diff --git a/v3/.Rhistory b/v3/.Rhistory
new file mode 100644
index 0000000..6fed280
--- /dev/null
+++ b/v3/.Rhistory
@@ -0,0 +1,512 @@
+l <- (TRUE, TRUE, FALSE, F, F, F T)
+l <- (TRUE, TRUE, FALSE, F, F, F, T)
+a <- (TRUE, TRUE, FALSE, F, F, F, T)
+a <- c(TRUE, TRUE, FALSE, F, F, F, T)
+mode(b)
+mode(a)
+install.packages('ggplot2')
+install.packages('dplyr')
+ls
+ls
+setcwd('/home/gasperspagnolo/Documents/faks/3-letnik/1sem/is/vaje/v3')
+setwd('/home/gasperspagnolo/Documents/faks/3-letnik/1sem/is/vaje/v3')
+ls
+ls
+# for example:
+# setwd("c:\\labs\\data\\")
+library(ggplot2)
+library(dplyr)
+# To read data from a text file, use the "read.table" command.
+# The parameter header=TRUE indicates that the file to be read includes a first line with the column names
+md <- read.table(file="movies.txt", sep=",", header=TRUE)
+head(md)
+summary(md)
+summary(md)
+str(md)
+names(md)
+md$Action <- as.factor(md$Action)
+md$Animation <- as.factor(md$Animation)
+str(md)
+# The remaining columns will be transformed using the for loop
+for (i in 20:24)
+md[,i] <- as.factor(md[,i])
+md[30,]
+md[30,3]
+md[30,"length"]
+md[,3]
+md$length
+plot(md$length)
+hist(md$length)
+plot(density(md$length))
+boxplot(md$length)
+barplot(table(md$Drama))
+pie(table(md$mpaa))
+## nicer plots with ggplot2 + dplyr
+md %>% ggplot(aes(length)) + geom_histogram(bins = 40) + ggtitle("A genetic histogram") + xlab("Length"
+## nicer plots with ggplot2 + dplyr
+md %>% ggplot(aes(length)) + geom_histogram(bins = 40) + ggtitle("A genetic histogram") + xlab("Length")
+## nicer plots with ggplot2 + dplyr
+md %>% ggplot(aes(length)) + geom_histogram(bins = 40) + ggtitle("A genetic histogram") + xlab("Length")
+## plotting w.r.t. multiple mpaa categories
+md %>% ggplot(aes(length,fill = mpaa)) + geom_density(alpha = 0.2)
+## What about a nicer boxplot w.r.t mpaa?
+## theme_bw() is more neutral theme
+md %>% ggplot(aes(Drama, rating, color = mpaa)) + geom_boxplot() + theme_bw()
+barplot(table(md$Comedy))
+barplot(table(md$Comedy))
+pie(table(md$Comedy))
+tab <- table(md$Comedy)
+names(tab) <- c("Other genres", "Comedies")
+tab
+barplot(table(md$Comedy))
+pie(table(md$Comedy))
+tab <- table(md$Comedy)
+names(tab) <- c("Other genres", "Comedies")
+tab
+tab <- table(md$Comedy)
+names(tab) <- c("Other genres", "Comedies")
+tab
+pie(tab)
+sum(tab)
+barplot(tab, ylab="Number of titles", main="Proportion of comedies to other genres")
+barplot(tab / sum(tab) * 100, ylab="Percentage of titles", main="The proportion of comedies to other genres")
+pie(tab, main = "Proportion of comedies to other genres")
+# Plot the rating distribution for comedies
+hist(md[md$Comedy == "1", "rating"], xlab="Rating", ylab="Frequency", main="Histogram of ratings for comedies")
+boxplot(md[md$Comedy == "1", "rating"], ylab="Rating", main="Boxplot of ratings for comedies")
+quantile(md$rating[md$Comedy == 1])
+comedy <- md$Comedy == "1"
+# Calculate the mean rating value for comedies and non-comedies
+mean(md[comedy,"rating"])
+mean(md[!comedy,"rating"])
+boxplot(rating ~ Comedy, data=md)
+boxplot(rating ~ Comedy, data=md, names=c("Other genres", "Comedies"), ylab="Rating", main="Comparison of ratings between comedies and non-comedies")
+md %>% group_by(Comedy) %>% select(rating) %>% summarise(mean(rating))
+md %>% group_by(Comedy)
+sel <- md$year >= 1990
+table(md$Comedy[sel], md$year[sel])
+table(md$year[sel])
+tabcomedy <- table(md$Comedy[sel], md$year[sel])
+tabyear <- table(md$year[sel])
+tabcomedy[2,]/tabyear
+ratio <- tabcomedy[2,]/tabyear
+barplot(ratio, xlab="Year", ylab="Relative frequency", main="Proportion of comedies")
+plot(x=names(ratio), y=as.vector(ratio), type="l", xlab="Year", ylab="Relative frequency", main="Proportion of comedies, 1990-2005")
+## Is this dependent on the mpaa?
+## or with dplyr + ggplot + adding votes
+md %>% select(budget, rating, votes, mpaa) %>%
+na.omit() %>%
+ggplot(aes(budget, rating, color = votes, fill = mpaa)) + geom_point() + geom_smooth(method = "lm", formula = y ~ x) + theme_bw()
+## or with dplyr directly
+md %>% filter(year >= 1990) %>%
+group_by(year, Comedy) %>%
+summarise(n = n()) %>% mutate(freq = n / sum(n)) %>%
+filter(Comedy == 1) %>% select(year, freq) %>%
+ggplot(aes(year, freq)) + geom_point() + ggtitle("Frequency of comedies") + ylab("Frequency") + xlab("Year")
+md %>% filter(year >= 1990)
+summary(md$budget)
+is.na(md$budget)
+table(is.na(md$budget))
+which(is.na(md$budget))
+# select complete observations only
+sel <- is.na(md$budget)
+mdsub <- md[!sel,]
+nrow(mdsub)
+summary(mdsub$budget)
+plot(mdsub$budget, mdsub$rating, xlab="Budget in $", ylab="Rating", main="Movie rating vs budget")
+# Plotted points are mostly located in the upper left part of the diagram,
+# which means that a higher budget usually leads to a higher rating
+# Utilization of the budget in terms of rating
+ratio <- mdsub$budget/mdsub$rating
+hist(ratio)
+# Which movie has the worst budget utilization?
+mdsub[which.max(ratio),]
+# Let's discretize these budgets to:
+# low (less than 1M), mid (between 1M and 50M) and big (more than 50M)
+disbudget <- cut(mdsub$budget, c(0, 1000000, 50000000, 500000000), labels=c("low", "mid", "big"))
+barplot(table(disbudget)/length(disbudget), xlab="Budget", ylab="Relative frequency", main="Proportion of movies vs budget")
+# Side-by-side boxplots of ratings grouped by budget values
+boxplot(mdsub$rating ~ disbudget, xlab="Budget", ylab="Rating", main="Boxplot of movie rating vs budget")
+## Is this dependent
+## or with dplyr + ggplot + adding votes
+md %>% select(budget, rating, votes, mpaa) %>%
+na.omit() %>%
+ggplot(aes(budget, rating, color = votes, fill = mpaa)) + geom_point() + geom_smooth(method = "lm", formula = y ~ x) + theme_bw()
+## or with dplyr
+md %>% select(budget, year) %>% na.omit() %>%
+group_by(year) %>% summarise(budget2 = sum(as.numeric(budget))) %>%
+arrange(year) %>% mutate(csum = cumsum(budget2)) %>%
+ggplot(aes(year, csum)) + geom_bar(stat = "identity") + theme_bw()
+## Is this dependent on the mpaa?
+## or with dplyr + ggplot + adding votes
+md %>% select(budget, rating, votes, mpaa) %>%
+na.omit() %>%
+ggplot(aes(budget, rating, color = votes, fill = mpaa)) + geom_point() + geom_smooth(method = "lm", formula = y ~ x) + theme_bw()
+#######################################
+md <- read.table("movies.txt", sep=",", header=TRUE)
+# - Are there more movies shorter than 100 min or longer than (or equal to) 100 minutes?
+#   (show your answer numerically and graphically)
+md
+md <- read.table("movies.txt", sep=",", header=TRUE)
+# - Are there more movies shorter than 100 min or longer than (or equal to) 100 minutes?
+#   (show your answer numerically and graphically)
+movies_shorter_or_equal_100_min <- md$length >= 100
+movies_shorter_or_equal_100_min
+barplot(movies, xlab="Year", ylab="Relative frequency", main="Proportion of comedies")
+barplot(movies_shorter_or_equal_100_min, xlab="Year", ylab="Relative frequency", main="Proportion of comedies")
+md[30,]
+md[30,3]
+md[30,"length"]
+md[,3]
+md$length
+# Useful data visualization functions
+plot(md$length)
+hist(md$length)
+plot(density(md$length))
+boxplot(md$length)
+barplot(table(md$Drama))
+pie(table(md$mpaa))
+## nicer plots with
+## nicer plots with ggplot2 + dplyr
+md %>% ggplot(aes(length)) + geom_histogram(bins = 40) + ggtitle("A genetic histogram") + xlab("Length")
+tab <- table(md$Comedy)
+names(tab) <- c("Other genres", "Comedies")
+tab
+pie(tab)
+tab
+tab <- table(md$Comedy)
+tab
+hist(md[md$Comedy == "1", "rating"], xlab="Rating", ylab="Frequency", main="Histogram of ratings for comedies")
+pie(table(md$Comedy))
+md$Comedy
+md$length
+names(tab) <- c("Other genres", "Comedies")
+tab
+pie(tab)
+barplot(table(md$length))
+movies_shorter_or_equal_100_min <- md$length >= 100
+table(movies_shorter_or_equal_100_min)
+movies_shorter_or_equal_100_min <- md$length >= 100
+tab <- table(movies_shorter_or_equal_100_min)
+names(tab) <- c("Less than 100", "More or equal to 100")
+pie(tab)
+df
+md
+md$Comedy
+md$Comedy
+md <- read.table("movies.txt", sep=",", header=TRUE)
+# We will transform binary attributes into nominal variables with a fixed number of possible values (factors)
+md$Action <- as.factor(md$Action)
+md$Animation <- as.factor(md$Animation)
+# The remaining columns will be transformed using the for loop
+for (i in 20:24)
+md[,i] <- as.factor(md[,i])
+movies_shorter_or_equal_100_min <- md$length >= 100
+tab <- table(movies_shorter_or_equal_100_min)
+names(tab) <- c("Less than 100", "More or equal to 100")
+pie(tab)
+<- md$Romance
+romantic_comedies
+romantic_comedies <- md$Romance
+romantic_comedies
+romantic_comedies <- sum(md$Romance == 1)
+romantic_comedies
+## or with dplyr directly
+md %>% filter(year >= 1990) %>%
+group_by(year, Comedy) %>%
+summarise(n = n()) %>% mutate(freq = n / sum(n)) %>%
+filter(Comedy == 1) %>% select(year, freq) %>%
+ggplot(aes(year, freq)) + geom_point() + ggtitle("Frequency of comedies") + ylab("Frequency") + xlab("Year") + geom_line() + theme_bw()
+######################################################
+# - Are there more action comedies or romantic comedies?
+md  %>% group_by(Comedy, Action)
+# - Are there more action comedies or romantic comedies?
+md  %>% group_by(Comedy, Action)  %>% summarise(n = n())
+# - Are there more action comedies or romantic comedies?
+md  %>% group_by(Action, Comedy)  %>% summarise(n = n())
+# - Are there more action comedies or romantic comedies?
+md  %>% group_by(Action == 1, Comedy)  %>% summarise(n = n())
+# - Are there more action comedies or romantic comedies?
+md  %>% group_by(Action == 1, Comedy == 1)  %>% summarise(n = n())
+# - Are there more action comedies or romantic comedies?
+md  %>% filter(Action == 1, Comedy == 1)  %>% summarise(n = n())
+md %>% filter(Action == 1, Comedy == 1)  %>% summarise(n = n())
+md %>% filter(Action == 1, Comedy == 1)  %>% summarise(n = n())
+md %>% filter(Romantic == 1, Comedy == 1)  %>% summarise(n = n())
+# - Are there more action comedies or romantic comedies?
+md  %>% filter(Comedy == 1)  %>% summarise(n = n())
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_actions = sum(Romance == 1))
+# - Are there more action comedies or romantic comedies?
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+select(number_of_action_movies, number_of_Romances)
+# - Are there more action comedies or romantic comedies?
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+select(number_of_action_movies, number_of_Romances)
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+select(number_of_action_movies, number_of_Romances) >%>%
+unique()
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+select(number_of_action_movies, number_of_Romances) %>%
+unique()
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+select(number_of_action_movies, number_of_Romances) %>%
+unique() %>% pie()
+# - Are there more action comedies or romantic comedies?
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+select(number_of_action_movies, number_of_Romances) %>%
+unique()
+# - Are there more action comedies or romantic comedies?
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+select(number_of_action_movies, number_of_Romances) %>%
+unique()
+# - Are there more action comedies or romantic comedies?
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+unique() %>%
+select(number_of_action_movies, number_of_Romances)
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+unique() %>%
+select(number_of_action_movies, number_of_Romances)
+md  %>% filter(Comedy == 1)  %>% mutate(number_of_actions = sum(Action == 1)) %>%
+mutate(number_of_action_movies = sum(Action == 1)) %>%
+mutate(number_of_Romances = sum(Romance == 1)) %>%
+select(number_of_action_movies, number_of_Romances) %>%
+unique()
+# - Plot a histogram of the ratings for drama movies.
+head(md)
+ratio <- mdsub$budget/mdsub$rating
+hist(ratio)
+plot(mdsub$budget, mdsub$rating, xlab="Budget in $", ylab="Rating", main="Movie rating vs budget")
+ratio <- mdsub$budget/mdsub$rating
+hist(ratio)
+hist(md$mpaa)
+hist(md$mpaa)
+hist(md$r1)
+(md$r1)
+hist(md$r1)
+md %>% filter(Drama == 1) %>% hist()
+md %>% filter(Drama == 1
+md %>% filter(Drama == 1)
+md %>% filter(Drama == 1)
+md %>% filter(Drama == 1) %>% select(raiting)
+md %>% filter(Drama == 1) %>% select(rating)
+md %>% filter(Drama == 1) %>% select(rating) %>% hist()
+md %>% filter(Drama == 1) %>% select(rating) %>% class()
+md %>% filter(Drama == 1) %>% select(rating)
+md %>% filter(Drama == 1) %>% select(rating) %>% hist(rating)
+md %>% filter(Drama == 1) %>% select(rating) %>% hist(.$rating)
+md %>% filter(Drama == 1) %>%  tidyr::gather(rating, value) %>%  ggplot(aes(value)
+md %>% filter(Drama == 1) %>%  tidyr::gather(rating, value) %>%  ggplot(aes(value))
+md %>% filter(Drama == 1) %>%  tidyr::gather(rating, value) %>%  ggplot(aes(value))
+md %>% filter(Drama == 1) %>%  ggplot(aes(rating))
+md %>% filter(Drama == 1) %>%  ggplot(rating)
+md %>% filter(Drama == 1) %>%  ggplot(rating)
+aes(
+md %>% filter(Drama == 1) %>%  ggplot(aes(rating)) geom_histogram(bins = 10))
+md %>% filter(Drama == 1) %>%  ggplot(aes(rating)) geom_histogram(bins = 10))
+md %>% filter(Drama == 1) %>%  ggplot(aes(rating))  + eom_histogram(bins = 10))
+md %>% filter(Drama == 1) %>%  ggplot(aes(rating))  + geom_histogram(bins = 10))
+md %>% filter(Drama == 1) %>%  ggplot(aes(rating))  + geom_histogram(bins = 10)
+md %>% filter(Drama == 1) %>% select(rating) %>%  mutate(higher_than_avg_rating = rating > mean(rating))
+md %>% filter(Drama == 1) %>% select(rating) %>%  mutate(higher_than_avg_rating = rating > mean(rating))%>%
+pie(table(aes(sum(rating == TRUE), aes(sum(rating == FALSE))
+md %>% filter(Drama == 1) %>% select(rating) %>%  mutate(higher_than_avg_rating = rating > mean(rating))%>%
+pie(table(aes(sum(rating == TRUE)), aes(sum(rating == FALSE)))
+md %>% filter(Drama == 1) %>% select(rating) %>%  mutate(higher_than_avg_rating = rating > mean(rating))%>%
+md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating))
+md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating)
+md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(counts = n())
+md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE))
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE)) %>%
+pie()
+md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE)) %>%
+pie()
+ggplot(aes(.))) +
+geom_bar(stat="identity", width=1) +
+coord_polar("y", start=0)
+md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE)) %>%
+ggplot(aes(.)) +
+geom_bar(stat="identity", width=1) +
+coord_polar("y", start=0)
+md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE)) %>%
+ggplot(aes(.)) +
+coord_polar("y", start=0)
+md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE)) %>%
+ggplot(aes(.)) +
+coord_polar("y", start=0)
+summary <- md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE)) %>%
+summary
+summary <- md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE)) %>%
+summary
+summary
+h <- md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE)) %>%
+h
+pie(h)
+h <- md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE)) %>%
+h <- md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE))
+md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE))
+lol <- md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating) %>%
+summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE))
+lol
+pie(lol)
+lol <- md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating)# %>%
+#  summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE))
+pie(lol)
+#  summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE))
+lol
+pie(table(lol))
+lol <- md %>% filter(Drama == 1) %>% select(rating) %>%
+mutate(higher_than_avg_rating = rating > mean(rating)) %>%
+select(higher_than_avg_rating)# %>%
+#  summarise(is_higher = sum(higher_than_avg_rating == TRUE), is_lower = sum(higher_than_avg_rating == FALSE))
+pie(table(lol))
+pie(table(lol))
+sel <- md$year >= 1990
+# the table() command can be used to get a two-way contigency table
+table(md$Comedy[sel], md$year[sel])
+sel <- md$year >= 1999 && md$year <= 2005
+table(md$Animation[sel])
+sel <- md$year >= 1999 && md$year <= 2005
+table(md$Animation[sel], md$year[sel])
+table(md$Animation[sel] == 1, md$year[sel])
+sel <- md$year >= 1999 && md$year <= 2005
+table(md$Animation[sel], md$year[sel])
+tabcomedy <- table(md$Comedy[sel], md$year[sel])
+tabyear <- table(md$year[sel])
+tabcomedy[2,]/tabyear
+tabyear <- table(md$year[sel])
+tabyear
+tabcomedy <- table(md$Comedy[sel], md$year[sel])
+tabcomedy <- table(md$Comedy[sel], md$year[sel])
+tabcomedy
+table(md$year[sel])
+table(md$Comedy[sel], md$year[sel])
+table(md$year[sel])
+tabcomedy <- table(md$Comedy[sel], md$year[sel])
+table(md$Comedy[sel], md$year[sel])
+tabcomedy <- table(md$Comedy[sel], md$year[sel])
+tabcomedy
+tabyear <- table(md$year[sel])
+tabyear
+ratio <- tabcomedy[2,]/tabyear
+## or with dplyr directly
+md %>% filter(year >= 1990) %>%
+group_by(year, Comedy) %>%
+summarise(n = n()) %>% mutate(freq = n / sum(n)) %>%
+filter(Comedy == 1) %>% select(year, freq) %>%
+ggplot(aes(year, freq)) + geom_point() + ggtitle("Frequency of comedies") + ylab("Frequency") + xlab("Year") + geom_line() + theme_bw()
+ratio <- tabcomedy[2,]/tabyear
+barplot(ratio, xlab="Year", ylab="Relative frequency", main="Proportion of comedies")
+ratio <- tabcomedy[2,]/tabyear
+sel <- md$year >= 1999 && md$year <= 2005
+table(md$Animation[sel], md$year[sel])
+tt[,2]
+tt <- table(md$Animation[sel], md$year[sel])
+tt[,2]
+tt <- table(md$Animation[sel], md$year[sel])
+tt[2,]
+sel <- md$year >= 1999 && md$year <= 2005
+tt <- table(md$Animation[sel], md$year[sel])
+sel <- md$year >= 1999 && md$year <= 2005
+tt <- table(md$Animation[sel], md$year[sel])
+tt[2,]
+sel <- md$year >= 1999 && md$year <= 2005
+sel
+tt <- table(md$Animation[sel], md$year[sel])
+tt[2,]
+sel <- md$year >= 1999 && md$year <= 2005
+sel
+tt <- table(md$Animation[sel], md$year[sel])
+tt <- table(md$Animation[sel], md$year[sel])
+tt[2,]
+# - Plot the number of animated movies being produced every year for the period 1995-2005.
+sel <- md$year >= 1999 && md$year <= 2005
+tt <- table(md$Animation[sel], md$year[sel])
+tt[2,]
+tt <- table(md$Animation[sel], md$year[sel])
+tt[3,]
+sel <- md$year >= 1999 && md$year <= 2005
+tt <- table(md$Animation[sel], md$year[sel])
+tt[1,]
+sel <- md$year >= 1999 && md$year <= 2005
+tt <- table(md$Animation[sel], md$year[sel])
+tt[2,]
+#####################
+barplot(tt[2,], xlab="Year", ylab="Relative frequency", main="Proportion of comedies")
+sel <- md$year >= 1999 and md$year <= 2005
+sel <- md[md$year >= 1999 && md$year <= 2005]
+sel <- md[md$year >= 1999 & md$year <= 2005]
+tt <- table(md$Animation[sel], md$year[sel])
+sel <- md[md$year >= 1999 & md$year <= 2005]
+sel <- md$year >= 1999 & md$year <= 2005
+sel
+tt <- table(md$Animation[sel], md$year[sel])
+barplot(tt[2,], xlab="Year", ylab="Relative frequency", main="Proportion of animated movies")
+sel <- md$year >= 1999 & md$year <= 2005
+tt <- table(md$Animation[sel], md$year[sel])
+barplot(tt[2,], xlab="Year", ylab="Relative frequency", main="Proportion of animated movies")
+#######################
diff --git a/v3/lab 2 - problems.R b/v3/lab 2 - problems.R
index 1c2e67a..87e16dd 100644
--- a/v3/lab 2 - problems.R	
+++ b/v3/lab 2 - problems.R	
@@ -70,7 +70,7 @@ pie(table(lol))
 # - Plot the number of animated movies being produced every year for the period 1995-2005.
 sel <- md$year >= 1999 & md$year <= 2005
 tt <- table(md$Animation[sel], md$year[sel])
-barplot(tt[2,], xlab="Year", ylab="Relative frequency", main="Proportion of animated movies")
+wbarplot(tt[2,], xlab="Year", ylab="Relative frequency", main="Proportion of animated movies")
 
 # - Is there a clear boundary between short and feature movies (according to their length)?
 
@@ -93,3 +93,15 @@ barplot(tt[2,], xlab="Year", ylab="Relative frequency", main="Proportion of anim
 #
 #######################################################################################################################
 
+players <- read.table("players.txt", sep=",", header = T)
+
+# - Plot the proportion of players according to playing positions.
+position_proportion <- players %>% group_by(position) %>% select(position) %>% table()
+pie(position_proportion)
+
+# - Compare career rebounds (the "reb" attribute) with respect to playing position
+boxplot(reb ~ position, data=players, ylab="Carrer rebounds", main="Comparison of carrer rebounds with respect to playing position")
+
+# - Show the distribution of free throw percentages.
+#   The percentage is determined by dividing the number of shots made ("ftm") by the total number of shots attempted ("fta").
+ftp <- players %>% mutate(free_throw_percentage = ftm/fta *100) %>% select(free_throw_percentage)