applied new template and reorganized a bit

code/day1_code.R

@@ -7,28 +7,25 @@ height_in_cm <- c(Mia=180, Paul=167, Ed=199)
 height_in_cm
 
 height_in_cm[3]       # get the first element
-height_in_cm[c(1,3)] # get the 1st and 3rd element
 height_in_cm["Paul"]  # get the element named "Paul"
 
+height_in_cm[c(1,3)]  # get the 1st and 3rd element
+
 ## creating vectors II
 
-numeric(5); character(4); logical(4)
 
 a <- 1:10
 a
 
-s <-seq(4,10,2) # from 4 to 10, by steps of 2
+s <-seq(0,2,0.5) # from 0 to 2, by steps of 0.5
 s
 
-c <- rep("WT", 3 )
-c
-
-b <- rep("KO", 3 )
-b
+genotypes <- rep( c('WT','KO') , 3 )​
+genotypes
 
 ## c() stands from concatenate. you can use it to group vectors
-c(c,b)
-genotypes <- c(rep("WT",3), rep("KO",3))
+c(a,s)
+
 
 ## trick : with [] you can extract element repeatedly
 tplayer <- c("Federer", "Nadal")
@@ -67,26 +64,15 @@ y
 sum(x)	# number that are true
 mean(x) # proportion that are true
 
-# Factors 
-genotype <- factor(c("WT", "WT", "Mut2", "Mut1", "Mut2"))
-genotype
-levels(genotype)
-
-geno <- as.character(genotype)
-geno
-
-# Factors II
-genotype <- factor(c("WT", "WT", "Mut2", "Mut1", "Mut2"),levels=c("WT","Mut1","Mut2"))
 
-genotype <- c("WT", "WT", "Mut2", "Mut1", "Mut2")
-genotype
-levels(genotype)
 
 ## logical operator
 
 ## == -> check equality
 c(1,3,2) == 2
 
+c(1,3,2) < 2
+
 ## ! inverses TRUE and FALSE
 ! (c(1,3,2) < 2)
 
@@ -143,6 +129,18 @@ poets <- data.frame(name, status, reader_rating)
 poets
 
 
+poets[2, 2]      # gets the element on row 2 in column 2
+poets[, c(1,3)]  # gets columns 1 and 3
+poets[, c("name", "reader_rating")] # gets columns "name" and "reader_rating"
+poets$name       # gets column "name"
+
+## names
+rownames(poets) # gets the row names
+colnames(poets) # gets the column names
+
+rownames(poets) <- c("J", "C", "H") # overwrites row names
+poets
+
 ## list
 vec <- c(0.4, 0.9, 0.6)
 mat <- cbind(c(1,1), c(2,1))
@@ -154,42 +152,22 @@ l
 l_with_names <- list(myvector=vec, mymatrix=mat, mydata=df)
 l_with_names
 
-
-
-## access elements
-
-# matrix:
-mat
-mat[2, 2]	# gets the element on row 2 in column 2
-mat[1:2, ]	# gets rows 1,2
-mat[, c(1,4)] # gets columns 1 and 4
-
-# data frame:
-poets
-poets[2, 2]      # gets the element on row 2 in column 2
-poets[, c(1,3)]  # gets columns 1 and 3
-poets[, c("name", "reader_rating")] # gets columns "name" and "reader_rating"
-poets$name       # gets column "name"
-
-# list:
+# access elements:
 l
 l[[1]]                 # gets the first object
 l_with_names[["myvec"]]# gets the object named "myvec"
 l_with_names$myvec     # gets the object named "myvec", too
 
 
 ## names
-rownames(poets) # gets the row names
-colnames(poets) # gets the column names
-
-rownames(poets) <- c("J", "C", "H") # overwrites row names
-poets
-
-# list:
 names(l_with_names) # gets the list elements' names
 names(l_with_names) <- c("A", "B", "C") # overwrites names
 
 
+
+
+
+
 ### File 
 
 file.path("C:", "Users", "Leo", "courses", "data", "snp.csv")
@@ -213,6 +191,22 @@ str( snps )
 summary( snps )
 
 
+# Factors --> not here anymore
+genotype <- factor(c("WT", "WT", "Mut2", "Mut1", "Mut2"))
+genotype
+levels(genotype)
+
+geno <- as.character(genotype)
+geno
+
+# Factors II
+genotype <- factor(c("WT", "WT", "Mut2", "Mut1", "Mut2"),levels=c("WT","Mut1","Mut2"))
+
+genotype <- c("WT", "WT", "Mut2", "Mut1", "Mut2")
+genotype
+levels(genotype)
+
+
 snps$chr <-factor(snps$chr)
 snps$minor <-factor(snps$minor)
 snps$major <-factor(snps$major)
@@ -232,7 +226,9 @@ subset(snps, chr==1 & major=="A")
 subset(snps, chr==1 & (major=="A" | major=="T"))
 
 ## tapply
-tapply(X=snps$pos, INDEX=snps$chr, FUN=min)
+data(sleep)
+head(sleep)
+tapply(X=sleep$extra, INDEX=sleep$group, FUN=mean)
 
 ##  adding rows
 snps_updated <- rbind(snps,

solutions/R_practice4_solution.R

@@ -1,23 +1,23 @@
-# 1) Create two vectors, "vector_a" and "vector_b", containing the values from −5 to 5 and from 10 down to 0, respectively.
-vector_a <- -5:5
-vector_b <- seq(10,0) # alternatively: vector_b <- c(10,9,8,7,6,5,4,3,2,1,0)
-
-# 2) Calculate the (elementwise) sum, difference and product between the elements of "vector_a" and "vector_b". 
-vector_a + vector_b #sum
-vector_a - vector_b #difference
-vector_a * vector_b #product
-
-# 3) a) Calculate the sum of elements in "vector_a"
-#    b) Calculate the overall sum of elements in both  "vector_a" and "vector_b".
-sum(vector_a)
-sum(vector_a, vector_b) # alternatively : sum(vector_a + vector_b)
-
-
-# 4) Identify the smallest and the largest value among both "vector_a" and "vector_b".
-min(vector_a, vector_b)
-max(vector_a, vector_b)
-
-# 5) Compute the overall mean of the values among both "vector_a" and "vector_b"
-mean( c( vector_a, vector_b) ) # mean() works only on a single vector, unlike sum, min and max! 
-# Concatenate both vectors (using c() ) before computing the mean
-
+# 1) Create two vectors, "vector_a" and "vector_b", containing the values from −5 to 5 and from 10 down to 0, respectively.
+vector_a <- -5:5
+vector_b <- seq(0,1,0.1) # alternatively (0:10)*0.1
+
+# 2) Calculate the (elementwise) sum, difference and product between the elements of "vector_a" and "vector_b". 
+vector_a + vector_b #sum
+vector_a - vector_b #difference
+vector_a * vector_b #product
+
+# 3) a) Calculate the sum of elements in "vector_a"
+#    b) Calculate the overall sum of elements in both  "vector_a" and "vector_b".
+sum(vector_a)
+sum(vector_a, vector_b) # alternatively : sum(vector_a + vector_b)
+
+
+# 4) Identify the smallest and the largest value among both "vector_a" and "vector_b".
+min(vector_a, vector_b)
+max(vector_a, vector_b)
+
+# 5) Compute the overall mean of the values among both "vector_a" and "vector_b"
+mean( c( vector_a, vector_b) ) # mean() works only on a single vector, unlike sum, min and max! 
+# Concatenate both vectors (using c() ) before computing the mean
+

solutions/R_practice5_solution.R

@@ -1,27 +1,21 @@
 
-# 1)Install and load the package MASS (or other CRAN packages).
-# install.packages("MASS")
+# 1) The following command lines loads the MASS library and the bacteria data.frame present in the MASS package. Execute it:
 library(MASS)
-
-
-# 2) The following command line loads the bacteria data.frame present in the MASS package. Execute it:
-
 data(bacteria)
 ?bacteria
 
-# 3) What are the names of the columns of the bacteria data.frame ?
+# 2) What are the names of the columns of the bacteria data.frame ?
 
 names(bacteria)
 
-# 4) Use the [] , to select in bacteria rows 100 to 119 in the column "ap".
+# 3) Use the [] , to select in bacteria rows 100 to 119 in the column "ap".
 
 bacteria[ 100:119 , "ap" ]
 
-# 5) Use $ to get the column "week" and check how many missing values it has.
-
-sum(is.na(bacteria$week))
+# 4) Use $ to get the column "week" and check how many 0 values it has.
 
-#Optional : 6) use comparison operators to count how many rows correspond to a “placebo” treatment (“trt” column).
+sum(bacteria$week == 0)
 
-sum(bacteria$trt == "placebo")
+# 5) Optional : using a comparison operator and [], select the rows which correspond to a “placebo” treatment (in the “trt” column).
 
+bacteria[ bacteria$trt == "placebo" , ]