1 00:00:01,024 --> 00:00:02,816 ‫Now let's move on to 2 00:00:03,072 --> 00:00:05,376 ‫Next library which is seaborn. 3 00:00:06,912 --> 00:00:10,240 ‫Seaborn is a library for data visualization 4 00:00:10,496 --> 00:00:13,824 ‫Most commonly used library is matplotlib 5 00:00:14,336 --> 00:00:20,480 ‫But for our course we think seaborn is much more suited that's why you will be discussing seaborn only 6 00:00:21,760 --> 00:00:27,392 ‫You want you can learn about ####### on your own. 7 00:00:28,928 --> 00:00:34,560 ‫First we will import the 8 00:00:45,568 --> 00:00:49,152 ‫seaborn library we will write input seaborn as SNS. 9 00:00:49,920 --> 00:00:50,432 ‫Now 10 00:00:51,200 --> 00:00:54,784 ‫To plot the distribution of our age variable 11 00:00:55,296 --> 00:00:58,880 ‫from our customer table will write SNS 12 00:00:59,904 --> 00:01:02,720 ‫.thisplot 13 00:01:02,976 --> 00:01:06,048 ‫Bracket I will mention my 14 00:01:06,816 --> 00:01:09,632 ‫Column name it is customer 15 00:01:10,912 --> 00:01:11,936 ‫data 2 16 00:01:12,960 --> 00:01:13,984 ‫Dot 17 00:01:14,240 --> 00:01:16,544 ‫age capital A. 18 00:01:22,432 --> 00:01:26,272 ‫You can see this histogram of our age variable 19 00:01:28,320 --> 00:01:29,344 ‫Is first 20 00:01:29,600 --> 00:01:32,160 ‫Creating bins of all the ages 21 00:01:33,184 --> 00:01:38,048 ‫So the minimum value in our age variable is 18 and the maximum is 17 22 00:01:38,560 --> 00:01:40,864 ‫Python has created different Bin 23 00:01:41,376 --> 00:01:43,168 ‫Between these two values 24 00:01:43,936 --> 00:01:44,704 ‫And then 25 00:01:44,960 --> 00:01:51,104 ‫Plotted the number of variables in those bins in the form of bar this is called histogram. 26 00:01:52,640 --> 00:01:56,736 ‫You can see most of our customer are in this last bucket 27 00:01:59,040 --> 00:02:04,160 ‫This line is also known as KDE kernel density estimate 28 00:02:05,440 --> 00:02:11,584 ‫And we are not going into explanation on how to arrive on this line so 29 00:02:11,840 --> 00:02:13,632 ‫We are just going to remove this line. 30 00:02:13,888 --> 00:02:15,168 ‫To remove this line 31 00:02:15,424 --> 00:02:21,568 ‫we'll Write SNS dot plot data to.age 32 00:02:24,384 --> 00:02:28,224 ‫And then KDE equal to false. 33 00:02:35,904 --> 00:02:38,720 ‫Now the KDE line is removed. 34 00:02:38,976 --> 00:02:40,768 ‫If you want to see 35 00:02:41,536 --> 00:02:46,144 ‫Arguments of any function you can just write help 36 00:02:46,400 --> 00:02:49,216 ‫And in bracket you can write that function. 37 00:02:49,472 --> 00:02:53,568 ‫Example in our case we'll write SNS dot plot. 38 00:02:57,664 --> 00:03:01,248 ‫It will show you the syntax of that function 39 00:03:01,504 --> 00:03:04,320 ‫All the variables that it is taking 40 00:03:04,832 --> 00:03:07,392 ‫And the default values of those variable 41 00:03:07,648 --> 00:03:12,512 ‫so by default KDE was true that's why we were getting the KDE plot 42 00:03:13,536 --> 00:03:17,632 ‫And you can change the value to false to to remove the KDE. 43 00:03:18,144 --> 00:03:20,704 ‫Similarly there are other variables as well 44 00:03:20,960 --> 00:03:25,056 ‫You can create a rug plot if you write#######equal to true 45 00:03:25,312 --> 00:03:29,664 ‫If you can have a look at this and read the documentation 46 00:03:29,920 --> 00:03:32,736 ‫Now you will change the colour of this graph. 47 00:03:41,440 --> 00:03:44,512 ‫You can see colour is also a variable 48 00:03:45,024 --> 00:03:45,792 ‫We will 49 00:03:46,048 --> 00:03:51,680 ‫Just write sns.thisplot 50 00:04:02,432 --> 00:04:05,504 ‫Colour equal to red 51 00:04:06,784 --> 00:04:12,928 ‫Red in double quotes run this can see the colour is now 52 00:04:13,184 --> 00:04:13,952 ‫Changed to red. 53 00:04:14,976 --> 00:04:19,071 ‫Seaborn library comes with various data sets 54 00:04:19,839 --> 00:04:24,703 ‫No we will just import one of such database also known as Iris 55 00:04:25,471 --> 00:04:28,543 ‫So will right Iris Iris is our 56 00:04:28,799 --> 00:04:32,127 ‫Name of variable containing Iris dataset 57 00:04:32,383 --> 00:04:35,199 ‫Then we'll write Sns.plot 58 00:04:35,455 --> 00:04:36,991 ‫Underscore data set 59 00:04:41,087 --> 00:04:44,415 ‫And in bracket will write Iris. 60 00:04:45,951 --> 00:04:47,743 ‫Run this 61 00:04:49,279 --> 00:04:53,119 ‫You can view a sample of this data set by using Iris 62 00:04:53,375 --> 00:04:54,655 ‫.####### 63 00:05:01,055 --> 00:05:03,871 ‫So our data contains 64 00:05:04,383 --> 00:05:05,663 ‫5 columns 65 00:05:05,919 --> 00:05:08,223 ‫sepal length,sepal width 66 00:05:08,735 --> 00:05:10,527 ‫petal length,petal width 67 00:05:10,783 --> 00:05:16,927 ‫and specie this is the data of flowers where we have sepal length and sepal width and petal 68 00:05:17,183 --> 00:05:18,207 ‫Length and Petal width. 69 00:05:18,719 --> 00:05:21,279 ‫And then the specie of that flower. 70 00:05:21,535 --> 00:05:26,399 ‫To get the number of columns we'll write Iris dot shape 71 00:05:28,959 --> 00:05:30,751 ‫and run this 72 00:05:33,055 --> 00:05:36,639 ‫You can see there are total 150 rows 73 00:05:36,895 --> 00:05:38,431 ‫There are five columns 74 00:05:40,735 --> 00:05:46,879 ‫You want to get the mean value median value minimum value and maximum value we can also write Iris. 75 00:05:47,135 --> 00:05:47,647 ‫Describe 76 00:05:58,911 --> 00:06:03,007 ‫This will you show us some statistics of all this 77 00:06:03,263 --> 00:06:04,287 ‫Four columns. 78 00:06:06,335 --> 00:06:06,847 ‫Now 79 00:06:07,103 --> 00:06:08,895 ‫Will plot a scatter plot 80 00:06:09,663 --> 00:06:12,223 ‫Between sepal Length and sepal width. 81 00:06:12,735 --> 00:06:15,295 ‫To do that will write ###### 82 00:06:16,575 --> 00:06:18,879 ‫####### 83 00:06:23,999 --> 00:06:25,535 ‫our x variable 84 00:06:25,791 --> 00:06:31,935 ‫Should be sepal length I'l write sepal length 85 00:06:33,727 --> 00:06:39,871 ‫And y variable is sepal width 86 00:06:41,151 --> 00:06:44,479 ‫And then our data is Iris. 87 00:06:49,343 --> 00:06:51,135 ‫If you run this 88 00:06:51,391 --> 00:06:52,671 ‫You are getting 89 00:06:53,183 --> 00:06:54,975 ‫Scatter plot 90 00:06:55,231 --> 00:06:57,535 ‫Between sepal length and sepal width 91 00:06:57,791 --> 00:07:01,119 ‫on the top we have distribution of sepal length 92 00:07:01,887 --> 00:07:02,655 ‫And 93 00:07:03,679 --> 00:07:07,519 ‫The right hand side we have distribution of sepal width. 94 00:07:13,919 --> 00:07:20,063 ‫There are other variations of this scatter plot also if you want to change the colour of 95 00:07:20,319 --> 00:07:26,463 ‫dots the size of this dot if you want a Shady plot with this histogram Shady plot or 96 00:07:26,719 --> 00:07:31,583 ‫####### You can find all this with the help option of joint 97 00:07:31,839 --> 00:07:36,447 ‫And we will discuss that during our uni variate analysis. 98 00:07:37,471 --> 00:07:37,983 ‫Next 99 00:07:38,239 --> 00:07:40,799 ‫Another important function is pair plot 100 00:07:41,311 --> 00:07:45,663 ‫So while doing our analysis instead of plotting 101 00:07:45,919 --> 00:07:48,735 ‫Scatter plot for all the variables we can 102 00:07:49,503 --> 00:07:52,575 ‫Do it for all the variables using just one command 103 00:07:53,343 --> 00:07:55,903 ‫That is sns.pairplot 104 00:07:59,743 --> 00:08:03,583 ‫And in bracket we just have to mention the data frame that is Iris. 105 00:08:06,655 --> 00:08:10,239 ‫It will create scatter plot for all the 106 00:08:10,495 --> 00:08:11,519 ‫Variable. 107 00:08:14,591 --> 00:08:17,663 ‫For example this is a distribution of 108 00:08:17,919 --> 00:08:18,943 ‫Sepal length 109 00:08:20,223 --> 00:08:23,807 ‫This is a scatter plot of sepal Length and sepal width 110 00:08:24,063 --> 00:08:28,671 ‫This is a scatter plot of sepal length and Petal length 111 00:08:28,927 --> 00:08:32,255 ‫This is a scatter plot of sepal length 112 00:08:33,023 --> 00:08:34,303 ‫and petal width. 113 00:08:35,071 --> 00:08:41,215 ‫This is a very useful command and in a single command we can get scatter plot for all our variables. 114 00:08:42,239 --> 00:08:46,591 ‫That's all for this video and that's all for Python crash course 115 00:08:46,847 --> 00:08:48,639 ‫This is just a crash course 116 00:08:48,895 --> 00:08:51,199 ‫You are not covering anything in deep 117 00:08:51,711 --> 00:08:56,063 ‫And as we go along will discuss all this things in more detail.