1 00:00:00,180 --> 00:00:05,970 Halaal, let's have a quick overview of what we have done in our previous session, in the previous 2 00:00:05,970 --> 00:00:06,390 session. 3 00:00:06,420 --> 00:00:13,320 We have imported our data and we have collected our entire data so that in all of our upcoming session, 4 00:00:13,470 --> 00:00:17,540 we will do the analysis we will do with our beautiful results. 5 00:00:17,970 --> 00:00:20,050 So that's what we have done in the session. 6 00:00:20,580 --> 00:00:26,610 So let me open the Sandeman for this session, which is exactly this one where we have to prepare our 7 00:00:26,610 --> 00:00:33,810 data for the analysis purple, because you will see this is my entire dataset, but still I have to 8 00:00:33,810 --> 00:00:41,070 do lots of preprocessing, lots of data preparation technique so that Antine, we will end up having 9 00:00:41,070 --> 00:00:43,770 some meaningful insights from this data. 10 00:00:44,220 --> 00:00:50,360 So what I am going to do now, let me copy this data frame, which is exactly my final. 11 00:00:50,370 --> 00:00:58,680 So I'm going to see a final copy because final is exact, actually the frame and whatever modification 12 00:00:58,680 --> 00:01:05,040 I am going to do now, I'm going to do in this D.F. That's why I am going to copy this. 13 00:01:05,220 --> 00:01:07,140 So I'm just going to suggest execute it. 14 00:01:07,140 --> 00:01:13,470 And if I'm going to call this had over there, you will see this is exactly your preview of the data 15 00:01:13,470 --> 00:01:17,130 frame on which you have to do certain kind of analysis. 16 00:01:17,370 --> 00:01:23,340 And if I'm going to say what exactly the data types of each and every variable on each and every column, 17 00:01:23,340 --> 00:01:26,850 you can call this data and you will also help. 18 00:01:27,120 --> 00:01:35,970 This data is still of object data type because Banas by default assign this date time as your objective 19 00:01:35,970 --> 00:01:36,380 to type. 20 00:01:36,600 --> 00:01:40,770 But we know this data and support some timestamp format. 21 00:01:41,130 --> 00:01:43,320 It means we have to convert this. 22 00:01:43,500 --> 00:01:47,360 We have to convert this data into some timestamp format. 23 00:01:47,520 --> 00:01:54,030 So for this, what I'm going to do, I'm just going to say b'day dot to underscore the time. 24 00:01:54,060 --> 00:01:58,710 And here I what I have to say, I have to send this daytimes here. 25 00:01:58,710 --> 00:02:04,070 I'm going to say I have to send this date slash time, which is exactly this one. 26 00:02:04,410 --> 00:02:11,340 And here, if you will shift plus tab, you will get all your documentation of this function, whatever 27 00:02:11,340 --> 00:02:13,200 custom parameters it will receive. 28 00:02:13,230 --> 00:02:20,040 So here you have a barometer, which is exactly my format, but it means in what format you have to 29 00:02:20,040 --> 00:02:21,730 convert this into daytime. 30 00:02:21,930 --> 00:02:26,840 So here I'm going to say I have to mention some format to some custom format here. 31 00:02:26,880 --> 00:02:29,730 I'm going to say my format is nothing. 32 00:02:29,730 --> 00:02:33,790 But let's say I'm going to say Munt very first. 33 00:02:33,840 --> 00:02:37,610 I have to say Munt, then I have to say date. 34 00:02:37,620 --> 00:02:41,910 Then I have to say my total one, which is exactly eer. 35 00:02:41,910 --> 00:02:48,390 So I'm going to say this eer once I have this format, then I have to mention one hour, minute and 36 00:02:48,390 --> 00:02:49,390 second as well. 37 00:02:49,650 --> 00:02:56,970 So now I'm going to see this placenta's capital at it means I will then I have to mention something 38 00:02:56,970 --> 00:03:02,970 my mainard so I'm going to say capital M which refers to my Mynatt that I have to mention something 39 00:03:02,970 --> 00:03:04,550 which is exactly my second. 40 00:03:04,740 --> 00:03:08,370 So here I have to say this is exactly my second one. 41 00:03:08,490 --> 00:03:13,240 I will do all this stuff then I have to update my this date time as well. 42 00:03:13,410 --> 00:03:18,460 So here I'm going to say I have to update it as you can press that as well. 43 00:03:18,720 --> 00:03:21,810 And this is exactly that feature that you have to update. 44 00:03:22,020 --> 00:03:27,510 Once you will perform all these stuff, then what you have to do, you have to just executed. 45 00:03:27,810 --> 00:03:33,460 It will take approx one minute depending upon what specification you have now. 46 00:03:33,510 --> 00:03:35,340 All this stuff gets executed. 47 00:03:35,340 --> 00:03:38,600 And if I'm going to call my data there, you will see. 48 00:03:38,610 --> 00:03:44,100 Now, this feature supports my daytime form and this is exactly what I need. 49 00:03:44,310 --> 00:03:51,420 And if, again, I'm going to call my doctor had over there now you will see over here, this is exactly 50 00:03:51,420 --> 00:03:52,600 my daytime feature. 51 00:03:52,920 --> 00:03:57,260 So from this daytime feature, let's say you have to perform some analysis. 52 00:03:57,510 --> 00:04:02,220 So what you can do, you can fetch your ear, you can fetch your mind, you can fetch your day, you 53 00:04:02,220 --> 00:04:06,470 can fetch our league days and lots of things from this date. 54 00:04:06,990 --> 00:04:08,880 So this is exactly my approach. 55 00:04:08,880 --> 00:04:14,880 I'm basically going to find some I have the attributes from this data because if you have to perform 56 00:04:14,880 --> 00:04:19,840 analysis in that, you have to factor this derived attributes from this data. 57 00:04:20,220 --> 00:04:27,010 So let's say I'm going to say from this D.F. of daytime's, the very first I have to access this data 58 00:04:27,120 --> 00:04:27,890 of data. 59 00:04:27,930 --> 00:04:29,570 You can just press tab as well. 60 00:04:29,730 --> 00:04:37,740 And on this, if I'm going to call this D dot de underscored name and if I'm going to execute it now, 61 00:04:37,740 --> 00:04:42,410 you will see with respect to each and every index you have some reflects it. 62 00:04:42,420 --> 00:04:43,860 I have to store it somewhere. 63 00:04:44,280 --> 00:04:46,890 Let's say very first I have to define that column. 64 00:04:46,890 --> 00:04:53,310 So I'm just going to define as let's say this is exactly my did whatever name you want to assign, it's 65 00:04:53,310 --> 00:04:54,350 all up to you. 66 00:04:54,540 --> 00:04:56,340 So just executed after it. 67 00:04:56,340 --> 00:04:59,250 What I'm going to do, let's say I'm going to say I. 68 00:04:59,600 --> 00:05:07,280 Some days before this, what I can do, I can call this dot, dot and whatever day it will return me, 69 00:05:07,460 --> 00:05:09,090 I have to store it somewhere else. 70 00:05:09,090 --> 00:05:16,300 So I'm going to say deal of, let's say, DFG all day once I will execute this stuff. 71 00:05:16,550 --> 00:05:21,860 So it will exactly return my day with respect to each and every death. 72 00:05:22,120 --> 00:05:31,040 Once I will do all the stuff I need, my Mynatt hour and month, so forth, is what we guys can do to 73 00:05:31,040 --> 00:05:32,170 access your minute. 74 00:05:32,180 --> 00:05:38,180 You can call Dot Minett over here, which is exactly this one. 75 00:05:38,390 --> 00:05:41,120 Once you will executed it, will it. 76 00:05:41,150 --> 00:05:43,190 And enough to let me store very full. 77 00:05:43,200 --> 00:05:48,860 So I'm just going to say it will whatever it will hit on me, I have to store it in minute column. 78 00:05:48,860 --> 00:05:52,910 So this will exactly away how you can define a new column in your data frame. 79 00:05:53,330 --> 00:05:58,010 Now what you have to do, let's say you have to access your money for this. 80 00:05:58,010 --> 00:06:03,650 I'm going to say Dortmunder, so it will exactly return me my money so I have to store it somewhere 81 00:06:03,650 --> 00:06:03,840 else. 82 00:06:03,840 --> 00:06:06,560 So I'm going to say DFI of of month. 83 00:06:06,560 --> 00:06:09,830 Whatever name you want to assign, it's all you want. 84 00:06:09,830 --> 00:06:12,200 You will do all the gist of what I'm going to do. 85 00:06:12,200 --> 00:06:15,290 I'm going to say I need some hours for this. 86 00:06:15,290 --> 00:06:18,140 I'm going to say dot our lunch. 87 00:06:18,170 --> 00:06:21,530 I will do all this stuff here this time. 88 00:06:21,530 --> 00:06:24,260 I just need some hours for this. 89 00:06:24,740 --> 00:06:26,140 I have to just store it. 90 00:06:26,150 --> 00:06:33,380 So here I'm going to say D of all our ones, I will do all the stuff you have to just execute it. 91 00:06:33,380 --> 00:06:39,770 And now what I'm going to do, I'm just going to call ahead to get a preview how exactly my data looks 92 00:06:39,770 --> 00:06:40,040 like. 93 00:06:40,310 --> 00:06:43,460 Now you will see over here, this is exactly what we did. 94 00:06:43,460 --> 00:06:44,780 This is exactly what day. 95 00:06:44,960 --> 00:06:49,450 And these are all these derived features from your data. 96 00:06:49,460 --> 00:06:56,960 It means up to some extent, your data is somehow ready and you can ready to perform lots of analysis 97 00:06:56,960 --> 00:06:57,830 on your data. 98 00:06:57,950 --> 00:07:04,130 And if, again, I'm going to call my dad over here now, you will see with respect to each and every 99 00:07:04,130 --> 00:07:07,730 future, there is some data that also gets assigned. 100 00:07:08,000 --> 00:07:10,700 Now, your data frame almost ready. 101 00:07:10,700 --> 00:07:13,640 Now you can go ahead with your analysis. 102 00:07:13,670 --> 00:07:17,960 In all our upcoming sessions, we are going to do lots of analysis. 103 00:07:17,960 --> 00:07:24,590 We are going to deal with lots of complex problems, statement with this data and in much, much depth. 104 00:07:24,920 --> 00:07:26,540 So that's all about decision. 105 00:07:26,550 --> 00:07:27,830 Hope you love it very much. 106 00:07:28,020 --> 00:07:28,670 Thank you. 107 00:07:28,700 --> 00:07:30,470 How nice to keep learning. 108 00:07:30,680 --> 00:07:32,600 Keep growing, keep motivating.