1
00:00:00,220 --> 00:00:07,610
Halaal, before going deep dive into the session, let's have a quick recap of what we all have until

2
00:00:07,650 --> 00:00:08,700
now in this session.

3
00:00:08,970 --> 00:00:15,210
So we have to import our data and doing lots of preprocessing, doing lots of analysis on our data.

4
00:00:15,450 --> 00:00:20,520
And we have come up with some various insights using some beautiful visas.

5
00:00:20,790 --> 00:00:27,120
And in the last sessions, we have somehow automate our analysis by writing these blocks of code in

6
00:00:27,120 --> 00:00:27,800
a function.

7
00:00:27,810 --> 00:00:33,530
And this is exactly my heat map that what we have done in all our previous session.

8
00:00:33,840 --> 00:00:39,050
So in this session, we have this assignment in which we have some problem with statement.

9
00:00:39,060 --> 00:00:44,360
So the very first is we have to perform analysis of location data points.

10
00:00:44,360 --> 00:00:50,390
So if let's say I'm going to check how exactly my data looks like or data frame looks like.

11
00:00:50,460 --> 00:00:53,800
So just call head over there and you will visualize overhead.

12
00:00:54,010 --> 00:00:56,130
Here you have two features.

13
00:00:56,250 --> 00:01:02,110
The very first is exactly the latitude and the second one is exactly your longitude.

14
00:01:02,280 --> 00:01:06,240
So considering both the features, you have to come up with some insight.

15
00:01:06,450 --> 00:01:08,960
So far, this is what I'm going to do over here.

16
00:01:08,970 --> 00:01:11,400
I'm just going to say BLT dot plot.

17
00:01:11,400 --> 00:01:16,250
And here I have to mention this, both the latitude and longitude.

18
00:01:16,260 --> 00:01:20,430
So the very first one, I'm going to say deserve all longitude.

19
00:01:20,670 --> 00:01:21,870
And the second feature.

20
00:01:21,870 --> 00:01:24,840
Exactly my D of latitude.

21
00:01:25,020 --> 00:01:31,170
And if you will pass shifts plus tab over here, you will get all the documentation, all the custom

22
00:01:31,170 --> 00:01:34,850
parameters over here, let's say if I'm going to execute it.

23
00:01:35,070 --> 00:01:39,410
So it will exactly return me this beautiful resource over here.

24
00:01:39,420 --> 00:01:43,590
But before executing it, you have to mention your color offered it up.

25
00:01:43,800 --> 00:01:51,450
Let's say I'm going to say are clouds so you can just go ahead with its documentation and you can check

26
00:01:51,450 --> 00:01:53,700
all the custom parameters over here.

27
00:01:53,880 --> 00:01:57,210
And these are basically ruffles here.

28
00:01:57,420 --> 00:02:01,170
I just want my data points in red color.

29
00:02:01,180 --> 00:02:01,740
That's it.

30
00:02:01,890 --> 00:02:08,070
And if I'm going to execute it, it will take some couple of seconds and it will exactly written some

31
00:02:08,070 --> 00:02:09,960
kind of beautiful result over here.

32
00:02:09,970 --> 00:02:13,350
So this will exactly determine this, some kind of complex.

33
00:02:13,460 --> 00:02:15,840
So let's say I have to modify over here.

34
00:02:15,840 --> 00:02:17,780
I'm going to assign my MSH.

35
00:02:18,030 --> 00:02:24,390
So here I'm going to say zero point five and let's say I have to assign my some X limit as well as some

36
00:02:24,600 --> 00:02:24,990
limit.

37
00:02:25,260 --> 00:02:32,300
Let's say I'm going to say my X limit is nothing, but let's say minus seventy four point two.

38
00:02:32,310 --> 00:02:40,350
You will see here all almost here, almost here, which is exactly my minus seventy four point two.

39
00:02:40,360 --> 00:02:47,400
So here I'm going to say minus seventy four point two and let's say from minus seventy four point two

40
00:02:47,850 --> 00:02:55,410
degrees, my nose seventy three point seven, which will exactly will be somewhere close to here.

41
00:02:55,800 --> 00:03:02,700
And after that, I'm also going to set my, let's say, y limit and y limit is nothing, but let's say

42
00:03:03,060 --> 00:03:07,200
starting from forty point five, or you can also see 40 points.

43
00:03:07,470 --> 00:03:08,280
It's on appeal.

44
00:03:08,850 --> 00:03:12,240
And the second one is exactly forty one.

45
00:03:12,240 --> 00:03:15,110
And let's say I have to customize this as well.

46
00:03:15,450 --> 00:03:17,700
So I'm going to say BLT dot figure.

47
00:03:18,090 --> 00:03:24,690
Just assign your own custom type, just press tab over here and you will get a parameter which is exactly

48
00:03:24,720 --> 00:03:25,590
this size.

49
00:03:25,800 --> 00:03:33,930
Let's say I just want our window side of to comma six and if you are going to execute it, it will take

50
00:03:33,930 --> 00:03:35,070
some couple of seconds.

51
00:03:35,160 --> 00:03:40,440
But this time you will definitely get some beautiful results from your previous.

52
00:03:40,440 --> 00:03:46,080
And now you will see here from this visual, you can easily come up with this insight.

53
00:03:46,080 --> 00:03:48,180
Yeah, add this reason.

54
00:03:48,180 --> 00:03:51,060
At this reason we are we have a darker density.

55
00:03:51,060 --> 00:03:55,820
It means at this particular reason we have some kind of higher rush.

56
00:03:55,860 --> 00:03:59,340
It means that the reason we have some kind of maximum.

57
00:03:59,340 --> 00:04:02,970
Right, let's say, is do I have to improve my analysis?

58
00:04:03,210 --> 00:04:07,950
So in some scenarios, you can go ahead with your spatial analysis.

59
00:04:07,950 --> 00:04:15,270
And this is exactly our next problem statement in which I have to perform this special analysis using

60
00:04:15,270 --> 00:04:23,190
heat map to get a clear cut of what exactly is a rush in New York or whatever latitude and longitude

61
00:04:23,190 --> 00:04:24,240
over here we have.

62
00:04:24,240 --> 00:04:30,900
But let's say if you have to conclude from this visual, then you will see this is exactly almost midtown

63
00:04:30,900 --> 00:04:31,620
Manhattan.

64
00:04:31,620 --> 00:04:33,750
So you can clearly see this.

65
00:04:33,750 --> 00:04:38,070
Midtown Manhattan is clearly a huge bright spot.

66
00:04:38,070 --> 00:04:46,870
And these are basically from my midtown to lower Manhattan, followed by basically upper Manhattan and

67
00:04:47,280 --> 00:04:48,870
heights of Brooklyn.

68
00:04:49,140 --> 00:04:54,630
Let's say I need this clear cut of what exactly the rush is for this.

69
00:04:54,630 --> 00:04:57,960
We can definitely go ahead with our spatial analysis.

70
00:04:58,320 --> 00:04:59,770
So let's say I have to pull.

71
00:04:59,830 --> 00:05:05,920
From this analysis on some particular day, let's say on weekend, so that if I have to add some filter

72
00:05:05,920 --> 00:05:14,200
over here, I'm going to say, my dear of every day it calls to let's say for Sunday, let's say I just

73
00:05:14,200 --> 00:05:16,180
need data of Sunday.

74
00:05:16,180 --> 00:05:19,360
So I have to just pass this filter in my data frame.

75
00:05:19,660 --> 00:05:25,750
Alexei, this final data frame name is nothing but like tedious on a score out, just executed.

76
00:05:25,750 --> 00:05:29,780
And if I'm going to call a shape or whatever.

77
00:05:30,470 --> 00:05:36,220
Now you'll see it had that much number of thought and it has that much number of columns.

78
00:05:36,370 --> 00:05:42,340
And let's say if I'm going to call ahead over there now, you would visualize how exactly your data

79
00:05:42,340 --> 00:05:49,210
from looks like now what you have to do, you have to group your data on the basis of this latitude

80
00:05:49,420 --> 00:05:57,520
and longitude because you need what exactly is a rush on particular city, on particular latitude and

81
00:05:57,520 --> 00:05:58,060
longitude.

82
00:05:58,060 --> 00:06:03,040
It means you have to group your data on the basis of this latitude and longitude.

83
00:06:03,280 --> 00:06:03,900
For this.

84
00:06:03,910 --> 00:06:10,180
I'm just going to say, Dave, underscore out Dot Grassby, I have to call this group by and very first

85
00:06:10,180 --> 00:06:13,310
I have to group my data on the basis of this latitude.

86
00:06:13,690 --> 00:06:18,070
After that I have to go it again on the basis of longitude.

87
00:06:18,070 --> 00:06:25,420
Once I have all this stuff I have to access this day and once I will access this every day, I have

88
00:06:25,420 --> 00:06:27,890
to just call this count or there.

89
00:06:28,120 --> 00:06:31,000
And if I'm going to execute it, I will see.

90
00:06:31,270 --> 00:06:35,340
With respect to all this team, you have some account value assigned.

91
00:06:35,650 --> 00:06:39,160
Now, let's say I have to convert this into my some data frames for this.

92
00:06:39,160 --> 00:06:42,510
I have to just call this reset and index over here.

93
00:06:42,940 --> 00:06:43,360
So it will.

94
00:06:43,360 --> 00:06:45,010
Exactly returning my data frame.

95
00:06:45,010 --> 00:06:51,070
I have to store it somewhere as let's say I'm going to say data frame name is nothing, but that's Arush

96
00:06:51,070 --> 00:06:52,210
just executed.

97
00:06:52,210 --> 00:06:58,360
And if I'm going to print it now, you will see with respect to this latitude and longitude, you have

98
00:06:58,360 --> 00:06:59,680
that much brush.

99
00:07:00,070 --> 00:07:06,760
It means with respect to this latitude and longitude, you have that much number of troops.

100
00:07:06,940 --> 00:07:11,470
And if you want to modify your column, you can definitely come up with that.

101
00:07:11,760 --> 00:07:17,200
I'm going to say the DOT columns and my column name is actually the very first one is latitude.

102
00:07:17,560 --> 00:07:23,440
The second one is, let's say longitude, and the third one, let's say a number of trips.

103
00:07:23,440 --> 00:07:25,720
So I'm going to say number of trips.

104
00:07:25,930 --> 00:07:27,070
So just executed.

105
00:07:27,070 --> 00:07:29,720
And if, again, I'm going to print that said.

106
00:07:29,740 --> 00:07:34,180
So this is exactly the data frame that you have to consider to perform.

107
00:07:34,180 --> 00:07:40,840
You're some kind of a spatial analysis depending upon what problem statement you have to perform your

108
00:07:40,990 --> 00:07:42,280
spatial analysis.

109
00:07:42,310 --> 00:07:46,530
You need some external modules, you need some heat map.

110
00:07:46,540 --> 00:07:54,220
So for this, I'm going to say from this podium, and if you haven't installed your solium, you guys

111
00:07:54,220 --> 00:08:03,580
can simply install using this PIP install SOLIUM, you can simply execute this one and it will install

112
00:08:03,580 --> 00:08:05,760
your Foleo in your environment.

113
00:08:06,010 --> 00:08:12,850
So from this FOLIA, what you have installed over here, you have to import your some module, which

114
00:08:12,850 --> 00:08:14,800
is exactly my plugin.

115
00:08:14,800 --> 00:08:21,220
So I'm going to say this plugins and I have to import something known as which is exactly my heat map,

116
00:08:21,520 --> 00:08:22,840
so just execute it.

117
00:08:22,840 --> 00:08:30,930
And now what I have to do, let's say I have to also import my so I'm going to say import your folia

118
00:08:31,180 --> 00:08:32,950
after importing or forelimb.

119
00:08:33,160 --> 00:08:39,060
Let's say I need some base map so that I can showcase my visual on top of that.

120
00:08:39,310 --> 00:08:43,560
So for days what I'm going to do, I'm just going to use this for longer.

121
00:08:43,600 --> 00:08:47,740
This I'm going to say for forelimb dot map here.

122
00:08:47,740 --> 00:08:54,580
It has some inbuilt function and if I'm going to execute it, it will return with some beautiful, inbuilt

123
00:08:54,880 --> 00:08:56,350
world map over here.

124
00:08:56,350 --> 00:08:58,270
And this is exactly that.

125
00:08:58,480 --> 00:09:03,460
You can zoom in, zoom out and various functionalities assigned to this map.

126
00:09:03,640 --> 00:09:05,230
Let's say I'm going to say it is nothing.

127
00:09:05,230 --> 00:09:08,740
It is just my base map just executed now.

128
00:09:08,920 --> 00:09:14,710
And now is the time to perform your spatial analysis using this heat map.

129
00:09:14,980 --> 00:09:18,970
So here I'm just going to say you have to use this heat map.

130
00:09:18,970 --> 00:09:20,530
So what exactly is the heat map?

131
00:09:20,770 --> 00:09:28,000
So wherever my count will be, higher heat map will reflect that has a higher density.

132
00:09:28,300 --> 00:09:28,900
That's it.

133
00:09:28,900 --> 00:09:33,580
That's all about my core idea behind heat map for this.

134
00:09:33,580 --> 00:09:37,300
What I'm going to do in this Rust column, I have something.

135
00:09:37,300 --> 00:09:41,590
So in this heat, my function, you have to just pass your data frame.

136
00:09:41,590 --> 00:09:42,130
That's it.

137
00:09:42,310 --> 00:09:45,850
And here you have some custom parameter, the very first one.

138
00:09:45,850 --> 00:09:47,260
What exactly is the frame?

139
00:09:47,260 --> 00:09:53,650
Then you have all this custom parameter that has some defined value, that has some predefined values

140
00:09:53,650 --> 00:09:58,720
defined by my python developers that say I have to customize my legs.

141
00:09:58,750 --> 00:09:59,600
I'm going to say my.

142
00:09:59,900 --> 00:10:07,880
Parameter values, 20 mile radii, or you can see a radius, whatever you can name it is my radius is

143
00:10:07,880 --> 00:10:14,860
nothing more, let's say 15 and whatever heat map it will return me, I have to simply add it to on

144
00:10:14,900 --> 00:10:16,490
the top of my base map.

145
00:10:16,700 --> 00:10:22,700
So for this, I have a function which is exactly adding a score to and here I have to mention my base

146
00:10:22,730 --> 00:10:23,030
map.

147
00:10:23,450 --> 00:10:28,070
Once I have all this stuff, then Simples and I have to print my basement.

148
00:10:28,070 --> 00:10:28,650
That's it.

149
00:10:29,000 --> 00:10:34,870
So just execute the SAT and it will take a while to showcase your beautiful heat map.

150
00:10:35,250 --> 00:10:36,210
You will see over here.

151
00:10:36,250 --> 00:10:38,420
This is exactly a beautiful heat map.

152
00:10:38,420 --> 00:10:44,030
And if you are going to zoom in this now, you can easily visualize it here easily.

153
00:10:44,030 --> 00:10:46,790
You can easily see this is exactly what Washington.

154
00:10:46,980 --> 00:10:48,200
Let me zoom in again.

155
00:10:48,200 --> 00:10:49,370
Let me zoom in again.

156
00:10:49,370 --> 00:10:52,260
And this is exactly where all these cities over here.

157
00:10:52,550 --> 00:10:59,220
Let me zoom in again and you can easily showcase all these conclusions from this we saw.

158
00:10:59,240 --> 00:11:04,910
And now you can definitely come up with some meaningful insight from this spatial analysis.

159
00:11:05,090 --> 00:11:10,960
Whereas if you are going to compare this, you can compare this heat map from the other one.

160
00:11:11,150 --> 00:11:18,050
You can definitely come up with some meaningful insights from this spatial rather than the previous

161
00:11:18,440 --> 00:11:23,510
disadvantage of using your patient analysis, using your heat map concept.

162
00:11:23,510 --> 00:11:27,610
And from this analysis, we can definitely come up with this insight.

163
00:11:27,790 --> 00:11:32,450
Yeah, this is The Zone, which is exactly my midtown Manhattan.

164
00:11:32,450 --> 00:11:38,960
And this is exactly a huge bright is what it means in this in this almost in the zone.

165
00:11:39,170 --> 00:11:42,110
We have a maximum number of rights in this zone.

166
00:11:42,440 --> 00:11:49,970
So whenever a user is going to Boca Gabb from this particular zone so we can offer some discount to

167
00:11:49,970 --> 00:11:51,110
increase my sales.

168
00:11:51,230 --> 00:11:54,280
So that's the type of the season we can with that.

169
00:11:54,590 --> 00:11:58,750
So that's the type of analysis how you can go ahead with the problem statement.

170
00:11:59,030 --> 00:12:05,170
So let's go ahead with our next statement in which I have to automate all this stuff.

171
00:12:05,390 --> 00:12:11,070
Whatever I have done over here, I have to just create a function in which I have.

172
00:12:11,090 --> 00:12:14,100
Right all these blocks of code for this.

173
00:12:14,150 --> 00:12:20,150
What I'm going to do, I'm just going to define a function that's a function name is DOT and whatever

174
00:12:20,150 --> 00:12:23,120
parameter it will receive me, I'm going to define it later.

175
00:12:23,600 --> 00:12:30,410
So what exactly was my very first task in the very first task I have as a data frame, depending upon

176
00:12:30,410 --> 00:12:34,820
my condition, depending upon the day on which I had to do this analysis.

177
00:12:34,820 --> 00:12:38,490
Let's say at this time I have to do analysis for some particular date.

178
00:12:38,810 --> 00:12:44,870
So here I'm going to say my weekday equally, because today it means this disvalue.

179
00:12:45,170 --> 00:12:48,170
Basically you are going to receive from functions here.

180
00:12:48,170 --> 00:12:52,790
The very first parameter is your function, let's say the very first one is data from the second one

181
00:12:52,790 --> 00:12:56,150
is the day that these are exactly both parameters.

182
00:12:56,150 --> 00:13:00,950
After what I have done, I have basically called this group by Auteur's here.

183
00:13:00,950 --> 00:13:07,430
I am going to say I have to just call this or you can just copy this from here and you have to just

184
00:13:07,430 --> 00:13:08,290
paste over here.

185
00:13:08,300 --> 00:13:08,760
That's it.

186
00:13:09,350 --> 00:13:17,510
Now, here you have to mention either you can store it in some data frame or you can directly pass this

187
00:13:17,510 --> 00:13:17,960
in some.

188
00:13:18,410 --> 00:13:23,570
Lexing will directly say, I have to just pass this stuff in my heat map.

189
00:13:23,810 --> 00:13:25,430
And your parameter.

190
00:13:25,430 --> 00:13:27,350
What was mine here?

191
00:13:27,350 --> 00:13:33,890
I have something which is my zoom parameter and I have something which is exactly my, let's say, radius

192
00:13:33,890 --> 00:13:34,550
parameter.

193
00:13:34,550 --> 00:13:40,790
My radius was, I think 50 and whatever heat map it will return me, I have to just add it to my best

194
00:13:40,790 --> 00:13:41,600
maps for this.

195
00:13:41,600 --> 00:13:47,560
I'm going to say add in this score to and here I have to see what exactly is my piece map.

196
00:13:47,570 --> 00:13:50,060
So very first you have to define your base map as well.

197
00:13:50,360 --> 00:13:57,710
So here I am going to say my base is nothing but this forelimb dot map and let's say I'm going to store

198
00:13:57,710 --> 00:13:57,880
it.

199
00:13:57,890 --> 00:14:00,360
So here my base map is this one.

200
00:14:00,390 --> 00:14:00,700
Yeah.

201
00:14:01,100 --> 00:14:02,140
And what's happening?

202
00:14:02,210 --> 00:14:03,950
All this stuff is what I have to do.

203
00:14:03,950 --> 00:14:09,250
I have to return this base map, whatever base map I have over here.

204
00:14:09,260 --> 00:14:10,710
So I have to simply return it.

205
00:14:11,030 --> 00:14:16,610
So now I have to just execute the sale and now I have to simply call this function here.

206
00:14:16,610 --> 00:14:22,130
I'm going to say I have to call this function what exactly my data from, which is exactly my idea.

207
00:14:22,190 --> 00:14:27,330
And let's say I just need my own analysis for that Saturday.

208
00:14:27,530 --> 00:14:30,320
So here I have to just past Saturday.

209
00:14:30,320 --> 00:14:37,130
And if you are going to execute it, you will get this type of amazing result from your huge chunk of

210
00:14:37,130 --> 00:14:38,150
data next year.

211
00:14:38,170 --> 00:14:40,040
I have to just zoom in this.

212
00:14:40,040 --> 00:14:41,750
Let me again zoom in it.

213
00:14:41,990 --> 00:14:45,000
Let me again zoom in it and you will observe.

214
00:14:45,020 --> 00:14:54,320
You can clearly observe is still your Mad Hatter is still your huge bright spot for your Saturday as

215
00:14:54,320 --> 00:14:54,560
well.

216
00:14:54,860 --> 00:14:58,880
But it's still there is some modification you will observe from my.

217
00:14:59,690 --> 00:15:06,170
One and in this one, yeah, you can definitely see this difference, so I hope you will love this session

218
00:15:06,170 --> 00:15:13,490
very much and how I have to meet all the analysts, how exactly I have performed is analysis on data.

219
00:15:14,060 --> 00:15:15,470
I hope you will love it very much.

220
00:15:15,590 --> 00:15:16,230
Thank you.

221
00:15:16,500 --> 00:15:18,350
How nice to keep learning.

222
00:15:18,350 --> 00:15:19,100
Keep growing.

223
00:15:19,310 --> 00:15:20,150
Keep practicing.