1
00:00:00,110 --> 00:00:08,390
Halaal, before we go into the session, let's have a quick recap of what we have done in this project.

2
00:00:08,680 --> 00:00:14,580
So in the very first session, we have prepared our data so that, again, we will analyze our data

3
00:00:14,580 --> 00:00:17,580
and find some friends, find some meaningful insight.

4
00:00:17,820 --> 00:00:24,990
And again, we will be such a machine learning model that can predict whether a particular booking is

5
00:00:24,990 --> 00:00:26,280
going to cancel or not.

6
00:00:26,430 --> 00:00:28,170
So we have to build such a model.

7
00:00:28,440 --> 00:00:32,280
But before building a model, you have to understand your data.

8
00:00:32,280 --> 00:00:37,740
And the best way to understand the data is by performing your last analysis on your data.

9
00:00:38,070 --> 00:00:44,040
So here in the previous session, we have performed lots of preparation, our data by just creating

10
00:00:44,040 --> 00:00:44,790
this filter.

11
00:00:44,940 --> 00:00:48,540
So in this session, what we have to do, we have to analyze our data very first.

12
00:00:48,540 --> 00:00:49,910
We have to understand our data.

13
00:00:50,190 --> 00:00:55,680
So the very first problem statement is where do the guests come from?

14
00:00:55,890 --> 00:01:00,860
The very first formal statement, you have to understand your guest.

15
00:01:00,870 --> 00:01:05,380
You have to understand where users from which location they are coming.

16
00:01:05,850 --> 00:01:08,850
So this is exactly the very first problem statement.

17
00:01:09,120 --> 00:01:16,230
So let me say, whenever you are going to perform your spatial analysis, so what exactly is spatial

18
00:01:16,230 --> 00:01:16,920
analysis?

19
00:01:17,310 --> 00:01:23,760
So spatial analysis is all about whenever you are going to visualize the data on some map so that you

20
00:01:23,760 --> 00:01:28,800
will get a clear cut yapped from which which location your guests are coming.

21
00:01:29,130 --> 00:01:31,670
So let me perform spatial analysis over there.

22
00:01:32,010 --> 00:01:37,230
But before performing it, I need some data so that I can easily perform.

23
00:01:37,230 --> 00:01:38,850
That is patient analysis.

24
00:01:38,850 --> 00:01:41,180
So very first for I'm going to do it here.

25
00:01:41,190 --> 00:01:44,460
Here I'm going to say data off here.

26
00:01:44,460 --> 00:01:47,040
I have a feature which is underscore canceled.

27
00:01:47,280 --> 00:01:54,390
And here I'm going to say it is equally close to zero because I just need that data that are my valid

28
00:01:54,570 --> 00:01:55,080
bookings.

29
00:01:55,080 --> 00:01:58,250
And wherever this is cancellation, it goes to zero.

30
00:01:58,260 --> 00:02:00,000
So this is exactly the invalid booking.

31
00:02:00,300 --> 00:02:06,660
So I have to just pass this filter in so that I will get my filter data frame.

32
00:02:07,020 --> 00:02:11,550
And on this filter data frame, I have to access my country.

33
00:02:11,550 --> 00:02:13,350
So I'm just going to access my country.

34
00:02:13,590 --> 00:02:21,540
And on this, if I'm going to call this value on a school counselor, dear, now you will get some idea

35
00:02:21,750 --> 00:02:24,960
from which, which country, who users are coming.

36
00:02:24,960 --> 00:02:28,830
You will see your Portugal and some European countries.

37
00:02:29,010 --> 00:02:30,810
But let's say I just need a clear cut.

38
00:02:30,810 --> 00:02:34,050
I just need to visualize this data on some map.

39
00:02:34,260 --> 00:02:38,280
So let me very first convert all this stuff into some data frames.

40
00:02:38,310 --> 00:02:43,350
I'm just going to say just gonna reset an index and I'll get executed.

41
00:02:43,350 --> 00:02:46,240
And this is your amazing data frame that you have to consider.

42
00:02:46,530 --> 00:02:48,260
So let me name this data frame.

43
00:02:48,300 --> 00:02:54,750
Let's say country score lies, underscore data and just execute it.

44
00:02:54,750 --> 00:03:01,410
And if I'm going to print it, you can just print it using this country on a scale and data and let's

45
00:03:01,410 --> 00:03:04,290
say I have to modify my column name.

46
00:03:04,290 --> 00:03:11,700
So I'm going to say this DOT columns, let me assign my own column name to the very first column name

47
00:03:11,700 --> 00:03:13,890
and exactly my country.

48
00:03:13,890 --> 00:03:18,930
And second column name is exactly my number of guest.

49
00:03:19,110 --> 00:03:25,250
And once I have all this stuff, so what I have to do, I have to simply print my data and exit.

50
00:03:25,530 --> 00:03:28,680
Now you will figure out this is exactly the data set.

51
00:03:28,950 --> 00:03:35,940
This is exactly that data frame that you have to consider, especially for this problem statement.

52
00:03:35,940 --> 00:03:37,330
Where do the guest come from?

53
00:03:37,560 --> 00:03:42,640
So now what you need, you need some external modules so that you can visualize.

54
00:03:42,660 --> 00:03:47,280
So basically you need a library, which is exactly my volume.

55
00:03:47,290 --> 00:03:53,560
So if you happen to start earlier, you guys can simply install using PIP, install FOLIA.

56
00:03:53,700 --> 00:03:55,260
So just execute this.

57
00:03:55,260 --> 00:03:58,920
Come on and your liberi get successfully executed.

58
00:03:59,100 --> 00:04:05,850
Now what I have to do so from this forelimb library, I have something Jusu so I'm just going to say

59
00:04:05,850 --> 00:04:12,900
don't plug ins, just press tab over here and you will figure out this is exactly the module.

60
00:04:12,930 --> 00:04:16,110
So from this I have to import something known as heat map.

61
00:04:16,410 --> 00:04:17,850
So it just execute it.

62
00:04:17,860 --> 00:04:26,010
Now, if using this volume, if I am going to call my map over there, which is exactly inbuilt function

63
00:04:26,010 --> 00:04:30,650
inside this volume, now you will figure out this is my global map.

64
00:04:30,660 --> 00:04:36,450
So the top of this base map, you can dump it as base maps on top of this base map.

65
00:04:36,750 --> 00:04:44,400
I have to visualize my map or I guess I had realize my visual depending upon what type of visual this

66
00:04:44,400 --> 00:04:45,500
data will me.

67
00:04:45,900 --> 00:04:48,570
So let's say this is exactly my basement.

68
00:04:48,570 --> 00:04:53,550
So I'm going to say this is exactly my base map and let me just execute it.

69
00:04:53,940 --> 00:04:58,530
Now, what you have to do, we have to import very basic stuff.

70
00:04:58,530 --> 00:04:59,670
You have to import your.

71
00:05:00,470 --> 00:05:06,830
So if you haven't installed plotless to install using this pipe installed properly, and if you guys

72
00:05:06,830 --> 00:05:14,300
don't know what exactly, the Pratley subplot laser advanced level data will liability that is extensively

73
00:05:14,300 --> 00:05:16,850
used for deployment level results.

74
00:05:17,360 --> 00:05:26,570
So let's say I'm just going to say import tautly, DOT Xpress and I have to create its Elías as, let's

75
00:05:26,570 --> 00:05:29,360
say oops and just execute it.

76
00:05:29,360 --> 00:05:33,980
Now, using this because I have something known as code of that map.

77
00:05:34,280 --> 00:05:40,070
And if you will pass to or you will figure out all your custom parameters.

78
00:05:40,070 --> 00:05:42,980
So then you have to perform this spatial analysis.

79
00:05:43,580 --> 00:05:46,790
There are two main function that are extensively used.

80
00:05:47,090 --> 00:05:50,030
The first one, it is exactly a heat map.

81
00:05:50,230 --> 00:05:55,060
Either you can consider this heat map or you can go ahead with this map.

82
00:05:55,070 --> 00:06:01,370
There's some minor difference between both and you will figure out there are some custom parameter.

83
00:06:01,380 --> 00:06:07,310
What is a data frame, latitude and longitude, all these different different parameters here?

84
00:06:07,310 --> 00:06:12,790
I have to say, my very first parameter is country and a school, which is called data after eight.

85
00:06:12,800 --> 00:06:18,950
What I have to do, I have a parameter which is exactly my location, which is exactly this one.

86
00:06:19,220 --> 00:06:22,960
It means I have to plot my country to that map.

87
00:06:23,150 --> 00:06:26,210
So for this I'm going to say a school and it's data.

88
00:06:26,210 --> 00:06:32,200
And in this I have a feature, which is exactly my so I'm going to say this is exactly my country.

89
00:06:32,510 --> 00:06:40,730
So after having all these stuff over here, I have again a parameter over here, which is exactly my

90
00:06:40,730 --> 00:06:45,480
color parameter, because to my quarterback map, I have to assign some color.

91
00:06:45,710 --> 00:06:49,820
So here I am going to say I have to assign color on the basis of number of guest.

92
00:06:50,070 --> 00:06:51,950
It means more than a number of guest.

93
00:06:51,950 --> 00:06:54,680
We have higher the density of the color.

94
00:06:54,680 --> 00:07:02,300
FILBY So here I'm going to say it is nothing but my number of you can press tab as well, which is exactly

95
00:07:02,300 --> 00:07:04,760
my number of guest.

96
00:07:04,940 --> 00:07:07,910
And it's still you have some dozens of parameters.

97
00:07:07,910 --> 00:07:11,240
You can play it whatever parameter you want.

98
00:07:11,420 --> 00:07:16,130
So here I have some more parameter which is exactly my who are on the score.

99
00:07:16,800 --> 00:07:22,770
Whenever you are going to hover your mouse on your visual, what exactly you want to reflect.

100
00:07:22,790 --> 00:07:28,450
So for this, I'm just going to say or underscore name, which is exactly this one.

101
00:07:28,460 --> 00:07:33,200
So I'm just going to say I just need to reflect my country names for this.

102
00:07:33,200 --> 00:07:37,730
I'm just going to say this is nothing but my this country.

103
00:07:37,910 --> 00:07:43,010
After having all this stuff, let's say I have to assign my subtitles for this.

104
00:07:43,010 --> 00:07:47,940
I'm just going to say title is nothing, but let's say whole country of guest.

105
00:07:48,170 --> 00:07:51,120
So home country of guests.

106
00:07:51,350 --> 00:07:56,380
So this is exactly my title of my quadruped map softheaded.

107
00:07:56,420 --> 00:07:59,540
What we have to do, let's say I'm just going to store it somewhere else.

108
00:07:59,690 --> 00:08:07,100
So I'm just going to say this is exactly my map underscore guest once having all this stuff on this

109
00:08:07,100 --> 00:08:08,270
map, underscore guest.

110
00:08:08,270 --> 00:08:10,790
I have to just call my show function.

111
00:08:10,790 --> 00:08:11,360
That's it.

112
00:08:11,570 --> 00:08:18,650
And if I'm going to execute this well now you will see over here, this is amazing quadruplet map and

113
00:08:18,650 --> 00:08:21,430
this is exactly your color bar over here.

114
00:08:21,800 --> 00:08:25,160
So almost observe over here almost.

115
00:08:25,160 --> 00:08:32,690
There are 80 to 85 percent of countries that have almost between zero to five thousand guests.

116
00:08:33,290 --> 00:08:39,740
But yeah, there are few countries, let's say, which are exactly my Portugal and some European countries

117
00:08:39,950 --> 00:08:42,350
where we have a maximum number of guest.

118
00:08:42,350 --> 00:08:45,500
So that's a type of entrance, how you can fetch stronger data.

119
00:08:45,770 --> 00:08:53,390
So let's go ahead with our next statement in which I have to analyze how much do guest pay for a room

120
00:08:53,390 --> 00:08:54,230
per night.

121
00:08:54,500 --> 00:09:01,520
So for this, let me Kollar had on my data frame to get a preview how exactly it looks like you will

122
00:09:01,520 --> 00:09:04,970
see this is exactly the data set that you have over here.

123
00:09:05,270 --> 00:09:07,730
But very first you need somebody looking.

124
00:09:07,730 --> 00:09:10,940
So I'm just going to say data of is on this call.

125
00:09:11,120 --> 00:09:13,940
Cancel it close to zero.

126
00:09:13,940 --> 00:09:18,060
I have to just pass this in my this one here.

127
00:09:18,080 --> 00:09:22,700
I'm going to say this is nothing but let's say my data too.

128
00:09:22,700 --> 00:09:30,860
So I have to just executed and now you will figure out in your problem statement you have to analyze

129
00:09:30,860 --> 00:09:34,310
how much do guest pay for night.

130
00:09:34,490 --> 00:09:40,940
It means you just need price distribution of each of the room type.

131
00:09:41,180 --> 00:09:47,210
So for this, whenever you need a distribution, either you can go ahead with your distribution function

132
00:09:47,210 --> 00:09:54,010
of Seabourne, either of a plot, or you can consider some fancy stuff like box plot.

133
00:09:54,020 --> 00:09:59,630
So I'm just going to say Asness Dot here, I have a very handy function, which is exact.

134
00:09:59,910 --> 00:10:06,860
My doctors, I'm just going to say it is exactly my box, but if you will pass shift BASTABLE here,

135
00:10:06,900 --> 00:10:08,800
you will get all the documentation.

136
00:10:08,820 --> 00:10:09,840
What is your X?

137
00:10:10,170 --> 00:10:10,680
What is it?

138
00:10:10,710 --> 00:10:11,160
Why?

139
00:10:11,160 --> 00:10:11,550
What is it?

140
00:10:11,580 --> 00:10:13,170
Who parameter humans?

141
00:10:13,170 --> 00:10:16,670
On which basis you have to split your box plot.

142
00:10:16,980 --> 00:10:21,210
So basically on this exact six what I need.

143
00:10:21,210 --> 00:10:21,900
Exactly.

144
00:10:21,930 --> 00:10:29,940
So let me say very first on this data to if I'm going to call my columns over here, you will see you

145
00:10:29,940 --> 00:10:32,610
have all your column names over here.

146
00:10:32,880 --> 00:10:40,350
So on this X axis, you exactly need your reserved room type, which is exactly this one.

147
00:10:40,350 --> 00:10:44,820
So I'm just going to copy from here and let me just paste it.

148
00:10:45,000 --> 00:10:48,930
And this is exactly on your x axis after it.

149
00:10:48,930 --> 00:10:55,260
On Y axis, you have to assign some your price because you need a distribution with the respective price.

150
00:10:55,500 --> 00:10:58,710
So on y axis, I'm going to say it is nothing but my ADR.

151
00:10:59,010 --> 00:11:02,370
And after it I have something which is exactly my hue.

152
00:11:02,760 --> 00:11:08,780
So here I'm going to say I just need distribution, both of resort as well as for that.

153
00:11:08,820 --> 00:11:11,870
So here I'm going to say you go to that operator.

154
00:11:11,880 --> 00:11:13,950
I have to mention my data frame as well.

155
00:11:13,960 --> 00:11:20,610
So I'm going to say data is nothing but basically my data to call data to the current data free on which

156
00:11:20,610 --> 00:11:21,610
we are working.

157
00:11:22,080 --> 00:11:29,640
So if let's say I have to customize this box as well, so I'm going to say PLT or figure I have to assign

158
00:11:29,640 --> 00:11:30,480
my own figures.

159
00:11:30,790 --> 00:11:37,490
So take side, let's say 12, Gunma eight, and let me assign some title as well.

160
00:11:37,500 --> 00:11:42,600
So I'm going to say t dot data and what exactly is meant to my title.

161
00:11:42,650 --> 00:11:42,990
Nothing.

162
00:11:42,990 --> 00:11:52,380
But let's say price of room types per night and per person.

163
00:11:52,410 --> 00:11:59,820
Or you can say only person once having this title you have to assign some X label, some Y level as

164
00:11:59,820 --> 00:12:00,000
well.

165
00:12:00,390 --> 00:12:07,150
So here I am going to say my X label is nothing but let's say my room type to her.

166
00:12:07,180 --> 00:12:11,430
I'm going to say X level is nothing but my type.

167
00:12:11,610 --> 00:12:15,530
After signing or X label, you have to assign Uruguay label as well.

168
00:12:15,810 --> 00:12:20,670
So my Y level is nothing but let's say price in euros.

169
00:12:20,670 --> 00:12:27,840
So I'm going to say price in euro after having all this is what you have to you have to simply show

170
00:12:27,840 --> 00:12:30,200
your matplotlib this to it.

171
00:12:30,330 --> 00:12:37,230
And here you have one more function, which is exactly what leakin because you have to show Leegin with

172
00:12:37,230 --> 00:12:40,830
respect to the result as well as with respect to your city hotel as well.

173
00:12:40,860 --> 00:12:46,980
So if I'm going to ask you that, you will see this amazing visual with respect to each of your room

174
00:12:46,980 --> 00:12:47,760
type over here.

175
00:12:48,060 --> 00:12:55,650
You will see this this blue this blue distribution is exactly a resort hotel and this orange one with

176
00:12:55,650 --> 00:12:56,850
respect to city hotel.

177
00:12:57,120 --> 00:13:07,490
But you will see the middle line is exactly your median, whereas this one is exactly four hundred percentile

178
00:13:07,560 --> 00:13:08,090
data.

179
00:13:08,130 --> 00:13:12,810
And this this one is exactly what, twenty fifth percentile data.

180
00:13:12,810 --> 00:13:21,440
And this one is exactly where 70 percent data and this just list is exactly zero percent data.

181
00:13:21,630 --> 00:13:24,110
So you can easily conclude from this.

182
00:13:24,120 --> 00:13:33,540
Yeah, the best distribution with respect to City Hotel is almost with my G type, whereas if I will

183
00:13:33,540 --> 00:13:40,890
talk about with respect to my resort hotel, it's the best distribution of price is almost 10 to with

184
00:13:40,890 --> 00:13:43,290
respect to this at room type.

185
00:13:43,290 --> 00:13:48,960
And what our data point that you will see over here, these are exactly your high values.

186
00:13:49,110 --> 00:13:52,090
Or you can see these are exactly the outliers.

187
00:13:52,140 --> 00:13:55,390
So you can definitely conclude as much as you can.

188
00:13:55,410 --> 00:13:56,480
So that's all about this.

189
00:13:56,500 --> 00:13:58,380
I hope you love the session very much.

190
00:13:58,530 --> 00:14:06,150
And if you have, don't just post your doubts in your Q&A section or via your personal mode of communication

191
00:14:06,150 --> 00:14:06,930
with me as well.

192
00:14:07,020 --> 00:14:08,050
Whatever you want.

193
00:14:08,190 --> 00:14:09,020
So thank you.

194
00:14:09,030 --> 00:14:10,000
Have a nice day.

195
00:14:10,020 --> 00:14:10,920
Keep learning.

196
00:14:10,920 --> 00:14:11,820
Keep growing.

197
00:14:11,820 --> 00:14:12,690
Keep practicing.