WEBVTT 00:01.030 --> 00:08.160 Welcome to the solution for coding exercise 7 and of import pen us and also the listings clean CSP fire 00:10.500 --> 00:17.730 and then we thought the listings that are framed by the IPO year column from old to new and then we 00:17.730 --> 00:20.680 reset the index and create a new Range Index. 00:20.730 --> 00:21.860 Starting from zero. 00:21.870 --> 00:30.470 So let's have a look here so here we have our listings sorted by the IPO year starting with the listings 00:30.600 --> 00:36.780 before nineteen hundred seventy and before we can create plots we have to import them at plot lip as 00:36.920 --> 00:39.860 appeared here and as a matter of taste. 00:39.900 --> 00:49.970 We use the Seabourn style by passing Seabourn to the method style that use and now the very first task 00:49.970 --> 00:51.360 is easier to create. 00:51.570 --> 00:58.860 The airline plot below and obviously this this airline plot organized as subplots and on the left hand 00:58.860 --> 01:03.570 side we can see here that the y axis has different scales. 01:03.630 --> 01:12.450 So on the last price column from 0 to 4000 then add the market cap column from 0 to pretty high here 01:12.990 --> 01:17.740 and in the IPO Yeah column from nineteen hundred seventy to 2020. 01:17.820 --> 01:25.230 And we can create these plots here by using the plot method and passing through to these subplots pair 01:25.230 --> 01:32.580 meta and for each and every subplot we have a separate sexes and therefore we pass also falls through 01:32.580 --> 01:39.300 these share X parameter and the default parameter for share Y is also false. 01:39.300 --> 01:47.550 So this is I got here and we determined to have a fixed size of 15 15 and we create a let's add. 01:47.570 --> 01:51.670 And finally we shouldn't forget to call P T data show. 01:51.870 --> 01:53.700 So let's have a look here. 01:54.090 --> 01:57.370 And uh the seer looks pretty good actually. 01:57.690 --> 02:05.910 Next we have to create a histogram for the last price column with 200 pins and we only have to select 02:05.910 --> 02:10.510 the listings with the last price smaller than 200. 02:10.620 --> 02:17.000 So that's the graph that we should create here and therefore we filled our listings data frame and to 02:17.010 --> 02:20.770 select only rows where the last price is smaller than 200. 02:21.030 --> 02:28.830 Then we can you see the highest method to create a histogram and we pass that 200 to the pins parameter. 02:28.830 --> 02:36.420 And finally we can also create a tighter last price frequency to see Putin then a label for the x axis 02:36.420 --> 02:41.180 price a label for the y axis frequency. 02:41.280 --> 02:49.190 And finally of course we call purity that so and that looks pretty good here. 02:50.560 --> 02:58.270 Now we the next exercise you have to create a scatter plot with the last price on the sexes market cap 02:58.270 --> 03:02.510 on the y axis and the IPO year is color. 03:02.680 --> 03:09.640 So let's have a look here at our code and again we use the plot method and we pass the scatter for scatter 03:09.640 --> 03:17.190 plot to the kind parameter and we pass the column last price to the expire meter end market cap to the 03:17.200 --> 03:18.450 White perimeter. 03:18.760 --> 03:24.560 And finally we pass the IPO year column to the color power meter. 03:24.610 --> 03:32.540 And finally we also add a title and labels for the X and the y axis. 03:32.590 --> 03:34.570 So this is that the graph here 03:37.410 --> 03:38.480 and next. 03:38.520 --> 03:46.320 We will create some seaborne plots and therefore first of all we import seaborne S S and S so that s 03:46.440 --> 03:47.610 the convention here 03:50.770 --> 03:56.020 and then first of all we create a counter plot and it should show the number or the count of listings 03:56.020 --> 04:00.370 per exchange per IPO year starting from 2001. 04:00.370 --> 04:02.540 So that's the graph here. 04:02.650 --> 04:07.510 And first of all we can set a figure size that with a pure dealer figure. 04:07.510 --> 04:10.660 And uh then we can create a count plot. 04:10.940 --> 04:16.880 This uh seaborne dot com plot and we pass our listing stellar frame. 04:16.900 --> 04:22.770 And actually here we have a field at Virgin so we filled our listings data frame only for listings with 04:22.780 --> 04:29.950 IPO year later than 2000 and then we pass the IPO year to the x axis. 04:29.950 --> 04:36.190 So here we are on the x axis that we have the IPO year and for each and every IPO year we differentiate 04:36.190 --> 04:38.530 between the exchanges. 04:38.590 --> 04:45.610 So yeah area for each and every year the number of IPOs for Nasdaq and New York Stock Exchange and Amex 04:46.270 --> 04:52.480 and we can split this up by passing the Exchange column to the Hugh perimeter. 04:52.540 --> 04:54.340 So let's run the sell here 04:59.320 --> 05:01.890 next we have to create the following plot. 05:01.900 --> 05:08.020 And this is a bomb plot and we should answer the question whether the lower market cap of stocks being 05:08.020 --> 05:11.970 Amex listed as statistically insignificant. 05:12.010 --> 05:14.910 So this is a seaborne bomb plot. 05:15.190 --> 05:21.910 And then we pass our listings data frame to the data parameter and on the exact source here we have 05:22.000 --> 05:23.560 the exchanges. 05:23.560 --> 05:25.060 And on the y axis. 05:25.150 --> 05:27.030 The market cap column. 05:27.250 --> 05:29.380 So let's create the plot here 05:32.800 --> 05:36.150 so here we are for the average market capitalizations. 05:36.220 --> 05:43.900 For the listings on Nasdaq nicely and Amex and he and black you can see kind of a confidence interval. 05:44.350 --> 05:51.220 And here we have the confidence interval for the Amex listings and the seems to be significant that 05:51.310 --> 05:56.490 listings on the Amex have on average a lower market cap. 05:56.510 --> 05:59.150 Here we shall impart the matrix 1. 05:59.190 --> 06:03.090 See as we file and let's do this here. 06:03.500 --> 06:13.810 Let's have a look so here we have a matrix with the IPO year index and these sectors as a column labels 06:14.920 --> 06:20.860 so for example there are eight companies active in the capital goods sector that had the IPO in the 06:20.860 --> 06:24.250 year nineteen hundred ninety three. 06:24.460 --> 06:32.390 So that's the Matrix the data frame here and now we have to create the following seaborne heat map by 06:32.510 --> 06:42.350 passing the matrix one data frame to the heat map method so we have as a net start heat map then you 06:42.350 --> 06:49.250 pass matrix 1 and as a color map we use we this and the v Max is 25. 06:49.250 --> 06:50.410 So let's have a look here 06:53.680 --> 06:59.990 and here we can see on the right hand side the color scale from 0 IPO is to 25 IPOs. 07:00.110 --> 07:03.290 So a yellow color marks the hot sectors. 07:03.400 --> 07:12.940 And for example in the U.S. The 230 into 218 we have more than 25 IPOs in the healthcare sector and 07:12.940 --> 07:20.400 also quite a lot in the finance sector and in the consumer services sector and also in the tech sector. 07:20.440 --> 07:24.870 So that's actually the hot sectors in the most recent years. 07:25.490 --> 07:25.960 All right. 07:25.960 --> 07:30.160 And with this we are finished here and I hope to see also in the next exercise by.