1 00:00:00,690 --> 00:00:01,650 Hey, welcome back. 2 00:00:01,650 --> 00:00:06,540 In this video, we will start coding our data science and Machine Learning project. 3 00:00:06,540 --> 00:00:13,410 So the movie recommendation system for this project, I'll use deep note. 4 00:00:13,440 --> 00:00:14,970 What is deep note? 5 00:00:15,090 --> 00:00:20,520 Deep note is a cloud based Jupyter Web app. 6 00:00:20,610 --> 00:00:23,820 So why am I switching to deep note? 7 00:00:23,850 --> 00:00:25,200 Well, for two reasons. 8 00:00:25,200 --> 00:00:32,130 First, I want to introduce you to cloud based Jupyter Notebooks, such as Deep Node, and second, 9 00:00:32,220 --> 00:00:41,070 using a cloud based Jupyter Notebook avoids many headaches with installation of third party packages 10 00:00:41,070 --> 00:00:47,490 such as Scikit Learn, which is sometimes hard to install in certain operating systems. 11 00:00:47,490 --> 00:00:53,520 It is also easy to set up a Jupyter notebook and to load one with deep note. 12 00:00:53,520 --> 00:01:01,120 And lastly, deep note is also good if you are collaborating with others and if you have heard of Google 13 00:01:01,120 --> 00:01:01,840 CoLab. 14 00:01:01,840 --> 00:01:07,420 So the CoLab notebooks, that's also a competitor of deep note. 15 00:01:07,420 --> 00:01:08,830 So that's an alternative. 16 00:01:08,860 --> 00:01:11,110 You can also use Google CoLab. 17 00:01:11,140 --> 00:01:17,350 I prefer deep note because it has more modern features and the experience is more flawless. 18 00:01:17,350 --> 00:01:23,470 So please consider using deep note, although you can also work with your local Jupyter notebook. 19 00:01:24,130 --> 00:01:33,070 So to use a deep note notebook, you have to go to deep note.com and then create an account there. 20 00:01:33,070 --> 00:01:34,090 It's free. 21 00:01:34,330 --> 00:01:39,370 Once you do that, you should be brought to the dashboard area. 22 00:01:39,370 --> 00:01:41,140 Here you can click on that name. 23 00:01:41,140 --> 00:01:46,600 So your name, if you click your name here, it should show you all the projects you have currently. 24 00:01:46,600 --> 00:01:48,760 So I have some existing projects here. 25 00:01:48,760 --> 00:01:56,710 Probably in your case this is empty and then you want to create your first new notebook project on deep 26 00:01:56,710 --> 00:01:57,340 note. 27 00:01:57,670 --> 00:02:02,770 To do that, you want to press that button and go to new project. 28 00:02:05,110 --> 00:02:08,740 And this will ask you to enter a name for the project. 29 00:02:08,740 --> 00:02:13,570 So just say movie recommendation system. 30 00:02:13,840 --> 00:02:14,560 Right. 31 00:02:14,590 --> 00:02:15,690 Press enter. 32 00:02:15,700 --> 00:02:24,490 And so the hierarchy here is that we have a project and we have several notebooks which can be associated 33 00:02:24,490 --> 00:02:25,900 with that project. 34 00:02:26,110 --> 00:02:28,920 So you can have one notebook or more. 35 00:02:28,930 --> 00:02:31,600 So let's start with one notebook. 36 00:02:31,600 --> 00:02:36,910 So basically here is the area where we will work on the notebook. 37 00:02:37,240 --> 00:02:42,640 But to initiate that actual notebook, you want to click on code block. 38 00:02:42,640 --> 00:02:44,470 So click on code Block. 39 00:02:44,500 --> 00:02:49,120 And now it looks like a real notebook, a Jupyter notebook. 40 00:02:49,120 --> 00:02:50,680 So this is a code cell. 41 00:02:50,680 --> 00:02:55,720 You can, of course, write Python code here, print hello. 42 00:02:56,260 --> 00:03:03,820 And you can also import something like import pandas, a third party library, and you'll see that Pandas 43 00:03:03,850 --> 00:03:08,780 is already installed and so are many, many data science libraries. 44 00:03:08,780 --> 00:03:11,870 So you don't need to set up things with deep nodes. 45 00:03:12,230 --> 00:03:18,470 And yeah, so with enter, you can create new lines within the code cell and then you can run this code 46 00:03:18,470 --> 00:03:23,300 cell using that button, or you can use this shortcut that shows up here. 47 00:03:23,300 --> 00:03:28,700 So whichever you prefer, just make sure to be inside the cell and press that shortcut. 48 00:03:28,700 --> 00:03:30,200 In my case it is commands. 49 00:03:30,200 --> 00:03:33,350 Enter the shortcut and you get the output down here. 50 00:03:33,350 --> 00:03:36,440 But I'd prefer to create a text block first. 51 00:03:36,440 --> 00:03:40,580 To do that, you want to go to this button? 52 00:03:41,380 --> 00:03:43,720 So above this cell. 53 00:03:43,960 --> 00:03:46,360 And so you have several options. 54 00:03:46,360 --> 00:03:49,090 So you see you have some model entries here. 55 00:03:49,090 --> 00:03:51,440 So perhaps you can write a. 56 00:03:52,150 --> 00:03:54,190 Heading to fonts. 57 00:03:54,220 --> 00:04:04,810 So for today, we're going to do some popularity based filtering. 58 00:04:04,840 --> 00:04:10,150 So we're going to develop a recommendation system based on popularity. 59 00:04:10,180 --> 00:04:11,560 So execute that. 60 00:04:11,560 --> 00:04:13,660 And then you want to import pandas. 61 00:04:13,690 --> 00:04:13,960 Right. 62 00:04:13,960 --> 00:04:15,550 So that's the first thing we do. 63 00:04:15,550 --> 00:04:19,810 And then we want to load the CSV files we have. 64 00:04:20,050 --> 00:04:28,300 But first, you want to upload your CSV files to this project, to the movie recommendation system project. 65 00:04:28,630 --> 00:04:31,450 So let's upload our CSV files. 66 00:04:31,480 --> 00:04:37,960 Now you can find the CSV files attached in the lecture resources in the previous video. 67 00:04:38,200 --> 00:04:44,050 So in the previous video we talked about the datasets and also attached the CSV files there. 68 00:04:44,470 --> 00:04:52,540 So then we want to click over this section files and over this plus icon. 69 00:04:52,540 --> 00:04:58,120 This section could be somewhere else in your case, so please try to find what it is. 70 00:04:58,120 --> 00:05:06,610 If it's not here, so press that button, go to upload the file and then try to find where your files 71 00:05:06,610 --> 00:05:07,300 are. 72 00:05:07,780 --> 00:05:14,890 You can select all of them pressing the shift and the arrow keys and press on upload. 73 00:05:16,310 --> 00:05:20,060 So they will upload here, as you can see. 74 00:05:22,950 --> 00:05:27,540 Ratings dot csv movies, dot csv and credits dot csv. 75 00:05:28,350 --> 00:05:32,190 So now we're ready to load them as data frames. 76 00:05:32,550 --> 00:05:40,470 Let's assign different names to movies and do pandas dot read CSV. 77 00:05:40,830 --> 00:05:42,300 So here goes. 78 00:05:43,620 --> 00:05:45,330 Movies dot CSV. 79 00:05:46,050 --> 00:05:47,430 Write that file. 80 00:05:50,120 --> 00:05:51,950 Credits for. 81 00:05:55,350 --> 00:05:57,330 Credits dot CSV. 82 00:05:58,650 --> 00:06:00,030 And lastly. 83 00:06:01,290 --> 00:06:02,340 Ratings. 84 00:06:06,480 --> 00:06:08,760 For ratings dot csv. 85 00:06:10,820 --> 00:06:15,230 And press that button to execute the cell or your keyboard shortcuts. 86 00:06:16,250 --> 00:06:17,390 So there we go. 87 00:06:17,480 --> 00:06:19,100 This was executed successfully. 88 00:06:19,100 --> 00:06:19,670 No errors. 89 00:06:19,670 --> 00:06:21,650 We got this tick mark here. 90 00:06:21,710 --> 00:06:26,510 And then you can create a new code cell by pressing that button. 91 00:06:28,010 --> 00:06:30,410 And here we want to display. 92 00:06:32,230 --> 00:06:35,800 The first rows of one of the data frames. 93 00:06:35,800 --> 00:06:39,280 Just just to check if everything is good. 94 00:06:39,290 --> 00:06:40,570 So there we go. 95 00:06:44,330 --> 00:06:47,030 Let's do the same for the other data set. 96 00:06:47,030 --> 00:06:48,530 So that's movies. 97 00:06:48,530 --> 00:06:52,700 And then we have credits Dot head. 98 00:06:54,750 --> 00:06:57,060 Ctrl enter to execute. 99 00:06:57,660 --> 00:07:01,290 And lastly, we have ratings dot head. 100 00:07:02,970 --> 00:07:03,780 Execute. 101 00:07:04,330 --> 00:07:08,360 And that's also the database with user ratings. 102 00:07:08,370 --> 00:07:12,060 So we loaded the data successfully. 103 00:07:12,150 --> 00:07:16,380 And with that, we can complete this video here. 104 00:07:16,380 --> 00:07:19,770 So that was how to set up a project and load the data. 105 00:07:19,770 --> 00:07:22,430 So we use DB nodes in the next video. 106 00:07:22,440 --> 00:07:26,760 Let's do some manipulations to these data. 107 00:07:27,660 --> 00:07:29,040 So I'll see you in the next video. 108 00:07:29,040 --> 00:07:29,430 Thanks.