WEBVTT 00:01.960 --> 00:07.120 In the last video we learned that being an adult male on the Titanic was a pretty bad combination for 00:07.120 --> 00:09.500 surviving the disaster. 00:09.520 --> 00:15.640 So now we want to check the opposite hypothesis and we know that there was a clear code of conduct to 00:15.640 --> 00:17.790 save women and children first. 00:17.800 --> 00:25.150 And what we want to do now is actually we want to check if being either a female or a child was favorable 00:25.150 --> 00:28.030 when it comes to surviving the disaster. 00:28.030 --> 00:34.950 So first of all we import pandas and we work with our Titanic data frame and we have actually two conditions 00:34.960 --> 00:41.130 so we want to check if we have a female and we store the residing panda serious of its boolean values 00:41.160 --> 00:51.430 and mask one and as a second condition we check whether the age of the peasants is less than 14 and 00:51.460 --> 00:54.070 we started this uh in uh mask 2. 00:55.900 --> 01:04.000 So now we have here two pandas serious with boolean values and now we want to combine both conditions 01:04.030 --> 01:05.490 with an ah operator. 01:05.500 --> 01:14.590 So we have to use here the pipes and the As are and the pipes symbol stands for the logic are so by 01:14.590 --> 01:20.920 combining mosque one and mosque two of us and the pipe symbol we should get all passengers that at least 01:20.920 --> 01:22.720 meet one condition. 01:22.720 --> 01:24.880 So we should get adult females. 01:24.880 --> 01:31.690 We should get young boys and at least one conditions means that we also should get all passengers that 01:31.690 --> 01:33.300 meet both conditions. 01:33.370 --> 01:40.260 So we also should get the guards below 4 9 year old so let's combine him mosque one and mosque two and 01:40.260 --> 01:44.570 let's have a look here so we get also here a boolean serious. 01:44.700 --> 01:50.120 So if you have a look at an exposition zero we have flaws or flaws. 01:50.430 --> 01:56.790 So no condition is met and we get a false and let's have a look at an exposition one where we have true 01:56.880 --> 01:57.750 or false. 01:57.780 --> 02:00.240 So at least one condition is met and we get a true 02:03.080 --> 02:06.280 so here we have no example where we have two times truly. 02:06.290 --> 02:10.130 So maybe let's increase year to 10 ten rows 02:15.550 --> 02:16.990 and that's still not enough here. 02:17.020 --> 02:18.100 Maybe 20 rows 02:21.830 --> 02:24.350 for I'm searching now a younger 02:32.330 --> 02:34.260 so he had an exposition 10. 02:34.520 --> 02:36.520 We have true for the female. 02:36.530 --> 02:37.960 So it's a female. 02:37.970 --> 02:42.460 And also we have a true for being younger than 14. 02:42.500 --> 02:44.360 So we have true or true. 02:44.360 --> 02:50.200 And this gets us by combining it with are the guests here. 02:50.210 --> 02:54.600 Also a true and now we can pass and the combined. 02:54.690 --> 03:00.870 We in series here to our Titanic data set and dialogue operator and by doing so we are filtering out 03:00.900 --> 03:03.240 all rows that meet at least one condition. 03:03.240 --> 03:04.500 So let's second here 03:08.170 --> 03:10.920 so here we are have adult females. 03:10.960 --> 03:14.590 Then we have a baby male adult females. 03:14.670 --> 03:18.810 Uh a very young female here a very young male here 03:21.830 --> 03:28.250 so we created a brand new data frame with only females and young boys. 03:28.280 --> 03:28.700 All right. 03:28.700 --> 03:35.870 So now we can further filter our data frame so we again use mass one or mosque two and we are only interested 03:35.870 --> 03:42.370 in the year survival column in The Passenger class sex and age so we are creating your a brand new data 03:42.370 --> 03:47.260 frame and we are starting the data frame here and the variable bundle not to run 03:50.540 --> 03:53.930 and let's check our new data frame the first five rows 03:56.930 --> 04:00.650 and let's get more information on our data frame here. 04:00.710 --> 04:08.750 So we have three hundred fifty one entries so we have 351 passengers that are either women or children 04:11.290 --> 04:19.420 and let's use them the described method to get even more information and we see here in the survived 04:19.450 --> 04:20.010 column. 04:20.020 --> 04:27.610 So we have a mean of 0 points 7 2 and that means with being either woman or child the probability of 04:27.610 --> 04:32.560 surviving the disaster was actually Seventy two percent and that's quite high actually. 04:32.550 --> 04:39.810 So we can also compare this to the survival rate of all passengers and we already know that this uh 04:39.940 --> 04:44.260 the survival rate of all passengers was only 38 percent. 04:44.650 --> 04:53.410 So actually our data set supports our hypothesis that being either a woman or a child was a very favorable 04:53.440 --> 04:59.360 characteristic on onboard of two titanic to survive from the disaster. 04:59.640 --> 05:00.000 All right. 05:00.000 --> 05:04.140 So now we are finished with this session and I hope to see you on the next one by.