- Housekeeping and recap
- "Ticket" variable
''Error in ggplot(data.combined[, ], aes(x = ticket.first.char, fill = survived)) :could not find function "ggplot"
ggplot(data.combined[,], aes(x = ticket.first.char, fill = survived)) +geom_bar() +facet_wrap(~pclass) +ggtitle("Pclass") +xlab("ticket.first.char") +ylab("Total Count") +ylim(0,300) +labs(fill = "Survived")
ggplot(test.combined[,], aes(x = ticket.first.char, fill = Sex)) +facet_wrap(~Pclass) +geom_bar(width = 0.8) + #no need to use 'count' here IDK why.ggtitle('Survival by Pclass - First char')xlab('TFC') +ylab('Total Count') +# ylim(0,300) +labs(fill = 'Sex')
Hi guys, I don't get one thing, in graph from people with '3' as a first letter are about 300 in second graph at 17:00 if I count them roughly 30. whats going on? When I plotted my graphs I got different 2nd graph and number of people with '3' sums up approximately to 300 as it should be. Am i wrong?
minute: my ggplot package does not work, i got this error;
Hi David, at the point you analyze the suvival rates by ticket.first.char and divide it by pclass (minute ) you have a ylim(0,150) therefore the plot is not showing the data of the third class correctly. If I do the plot without the ylim() I can see that most people of the third class have a ticket beginning with the first char being a "3".
There appears to be a bug at . My analysis is showing a strong correlation between ticket first character of '3' and Pclass of 3.
- "Fares" variable and overfitting
Sir, I have an issue, in , GGPLOT of fare, when you change the binwidth like 2, 4 or any other number, graph changes realizing that it would a total diff analysis. Please help.
- "Cabin" variable
overfitting bad,bad,bad,bad <3
- "Embarked" variable
