01,980
were one uh the so-called true positives

397
00:17:01,980 --> 00:17:04,500
at the top left and also cases where

398
00:17:04,500 --> 00:17:06,600
both the predicted and the actual values

399
00:17:06,600 --> 00:17:08,459
were zero the so-called true negatives

400
00:17:08,459 --> 00:17:10,919
at the bottom right while the other

401
00:17:10,919 --> 00:17:13,679
cells show cases where the predicting

402
00:17:13,679 --> 00:17:15,380
and actual values differ

403
00:17:15,380 --> 00:17:17,939
called false positive and false

404
00:17:17,939 --> 00:17:19,919
negatives and this is an example of a

405
00:17:19,919 --> 00:17:23,579
confusion Matrix for a binary classifier

406
00:17:23,579 --> 00:17:25,559
why for a multi-class classification

407
00:17:25,559 --> 00:17:28,079
model the same approach is used to

408
00:17:28,079 --> 00:17:30,120
tabulate each possible combination of

409
00:17:30,120 --> 00:17:32,940
actual and predictive value counts so

410
00:17:32,940 --> 00:17:34,740
for example a model with three possible

411
00:17:34,740 --> 00:17:37,559
classes would result in three times

412
00:17:37,559 --> 00:17:39,120
three Matrix

413
00:17:39,120 --> 00:17:41,880
the confusion Matrix is also useful for

414
00:17:41,880 --> 00:17:43,860
the metrics that can be derived from it

415
00:17:43,860 --> 00:17:48,260
like accuracy recall or precision

416
00:17:49,320 --> 00:17:52,080
um we we say that the last step is

417
00:17:52,080 --> 00:17:55,620
deploying the train model to a real-time

418
00:17:55,620 --> 00:17:59,280
endpoint as a predictive service and in

419
00:17:59,280 --> 00:18:00,900
order to automate your model into

420
00:18:00,900 --> 00:18:02,760
service that makes continuous

421
00:18:02,760 --> 00:18:04,980
predictions you need first of all to

422
00:18:04,980 --> 00:18:08,039
create any and and then deploy an

423
00:18:08,039 --> 00:18:10,080
inference pipeline the process of

424
00:18:10,080 --> 00:18:11,940
converting the training pipeline into a

425
00:18:11,940 --> 00:18:13,980
real-time inference pipeline removes

426
00:18:13,980 --> 00:18:16,260
training components and adds web service

427
00:18:16,260 --> 00:18:18,960
inputs and outputs to handle requests

428
00:18:18,960 --> 00:18:21,240
and the inference pipeline performs they

429
00:18:21,240 --> 00:18:22,679
seem that the transformation as the

430
00:18:22,679 --> 00:18:26,160
first pipeline but for new data then it

431
00:18:26,160 --> 00:18:28,679
uses the train model to infer or predict

432
00:18:28,679 --> 00:18:32,539
label values based on its feature

433
00:18:32,820 --> 00:18:36,120
um so I think I've talked a lot for now

434
00:18:36,120 --> 00:18:40,380
I would like to let John show us

435
00:18:40,380 --> 00:18:44,340
something in practice uh with uh with

436
00:18:44,340 --> 00:18:47,280
the Hands-On demo so please John go

437
00:18:47,280 --> 00:18:49,860
ahead sharing your screen and guide us

438
00:18:49,860 --> 00:18:52,380
through this demo of creating a

439
00:18:52,380 --> 00:18:53,760
classification with the Azure machine

440
00:18:53,760 --> 00:18:55,860
learning designer

441
00:18:55,860 --> 00:18:58,919
uh thank you so much Carlotta for this

442
00:18:58,919 --> 00:19:01,380
interesting explanation of the Azure ml

443
00:19:01,380 --> 00:19:04,740
designer and now

444
00:19:04,740 --> 00:19:07,500
um I'm going to start with you in the

445
00:19:07,500 --> 00:19:10,200
Practical demo part so uh if you want to

446
00:19:10,200 --> 00:19:13,320
follow along go to the link that Carlota

447
00:19:13,320 --> 00:19:18,380
sent in the chat so like you can do

448
00:19:18,380 --> 00:19:21,840
the demo or the Practical part with me

449
00:19:21,840 --> 00:19:25,260
I'm just going to share my screen

450
00:19:25,260 --> 00:19:27,140
and

451
00:19:27,140 --> 00:19:31,559
go here so uh

452
00:19:31,559 --> 00:19:34,320
where am I right now I'm inside the

453
00:19:34,320 --> 00:19:36,960
Microsoft learn documentation this is

454
00:19:36,960 --> 00:19:40,260
the exercise part of this module and we

455
00:19:40,260 --> 00:19:43,080
will start by setting two things which

456
00:19:43,080 --> 00:19:45,299
are a prequisite for us to work inside

457
00:19:45,299 --> 00:19:49,919
this module which are the users group

458
00:19:49,919 --> 00:19:52,400
and the Azure machine learning workspace

459
00:19:52,400 --> 00:19:55,620
and something extra which is the compute

460
00:19:55,620 --> 00:19:59,760
cluster that calendar Target about so I

461
00:19:59,760 --> 00:20:02,100
just want to make sure that you all have

462
00:20:02,100 --> 00:20:05,660
a resource Group created inside your

463
00:20:05,660 --> 00:20:08,039
auditor inside your Microsoft Azure

464
00:20:08,039 --> 00:20:11,100
platform so this is my research group

465
00:20:11,100 --> 00:20:14,640
inside this is this Resource Group I

466
00:20:14,640 --> 00:20:17,299
have created an Azure machine learning

467
00:20:17,299 --> 00:20:21,539
workspace so I'm just going to access

468
00:20:21,539 --> 00:20:24,000
the workspace that I have created

469
00:20:24,000 --> 00:20:27,000
already from this link I am going to

470
00:20:27,000 --> 00:20:30,240
open it which is the studio web URL and

471
00:20:30,240 --> 00:20:33,000
I will follow the steps so what is this

472
00:20:33,000 --> 00:20:35,760
this is your machine learning workspace

473
00:20:35,760 --> 00:20:38,220
or machine Learning Studio you can do a

474
00:20:38,220 --> 00:20:40,080
lot of things here but we are going to

475
00:20:40,080 --> 00:20:42,419
focus mainly on the designer and the

476
00:20:42,419 --> 00:20:46,080
data and the compute so another

477
00:20:46,080 --> 00:20:49,140
prequisite here as Carlotta told you and

478
00:20:49,140 --> 00:20:51,480
we need some resources to power up the

479
00:20:51,480 --> 00:20:54,299
the classification the processes that

480
00:20:54,299 --> 00:20:55,140
will happen

481
00:20:55,140 --> 00:20:58,080
so we have created this Computing

482
00:20:58,080 --> 00:20:59,100
cluster

483
00:20:59,100 --> 00:21:02,880
and we have like Set uh some presets for

484
00:21:02,880 --> 00:21:04,140
it so

485
00:21:04,140 --> 00:21:07,080
where can you find this preset you go

486
00:21:07,080 --> 00:21:10,200
here under the create compute you'll

487
00:21:10,200 --> 00:21:13,220
find everything that you need to do so

488
00:21:13,220 --> 00:21:16,740
the size is the Standard ds11 Version 2

489
00:21:16,740 --> 00:21:19,799
and it's a CPU not GPU because we don't

490
00:21:19,799 --> 00:21:22,500
know the GPU and we don't need a GPU and

491
00:21:22,500 --> 00:21:25,799
a like it is ready for us to use

492
00:21:25,799 --> 00:21:30,900
the next thing which we will look into

493
00:21:30,900 --> 00:21:33,600
is the designer how can you access the

494
00:21:33,600 --> 00:21:35,100
designer

495
00:21:35,100 --> 00:21:37,679
you can either click on this icon or

496
00:21:37,679 --> 00:21:40,020
click on the navigation menu and click

497
00:21:40,020 --> 00:21:42,299
on the designer for me

498
00:21:42,299 --> 00:21:42,900
um

499
00:21:42,900 --> 00:21:45,780
now I am inside my designer

500
00:21:45,780 --> 00:21:47,640
what we are going to do now is the

501
00:21:47,640 --> 00:21:50,280
pipeline that Carlotta told you about

502
00:21:50,280 --> 00:21:54,360
and from where can I know these steps if

503
00:21:54,360 --> 00:21:57,120
you follow along in the learn module you

504
00:21:57,120 --> 00:21:58,740
will find everything that I'm doing

505
00:21:58,740 --> 00:22:02,340
right now in details uh with screenshots

506
00:22:02,340 --> 00:22:05,820
of course so I'm going to create a new

507
00:22:05,820 --> 00:22:09,120
pipeline and I can do so by clicking on

508
00:22:09,120 --> 00:22:10,980
this plus button

509
00:22:10,980 --> 00:22:13,740
it's going to redirect me to the

510
00:22:13,740 --> 00:22:17,100
designer authoring the pipeline uh where

511
00:22:17,100 --> 00:22:19,500
I can drag and drop data and components

512
00:22:19,500 --> 00:22:21,780
that the Carlota told you the difference

513
00:22:21,780 --> 00:22:22,980
between

514
00:22:22,980 --> 00:22:26,340
and here I am going to do some changes

515
00:22:26,340 --> 00:22:29,100
to the settings I am going to connect

516
00:22:29,100 --> 00:22:31,860
this with my compute cluster that I

517
00:22:31,860 --> 00:22:35,120
created previously so I can utilize it

518
00:22:35,120 --> 00:22:38,100
from here I'm going to choose this

519
00:22:38,100 --> 00:22:40,380
compute cluster demo that I have showed

520
00:22:40,380 --> 00:22:42,600
you before in the Clusters here

521
00:22:42,600 --> 00:22:45,900
and I am going to change the name to

522
00:22:45,900 --> 00:22:47,820
something more meaningful instead of

523
00:22:47,820 --> 00:22:50,580
byline and the date of today I'm going

524
00:22:50,580 --> 00:22:53,760
to name it diabetes

525
00:22:53,760 --> 00:22:56,120
and

526
00:22:56,120 --> 00:23:00,020
let's just check this training

527
00:23:00,020 --> 00:23:05,100
let's say training 0.1 or okay

528
00:23:05,100 --> 00:23:09,360
and I am going to close this tab and in

529
00:23:09,360 --> 00:23:12,000
order to have a bigger place to work

530
00:23:12,000 --> 00:23:14,700
inside because this is where we will

531
00:23:14,700 --> 00:23:17,220
work where everything will happen so I

532
00:23:17,220 --> 00:23:19,559
will click on close from here

533
00:23:19,559 --> 00:23:23,460
and I will go to the data and I will

534
00:23:23,460 --> 00:23:25,620
create a new data set

535
00:23:25,620 --> 00:23:27,900
how can I create a new data set there is

536
00:23:27,900 --> 00:23:29,880
multiple options here you can find from

537
00:23:29,880 --> 00:23:31,799
local files from data store from web

538
00:23:31,799 --> 00:23:34,020
files from open data set but I'm going

539
00:23:34,020 --> 00:23:36,539
to choose from web files as this is the

540
00:23:36,539 --> 00:23:40,280
way we're going to create our data

541
00:23:40,280 --> 00:23:43,380
from here the information of my data set

542
00:23:43,380 --> 00:23:47,340
I'm going to get them from the Microsoft

543
00:23:47,340 --> 00:23:50,820
learn module so if we go to the step

544
00:23:50,820 --> 00:23:52,860
that says create a data set

545
00:23:52,860 --> 00:23:55,020
under it it illustrates that you can

546
00:23:55,020 --> 00:23:57,720
access the data from inside the asset

547
00:23:57,720 --> 00:23:59,760
library and inside your asset liability

548
00:23:59,760 --> 00:24:01,679
you'll find the data and find the

549
00:24:01,679 --> 00:24:05,539
component and I'm going to select

550
00:24:05,539 --> 00:24:09,000
this link because this is where my data

551
00:24:09,000 --> 00:24:12,000
is stored if you open this link you will

552
00:24:12,000 --> 00:24:14,820
find this is this is a CSV file I think

553
00:24:14,820 --> 00:24:17,400
yeah and you can like all the data are

554
00:24:17,400 --> 00:24:18,360
here

555
00:24:18,360 --> 00:24:21,419
all right now let's get back

556
00:24:21,419 --> 00:24:21,540
um

557
00:24:21,540 --> 00:24:24,770
[Music]

558
00:24:26,880 --> 00:24:28,200
and you are going to do something

559
00:24:28,200 --> 00:24:29,880
meaningful but because I have already

560
00:24:29,880 --> 00:24:31,820
created it before twice so I'm gonna

561
00:24:31,820 --> 00:24:34,980
like add a number to the name

562
00:24:34,980 --> 00:24:37,559
uh the data set is tabular and there is

563
00:24:37,559 --> 00:24:39,360
the file but this is a table so we're

564
00:24:39,360 --> 00:24:40,760
going to choose the table

565
00:24:40,760 --> 00:24:42,240
[Music]

566
00:24:42,240 --> 00:24:43,740
for data set time

567
00:24:43,740 --> 00:24:46,260
now we will click on next that's gonna

568
00:24:46,260 --> 00:24:51,179
review or uh display for you the content

569
00:24:51,179 --> 00:24:54,020
of this file that you have

570
00:24:54,020 --> 00:24:57,419
like imported to this workspace

571
00:24:57,419 --> 00:25:01,559
and for these settings these are like

572
00:25:01,559 --> 00:25:03,720
related to our filed format

573
00:25:03,720 --> 00:25:08,280
so this is a delimited file and it's not

574
00:25:08,280 --> 00:25:11,400
plain text it's not a Json the delimiter

575
00:25:11,400 --> 00:25:14,159
is comma as like we have seen that they

576
00:25:14,159 --> 00:25:16,640
those

577
00:25:26,700 --> 00:25:29,039
so I'm choosing

578
00:25:29,039 --> 00:25:32,900
errors because the only the first five

579
00:25:33,510 --> 00:25:34,880
[Music]

580
00:25:34,880 --> 00:25:38,159
for example okay uh if you have any

581
00:25:38,159 --> 00:25:39,960
doubts if you have any problems please

582
00:25:39,960 --> 00:25:42,960
don't hesitate to all right through me

583
00:25:42,960 --> 00:25:45,020
in the chat

584
00:25:45,020 --> 00:25:48,480
and like what what is blocking you and

585
00:25:48,480 --> 00:25:50,940
me and Carlota will try to help you and

586
00:25:50,940 --> 00:25:53,220
like whenever possible

587
00:25:53,220 --> 00:25:55,799
and now this is the new preview for my

588
00:25:55,799 --> 00:25:57,840
data set I can see that I have an ID I

589
00:25:57,840 --> 00:25:59,700
have patient ID I have pregnancies I

590
00:25:59,700 --> 00:26:02,220
have the age of the people

591
00:26:02,220 --> 00:26:05,720
have the body mass together I think

592
00:26:05,720 --> 00:26:08,460
and they have diabetical or not as a

593
00:26:08,460 --> 00:26:10,679
zero and one zero indicates a negative

594
00:26:10,679 --> 00:26:14,159
the person doesn't have diabetes and one

595
00:26:14,159 --> 00:26:16,080
indicates a positive that this person

596
00:26:16,080 --> 00:26:18,299
has diabetes okay

597
00:26:18,299 --> 00:26:20,520
now I'm going to click on next here I am

598
00:26:20,520 --> 00:26:23,400
defining my schema all the data types

599
00:26:23,400 --> 00:26:25,380
inside my columns the column names which

600
00:26:25,380 --> 00:26:28,760
columns to include which to exclude and

601
00:26:28,760 --> 00:26:31,500
here we will include everything except

602
00:26:31,500 --> 00:26:35,580
the path of the bath color and we are

603
00:26:35,580 --> 00:26:37,860
going to review the data types of each

604
00:26:37,860 --> 00:26:40,440
column so let's review this first one

605
00:26:40,440 --> 00:26:43,320
this is numbers numbers then it's the

606
00:26:43,320 --> 00:26:45,779
integer and this is

607
00:26:45,779 --> 00:26:48,679
um like decimal

608
00:26:48,679 --> 00:26:50,900
dotted

609
00:26:50,900 --> 00:26:53,580
decimal number so we are going to choose

610
00:26:53,580 --> 00:26:55,020
this data type

611
00:26:55,020 --> 00:26:57,200
and for this one

612
00:26:57,200 --> 00:27:01,200
it says diabetic and it's a zero under

613
00:27:01,200 --> 00:27:02,460
one and we are going to make it as

614
00:27:02,460 --> 00:27:04,460
integerables

615
00:27:04,460 --> 00:27:07,980
now we are going to click on next and

616
00:27:07,980 --> 00:27:10,080
move to reviewing everything this is

617
00:27:10,080 --> 00:27:11,279
everything that we have defined together

618
00:27:11,279 --> 00:27:13,500
I will click on create

619
00:27:13,500 --> 00:27:15,179
and

620
00:27:15,179 --> 00:27:17,940
now the first step has ended we have

621
00:27:17,940 --> 00:27:19,919
gotten our data ready

622
00:27:19,919 --> 00:27:22,440
now what now we're going to utilize the

623
00:27:22,440 --> 00:27:24,360
designer

624
00:27:24,360 --> 00:27:26,820
um Power we're going to drag and drop

625
00:27:26,820 --> 00:27:29,820
our data set to create the pipeline

626
00:27:29,820 --> 00:27:33,179
so I have like click on it and drag it

627
00:27:33,179 --> 00:27:35,640
to this space it's gonna appear to you

628
00:27:35,640 --> 00:27:39,659
and we can inspect it by right click and

629
00:27:39,659 --> 00:27:42,179
choose preview data

630
00:27:42,179 --> 00:27:46,200
to see what we have created together

631
00:27:46,200 --> 00:27:48,900
from here you can see everything that we

632
00:27:48,900 --> 00:27:50,700
have like seen previously but in more

633
00:27:50,700 --> 00:27:53,100
details and we are just going to close

634
00:27:53,100 --> 00:27:56,580
this now what now we are gonna do the

635
00:27:56,580 --> 00:28:00,799
processing that Carlota like mentioned

636
00:28:00,799 --> 00:28:03,659
these are some instructions about the

637
00:28:03,659 --> 00:28:05,460
data about how you can loot them how you

638
00:28:05,460 --> 00:28:07,140
can open them but we are going to move

639
00:28:07,140 --> 00:28:09,720
to the transformation or the processing

640
00:28:09,720 --> 00:28:13,500
so as Carlotta told you like any data

641
00:28:13,500 --> 00:28:15,480
for us to work on we have to do some

642
00:28:15,480 --> 00:28:17,299
processing to it

643
00:28:17,299 --> 00:28:20,159
to make it easy easier for the model to

644
00:28:20,159 --> 00:28:23,279
be trained and easier to work with so uh

645
00:28:23,279 --> 00:28:25,860
we're gonna do the normalization and

646
00:28:25,860 --> 00:28:29,159
normalization meaning is uh

647
00:28:29,159 --> 00:28:33,539
to scale our data either down or up but

648
00:28:33,539 --> 00:28:35,400
we're going to scale them down

649
00:28:35,400 --> 00:28:38,820
and like we are going to decrease and

650
00:28:38,820 --> 00:28:40,799
relatively decrease

651
00:28:40,799 --> 00:28:44,640
the the values all the values to work

652
00:28:44,640 --> 00:28:48,120
with lower numbers and if we are working

653
00:28:48,120 --> 00:28:49,559
with larger numbers it's going to take

654
00:28:49,559 --> 00:28:52,500
more time if we're working with smaller

655
00:28:52,500 --> 00:28:54,779
numbers it's going to take less time to

656
00:28:54,779 --> 00:28:59,159
calculate them and that's it so

657
00:28:59,159 --> 00:29:02,159
where can I find the normalized data I

658
00:29:02,159 --> 00:29:04,260
can find it inside my component

659
00:29:04,260 --> 00:29:06,720
so I will choose the component and

660
00:29:06,720 --> 00:29:09,659
search for normalized data

661
00:29:09,659 --> 00:29:12,360
I will drag and drop it as usual and I

662
00:29:12,360 --> 00:29:14,820
will connect between these two things

663
00:29:14,820 --> 00:29:18,360
by clicking on this spot this like

664
00:29:18,360 --> 00:29:20,159
Circle and

665
00:29:20,159 --> 00:29:23,159
drag and drop until the next circuit

666
00:29:23,159 --> 00:29:24,899
now we are going to Define our

667
00:29:24,899 --> 00:29:27,419
normalization method

668
00:29:27,419 --> 00:29:31,080
so I'm going to double click on the

669
00:29:31,080 --> 00:29:32,640
normalized data

670
00:29:32,640 --> 00:29:34,860
it's going to open the settings for the

671
00:29:34,860 --> 00:29:36,480
normalization

672
00:29:36,480 --> 00:29:38,820
as better transformation method which is

673
00:29:38,820 --> 00:29:40,500
a mathematical way

674
00:29:40,500 --> 00:29:42,299
that is going to scale our data

675
00:29:42,299 --> 00:29:44,520
according to

676
00:29:44,520 --> 00:29:47,760
we're going to choose min max and for

677
00:29:47,760 --> 00:29:51,539
this one we are going to choose use 0

678
00:29:51,539 --> 00:29:53,100
for constant column we are going to

679
00:29:53,100 --> 00:29:54,480
choose true

680
00:29:54,480 --> 00:29:56,880
and we are going to Define which columns

681
00:29:56,880 --> 00:29:58,860
to normalize so we are not going to

682
00:29:58,860 --> 00:30:01,080
normalize the whole data set we are

683
00:30:01,080 --> 00:30:02,760
going to choose a subset from the data

684
00:30:02,760 --> 00:30:04,559
set to normalize so we're going to

685
00:30:04,559 --> 00:30:07,020
choose everything except for the patient

686
00:30:07,020 --> 00:30:09,000
ID and the diabetic because the patient

687
00:30:09,000 --> 00:30:10,919
ID is a number but it's a categorical

688
00:30:10,919 --> 00:30:13,740
data it describes a vision it's not a

689
00:30:13,740 --> 00:30:17,460
number that I can sum I can say patient

690
00:30:17,460 --> 00:30:20,159
ID number one plus patient ID number two

691
00:30:20,159 --> 00:30:21,720
no this is a patient and another

692
00:30:21,720 --> 00:30:23,399
location it's not a number that I can do

693
00:30:23,399 --> 00:30:25,740
mathematical operations on so I'm not

694
00:30:25,740 --> 00:30:28,200
going to choose it so we will choose

695
00:30:28,200 --> 00:30:30,539
everything as I said except for the

696
00:30:30,539 --> 00:30:33,480
diabetic and the patient might I will

697
00:30:33,480 --> 00:30:34,860
click on Save

698
00:30:34,860 --> 00:30:37,740
and it's not showing me a warning again

699
00:30:37,740 --> 00:30:39,480
everything is good

700
00:30:39,480 --> 00:30:41,880
now I can click on submit

701
00:30:41,880 --> 00:30:46,799
and review my normalization output

702
00:30:46,799 --> 00:30:48,240
um

703
00:30:48,240 --> 00:30:51,659
so uh if you click on submit here

704
00:30:51,659 --> 00:30:54,659
and you will like choose create new and

705
00:30:54,659 --> 00:30:56,460
set the name that is mentioned here

706
00:30:56,460 --> 00:30:59,899
inside the notebook so it it tells you

707
00:30:59,899 --> 00:31:03,419
to like create a job and name it name

708
00:31:03,419 --> 00:31:05,460
the experiment Ms learn diabetes

709
00:31:05,460 --> 00:31:06,720
training because you will continue

710
00:31:06,720 --> 00:31:10,440
working on and building component later

711
00:31:10,440 --> 00:31:13,020
I have it already like created I am the

712
00:31:13,020 --> 00:31:16,919
like we can review it together so uh let

713
00:31:16,919 --> 00:31:19,860
me just open this in another tab I think

714
00:31:19,860 --> 00:31:21,000
I have it

715
00:31:21,000 --> 00:31:23,659
here

716
00:31:25,679 --> 00:31:28,220
okay

717
00:31:30,720 --> 00:31:34,740
so these are all the jobs that I have

718
00:31:34,740 --> 00:31:37,340
read them

719
00:31:37,860 --> 00:31:39,899
all the jobs there let's do this over

720
00:31:39,899 --> 00:31:42,059
these are all the jobs that I have

721
00:31:42,059 --> 00:31:43,679
submitted previously

722
00:31:43,679 --> 00:31:45,840
and I think this one is the

723
00:31:45,840 --> 00:31:48,360
normalization job so let's see the

724
00:31:48,360 --> 00:31:50,100
output of it

725
00:31:50,100 --> 00:31:54,120
as you can see it says uh check mark yes

726
00:31:54,120 --> 00:31:56,640
which means that it worked and we can

727
00:31:56,640 --> 00:31:59,399
preview it how can I do that right click

728
00:31:59,399 --> 00:32:02,539
on it choose preview data

729
00:32:02,539 --> 00:32:06,659
and as you can see all the data are

730
00:32:06,659 --> 00:32:08,399
scaled down

731
00:32:08,399 --> 00:32:10,980
so everything is between zero

732
00:32:10,980 --> 00:32:15,860
and uh one I think

733
00:32:15,860 --> 00:32:18,899
so like everything is good for us now we

734
00:32:18,899 --> 00:32:21,840
can move forward to the next step

735
00:32:21,840 --> 00:32:27,799
which is to create the whole pipeline so

736
00:32:27,799 --> 00:32:30,840
uh Carlota told you that

737
00:32:30,840 --> 00:32:33,179
we're going to use a classification

738
00:32:33,179 --> 00:32:37,260
model to create this data set so uh let

739
00:32:37,260 --> 00:32:40,620
me just drag and drop everything

740
00:32:40,620 --> 00:32:45,380
to get runtime and we're doing

741
00:32:45,799 --> 00:32:50,419
about about everything by

742
00:32:51,419 --> 00:32:52,919
so

743
00:32:52,919 --> 00:32:57,380
as a result we are going to explain

744
00:32:59,760 --> 00:33:03,600
yeah so I'm going to give this split

745
00:33:03,600 --> 00:33:06,240
data I'm going to take the

746
00:33:06,240 --> 00:33:08,880
transformation data to split data and

747
00:33:08,880 --> 00:33:10,380
connect it like that

748
00:33:10,380 --> 00:33:12,299
I'm going to get a three model

749
00:33:12,299 --> 00:33:15,240
components because I want to train my

750
00:33:15,240 --> 00:33:16,679
model

751
00:33:16,679 --> 00:33:19,740
and I'm going to put it right here

752
00:33:19,740 --> 00:33:21,740
okay

753
00:33:21,740 --> 00:33:24,419
like let's just move it down there okay

754
00:33:24,419 --> 00:33:27,059
and we are going to use a classification

755
00:33:27,059 --> 00:33:28,620
model

756
00:33:28,620 --> 00:33:31,880
a two class

757
00:33:32,240 --> 00:33:35,399
logistic regression model

758
00:33:35,399 --> 00:33:38,159
so I'm going to give this algorithm to

759
00:33:38,159 --> 00:33:41,480
enable my model to work

760
00:33:41,820 --> 00:33:45,960
this is the untrained model this is

761
00:33:45,960 --> 00:33:48,059
here

762
00:33:48,059 --> 00:33:51,120
the left the left

763
00:33:51,120 --> 00:33:52,860
the left like Circle I'm going to

764
00:33:52,860 --> 00:33:54,899
connect it to the data set and the right

765
00:33:54,899 --> 00:33:56,940
one we are going to connect it to

766
00:33:56,940 --> 00:33:59,700
evaluate model

767
00:33:59,700 --> 00:34:02,640
evaluate model so let's search for

768
00:34:02,640 --> 00:34:05,220
evaluate model here

769
00:34:05,220 --> 00:34:07,440
so because we want to do what we want to

770
00:34:07,440 --> 00:34:10,800
evaluate our model and see how it it has

771
00:34:10,800 --> 00:34:14,580
been doing it is it good is it bad

772
00:34:14,580 --> 00:34:18,200
um sorry like

773
00:34:19,980 --> 00:34:22,820
this is

774
00:34:23,460 --> 00:34:25,560
down there

775
00:34:25,560 --> 00:34:28,139
after the school

776
00:34:28,139 --> 00:34:31,320
so we have to get the score model first

777
00:34:31,320 --> 00:34:33,960
so let's get it

778
00:34:33,960 --> 00:34:36,119
and this will take the trained model and

779
00:34:36,119 --> 00:34:37,260
the data set

780
00:34:37,260 --> 00:34:39,419
to score our model and see if it's

781
00:34:39,419 --> 00:34:42,179
performing good or bad

782
00:34:42,179 --> 00:34:44,899
and

783
00:34:45,240 --> 00:34:47,159
um

784
00:34:47,159 --> 00:34:49,080
after that like we have finished

785
00:34:49,080 --> 00:34:51,060
everything now we are going to do the

786
00:34:51,060 --> 00:34:52,139
what

787
00:34:52,139 --> 00:34:54,359
the presets for everything

788
00:34:54,359 --> 00:34:56,820
as a starter we will be splitting our

789
00:34:56,820 --> 00:34:58,920
data so

790
00:34:58,920 --> 00:35:01,140
how are we going to do this according to

791
00:35:01,140 --> 00:35:03,780
what to the split rules so I'm going to

792
00:35:03,780 --> 00:35:05,940
double click on and choose split rows

793
00:35:05,940 --> 00:35:09,420
and the percentage is

794
00:35:09,420 --> 00:35:12,780
70 percent for the and 30 percent of the

795
00:35:12,780 --> 00:35:14,820
data for

796
00:35:14,820 --> 00:35:18,420
the valuation or for the scoring okay

797
00:35:18,420 --> 00:35:20,880
I'm going to make it a randomization so

798
00:35:20,880 --> 00:35:22,980
I'm going to split data randomly and the

799
00:35:22,980 --> 00:35:26,060
seat is uh

800
00:35:26,060 --> 00:35:29,339
132 23 I think yeah

801
00:35:29,339 --> 00:35:32,520
and I think that's it

802
00:35:32,520 --> 00:35:35,040
the split says why this holes and that's

803
00:35:35,040 --> 00:35:36,240
good

804
00:35:36,240 --> 00:35:39,540
now for the next one which is the train

805
00:35:39,540 --> 00:35:42,000
model we are going to connect it as

806
00:35:42,000 --> 00:35:43,500
mentioned here

807
00:35:43,500 --> 00:35:48,660
and like we have done that and then why

808
00:35:48,660 --> 00:35:50,700
am I having here like let's double click

809
00:35:50,700 --> 00:35:54,660
on it yeah it has like it needs the

810
00:35:54,660 --> 00:35:57,180
label column that I am trying to predict

811
00:35:57,180 --> 00:35:58,680
so from here I'm going to choose

812
00:35:58,680 --> 00:36:01,380
diabetic I'm going to save

813
00:36:01,380 --> 00:36:05,180
I'm going to close this one

814
00:36:05,520 --> 00:36:07,380
so it says here

815
00:36:07,380 --> 00:36:10,619
the diabetic label the model it will

816
00:36:10,619 --> 00:36:12,300
predict the zero and one because this is

817
00:36:12,300 --> 00:36:14,700
a binary classification algorithm so

818
00:36:14,700 --> 00:36:16,260
it's going to predict either this or

819
00:36:16,260 --> 00:36:17,520
that

820
00:36:17,520 --> 00:36:18,900
and

821
00:36:18,900 --> 00:36:20,160
um

822
00:36:20,160 --> 00:36:23,880
I think that's everything to run the the

823
00:36:23,880 --> 00:36:25,859
pipeline

824
00:36:25,859 --> 00:36:29,040
so everything is done everything is good

825
00:36:29,040 --> 00:36:31,200
for this one we're just gonna leave it

826
00:36:31,200 --> 00:36:34,140
like for now because this is the next

827
00:36:34,140 --> 00:36:36,480
step

828
00:36:36,480 --> 00:36:39,839
um this will like be put instead of the

829
00:36:39,839 --> 00:36:43,520
score model but then it's

830
00:36:44,099 --> 00:36:46,920
delete it for now

831
00:36:46,920 --> 00:36:49,500
okay

832
00:36:49,500 --> 00:36:52,920
now we have to submit the job in order

833
00:36:52,920 --> 00:36:55,680
to see the output of it so I can click

834
00:36:55,680 --> 00:36:59,280
on submit and choose the previous job

835
00:36:59,280 --> 00:37:01,200
which is the one that I have showed you

836
00:37:01,200 --> 00:37:02,460
before

837
00:37:02,460 --> 00:37:05,460
and then let's review its output

838
00:37:05,460 --> 00:37:06,960
together here

839
00:37:06,960 --> 00:37:09,960
so if I go to the jobs

840
00:37:09,960 --> 00:37:15,119
if I go to Ms learn maybe it is training

841
00:37:15,119 --> 00:37:18,180
I think it's the one that lasted the

842
00:37:18,180 --> 00:37:20,640
longest this one here

843
00:37:20,640 --> 00:37:23,700
so here I can see

844
00:37:23,700 --> 00:37:27,079
the job output what happened inside

845
00:37:27,079 --> 00:37:30,420
the model as you can see

846
00:37:30,420 --> 00:37:33,839
so the normalization we have like seen

847
00:37:33,839 --> 00:37:36,540
before the split data I can preview it

848
00:37:36,540 --> 00:37:39,359
the result one or the result two as it

849
00:37:39,359 --> 00:37:41,760
splits the data to 70 here and three

850
00:37:41,760 --> 00:37:44,339
thirty percent here

851
00:37:44,339 --> 00:37:46,859
um I can see the score model which is

852
00:37:46,859 --> 00:37:49,140
like something that we need

853
00:37:49,140 --> 00:37:51,920
to review

854
00:37:52,380 --> 00:37:56,820
um inside the scroll model uh like from

855
00:37:56,820 --> 00:37:57,960
here

856
00:37:57,960 --> 00:38:00,960
we can see that

857
00:38:00,960 --> 00:38:04,460
let's get back here

858
00:38:05,940 --> 00:38:08,220
like this is the data that the model has

859
00:38:08,220 --> 00:38:11,579
been scored and this is a scoring output

860
00:38:11,579 --> 00:38:15,300
so it says code label true and if he is

861
00:38:15,300 --> 00:38:18,300
not diabetic so this is

862
00:38:18,300 --> 00:38:19,200
um

863
00:38:19,200 --> 00:38:21,839
around prediction let's say

864
00:38:21,839 --> 00:38:23,880
for this one it's true and true and this

865
00:38:23,880 --> 00:38:26,880
is like a good like what do you say

866
00:38:26,880 --> 00:38:29,460
prediction and the probabilities of this

867
00:38:29,460 --> 00:38:30,420
score

868
00:38:30,420 --> 00:38:33,119
which means the certainty of our model

869
00:38:33,119 --> 00:38:36,960
of that this is really true it's 80 for

870
00:38:36,960 --> 00:38:38,780
this one is 75

871
00:38:38,780 --> 00:38:42,599
so these are some cool metrics that we

872
00:38:42,599 --> 00:38:45,359
can review to understand how our model

873
00:38:45,359 --> 00:38:47,700
is performing it's performing good for

874
00:38:47,700 --> 00:38:48,540
now

875
00:38:48,540 --> 00:38:53,180
let's check our evaluation model

876
00:38:53,180 --> 00:38:56,700
so this is the extra one that I told you

877
00:38:56,700 --> 00:38:59,579
about instead of the like

878
00:38:59,579 --> 00:39:01,800
score model only we are going to add

879
00:39:01,800 --> 00:39:04,260
what evaluate model

880
00:39:04,260 --> 00:39:06,900
after it so here

881
00:39:06,900 --> 00:39:09,420
we're going to go to our asset library

882
00:39:09,420 --> 00:39:12,180
and we are going to choose the evaluate

883
00:39:12,180 --> 00:39:14,940
model

884
00:39:14,940 --> 00:39:17,760
and we are going to put it here and we

885
00:39:17,760 --> 00:39:20,220
are going to connect it and we are going

886
00:39:20,220 --> 00:39:23,099
to submit the job using the same name of

887
00:39:23,099 --> 00:39:25,140
the job that we used previously

888
00:39:25,140 --> 00:39:29,520
let's review it uh also so after it

889
00:39:29,520 --> 00:39:33,300
finishes you will find it here so I have

890
00:39:33,300 --> 00:39:35,280
already done it before this is how I'm

891
00:39:35,280 --> 00:39:37,380
able to see the output

892
00:39:37,380 --> 00:39:40,320
so let's see

893
00:39:40,320 --> 00:39:43,280
what what is the output of this

894
00:39:43,280 --> 00:39:45,660
evaluation process

895
00:39:45,660 --> 00:39:49,800
here it mentioned to you that there are

896
00:39:49,800 --> 00:39:51,480
some metrics

897
00:39:51,480 --> 00:39:54,839
like the confusion Matrix which Carlotta

898
00:39:54,839 --> 00:39:57,060
told you about there is the accuracy the

899
00:39:57,060 --> 00:39:59,760
Precision the recall and F1 School

900
00:39:59,760 --> 00:40:02,339
every Matrix gives us some insight about

901
00:40:02,339 --> 00:40:04,920
our model it helps us to understand it

902
00:40:04,920 --> 00:40:08,579
more more and

903
00:40:08,579 --> 00:40:10,560
like understand if it's overfitting if

904
00:40:10,560 --> 00:40:12,240
it's good if it's bad and really really

905
00:40:12,240 --> 00:40:16,339
like understand how it's working

906
00:40:17,060 --> 00:40:20,400
now I'm just waiting for the job to load

907
00:40:20,400 --> 00:40:22,920
until it loads

908
00:40:22,920 --> 00:40:23,640
um

909
00:40:23,640 --> 00:40:26,040
we can continue to

910
00:40:26,040 --> 00:40:28,740
to work on our

911
00:40:28,740 --> 00:40:31,800
model so I will go to my designer I'm

912
00:40:31,800 --> 00:40:34,740
just going to confirm this

913
00:40:34,740 --> 00:40:38,280
and I'm going to continue working on it

914
00:40:38,280 --> 00:40:39,780
from

915
00:40:39,780 --> 00:40:42,119
where we have stopped where have we

916
00:40:42,119 --> 00:40:43,560
stopped

917
00:40:43,560 --> 00:40:46,440
we have stopped on the evaluate model so

918
00:40:46,440 --> 00:40:48,960
I'm going to choose this one

919
00:40:48,960 --> 00:40:53,420
and it says here

920
00:40:54,180 --> 00:40:56,940
select experiment create inference

921
00:40:56,940 --> 00:40:58,200
pipeline so

922
00:40:58,200 --> 00:41:01,079
I am going to go to the jobs

923
00:41:01,079 --> 00:41:04,680
I'm going to select my experiment

924
00:41:04,680 --> 00:41:06,660
I hope this works

925
00:41:06,660 --> 00:41:09,720
okay salute finally now we have our

926
00:41:09,720 --> 00:41:12,180
evaluate model output

927
00:41:12,180 --> 00:41:15,480
let's previews evaluation results

928
00:41:15,480 --> 00:41:18,660
and uh

929
00:41:18,660 --> 00:41:22,220
cool come on

930
00:41:25,500 --> 00:41:28,020
finally now we can create our inference

931
00:41:28,020 --> 00:41:31,020
pipeline so

932
00:41:31,020 --> 00:41:34,200
I think it says that

933
00:41:34,200 --> 00:41:35,280
um

934
00:41:35,280 --> 00:41:38,160
select the experiment then select Ms

935
00:41:38,160 --> 00:41:39,359
learn so

936
00:41:39,359 --> 00:41:43,320
I am just going to select it

937
00:41:43,320 --> 00:41:48,300
and finally now we can the ROC curve we

938
00:41:48,300 --> 00:41:51,000
can see it that the true positive rate

939
00:41:51,000 --> 00:41:53,760
and the force was integrate the false

940
00:41:53,760 --> 00:41:56,660
positive rate is increasing with time

941
00:41:56,660 --> 00:42:01,020
and also the true positive rate true

942
00:42:01,020 --> 00:42:03,540
positive is something that it predicted

943
00:42:03,540 --> 00:42:06,960
that it is uh positive it has diabetes

944
00:42:06,960 --> 00:42:09,480
and it's really a it's really true it

945
00:42:09,480 --> 00:42:12,599
the person really has diabetes okay and

946
00:42:12,599 --> 00:42:14,760
for the false positive it predicted that

947
00:42:14,760 --> 00:42:17,579
someone has diabetes and someone doesn't

948
00:42:17,579 --> 00:42:20,960
has it this is what true position and

949
00:42:20,960 --> 00:42:24,960
false positive means this is The Recoil

950
00:42:24,960 --> 00:42:28,020
curve so we can like review the metrics

951
00:42:28,020 --> 00:42:32,160
of our model this is the lift curve I

952
00:42:32,160 --> 00:42:36,000
can change the threshold of my confusion

953
00:42:36,000 --> 00:42:37,740
Matrix here

954
00:42:37,740 --> 00:42:39,119
and this could look don't want to add

955
00:42:39,119 --> 00:42:43,920
anything about the the the graphs and

956
00:42:43,920 --> 00:42:47,000
you can do so

957
00:42:50,460 --> 00:42:51,000
um

958
00:42:51,000 --> 00:42:54,720
yeah so just wanted to if you go yeah I

959
00:42:54,720 --> 00:42:57,119
just wanted to comment comment for the

960
00:42:57,119 --> 00:43:00,480
RSC curve uh that actually from this

961
00:43:00,480 --> 00:43:03,900
graph the metric which uh usually we're

962
00:43:03,900 --> 00:43:06,960
going to compute is the end area under

963
00:43:06,960 --> 00:43:09,900
under the curve and this coefficient or

964
00:43:09,900 --> 00:43:12,240
metric

965
00:43:12,240 --> 00:43:15,060
um it's a confusion

966
00:43:15,060 --> 00:43:18,420
um is a value that could span from from

967
00:43:18,420 --> 00:43:22,920
zero to one and the the highest is

968
00:43:22,920 --> 00:43:23,480
um

969
00:43:23,480 --> 00:43:26,700
this the highest is the the score so the

970
00:43:26,700 --> 00:43:29,220
the closest one

971
00:43:29,220 --> 00:43:32,760
um so the the highest is the amount of

972
00:43:32,760 --> 00:43:35,280
area under this curve

973
00:43:35,280 --> 00:43:40,500
um the the the highest performance uh we

974
00:43:40,500 --> 00:43:43,319
we've got from from our model and

975
00:43:43,319 --> 00:43:46,440
another thing is what John is

976
00:43:46,440 --> 00:43:49,680
um playing with so this threshold for

977
00:43:49,680 --> 00:43:51,380
the logistic

978
00:43:51,380 --> 00:43:55,920
regression is the threshold used by the

979
00:43:55,920 --> 00:43:57,180
model

980
00:43:57,180 --> 00:43:58,740
um to

981
00:43:58,740 --> 00:43:59,520
um

982
00:43:59,520 --> 00:44:02,940
to predict uh if the category is zero or

983
00:44:02,940 --> 00:44:05,220
one so if the probability the

984
00:44:05,220 --> 00:44:08,599
probability score is above the threshold

985
00:44:08,599 --> 00:44:11,579
then the category will be predicted as

986
00:44:11,579 --> 00:44:15,359
one while if the the probability is

987
00:44:15,359 --> 00:44:17,460
below the threshold in this case for

988
00:44:17,460 --> 00:44:21,300
example 0.5 the category is predicted as

989
00:44:21,300 --> 00:44:23,579
as zero so that's why it's very

990
00:44:23,579 --> 00:44:26,099
important to um to choose the the

991
00:44:26,099 --> 00:44:27,839
threshold because the performance really

992
00:44:27,839 --> 00:44:29,520
can vary

993
00:44:29,520 --> 00:44:30,560
um

994
00:44:30,560 --> 00:44:34,380
with this threshold value

995
00:44:34,380 --> 00:44:41,099
uh thank you uh so much uh kellota and

996
00:44:41,400 --> 00:44:44,400
as I mentioned now we are going to like

997
00:44:44,400 --> 00:44:46,560
create our inference pipeline so we are

998
00:44:46,560 --> 00:44:48,540
going to select the latest one which I

999
00:44:48,540 --> 00:44:50,819
already have it opened here this is the

1000
00:44:50,819 --> 00:44:52,859
one that we were reviewing together this

1001
00:44:52,859 --> 00:44:55,500
is where we have stopped and we're going

1002
00:44:55,500 --> 00:44:57,599
to create an inference pipeline we are

1003
00:44:57,599 --> 00:44:59,520
going to choose a real-time inference

1004
00:44:59,520 --> 00:45:02,520
pipeline okay

1005
00:45:02,520 --> 00:45:05,160
um from where I can find this here as it

1006
00:45:05,160 --> 00:45:08,099
says real-time inference pipeline

1007
00:45:08,099 --> 00:45:10,680
so it's gonna add some things to my

1008
00:45:10,680 --> 00:45:12,420
workspace it's going to add the web

1009
00:45:12,420 --> 00:45:13,980
service inboard it's going to have the

1010
00:45:13,980 --> 00:45:15,780
web service output because we will be

1011
00:45:15,780 --> 00:45:18,180
creating it as a web service to access

1012
00:45:18,180 --> 00:45:19,740
it from the internet

1013
00:45:19,740 --> 00:45:21,900
uh what are we going to do we're going

1014
00:45:21,900 --> 00:45:24,720
to remove this diabetes data okay

1015
00:45:24,720 --> 00:45:27,540
and we are going to get a component

1016
00:45:27,540 --> 00:45:29,359
called Web

1017
00:45:29,359 --> 00:45:33,180
input and what's up let me check

1018
00:45:33,180 --> 00:45:35,940
it's enter data manually

1019
00:45:35,940 --> 00:45:38,400
we have we already have the with input

1020
00:45:38,400 --> 00:45:39,540
present

1021
00:45:39,540 --> 00:45:42,119
so we are going to get the entire data

1022
00:45:42,119 --> 00:45:43,200
manually

1023
00:45:43,200 --> 00:45:45,420
and we're going to collect it to connect

1024
00:45:45,420 --> 00:45:49,560
it as it was connected before like that

1025
00:45:49,560 --> 00:45:53,040
and also I am not going to directly take

1026
00:45:53,040 --> 00:45:55,260
the web service sorry escort model to

1027
00:45:55,260 --> 00:45:57,839
the web service output like that

1028
00:45:57,839 --> 00:46:00,240
I'm going to delete this

1029
00:46:00,240 --> 00:46:03,960
and I'm going to execute a python script

1030
00:46:03,960 --> 00:46:05,880
before

1031
00:46:05,880 --> 00:46:09,500
I display my result

1032
00:46:10,680 --> 00:46:12,060
so

1033
00:46:12,060 --> 00:46:17,480
this will be connected like okay but

1034
00:46:19,260 --> 00:46:20,400
so

1035
00:46:20,400 --> 00:46:23,599
the other way around

1036
00:46:23,599 --> 00:46:27,660
and from here I am going to connect this

1037
00:46:27,660 --> 00:46:30,960
with that and there is some data uh that

1038
00:46:30,960 --> 00:46:33,480
we will be getting from the node or from

1039
00:46:33,480 --> 00:46:37,680
the the examination here and this is the

1040
00:46:37,680 --> 00:46:40,740
data that will be entered like to our

1041
00:46:40,740 --> 00:46:44,400
website manually okay this is instead of

1042
00:46:44,400 --> 00:46:47,460
the data that we have been getting from

1043
00:46:47,460 --> 00:46:49,740
our data set that we created so I'm just

1044
00:46:49,740 --> 00:46:51,960
going to double click on it and choose

1045
00:46:51,960 --> 00:46:55,579
CSV and I will choose it has headers

1046
00:46:55,579 --> 00:47:00,839
and I will take or copy this content and

1047
00:47:00,839 --> 00:47:02,819
put it there okay

1048
00:47:02,819 --> 00:47:05,700
so let's do it

1049
00:47:05,700 --> 00:47:07,920
I think I have to click on edit code now

1050
00:47:07,920 --> 00:47:10,680
I can click on Save and I can close it

1051
00:47:10,680 --> 00:47:13,079
another thing which is the python script

1052
00:47:13,079 --> 00:47:16,700
that we will be executing

1053
00:47:17,099 --> 00:47:19,380
um yeah we are going to remove this also

1054
00:47:19,380 --> 00:47:21,140
we don't need the evaluate model anymore

1055
00:47:21,140 --> 00:47:24,319
so we are going to remove

1056
00:47:24,319 --> 00:47:28,579
script that I will be executing okay

1057
00:47:28,579 --> 00:47:32,599
I can find it here

1058
00:47:33,540 --> 00:47:34,619
um

1059
00:47:34,619 --> 00:47:35,760
yeah

1060
00:47:35,760 --> 00:47:38,640
this is the python script that we will

1061
00:47:38,640 --> 00:47:41,520
execute and it says to you that this

1062
00:47:41,520 --> 00:47:43,619
code selects only the patient's ID

1063
00:47:43,619 --> 00:47:45,000
that's correct label the school

1064
00:47:45,000 --> 00:47:47,700
probability and return returns them to

1065
00:47:47,700 --> 00:47:49,980
the web service output so we don't want

1066
00:47:49,980 --> 00:47:51,960
to return all the columns as we have

1067
00:47:51,960 --> 00:47:53,339
seen previously

1068
00:47:53,339 --> 00:47:55,560
uh the determines everything

1069
00:47:55,560 --> 00:47:56,940
so

1070
00:47:56,940 --> 00:47:59,040
we want to return certain stuff the

1071
00:47:59,040 --> 00:48:02,940
stuff that we will use inside our

1072
00:48:02,940 --> 00:48:05,640
endpoint so I'm just going to select

1073
00:48:05,640 --> 00:48:07,980
everything and delete it and

1074
00:48:07,980 --> 00:48:11,060
paste the code that I have gotten from

1075
00:48:11,060 --> 00:48:14,280
the uh

1076
00:48:14,280 --> 00:48:16,500
the Microsoft learn Docs

1077
00:48:16,500 --> 00:48:19,079
now I can click on Save and I can close

1078
00:48:19,079 --> 00:48:20,280
this

1079
00:48:20,280 --> 00:48:21,960
let me check something I don't think

1080
00:48:21,960 --> 00:48:25,020
it's saved it's saved but the display is

1081
00:48:25,020 --> 00:48:26,160
wrong okay

1082
00:48:26,160 --> 00:48:30,300
and now I think everything is good to go

1083
00:48:30,300 --> 00:48:32,640
I'm just gonna double check everything

1084
00:48:32,640 --> 00:48:36,359
so uh yeah we are gonna change the name

1085
00:48:36,359 --> 00:48:38,640
of this uh

1086
00:48:38,640 --> 00:48:40,800
Pipeline and we are gonna call it

1087
00:48:40,800 --> 00:48:42,780
predict

1088
00:48:42,780 --> 00:48:46,319
diabetes okay

1089
00:48:46,319 --> 00:48:50,339
now let's close it and

1090
00:48:50,339 --> 00:48:57,119
I think that we are good to go so

1091
00:48:57,119 --> 00:48:59,300
um

1092
00:48:59,720 --> 00:49:04,460
okay I think everything is good for us

1093
00:49:06,420 --> 00:49:08,339
I just want to make sure of something is

1094
00:49:08,339 --> 00:49:12,420
the data is correct the data is uh yeah

1095
00:49:12,420 --> 00:49:13,560
it's correct

1096
00:49:13,560 --> 00:49:16,319
okay now I can run the pipeline let's

1097
00:49:16,319 --> 00:49:17,640
submit

1098
00:49:17,640 --> 00:49:21,000
select an existing Pipeline and we're

1099
00:49:21,000 --> 00:49:22,740
going to choose the MS layer and

1100
00:49:22,740 --> 00:49:24,599
diabetes training which is the pipeline

1101
00:49:24,599 --> 00:49:27,060
that we have been working on

1102
00:49:27,060 --> 00:49:31,619
from the beginning of this module

1103
00:49:31,680 --> 00:49:33,839
I don't think that this is going to take

1104
00:49:33,839 --> 00:49:36,060
much time so we have submitted the job

1105
00:49:36,060 --> 00:49:37,319
and it's running

1106
00:49:37,319 --> 00:49:40,140
until the job ends we are going to set

1107
00:49:40,140 --> 00:49:41,720
everything

1108
00:49:41,720 --> 00:49:45,599
and for deploying a service

1109
00:49:45,599 --> 00:49:49,560
in order to deploy a service okay

1110
00:49:49,560 --> 00:49:50,520
um

1111
00:49:50,520 --> 00:49:54,000
I have to have the job ready so

1112
00:49:54,000 --> 00:49:56,040
until it's ready or you can deploy it so

1113
00:49:56,040 --> 00:49:58,319
let's go to the job the job details from

1114
00:49:58,319 --> 00:50:01,319
here okay

1115
00:50:01,319 --> 00:50:05,119
and until it finishes

1116
00:50:05,119 --> 00:50:07,260
Carlotta do you think that we can have

1117
00:50:07,260 --> 00:50:09,240
the questions and then we can get back

1118
00:50:09,240 --> 00:50:12,859
to the job I'm deploying it

1119
00:50:13,700 --> 00:50:17,579
yeah yeah yeah so yeah yeah guys if you

1120
00:50:17,579 --> 00:50:18,980
have any questions

1121
00:50:18,980 --> 00:50:24,119
uh on on what you just uh just saw here

1122
00:50:24,119 --> 00:50:26,940
or into introductions feel free this is

1123
00:50:26,940 --> 00:50:30,300
a good moment we can uh we can discuss

1124
00:50:30,300 --> 00:50:33,900
now while we wait for this job to to

1125
00:50:33,900 --> 00:50:36,260
finish

1126
00:50:36,300 --> 00:50:38,760
uh and the

1127
00:50:38,760 --> 00:50:40,220
can can

1128
00:50:40,220 --> 00:50:45,000
we have the energy check one or like

1129
00:50:45,000 --> 00:50:47,700
what do you think uh yeah we can also go

1130
00:50:47,700 --> 00:50:49,680
to the knowledge check

1131
00:50:49,680 --> 00:50:50,940
um

1132
00:50:50,940 --> 00:50:56,339
yeah okay so let me share my screen

1133
00:50:56,339 --> 00:50:58,980
yeah so if you have not any questions

1134
00:50:58,980 --> 00:51:01,619
for us we can maybe propose some

1135
00:51:01,619 --> 00:51:05,339
questions to to you that you can

1136
00:51:05,339 --> 00:51:06,240
um

1137
00:51:06,240 --> 00:51:09,660
uh to check our knowledge so far and you

1138
00:51:09,660 --> 00:51:12,900
can uh maybe answer to these questions

1139
00:51:12,900 --> 00:51:15,420
uh via chat

1140
00:51:15,420 --> 00:51:18,300
um so we have do you see my screen can

1141
00:51:18,300 --> 00:51:19,859
you see my screen

1142
00:51:19,859 --> 00:51:22,020
yes

1143
00:51:22,020 --> 00:51:25,440
um so John I think I will read this

1144
00:51:25,440 --> 00:51:29,040
question loud and ask it to you okay so

1145
00:51:29,040 --> 00:51:32,040
are you ready to transfer

1146
00:51:32,040 --> 00:51:33,660
yes I am

1147
00:51:33,660 --> 00:51:35,460
so

1148
00:51:35,460 --> 00:51:37,260
um you're using Azure machine learning

1149
00:51:37,260 --> 00:51:39,780
designer to create a training pipeline

1150
00:51:39,780 --> 00:51:42,540
for a binary classification model so

1151
00:51:42,540 --> 00:51:45,300
what what we were doing in our demo

1152
00:51:45,300 --> 00:51:48,059
right and you have added a data set

1153
00:51:48,059 --> 00:51:51,660
containing features and labels uh a true

1154
00:51:51,660 --> 00:51:54,359
class decision Forest module so we used

1155
00:51:54,359 --> 00:51:56,819
a logistic regression model our

1156
00:51:56,819 --> 00:51:59,099
um in our example here we're using A2

1157
00:51:59,099 --> 00:52:01,260
class decision force model

1158
00:52:01,260 --> 00:52:04,500
and of course a trained model model you

1159
00:52:04,500 --> 00:52:07,200
plan now to use score model and evaluate

1160
00:52:07,200 --> 00:52:09,480
model modules to test the train model

1161
00:52:09,480 --> 00:52:11,640
with the subset of the data set that

1162
00:52:11,640 --> 00:52:13,500
wasn't used for training

1163
00:52:13,500 --> 00:52:15,960
but what are we missing so what's

1164
00:52:15,960 --> 00:52:18,780
another model you should add and we have

1165
00:52:18,780 --> 00:52:21,660
three options we have join data we have

1166
00:52:21,660 --> 00:52:25,200
split data or we have select columns in

1167
00:52:25,200 --> 00:52:26,819
in that set

1168
00:52:26,819 --> 00:52:28,260
so

1169
00:52:28,260 --> 00:52:32,040
um while John thinks about the answer uh

1170
00:52:32,040 --> 00:52:33,839
go ahead and

1171
00:52:33,839 --> 00:52:34,800
um

1172
00:52:34,800 --> 00:52:37,800
answer yourself so give us your your

1173
00:52:37,800 --> 00:52:39,540
guess

1174
00:52:39,540 --> 00:52:41,940
put in the chat or just come off mute

1175
00:52:41,940 --> 00:52:44,900
and announcer

1176
00:52:46,740 --> 00:52:48,960
a b yes

1177
00:52:48,960 --> 00:52:50,579
yeah what do you think is the correct

1178
00:52:50,579 --> 00:52:53,579
answer for this one I need something to

1179
00:52:53,579 --> 00:52:56,579
uh like I have to score my model and I

1180
00:52:56,579 --> 00:53:00,359
have to evaluate it so I I like I need

1181
00:53:00,359 --> 00:53:03,119
something to enable me to do these two

1182
00:53:03,119 --> 00:53:05,359
things

1183
00:53:06,660 --> 00:53:09,119
I think it's something you showed us in

1184
00:53:09,119 --> 00:53:12,980
in your pipeline right John

1185
00:53:13,260 --> 00:53:16,819
of course I did

1186
00:53:23,460 --> 00:53:28,020
uh we have no guests yeah

1187
00:53:28,020 --> 00:53:32,280
can someone like someone want to guess

1188
00:53:32,280 --> 00:53:35,579
uh we have a b yeah

1189
00:53:35,579 --> 00:53:38,760
uh maybe

1190
00:53:38,760 --> 00:53:43,260
so uh in order to do this in order to do

1191
00:53:43,260 --> 00:53:46,200
this I mentioned the

1192
00:53:46,200 --> 00:53:49,380
the module that is going to help me to

1193
00:53:49,380 --> 00:53:53,819
to divide my data into two things 70 for

1194
00:53:53,819 --> 00:53:56,220
the training and thirty percent for the

1195
00:53:56,220 --> 00:53:59,339
evaluation so what did I use I used

1196
00:53:59,339 --> 00:54:01,859
split data because this is what is going

1197
00:54:01,859 --> 00:54:05,280
to split my data randomly into training

1198
00:54:05,280 --> 00:54:08,579
data and validation data so the correct

1199
00:54:08,579 --> 00:54:12,240
answer is B and good job eek thank you

1200
00:54:12,240 --> 00:54:13,980
for participating

1201
00:54:13,980 --> 00:54:17,400
next question please

1202
00:54:17,400 --> 00:54:19,339
yes

1203
00:54:19,339 --> 00:54:22,559
answer so thanks John

1204
00:54:22,559 --> 00:54:26,040
uh for uh explaining us the the correct

1205
00:54:26,040 --> 00:54:26,940
one

1206
00:54:26,940 --> 00:54:30,420
and we want to go with question two

1207
00:54:30,420 --> 00:54:33,180
yeah so uh I'm going to ask you now

1208
00:54:33,180 --> 00:54:35,880
karnata you use Azure machine learning

1209
00:54:35,880 --> 00:54:38,280
designer to create a training pipeline

1210
00:54:38,280 --> 00:54:40,500
for your classification model

1211
00:54:40,500 --> 00:54:44,099
what must you do before you deploy this

1212
00:54:44,099 --> 00:54:45,960
model as a service you have to do

1213
00:54:45,960 --> 00:54:47,579
something before you deploy it what do

1214
00:54:47,579 --> 00:54:49,740
you think is the correct answer

1215
00:54:49,740 --> 00:54:52,740
is it a b or c

1216
00:54:52,740 --> 00:54:55,020
share your thoughts without in touch

1217
00:54:55,020 --> 00:54:58,380
with us in the chat and

1218
00:54:58,380 --> 00:55:00,180
um and I'm also going to give you some

1219
00:55:00,180 --> 00:55:02,940
like minutes to think of it before I

1220
00:55:02,940 --> 00:55:06,020
like tell you about

1221
00:55:06,599 --> 00:55:09,000
yeah so let me go through the possible

1222
00:55:09,000 --> 00:55:12,359
answers right so we have a uh create an

1223
00:55:12,359 --> 00:55:14,940
inference pipeline from the training

1224
00:55:14,940 --> 00:55:16,020
pipeline

1225
00:55:16,020 --> 00:55:19,260
uh B we have ADD and evaluate model

1226
00:55:19,260 --> 00:55:22,380
module to the training Pipeline and then

1227
00:55:22,380 --> 00:55:25,079
three we have uh clone the training

1228
00:55:25,079 --> 00:55:29,480
Pipeline with a different name

1229
00:55:29,520 --> 00:55:31,559
so what do you think is the correct

1230
00:55:31,559 --> 00:55:33,960
answer a b or c

1231
00:55:33,960 --> 00:55:36,660
uh also this time I think it's something

1232
00:55:36,660 --> 00:55:39,300
we mentioned both in the decks and in

1233
00:55:39,300 --> 00:55:41,960
the demo right

1234
00:55:42,599 --> 00:55:44,819
yes it is

1235
00:55:44,819 --> 00:55:48,720
it's something that I have done like two

1236
00:55:48,720 --> 00:55:51,800
like five minutes ago

1237
00:55:51,800 --> 00:55:57,200
it's real time real time what's

1238
00:55:58,020 --> 00:55:58,760
um

1239
00:55:58,760 --> 00:56:02,040
yeah so think about you need to deploy

1240
00:56:02,040 --> 00:56:05,460
uh the model as a service so uh if I'm

1241
00:56:05,460 --> 00:56:07,980
going to deploy model

1242
00:56:07,980 --> 00:56:10,380
um I cannot like evaluate the model

1243
00:56:10,380 --> 00:56:12,839
after deploying it right because I

1244
00:56:12,839 --> 00:56:14,940
cannot go into production if I'm not

1245
00:56:14,940 --> 00:56:17,579
sure I'm not satisfied over my model and

1246
00:56:17,579 --> 00:56:19,500
I'm not sure that my model is performing

1247
00:56:19,500 --> 00:56:20,280
well

1248
00:56:20,280 --> 00:56:23,460
so that's why I would go with

1249
00:56:23,460 --> 00:56:24,319
um

1250
00:56:24,319 --> 00:56:30,480
I would like exclude B from from my from

1251
00:56:30,480 --> 00:56:31,520
my answer

1252
00:56:31,520 --> 00:56:33,599
uh while

1253
00:56:33,599 --> 00:56:36,960
um thinking about C uh I don't see you I

1254
00:56:36,960 --> 00:56:39,480
didn't see you John cloning uh the

1255
00:56:39,480 --> 00:56:41,420
training Pipeline with a different name

1256
00:56:41,420 --> 00:56:44,640
uh so I I don't think this is the the

1257
00:56:44,640 --> 00:56:46,920
right answer

1258
00:56:46,920 --> 00:56:49,619
um while I've seen you creating an

1259
00:56:49,619 --> 00:56:52,859
inference pipeline uh yeah from the

1260
00:56:52,859 --> 00:56:55,020
training Pipeline and you just converted

1261
00:56:55,020 --> 00:56:59,280
it using uh a one-click button right

1262
00:56:59,280 --> 00:57:03,300
yeah that's correct so uh this is the

1263
00:57:03,300 --> 00:57:04,280
right answer

1264
00:57:04,280 --> 00:57:07,460
uh good job so I created an inference

1265
00:57:07,460 --> 00:57:11,280
real-time Pipeline and it has done it

1266
00:57:11,280 --> 00:57:13,440
like it finished it finished the job is

1267
00:57:13,440 --> 00:57:18,000
finished so uh we can now deploy

1268
00:57:18,000 --> 00:57:19,400
ment

1269
00:57:19,400 --> 00:57:21,500
yeah

1270
00:57:21,500 --> 00:57:25,339
exactly like on time

1271
00:57:25,380 --> 00:57:27,839
I like it finished like two seconds

1272
00:57:27,839 --> 00:57:30,859
three three four seconds ago

1273
00:57:30,859 --> 00:57:33,119
so uh

1274
00:57:33,119 --> 00:57:36,480
until like um

1275
00:57:36,480 --> 00:57:39,839
this is my job review so

1276
00:57:39,839 --> 00:57:43,260
uh like this is the job details that I

1277
00:57:43,260 --> 00:57:45,540
have already submitted it's just opening

1278
00:57:45,540 --> 00:57:48,119
and once it opens

1279
00:57:48,119 --> 00:57:50,180
um

1280
00:57:50,400 --> 00:57:52,740
like I don't know why it's so heavy

1281
00:57:52,740 --> 00:57:56,780
today it's not like that usually

1282
00:57:58,740 --> 00:58:01,020
yeah it's probably because you are also

1283
00:58:01,020 --> 00:58:06,000
showing your your screen on teams

1284
00:58:06,000 --> 00:58:08,160
okay so that's the bandwidth of your

1285
00:58:08,160 --> 00:58:10,740
connection is exactly do something here

1286
00:58:10,740 --> 00:58:13,740
because yeah finally

1287
00:58:13,740 --> 00:58:16,440
I can switch to my mobile internet if it

1288
00:58:16,440 --> 00:58:18,599
did it again so I will click on deploy

1289
00:58:18,599 --> 00:58:20,700
it's that simple I'll just click on

1290
00:58:20,700 --> 00:58:23,040
deploy and

1291
00:58:23,040 --> 00:58:25,619
I am going to deploy a new real-time

1292
00:58:25,619 --> 00:58:27,960
endpoint

1293
00:58:27,960 --> 00:58:30,300
so what I'm going to name it I'm

1294
00:58:30,300 --> 00:58:31,740
description and the compute type

1295
00:58:31,740 --> 00:58:33,720
everything is already mentioned for me

1296
00:58:33,720 --> 00:58:36,240
here so I'm just gonna copy and paste it

1297
00:58:36,240 --> 00:58:38,940
because we like we have we are running

1298
00:58:38,940 --> 00:58:41,280
out of time

1299
00:58:41,280 --> 00:58:45,680
so it's all Azure container instance

1300
00:58:45,680 --> 00:58:48,720
which is a containerization service also

1301
00:58:48,720 --> 00:58:51,059
both are for containerization but this

1302
00:58:51,059 --> 00:58:52,440
gives you something and this gives you

1303
00:58:52,440 --> 00:58:54,960
something else for the advanced options

1304
00:58:54,960 --> 00:58:57,420
it doesn't say for us to do anything so

1305
00:58:57,420 --> 00:59:00,420
we are just gonna click on deploy

1306
00:59:00,420 --> 00:59:05,220
and now we can test our endpoint from

1307
00:59:05,220 --> 00:59:07,859
the endpoints that we can find here so

1308
00:59:07,859 --> 00:59:11,460
it's in progress if I go here

1309
00:59:11,460 --> 00:59:13,799
under the assets I can find something

1310
00:59:13,799 --> 00:59:16,680
called endpoints and I can find the

1311
00:59:16,680 --> 00:59:18,599
real-time ones and the batch endpoints

1312
00:59:18,599 --> 00:59:22,020
and we have created a real-time endpoint

1313
00:59:22,020 --> 00:59:25,260
so we are going to find it under this uh

1314
00:59:25,260 --> 00:59:29,760
title so if I like click on it I should

1315
00:59:29,760 --> 00:59:32,640
be able to test it once it's ready

1316
00:59:32,640 --> 00:59:37,200
it's still like loading but this is the

1317
00:59:37,200 --> 00:59:40,980
input and this is the output that we

1318
00:59:40,980 --> 00:59:45,200
will get back so if I click on test and

1319
00:59:45,200 --> 00:59:49,920
from here I will input some data to the

1320
00:59:49,920 --> 00:59:50,900
endpoint

1321
00:59:50,900 --> 00:59:54,599
which are the patient information The

1322
00:59:54,599 --> 00:59:57,119
Columns that we have already seen in our

1323
00:59:57,119 --> 01:00:00,380
data set the patient ID the pregnancies

1324
01:00:00,380 --> 01:00:03,960
and of course of course I'm not gonna

1325
01:00:03,960 --> 01:00:05,940
enter the label that I'm trying to

1326
01:00:05,940 --> 01:00:08,099
predict so I'm not going to give him if

1327
01:00:08,099 --> 01:00:10,680
the patient is diabetic or not this end

1328
01:00:10,680 --> 01:00:13,200
point is to tell me this is the end

1329
01:00:13,200 --> 01:00:15,599
point or the URL is going to give me

1330
01:00:15,599 --> 01:00:17,640
back this information whether someone

1331
01:00:17,640 --> 01:00:22,680
has diabetes or he doesn't so if I input

1332
01:00:22,680 --> 01:00:24,780
these this data I'm just going to copy

1333
01:00:24,780 --> 01:00:27,780
it and go to my endpoint and click on

1334
01:00:27,780 --> 01:00:30,180
test I'm gonna give the result pack

1335
01:00:30,180 --> 01:00:32,359
which are the three columns that we have

1336
01:00:32,359 --> 01:00:35,520
defined inside our python script the

1337
01:00:35,520 --> 01:00:37,859
patient ID the diabetic prediction and

1338
01:00:37,859 --> 01:00:41,040
the probability the certainty of whether

1339
01:00:41,040 --> 01:00:45,720
someone is diabetic or not based on the

1340
01:00:45,720 --> 01:00:50,660
uh based on the prediction so that's it

1341
01:00:50,660 --> 01:00:54,359
and like uh I think that this is really

1342
01:00:54,359 --> 01:00:56,819
simple step to do you can do it on your

1343
01:00:56,819 --> 01:00:58,380
own you can test it

1344
01:00:58,380 --> 01:01:01,140
and I think that I have finished so

1345
01:01:01,140 --> 01:01:03,020
thank you

1346
01:01:03,020 --> 01:01:06,599
uh yes we are running out of time I I

1347
01:01:06,599 --> 01:01:09,780
just wanted to uh thank you John for for

1348
01:01:09,780 --> 01:01:12,299
this demo for going through all these

1349
01:01:12,299 --> 01:01:14,099
steps to

1350
01:01:14,099 --> 01:01:16,740
um create train a classification model

1351
01:01:16,740 --> 01:01:19,680
and also deploy it as a predictive

1352
01:01:19,680 --> 01:01:23,040
service and I encourage you all to go

1353
01:01:23,040 --> 01:01:25,079
back to the learn module

1354
01:01:25,079 --> 01:01:28,260
um and uh like depend all these topics

1355
01:01:28,260 --> 01:01:31,760
at your at your own pace and also maybe

1356
01:01:31,760 --> 01:01:34,799
uh do this demo on your own on your

1357
01:01:34,799 --> 01:01:37,140
subscription on your Azure for student

1358
01:01:37,140 --> 01:01:39,359
subscription

1359
01:01:39,359 --> 01:01:43,200
um and I would also like to recall that

1360
01:01:43,200 --> 01:01:46,260
this is part of a series of study

1361
01:01:46,260 --> 01:01:49,500
sessions of cloud skill challenge study

1362
01:01:49,500 --> 01:01:51,059
sessions

1363
01:01:51,059 --> 01:01:54,059
um so you will have more in the in the

1364
01:01:54,059 --> 01:01:57,540
in the following days and this is for

1365
01:01:57,540 --> 01:02:00,480
you to prepare let's say to to help you

1366
01:02:00,480 --> 01:02:04,880
in taking the a cloud skills challenge

1367
01:02:04,880 --> 01:02:07,040
which collect

1368
01:02:07,040 --> 01:02:10,799
a very interesting learn module that you

1369
01:02:10,799 --> 01:02:14,540
can use to scale up on various topics

1370
01:02:14,540 --> 01:02:18,359
and some of them are focused on AI and

1371
01:02:18,359 --> 01:02:20,819
ml so if you are interested in these

1372
01:02:20,819 --> 01:02:23,099
topics you can select these these learn

1373
01:02:23,099 --> 01:02:24,780
modules

1374
01:02:24,780 --> 01:02:27,660
um so let me also copy

1375
01:02:27,660 --> 01:02:29,819
um the link the short link to the

1376
01:02:29,819 --> 01:02:32,700
challenge in the chat uh remember that

1377
01:02:32,700 --> 01:02:34,980
you have time until the 13th of

1378
01:02:34,980 --> 01:02:37,980
September to take the challenge and also

1379
01:02:37,980 --> 01:02:40,440
remember that in October on the 7th of

1380
01:02:40,440 --> 01:02:43,020
October you have the you can join the

1381
01:02:43,020 --> 01:02:46,619
student the the student developer Summit

1382
01:02:46,619 --> 01:02:50,640
which is uh which will be a virtual or

1383
01:02:50,640 --> 01:02:53,220
in for some for some cases and hybrid

1384
01:02:53,220 --> 01:02:56,040
event so stay tuned because you will

1385
01:02:56,040 --> 01:02:58,559
have some surprises in the following

1386
01:02:58,559 --> 01:03:01,260
days and if you want to learn more about

1387
01:03:01,260 --> 01:03:03,480
this event you can check the Microsoft

1388
01:03:03,480 --> 01:03:08,099
Imaging cap Twitter page and stay tuned

1389
01:03:08,099 --> 01:03:11,460
so thank you everyone for uh for joining

1390
01:03:11,460 --> 01:03:13,079
this session today and thank you very

1391
01:03:13,079 --> 01:03:16,500
much Sean for co-hosting with with this

1392
01:03:16,500 --> 01:03:20,359
session with me it was a pleasure

1393
01:03:21,839 --> 01:03:24,119
thank you so much Carlotta for having me

1394
01:03:24,119 --> 01:03:26,579
with you today and thank you like for

1395
01:03:26,579 --> 01:03:28,079
giving me this opportunity to be with

1396
01:03:28,079 --> 01:03:30,180
you here

1397
01:03:30,180 --> 01:03:33,480
great I hope that uh yeah I hope that we

1398
01:03:33,480 --> 01:03:36,480
work again in the future sure I I hope

1399
01:03:36,480 --> 01:03:38,160
so as well

1400
01:03:38,160 --> 01:03:40,760
um so

1401
01:03:44,099 --> 01:03:46,500
bye bye speak to you soon

1402
01:03:46,500 --> 01:03:48,920
bye