1
00:00:00,000 --> 00:00:00,000
We just show you?

2
00:00:00,000 --> 00:00:02,000
How do we load the pickle file?

3
00:00:02,000 --> 00:00:05,000
Because we need to do the prediction, right?

4
00:00:05,000 --> 00:00:07,000
So how do we load the pickle file?

5
00:00:07,000 --> 00:00:13,000
That is very much important to show, because at the end of the day when we create a end to end Streamlit

6
00:00:13,000 --> 00:00:14,000
project.

7
00:00:14,000 --> 00:00:16,000
So we definitely require all the pickle files.

8
00:00:16,000 --> 00:00:19,000
So in order to load the pickle file.

9
00:00:19,000 --> 00:00:26,000
So first of all, uh, um, what I have to do because see here I now have three pickle files.

10
00:00:26,000 --> 00:00:27,000
I have all my model trained.

11
00:00:27,000 --> 00:00:32,000
Now I have to make sure that I load that particular pickle file and I do the prediction right.

12
00:00:32,000 --> 00:00:34,000
That is what I have to actually do.

13
00:00:34,000 --> 00:00:37,000
If I don't do that, then it will not work out right.

14
00:00:37,000 --> 00:00:40,000
So let me quickly go ahead and import all the libraries again.

15
00:00:40,000 --> 00:00:43,000
So let's say that I'm doing it in my new file okay.

16
00:00:43,000 --> 00:00:45,000
Or let's consider a new file.

17
00:00:45,000 --> 00:00:50,000
So here I will say prediction dot ipynb okay.

18
00:00:52,000 --> 00:00:55,000
Here the first thing first I will go ahead and import this.

19
00:00:55,000 --> 00:00:57,000
Select the kernel okay.

20
00:00:57,000 --> 00:01:01,000
So here you will be able to see that I'm going to execute this okay.

21
00:01:01,000 --> 00:01:05,000
Now we are going to load all the trained model right.

22
00:01:05,000 --> 00:01:06,000
So how many trained model we have.

23
00:01:06,000 --> 00:01:17,000
So load the an trained model then um scalar pickle file and the one hot encoding pickle file also.

24
00:01:17,000 --> 00:01:18,000
Right.

25
00:01:18,000 --> 00:01:19,000
One hot encoding.

26
00:01:19,000 --> 00:01:20,000
So we'll load this.

27
00:01:20,000 --> 00:01:24,000
So I'll go ahead and write mode model is equal to load underscore model.

28
00:01:24,000 --> 00:01:29,000
So here is what we have imported see from TensorFlow Keras dot models import load underscore model.

29
00:01:29,000 --> 00:01:31,000
So here I'm going to write load underscore model.

30
00:01:32,000 --> 00:01:37,000
And here I'm going to take my model dot h5 file okay.

31
00:01:38,000 --> 00:01:44,000
When I probably go ahead and use this here you'll be able to see I will also go ahead and load my load

32
00:01:44,000 --> 00:01:47,000
the encoders and scaler.

33
00:01:47,000 --> 00:01:53,000
Now in order to encode, uh, load this I will go ahead and use with open quickly.

34
00:01:53,000 --> 00:01:59,000
Let's go ahead and write label underscore encoder underscore geo dot pickle file.

35
00:01:59,000 --> 00:02:00,000
So this will be my pickle file.

36
00:02:00,000 --> 00:02:05,000
It will we will be reading this time in the read byte mode as file.

37
00:02:06,000 --> 00:02:09,000
Because pickling is nothing but it is a deserialized format, right?

38
00:02:09,000 --> 00:02:10,000
We can serialize it, we can deserialize it.

39
00:02:10,000 --> 00:02:16,000
So here I'm going to basically you go ahead and use this label underscore underscore Geo is nothing

40
00:02:16,000 --> 00:02:21,000
but pickle dot load this specific file name okay.

41
00:02:22,000 --> 00:02:23,000
So here is what I get.

42
00:02:23,000 --> 00:02:25,000
This particular pickle file over here okay.

43
00:02:25,000 --> 00:02:32,000
And similarly I will go ahead and do the same thing for the gender and for the scalar.

44
00:02:32,000 --> 00:02:36,000
Okay, so here I have my gender and for my scalar.

45
00:02:36,000 --> 00:02:38,000
Now let's take some input data.

46
00:02:38,000 --> 00:02:40,000
So I will take some input data.

47
00:02:40,000 --> 00:02:42,000
So this I will go ahead and execute it.

48
00:02:42,000 --> 00:02:45,000
Uh label encoder underscore geo.

49
00:02:45,000 --> 00:02:46,000
What is the name that I've given.

50
00:02:46,000 --> 00:02:50,000
Label encoder uh underscore gender.

51
00:02:50,000 --> 00:02:50,000
Sorry.

52
00:02:50,000 --> 00:02:52,000
It should be gender not geo.

53
00:02:56,000 --> 00:02:57,000
Okay.

54
00:02:57,000 --> 00:02:57,000
Oh, no.

55
00:02:57,000 --> 00:03:02,000
This pickle file should be my geo pickle file is what?

56
00:03:02,000 --> 00:03:04,000
Uh, one hot encoder.

57
00:03:04,000 --> 00:03:04,000
Geo.

58
00:03:04,000 --> 00:03:05,000
Right?

59
00:03:05,000 --> 00:03:06,000
Not label encoder.

60
00:03:06,000 --> 00:03:07,000
So here I'll go ahead and write.

61
00:03:07,000 --> 00:03:08,000
One hot.

62
00:03:10,000 --> 00:03:11,000
One hot.

63
00:03:12,000 --> 00:03:17,000
Let me rename this and let me copy this entire pickle file okay.

64
00:03:17,000 --> 00:03:22,000
So here I'm just going to go ahead and write one underscore hot encoder underscore geo dot pickle file.

65
00:03:22,000 --> 00:03:24,000
Now let me go ahead and execute it.

66
00:03:24,000 --> 00:03:25,000
Now it works absolutely fine.

67
00:03:25,000 --> 00:03:29,000
Right now I'm going to take some example input data.

68
00:03:29,000 --> 00:03:32,000
Because based on this input data I'm going to do the prediction.

69
00:03:32,000 --> 00:03:34,000
So here I have written credit score is equal to 600.

70
00:03:34,000 --> 00:03:35,000
Geography France.

71
00:03:35,000 --> 00:03:35,000
Male.

72
00:03:35,000 --> 00:03:37,000
Gender male age 40.

73
00:03:37,000 --> 00:03:38,000
Tenure 30.

74
00:03:38,000 --> 00:03:39,000
This this this.

75
00:03:39,000 --> 00:03:39,000
There.

76
00:03:40,000 --> 00:03:44,000
Now when I'm giving this particular data, the first thing that I need to think is that how do I convert

77
00:03:44,000 --> 00:03:48,000
this particular value into numerical and this particular value into numerical.

78
00:03:48,000 --> 00:03:48,000
Right.

79
00:03:48,000 --> 00:03:54,000
So and then after that take all the numerical value and convert that into standard means.

80
00:03:54,000 --> 00:03:56,000
Scale down that particular value using standard scaler.

81
00:03:56,000 --> 00:03:59,000
That is the reason we have stored this in the form of pickle file.

82
00:03:59,000 --> 00:04:00,000
Okay.

83
00:04:01,000 --> 00:04:04,000
Now uh, let's quickly go ahead and do this.

84
00:04:04,000 --> 00:04:09,000
Uh, first of all, uh, I would like to see just think over it.

85
00:04:09,000 --> 00:04:09,000
Okay?

86
00:04:09,000 --> 00:04:17,000
You, uh, just try to think, like, how do we probably go ahead and apply, uh, one hot encoding

87
00:04:17,000 --> 00:04:18,000
in this?

88
00:04:18,000 --> 00:04:23,000
Okay, now, you really need to think, guys, uh, you cannot, uh, just think over it, okay?

89
00:04:23,000 --> 00:04:23,000
I'll.

90
00:04:23,000 --> 00:04:24,000
I'll give you five minutes.

91
00:04:24,000 --> 00:04:25,000
Just pause the video.

92
00:04:25,000 --> 00:04:27,000
But what task you really need to do?

93
00:04:27,000 --> 00:04:30,000
Okay, this is my new input data I'm actually getting.

94
00:04:31,000 --> 00:04:37,000
And now with respect to this new input data, you need to think, how can I probably take this particular

95
00:04:37,000 --> 00:04:41,000
data and perform a convert categorical features into numerical features?

96
00:04:41,000 --> 00:04:43,000
That is what you really need to think first of all.

97
00:04:43,000 --> 00:04:48,000
The second thing is, uh uh, how do you apply standard scaling?

98
00:04:48,000 --> 00:04:48,000
Right.

99
00:04:48,000 --> 00:04:51,000
And then how do you do the prediction with respect to the model?

100
00:04:51,000 --> 00:04:51,000
Okay.

101
00:04:53,000 --> 00:04:54,000
That is what we are going to probably see.

102
00:04:54,000 --> 00:04:55,000
Okay.

103
00:04:55,000 --> 00:04:58,000
So first of all, uh, pause the video and do it.

104
00:04:58,000 --> 00:05:01,000
Till then I will start copying and pasting the code over here.

105
00:05:01,000 --> 00:05:04,000
The reason is very simple because I have already told you all these things.

106
00:05:04,000 --> 00:05:05,000
Okay.

107
00:05:05,000 --> 00:05:08,000
So here, uh, one hot.

108
00:05:08,000 --> 00:05:12,000
Uh, so let me just go ahead and write this label encoder g0.

109
00:05:13,000 --> 00:05:18,000
So I'll take this label encoder g0 dot transform okay.

110
00:05:18,000 --> 00:05:23,000
And here you'll be able to see that I am getting some values over here like key value pairs.

111
00:05:24,000 --> 00:05:24,000
Right.

112
00:05:24,000 --> 00:05:25,000
Key value pairs over here.

113
00:05:26,000 --> 00:05:31,000
Now when I get this key value pairs I need to take out the information of this particular geography.

114
00:05:31,000 --> 00:05:40,000
So what I will do I will say hey uh uh label underscore underscore encoder dot transform.

115
00:05:40,000 --> 00:05:50,000
And here I'm just going to use my input underscore data okay I think it is input underscore data of

116
00:05:50,000 --> 00:05:52,000
geographic column okay.

117
00:05:52,000 --> 00:05:55,000
And then uh this geography is basically my key.

118
00:05:55,000 --> 00:06:00,000
So let me just go ahead and copy and paste it over here with respect to this.

119
00:06:00,000 --> 00:06:03,000
So I will be able to get my key okay.

120
00:06:03,000 --> 00:06:07,000
And then finally I get the I convert this into an array okay.

121
00:06:08,000 --> 00:06:13,000
Now once you do this again I'll be using this label underscore Geo okay.

122
00:06:13,000 --> 00:06:15,000
Dot get feature names out of geography.

123
00:06:15,000 --> 00:06:18,000
And this is what I mean by geo encoded that I'm actually giving okay.

124
00:06:19,000 --> 00:06:25,000
So if you see this is for my new data that I'm actually able to get this right.

125
00:06:25,000 --> 00:06:30,000
So here it says uh reshape one comma one okay.

126
00:06:30,000 --> 00:06:31,000
Let's see this.

127
00:06:31,000 --> 00:06:31,000
Okay.

128
00:06:32,000 --> 00:06:35,000
Um, here I will just go ahead and use this as like this.

129
00:06:35,000 --> 00:06:36,000
Then it should work.

130
00:06:37,000 --> 00:06:38,000
Okay.

131
00:06:38,000 --> 00:06:39,000
Uh, expected 2D array.

132
00:06:39,000 --> 00:06:42,000
Got one 1D array instead.

133
00:06:42,000 --> 00:06:48,000
Okay, so array of France I have given over here I'm using this transform.

134
00:06:49,000 --> 00:06:49,000
Okay.

135
00:06:50,000 --> 00:06:50,000
Um.

136
00:06:50,000 --> 00:06:51,000
Mhm.

137
00:06:53,000 --> 00:07:01,000
This is okay I have to use one more brackets because that is the uh that is the reason how we got it

138
00:07:01,000 --> 00:07:02,000
right now.

139
00:07:02,000 --> 00:07:03,000
It should work.

140
00:07:03,000 --> 00:07:06,000
So here you can see geography underscore front geography underscore Germany.

141
00:07:06,000 --> 00:07:08,000
Geography underscore Spain.

142
00:07:08,000 --> 00:07:12,000
Guys you may be thinking how did I get to know that I have to use, uh, double brackets.

143
00:07:12,000 --> 00:07:19,000
See over here, if you go ahead and see with respect to the transformation that we did with the help

144
00:07:19,000 --> 00:07:22,000
of, uh, one hot encoding, right?

145
00:07:22,000 --> 00:07:29,000
So here, when we use this one hot encoding here, you can see that, uh, let's see where it is okay.

146
00:07:29,000 --> 00:07:34,000
Uh, here you can see I'm actually giving this one hot encoding over here.

147
00:07:34,000 --> 00:07:37,000
And I'm giving to a list of features, right?

148
00:07:37,000 --> 00:07:38,000
List of features.

149
00:07:38,000 --> 00:07:42,000
And similarly, I also have to give a list of features over here.

150
00:07:42,000 --> 00:07:44,000
That is the reason this is one of my feature over here.

151
00:07:44,000 --> 00:07:46,000
And I'm giving it as a list of features.

152
00:07:46,000 --> 00:07:47,000
Right.

153
00:07:47,000 --> 00:07:49,000
So that is the reason I'm able to get it okay.

154
00:07:49,000 --> 00:07:57,000
So once I do this uh then I will go ahead and combine this entire data, this data with my input data.

155
00:07:57,000 --> 00:08:00,000
So I'll say input data dot reset index drop is equal to true.

156
00:08:00,000 --> 00:08:07,000
Because if I do the reset index I'm actually going to get that uh default index value row index value.

157
00:08:07,000 --> 00:08:09,000
And I'm saying drop drop is equal to true.

158
00:08:09,000 --> 00:08:14,000
And then I'm uh adding this geo underscore uh encoded underscore df okay.

159
00:08:14,000 --> 00:08:19,000
So if I go ahead and see my input data now input data.

160
00:08:19,000 --> 00:08:19,000
See.

161
00:08:19,000 --> 00:08:23,000
So guys uh, here you can actually see that I'm getting this particular error.

162
00:08:23,000 --> 00:08:28,000
Uh, additionally object has no attribute reset index because I just made one simple mistake after this

163
00:08:28,000 --> 00:08:28,000
particular code.

164
00:08:28,000 --> 00:08:32,000
See, the input data right now is in the form of key value pairs, right?

165
00:08:32,000 --> 00:08:35,000
I need to convert this into, uh data frame.

166
00:08:35,000 --> 00:08:40,000
So in order to convert this into a data frame we will go ahead and write PD dot data frame.

167
00:08:40,000 --> 00:08:44,000
And let me quickly go ahead and use this input underscore data.

168
00:08:44,000 --> 00:08:45,000
Okay.

169
00:08:45,000 --> 00:08:49,000
And once I get this this will basically be my input underscore DF.

170
00:08:50,000 --> 00:08:51,000
And let's go ahead and execute this.

171
00:08:51,000 --> 00:08:54,000
So here is my input underscore df.

172
00:08:55,000 --> 00:08:58,000
Um and this is what is my entire row right now.

173
00:08:58,000 --> 00:09:03,000
This row only I have to pass it over there right now for this particular row, what I really need to

174
00:09:03,000 --> 00:09:06,000
do, first of all, I need to do the concatenation, right.

175
00:09:06,000 --> 00:09:08,000
So my this is my input underscore DF.

176
00:09:08,000 --> 00:09:14,000
And I uh, after converting this into my data frame, I should probably, uh, uh, concatenate my geographic

177
00:09:14,000 --> 00:09:15,000
column.

178
00:09:15,000 --> 00:09:15,000
Right.

179
00:09:15,000 --> 00:09:18,000
So I will do that concatenation right now.

180
00:09:18,000 --> 00:09:18,000
Okay.

181
00:09:18,000 --> 00:09:24,000
I have actually changed all the values with respect to the geography column over here.

182
00:09:24,000 --> 00:09:24,000
Right.

183
00:09:24,000 --> 00:09:26,000
So it is basically into two array.

184
00:09:26,000 --> 00:09:30,000
We have actually done this and I've actually got this geo underscore uh encoded underscore df.

185
00:09:30,000 --> 00:09:38,000
Now let's uh quickly encode my categorical variables okay.

186
00:09:38,000 --> 00:09:46,000
Now I will say hey let's take this input underscore df and let's convert first of all this gender because

187
00:09:46,000 --> 00:09:49,000
gender also needs to be replaced with some label encoded value.

188
00:09:49,000 --> 00:09:51,000
So I'm just going to use this label encoder.

189
00:09:52,000 --> 00:09:54,000
Label encoder Uh.

190
00:09:55,000 --> 00:09:56,000
Label encoder.

191
00:09:56,000 --> 00:09:57,000
Underscore gender.

192
00:09:57,000 --> 00:10:04,000
And I'll say hey go ahead and do this transform operation on my input underscore df input underscore

193
00:10:04,000 --> 00:10:07,000
df on which column on the gender column.

194
00:10:07,000 --> 00:10:11,000
So this basically becomes my input underscore df.

195
00:10:11,000 --> 00:10:13,000
So if you go ahead and see my input underscore df.

196
00:10:13,000 --> 00:10:16,000
Now the gender column will either have zeros or one.

197
00:10:16,000 --> 00:10:18,000
So right now it is one right.

198
00:10:18,000 --> 00:10:20,000
So this particular value may be a male.

199
00:10:20,000 --> 00:10:22,000
Before now it has basically got one okay.

200
00:10:22,000 --> 00:10:23,000
So this is perfect.

201
00:10:23,000 --> 00:10:25,000
Till here we are able to get it okay.

202
00:10:26,000 --> 00:10:29,000
Uh I've already done the one hot encoding for geographic column.

203
00:10:29,000 --> 00:10:32,000
So I have this geo underscore encoded underscore df.

204
00:10:32,000 --> 00:10:37,000
Now what I will do is that I will quickly go ahead and do the concatenation.

205
00:10:37,000 --> 00:10:40,000
Now finally let's do the concatenation.

206
00:10:41,000 --> 00:10:46,000
Concatenation Um, with one hot encoded data.

207
00:10:47,000 --> 00:10:49,000
One hot encoded data.

208
00:10:49,000 --> 00:10:52,000
And uh, along with this we also need to add the, uh.

209
00:10:52,000 --> 00:10:55,000
Uh, no need to add the gender data because it is already done.

210
00:10:55,000 --> 00:10:57,000
The changes in input underscore PDF.

211
00:10:57,000 --> 00:11:02,000
Now what we'll do is that whatever encoding we have done for the geography column, right.

212
00:11:02,000 --> 00:11:04,000
We need to append all those columns inside this.

213
00:11:04,000 --> 00:11:06,000
And we need to drop this column.

214
00:11:06,000 --> 00:11:13,000
So here I will just go ahead and quickly write input underscore DF is equal to PD dot concatenation.

215
00:11:14,000 --> 00:11:19,000
Uh let's concatenate our input underscore df.

216
00:11:20,000 --> 00:11:23,000
And from this I'm just going to drop my geographic column.

217
00:11:23,000 --> 00:11:23,000
Same thing.

218
00:11:23,000 --> 00:11:26,000
What we have actually done over there right.

219
00:11:26,000 --> 00:11:31,000
So geographic column and this drop will be done with respect to axis is equal to one.

220
00:11:31,000 --> 00:11:37,000
And here I'm just going to go ahead and write geo underscore underscore uh encoding underscore DF right.

221
00:11:37,000 --> 00:11:42,000
So geo underscore encoded underscore DF is nothing but this particular value which has this one uh,

222
00:11:42,000 --> 00:11:45,000
which has this one hot encoding of this particular feature.

223
00:11:45,000 --> 00:11:45,000
Okay.

224
00:11:45,000 --> 00:11:48,000
That is what we are basically going to do over here.

225
00:11:48,000 --> 00:11:54,000
And uh, I have to also make sure that I put with axis equal to one, otherwise it will become row wise

226
00:11:54,000 --> 00:11:57,000
concatenation instead column wise concatenation.

227
00:11:57,000 --> 00:12:02,000
Now if I go ahead and write input underscore df, you'll be able to see that gender has got converted

228
00:12:02,000 --> 00:12:04,000
from male to one.

229
00:12:04,000 --> 00:12:07,000
And here you'll be also able to see that my three features have got added.

230
00:12:07,000 --> 00:12:09,000
One is geography France, Germany and Spain.

231
00:12:09,000 --> 00:12:10,000
Okay.

232
00:12:11,000 --> 00:12:13,000
Uh, now one more transformation is left.

233
00:12:13,000 --> 00:12:17,000
Uh, that is nothing but scaling the data.

234
00:12:17,000 --> 00:12:19,000
Scaling the input data.

235
00:12:19,000 --> 00:12:21,000
Now, in order to do the scaling part.

236
00:12:21,000 --> 00:12:25,000
So I will be using scaler dot transform.

237
00:12:26,000 --> 00:12:29,000
And here let's go ahead and write input underscore df okay.

238
00:12:30,000 --> 00:12:37,000
So this will basically be my input underscore scale done okay.

239
00:12:37,000 --> 00:12:43,000
Now if you go ahead and see this input underscore scaled I will basically get all the data in the form

240
00:12:43,000 --> 00:12:44,000
of array.

241
00:12:44,000 --> 00:12:47,000
And all these values has basically got scaled.

242
00:12:47,000 --> 00:12:47,000
Okay.

243
00:12:47,000 --> 00:12:52,000
Now finally we need to just predict and see whether the person is going to leave the bank or not.

244
00:12:52,000 --> 00:12:54,000
So I'll go ahead and write prediction.

245
00:12:55,000 --> 00:13:00,000
Uh, in order to do the prediction I'll just go ahead and run model dot predict here, give all the

246
00:13:00,000 --> 00:13:03,000
values over here like input underscore scaled okay.

247
00:13:04,000 --> 00:13:05,000
Get my prediction.

248
00:13:07,000 --> 00:13:08,000
Get my prediction.

249
00:13:08,000 --> 00:13:13,000
So I will just go ahead and print my prediction quickly.

250
00:13:13,000 --> 00:13:20,000
So here you can see that I'm getting this particular value 0.20.02976.

251
00:13:20,000 --> 00:13:21,000
So and so.

252
00:13:21,000 --> 00:13:21,000
Right.

253
00:13:22,000 --> 00:13:28,000
Um, I can just go ahead and uh get my prediction probability also.

254
00:13:28,000 --> 00:13:34,000
So if I just go ahead and write like this prediction of zero of zero, I'll be able to see that I'm,

255
00:13:34,000 --> 00:13:37,000
I'm, I'm okay right now or let's see this.

256
00:13:37,000 --> 00:13:40,000
I will just go ahead and write prediction scope probability.

257
00:13:40,000 --> 00:13:42,000
So here you'll be able to see 0.297.

258
00:13:42,000 --> 00:13:45,000
It is there I will go ahead and say this particular condition.

259
00:13:45,000 --> 00:13:49,000
If the prediction probability is greater than 0.5 the customer is likely to churn.

260
00:13:49,000 --> 00:13:51,000
Otherwise the customer is not likely to churn.

261
00:13:51,000 --> 00:13:52,000
Okay.

262
00:13:52,000 --> 00:13:54,000
Because this is a binary output.

263
00:13:54,000 --> 00:13:57,000
And I'm just going to keep the binary output with respect to 0.5.

264
00:13:57,000 --> 00:13:59,000
But here I'm actually getting 0.029.

265
00:13:59,000 --> 00:14:01,000
So the customer is not likely to churn.

266
00:14:02,000 --> 00:14:05,000
So in this video entirely right.

267
00:14:05,000 --> 00:14:07,000
How to do the specific prediction?

268
00:14:07,000 --> 00:14:08,000
I've actually done it again.

269
00:14:08,000 --> 00:14:10,000
First of all we have loaded all the pickle files.

270
00:14:10,000 --> 00:14:14,000
Then whenever we get any input data, first of all we converted that into a data frame.

271
00:14:14,000 --> 00:14:16,000
Then we did the one hot encoding of geography.

272
00:14:16,000 --> 00:14:19,000
Then we did label encoding for gender.

273
00:14:19,000 --> 00:14:21,000
Then we combined all those things.

274
00:14:21,000 --> 00:14:24,000
Then we created our entire data frame.

275
00:14:24,000 --> 00:14:27,000
Then we did the scaling right again.

276
00:14:27,000 --> 00:14:30,000
We used the transform feature, then we did the prediction.

277
00:14:30,000 --> 00:14:32,000
Then finally we got the probability.

278
00:14:32,000 --> 00:14:36,000
And then we finally checked whether the person is likely to churn or not.

279
00:14:36,000 --> 00:14:37,000
Right.

280
00:14:37,000 --> 00:14:39,000
So yes, this was it.

281
00:14:39,000 --> 00:14:44,000
Now in my next video, what I'm actually going to do is that I'm going to deploy this entire content

282
00:14:44,000 --> 00:14:47,000
with the help of Streamlit in the Streamlit platform itself.

283
00:14:47,000 --> 00:14:47,000
Right.

284
00:14:47,000 --> 00:14:50,000
So I will see you all in the next video.

285
00:14:50,000 --> 00:14:50,000
Thank you.