daviddoji/JuliaForDataAnalysis
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update chapters 4 and 5

Browse Source
This commit is contained in:
Bogumił Kamiński 2022-02-11 00:14:38 +01:00
parent bbd8bbf571
commit e73dbaf370
3 changed files with 181 additions and 169 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
appB.jl
View File

@ -16,9 +16,7 @@ y = collect(x);
@btime sort($y); @btime sort($y);
@edit sort(x) @edit sort(x)
# CODES BELOW REQUIRE RE-NUMBERING # Code for exercise 4.1
# Code for exercise 3.1
using Statistics using Statistics
using BenchmarkTools using BenchmarkTools
@ -36,7 +34,7 @@ aq = [10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58
@benchmark [cor($aq[:, i], $aq[:, i+1]) for i in 1:2:7] @benchmark [cor($aq[:, i], $aq[:, i+1]) for i in 1:2:7]
@benchmark [cor(view($aq, :, i), view($aq, :, i+1)) for i in 1:2:7] @benchmark [cor(view($aq, :, i), view($aq, :, i+1)) for i in 1:2:7]
# Code for exercise 3.2 # Code for exercise 4.2
function dice_distribution(dice1, dice2) function dice_distribution(dice1, dice2)
distribution = Dict{Int, Int}() distribution = Dict{Int, Int}()
@ -73,17 +71,19 @@ end
test_dice() test_dice()
# Code for exercise 3.3 # Code for exercise 4.3
plot(scatter(data.set1.x, data.set1.y; legend=false), plot(scatter(data.set1.x, data.set1.y; legend=false),
scatter(data.set2.x, data.set2.y; legend=false), scatter(data.set2.x, data.set2.y; legend=false),
scatter(data.set3.x, data.set3.y; legend=false), scatter(data.set3.x, data.set3.y; legend=false),
scatter(data.set4.x, data.set4.y; legend=false)) scatter(data.set4.x, data.set4.y; legend=false))
# Code for exercise 3.4 # Code for exercise 5.1
parse.(Int, ["1", "2", "3"]) parse.(Int, ["1", "2", "3"])
# CODES BELOW REQUIRE RE-NUMBERING
# Code for exercise 4.1 # Code for exercise 4.1
years_table = freqtable(years) years_table = freqtable(years)

177
ch045.jl → ch04.jl
View File

@ -1,8 +1,8 @@
# Bogumił Kamiński, 2021 # Bogumił Kamiński, 2021
# Codes for chapter 3 # Codes for chapter 4
# Code for listing 3.1 # Code for listing 4.1
aq = [10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58 aq = [10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58
8.0 6.95 8.0 8.14 8.0 6.77 8.0 5.76 8.0 6.95 8.0 8.14 8.0 6.77 8.0 5.76
@ -32,13 +32,13 @@ v[1] = 10
v v
t[1] = 10 t[1] = 10
# Code for figure 3.2 # Code for figure 4.2
using BenchmarkTools using BenchmarkTools
@benchmark (1, 2, 3) @benchmark (1, 2, 3)
@benchmark [1, 2, 3] @benchmark [1, 2, 3]
# Code for section 3.1.2 # Code for section 4.1.2
using Statistics using Statistics
mean(aq; dims=1) mean(aq; dims=1)
@ -54,7 +54,7 @@ end
[mean(col) for col in eachcol(aq)] [mean(col) for col in eachcol(aq)]
[std(col) for col in eachcol(aq)] [std(col) for col in eachcol(aq)]
# Code for section 3.1.3 # Code for section 4.1.3
[mean(aq[:, j]) for j in axes(aq, 2)] [mean(aq[:, j]) for j in axes(aq, 2)]
[std(aq[:, j]) for j in axes(aq, 2)] [std(aq[:, j]) for j in axes(aq, 2)]
@ -65,7 +65,7 @@ axes(aq, 2)
[mean(view(aq, :, j)) for j in axes(aq, 2)] [mean(view(aq, :, j)) for j in axes(aq, 2)]
[std(@view aq[:, j]) for j in axes(aq, 2)] [std(@view aq[:, j]) for j in axes(aq, 2)]
# Code for section 3.1.4 # Code for section 4.1.4
using BenchmarkTools using BenchmarkTools
x = ones(10^7, 10) x = ones(10^7, 10)
@ -73,12 +73,12 @@ x = ones(10^7, 10)
@benchmark [mean($x[:, j]) for j in axes($x, 2)] @benchmark [mean($x[:, j]) for j in axes($x, 2)]
@benchmark mean($x, dims=1) @benchmark mean($x, dims=1)
# Code for section 3.1.5 # Code for section 4.1.5
[cor(aq[:, i], aq[:, i+1]) for i in 1:2:7] [cor(aq[:, i], aq[:, i+1]) for i in 1:2:7]
collect(1:2:7) collect(1:2:7)
# Code for section 3.1.6 # Code for section 4.1.6
y = aq[:, 2] y = aq[:, 2]
X = [ones(11) aq[:, 1]] X = [ones(11) aq[:, 1]]
@ -99,7 +99,7 @@ end
?² ?²
# Code for section 3.1.7 # Code for section 4.1.7
using Plots using Plots
scatter(aq[:, 1], aq[:, 2]; legend=false) scatter(aq[:, 1], aq[:, 2]; legend=false)
@ -112,7 +112,7 @@ plot(scatter(aq[:, 1], aq[:, 2]; legend=false),
plot([scatter(aq[:, i], aq[:, i+1]; legend=false) plot([scatter(aq[:, i], aq[:, i+1]; legend=false)
for i in 1:2:7]...) for i in 1:2:7]...)
# Code for section 3.2 # Code for section 4.2
two_standard = Dict{Int, Int}() two_standard = Dict{Int, Int}()
for i in [1, 2, 3, 4, 5, 6] for i in [1, 2, 3, 4, 5, 6]
@ -156,7 +156,7 @@ for d1 in all_dice, d2 in all_dice
end end
end end
# Code for section 3.3 # Code for section 4.3
aq = [10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58 aq = [10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58
8.0 6.95 8.0 8.14 8.0 6.77 8.0 5.76 8.0 6.95 8.0 8.14 8.0 6.77 8.0 5.76
@ -175,14 +175,14 @@ dataset1 = (x=aq[:, 1], y=aq[:, 2])
dataset1[1] dataset1[1]
dataset1.x dataset1.x
# Code for listing 3.2 # Code for listing 4.2
data = (set1=(x=aq[:, 1], y=aq[:, 2]), data = (set1=(x=aq[:, 1], y=aq[:, 2]),
set2=(x=aq[:, 3], y=aq[:, 4]), set2=(x=aq[:, 3], y=aq[:, 4]),
set3=(x=aq[:, 5], y=aq[:, 6]), set3=(x=aq[:, 5], y=aq[:, 6]),
set4=(x=aq[:, 7], y=aq[:, 8])) set4=(x=aq[:, 7], y=aq[:, 8]))
# Code for section 3.3.2 # Code for section 4.3.2
using Statistics using Statistics
map(s -> mean(s.x), data) map(s -> mean(s.x), data)
@ -194,7 +194,7 @@ model = lm(@formula(y ~ x), data.set1)
r2(model) r2(model)
# Code for section 3.3.3 # Code for section 4.3.3
model.mm model.mm
@ -208,152 +208,3 @@ empty_field!(nt, i) = empty!(nt[i])
nt = (dict = Dict("a" => 1, "b" => 2), int=10) nt = (dict = Dict("a" => 1, "b" => 2), int=10)
empty_field!(nt, 1) empty_field!(nt, 1)
nt nt
# Code for section 3.4.1
x = [1 2 3]
y = [1, 2, 3]
x * y
a = [1, 2, 3]
b = [4, 5, 6]
a * b
a .* b
map(*, a, b)
[a[i] * b[i] for i in eachindex(a, b)]
eachindex(a, b)
eachindex([1, 2, 3], [4, 5])
map(*, [1, 2, 3], [4, 5])
[1, 2, 3] .* [4, 5]
# Code for section 3.4.2
[1, 2, 3] .* [4]
[1, 2, 3] .^ 2
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10] .* [1 2 3 4 5 6 7 8 9 10]
["x", "y", "z"] .=> [sum minimum maximum]
abs.([1, -2, 3, -4])
abs([1, 2, 3])
string(1, 2, 3)
string.("x", 1:10)
f(i::Int) = string("got integer ", i)
f(s::String) = string("got string ", s)
f.([1, "1"])
# Code for section 3.4.3
in(1, [1, 2, 3])
in(4, [1, 2, 3])
in([1, 3, 5, 7, 9], [1, 2, 3, 4])
in.([1, 3, 5, 7, 9], [1, 2, 3, 4])
in.([1, 3, 5, 7, 9], Ref([1, 2, 3, 4]))
# Code for section 3.4.4
aq = [10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58
8.0 6.95 8.0 8.14 8.0 6.77 8.0 5.76
13.0 7.58 13.0 8.74 13.0 12.74 8.0 7.71
9.0 8.81 9.0 8.77 9.0 7.11 8.0 8.84
11.0 8.33 11.0 9.26 11.0 7.81 8.0 8.47
14.0 9.96 14.0 8.1 14.0 8.84 8.0 7.04
6.0 7.24 6.0 6.13 6.0 6.08 8.0 5.25
4.0 4.26 4.0 3.1 4.0 5.39 19.0 12.50
12.0 10.84 12.0 9.13 12.0 8.15 8.0 5.56
7.0 4.82 7.0 7.26 7.0 6.42 8.0 7.91
5.0 5.68 5.0 4.74 5.0 5.73 8.0 6.89]
using Statistics
mean.(eachcol(aq))
mean(eachcol(aq))
function R²(x, y)
X = [ones(11) x]
model = X \ y
prediction = X * model
error = y - prediction
SS_res = sum(v -> v ^ 2, error)
mean_y = mean(y)
SS_tot = sum(v -> (v - mean_y) ^ 2, y)
return 1 - SS_res / SS_tot
end
function R²(x, y)
X = [ones(11) x]
model = X \ y
prediction = X * model
SS_res = sum((y .- prediction) .^ 2)
SS_tot = sum((y .- mean(y)) .^ 2)
return 1 - SS_res / SS_tot
end
# Code for section 3.5
[]
Dict()
Float64[1, 2, 3]
Dict{UInt8, Float64}(0 => 0, 1 => 1)
UInt32(200)
Real[1, 1.0, 0x3]
v1 = Any[1, 2, 3]
eltype(v1)
v2 = Float64[1, 2, 3]
eltype(v2)
v3 = [1, 2, 3]
eltype(v2)
d1 = Dict()
eltype(d1)
d2 = Dict(1 => 2, 3 => 4)
eltype(d2)
p = 1 => 2
typeof(p)
# Code for section 3.5.1
[1, 2, 3] isa AbstractVector{Int}
[1, 2, 3] isa AbstractVector{Real}
AbstractVector{<:Real}
# Code for section 3.5.2
using Statistics
function ourcov(x::AbstractVector{<:Real},
y::AbstractVector{<:Real})
len = length(x)
@assert len == length(y) > 0
return sum((x .- mean(x)) .* (y .- mean(y))) / (len - 1)
end
ourcov(1:4, [1.0, 3.0, 2.0, 4.0])
cov(1:4, [1.0, 3.0, 2.0, 4.0])
ourcov(1:4, Any[1.0, 3.0, 2.0, 4.0])
x = Any[1, 2, 3]
identity.(x)
y = Any[1, 2.0]
identity.(y)

161
ch05.jl Normal file
View File

@ -0,0 +1,161 @@
# Bogumił Kamiński, 2021
# Codes for chapter 5
# Code for section 5.1.1
x = [1 2 3]
y = [1, 2, 3]
x * y
a = [1, 2, 3]
b = [4, 5, 6]
a * b
a .* b
map(*, a, b)
[a[i] * b[i] for i in eachindex(a, b)]
eachindex(a, b)
eachindex([1, 2, 3], [4, 5])
map(*, [1, 2, 3], [4, 5])
[1, 2, 3] .* [4, 5]
# Code for section 5.1.2
[1, 2, 3] .^ [2]
[1, 2, 3] .^ 2
[1, 2, 3, 4, 5, 6, 7, 8, 9, 10] .* [1 2 3 4 5 6 7 8 9 10]
["x", "y", "z"] .=> [sum minimum maximum]
abs.([1, -2, 3, -4])
abs([1, 2, 3])
string(1, 2, 3)
string.("x", 1:10)
f(i::Int) = string("got integer ", i)
f(s::String) = string("got string ", s)
f.([1, "1"])
# Code for section 5.1.3
in(1, [1, 2, 3])
in(4, [1, 2, 3])
1 in [1, 2, 3]
4 in [1, 2, 3]
in([1, 3, 5, 7, 9], [1, 2, 3, 4])
in([1, 3, 5, 7, 9], [1, 2, 3, 4, ([1, 3, 5, 7, 9]])
in.([1, 3, 5, 7, 9], [1, 2, 3, 4])
in.([1, 3, 5, 7, 9], Ref([1, 2, 3, 4]))
isodd.([1, 2, 3, 4, 5, 6, 7, 8, 9, 10] .+ [1 2 3 4 5 6 7 8 9 10])
Matrix{Any}(isodd.([1, 2, 3, 4, 5, 6, 7, 8, 9, 10] .* [1 2 3 4 5 6 7 8 9 10]))
# Code for section 5.1.4
aq = [10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58
8.0 6.95 8.0 8.14 8.0 6.77 8.0 5.76
13.0 7.58 13.0 8.74 13.0 12.74 8.0 7.71
9.0 8.81 9.0 8.77 9.0 7.11 8.0 8.84
11.0 8.33 11.0 9.26 11.0 7.81 8.0 8.47
14.0 9.96 14.0 8.1 14.0 8.84 8.0 7.04
6.0 7.24 6.0 6.13 6.0 6.08 8.0 5.25
4.0 4.26 4.0 3.1 4.0 5.39 19.0 12.50
12.0 10.84 12.0 9.13 12.0 8.15 8.0 5.56
7.0 4.82 7.0 7.26 7.0 6.42 8.0 7.91
5.0 5.68 5.0 4.74 5.0 5.73 8.0 6.89]
using Statistics
mean.(eachcol(aq))
mean(eachcol(aq))
function R²(x, y)
X = [ones(11) x]
model = X \ y
prediction = X * model
error = y - prediction
SS_res = sum(v -> v ^ 2, error)
mean_y = mean(y)
SS_tot = sum(v -> (v - mean_y) ^ 2, y)
return 1 - SS_res / SS_tot
end
function R²(x, y)
X = [ones(11) x]
model = X \ y
prediction = X * model
SS_res = sum((y .- prediction) .^ 2)
SS_tot = sum((y .- mean(y)) .^ 2)
return 1 - SS_res / SS_tot
end
# Code for section 5.2
[]
Dict()
Float64[1, 2, 3]
Dict{UInt8, Float64}(0 => 0, 1 => 1)
UInt32(200)
Real[1, 1.0, 0x3]
v1 = Any[1, 2, 3]
eltype(v1)
v2 = Float64[1, 2, 3]
eltype(v2)
v3 = [1, 2, 3]
eltype(v3)
d1 = Dict()
eltype(d1)
d2 = Dict(1 => 2, 3 => 4)
eltype(d2)
p = 1 => 2
typeof(p)
# Code for section 5.2.1
[1, 2, 3] isa AbstractVector{Int}
[1, 2, 3] isa AbstractVector{Real}
AbstractVector{<:Real} == AbstractVector{T} where T<:Real
# Code for section 5.2.2
using Statistics
function ourcov(x::AbstractVector{<:Real},
y::AbstractVector{<:Real})
len = length(x)
@assert len == length(y) > 0
return sum((x .- mean(x)) .* (y .- mean(y))) / (len - 1)
end
ourcov(1:4, [1.0, 3.0, 2.0, 4.0])
cov(1:4, [1.0, 3.0, 2.0, 4.0])
ourcov(1:4, Any[1.0, 3.0, 2.0, 4.0])
x = Any[1, 2, 3]
identity.(x)
y = Any[1, 2.0]
identity.(y)