update codes

Manifest.toml

@@ -1,6 +1,6 @@
 # This file is machine-generated - editing it directly is not advised
 
-julia_version = "1.7.1"
+julia_version = "1.7.2"
 manifest_format = "2.0"
 
 [[deps.AbstractFFTs]]
@@ -133,6 +133,12 @@ version = "3.41.0"
 deps = ["Artifacts", "Libdl"]
 uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
 
+[[deps.Conda]]
+deps = ["Downloads", "JSON", "VersionParsing"]
+git-tree-sha1 = "6cdc8832ba11c7695f494c9d9a1c31e90959ce0f"
+uuid = "8f4d0f93-b110-5947-807f-2305c1781a2d"
+version = "1.6.0"
+
 [[deps.Contour]]
 deps = ["StaticArrays"]
 git-tree-sha1 = "9f02045d934dc030edad45944ea80dbd1f0ebea7"
@@ -741,6 +747,12 @@ git-tree-sha1 = "78aadffb3efd2155af139781b8a8df1ef279ea39"
 uuid = "1fd47b50-473d-5c70-9696-f719f8f3bcdc"
 version = "2.4.2"
 
+[[deps.RCall]]
+deps = ["CategoricalArrays", "Conda", "DataFrames", "DataStructures", "Dates", "Libdl", "Missings", "REPL", "Random", "Requires", "StatsModels", "WinReg"]
+git-tree-sha1 = "72fddd643785ec1f36581cbc3d288529b96e99a7"
+uuid = "6f49c342-dc21-5d91-9882-a32aef131414"
+version = "0.13.13"
+
 [[deps.REPL]]
 deps = ["InteractiveUtils", "Markdown", "Sockets", "Unicode"]
 uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
@@ -955,6 +967,11 @@ git-tree-sha1 = "34db80951901073501137bdbc3d5a8e7bbd06670"
 uuid = "41fe7b60-77ed-43a1-b4f0-825fd5a5650d"
 version = "0.1.2"
 
+[[deps.VersionParsing]]
+git-tree-sha1 = "58d6e80b4ee071f5efd07fda82cb9fbe17200868"
+uuid = "81def892-9a0e-5fdd-b105-ffc91e053289"
+version = "1.3.0"
+
 [[deps.Wayland_jll]]
 deps = ["Artifacts", "Expat_jll", "JLLWrappers", "Libdl", "Libffi_jll", "Pkg", "XML2_jll"]
 git-tree-sha1 = "3e61f0b86f90dacb0bc0e73a0c5a83f6a8636e23"
@@ -973,6 +990,12 @@ git-tree-sha1 = "c69f9da3ff2f4f02e811c3323c22e5dfcb584cfa"
 uuid = "ea10d353-3f73-51f8-a26c-33c1cb351aa5"
 version = "1.4.1"
 
+[[deps.WinReg]]
+deps = ["Test"]
+git-tree-sha1 = "808380e0a0483e134081cc54150be4177959b5f4"
+uuid = "1b915085-20d7-51cf-bf83-8f477d6f5128"
+version = "0.3.1"
+
 [[deps.XML2_jll]]
 deps = ["Artifacts", "JLLWrappers", "Libdl", "Libiconv_jll", "Pkg", "Zlib_jll"]
 git-tree-sha1 = "1acf5bdf07aa0907e0a37d3718bb88d4b687b74a"

Project.toml

@@ -16,5 +16,6 @@ Loess = "4345ca2d-374a-55d4-8d30-97f9976e7612"
 Missings = "e1d29d7a-bbdc-5cf2-9ac0-f12de2c33e28"
 Plots = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
 PooledArrays = "2dfb63ee-cc39-5dd5-95bd-886bf059d720"
+RCall = "6f49c342-dc21-5d91-9882-a32aef131414"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 ZipFile = "a5390f91-8eb1-5f08-bee0-b1d1ffed6cea"

appB.jl

@@ -82,16 +82,14 @@ plot(scatter(data.set1.x, data.set1.y; legend=false),
 
 parse.(Int, ["1", "2", "3"])
 
-# CODES BELOW REQUIRE RE-NUMBERING
+# Code for exercise 6.1
-
-# Code for exercise 4.1
 
 years_table = freqtable(years)
 plot(names(years_table, 1), years_table; legend=false,
            xlabel="year", ylabel="# of movies")
 
 
-# Code for exercise 4.2
+# Code for exercise 6.2
 
 s3 = Symbol.(s1)
 @benchmark sort($s3)
@@ -99,7 +97,7 @@ s3 = Symbol.(s1)
 @benchmark unique($s2)
 @benchmark unique($s3)
 
-# Code for exercise 5.1
+# Code for exercise 7.1
 
 v = ["1", "2", missing, "4"]
 [ismissing(x) ? missing : parse(Int, x) for x in v]
@@ -113,43 +111,43 @@ end
 using Missings
 passmissing(parse).(Int, v)
 
-# Code for exercise 5.2
+# Code for exercise 7.2
 
 using Dates
 Date(2021, 1, 1):Month(1):Date(2021, 12, 1)
 collect(Date(2021, 1, 1):Month(1):Date(2021, 12, 1))
 
-# Code for exercise 6.1
+# Code for exercise 8.1
 
 using BenchmarkTools
 @benchmark $puzzles."Rating"
 
-# Code for exercise 6.2
+# Code for exercise 9.1
 
 using StatsBase
 summarystats(puzzles[puzzles.Popularity .== 100, "NbPlays"])
 summarystats(puzzles[puzzles.Popularity .== -100, "NbPlays"])
 
-# Code for exercise 6.3
+# Code for exercise 9.2
 
 sum(length, values(rating_mapping))
 nrow(good)
 
-# Code for exercise 7.1
+# Code for exercise 10.1
 
 using BenchmarkTools
 x = rand(10^6);
 @btime DataFrame(x=$x);
 @btime DataFrame(x=$x; copycols=false);
 
-# Code for exercise 7.2
+# Code for exercise 10.2
 
 df1 = DataFrame(a=1,b=2)
 df2 = DataFrame(b=3, a=4)
 vcat(df1, df2)
 vcat(df1, df2, cols=:orderequal)
 
-# Code for exercise 7.3
+# Code for exercise 10.3
 
 function walk_unique_2ahead()
     walk = DataFrame(x=0, y=0)
@@ -162,18 +160,18 @@ end
 Random.seed!(2);
 proptable([walk_unique_2ahead() for _ in 1:10^5])
 
-# Code for exercise 7.4
+# Code for exercise 11.1
 
 @time wide = DataFrame(ones(1, 10_000), :auto);
 @time Tables.columntable(wide);
 
-# Code for exercise 8.1
+# Code for exercise 12.1
 
 cg = complete_graph(37700)
 Base.summarysize(cg)
 @time deg_class(cg, classes_df.ml_target);
 
-# Code for exercise 8.2
+# Code for exercise 12.2
 
 scatter(log1p.(agg_df.deg_ml),
         log1p.(agg_df.deg_web);
@@ -184,12 +182,12 @@ scatter(log1p.(agg_df.deg_ml),
         xticks=gen_ticks(maximum(classes_df.deg_ml)),
         yticks=gen_ticks(maximum(classes_df.deg_web)))
 
-# Code for exercise 8.3
+# Code for exercise 12.3
 
 glm(@formula(ml_target~log1p(deg_ml)+log1p(deg_web)),
     classes_df, Binomial(), ProbitLink())
 
-# Code for exercise 8.4
+# Code for exercise 12.4
 
 df = DataFrame()
 df.a = [1, 2, 3]

ch10.jl

@@ -1,8 +1,8 @@
 # Bogumił Kamiński, 2022
 
-# Codes for chapter 7
+# Codes for chapter 10
 
-# Code for section 7.1
+# Code for section 10.1
 
 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
@@ -16,16 +16,11 @@ aq = [10.0   8.04  10.0  9.14  10.0   7.46   8.0   6.58
        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];
 
-data = (set1=(x=aq[:, 1], y=aq[:, 2]),
-        set2=(x=aq[:, 3], y=aq[:, 4]),
-        set3=(x=aq[:, 5], y=aq[:, 6]),
-        set4=(x=aq[:, 7], y=aq[:, 8]));
-
 using DataFrames
 
-# Code for listing 7.1
+# Code for listing 10.1
 
-aq1 = ataFrame(aq, ["x1", "y1", "x2", "y2", "x3", "y3", "x4", "y4"])
+aq1 = DataFrame(aq, ["x1", "y1", "x2", "y2", "x3", "y3", "x4", "y4"])
 DataFrame(aq, [:x1, :y1, :x2, :y2, :x3, :y3, :x4, :y4])
 
 # Code for creating DataFrame with automatic column names
@@ -38,7 +33,12 @@ aq_vec = collect(eachcol(aq))
 DataFrame(aq_vec, ["x1", "y1", "x2", "y2", "x3", "y3", "x4", "y4"])
 DataFrame(aq_vec, :auto)
 
-# Codes for section 7.1.2
+# Codes for section 10.1.2
+
+data = (set1=(x=aq[:, 1], y=aq[:, 2]),
+        set2=(x=aq[:, 3], y=aq[:, 4]),
+        set3=(x=aq[:, 5], y=aq[:, 6]),
+        set4=(x=aq[:, 7], y=aq[:, 8]));
 
 data.set1.x
 
@@ -84,7 +84,11 @@ df.x
 
 DataFrame(x=[1], y=[1, 2, 3])
 
-# Codes for section 7.1.3
+using RCall
+r_df = R"data.frame(a=1:6, b=1:2, c=1:3)"
+julia_df = rcopy(r_df)
+
+# Codes for section 10.1.3
 
 data.set1
 DataFrame(data.set1)
@@ -93,11 +97,11 @@ DataFrame([(a=1, b=2), (a=3, b=4), (a=5, b=6)])
 
 data
 
-# Code for listing 7.2
+# Code for listing 10.2
 
 aq2 = DataFrame(data)
 
-# Codes for listing 7.3
+# Codes for listing 10.3
 
 data_dfs = map(DataFrame, data)
 
@@ -114,14 +118,14 @@ vcat(data_dfs.set1, data_dfs.set2, data_dfs.set3, data_dfs.set4;
 reduce(vcat, collect(data_dfs);
        source="source_id"=>string.("set", 1:4))
 
-# Code for listing 7.4
+# Code for listing 10.4
 
 df1 = DataFrame(a=1:3, b=11:13)
 df2 = DataFrame(a=4:6, c=24:26)
 vcat(df1, df2)
 vcat(df1, df2; cols=:union)
 
-# Code for listing 7.5
+# Code for listing 10.5
 
 df_agg = DataFrame()
 append!(df_agg, data_dfs.set1)
@@ -140,7 +144,7 @@ df2 = DataFrame(a=4:6, b=[14, missing, 16])
 append!(df1, df2)
 append!(df1, df2; promote=true)
 
-# Code for section 7.2.3
+# Code for section 10.2.3
 
 df = DataFrame()
 push!(df, (a=1, b=2))
@@ -188,7 +192,7 @@ range(1, 5)
 
 (3/4)^9
 
-# Code for listing 7.6
+# Code for listing 10.6
 
 function walk_unique() #A
     walk = DataFrame(x=0, y=0)
@@ -201,79 +205,8 @@ end
 Random.seed!(2);
 proptable([walk_unique() for _ in 1:10^5])
 
-# Code for a note on conversion
+# code for serialization
 
-x = [1.5]
+using Serialization
-x[1] = 1
+serialize("walk.bin", walk)
-x
+deserialize("walk.bin") == walk
-
-# Code from section 7.3.1
-
-Matrix(walk)
-Matrix{Any}(walk)
-Matrix{String}(walk)
-
-plot(walk)
-
-plot(Matrix(walk); labels=["x" "y"] , legend=:topleft)
-
-# Code from section 7.3.2
-
-Tables.columntable(walk)
-
-using BenchmarkTools
-function mysum(table)
-           s = 0 #A
-           for v in table.x #B
-               s += v
-           end
-           return s
-       end
-df = DataFrame(x=1:1_000_000);
-@btime mysum($df)
-
-tab = Tables.columntable(df);
-@btime mysum($tab)
-
-@code_warntype mysum(df)
-
-@code_warntype mysum(tab)
-
-typeof(tab)
-
-function barrier_mysum2(x)
-    s = 0
-    for v in x
-        s += v
-    end
-    return s
-end
-mysum2(table) = barrier_mysum2(table.x)
-@btime mysum2($df)
-
-df = DataFrame(a=[1, 1, 2], b=[1, 1, 2])
-unique(df)
-
-tab = Tables.columntable(df)
-unique(tab)
-
-# Code from section 7.3.3
-
-Tables.rowtable(walk)
-
-nti = Tables.namedtupleiterator(walk)
-for v in nti
-    println(v)
-end
-
-er = eachrow(walk)
-er[1]
-er[end]
-ec = eachcol(walk)
-ec[1]
-ec[end]
-
-identity.(eachcol(walk))
-
-df = DataFrame(x=1:2, b=["a", "b"])
-identity.(eachcol(df))

ch11.jl

@@ -0,0 +1,85 @@
+# Bogumił Kamiński, 2022
+
+# Codes for chapter 11
+
+# Code for section 11.1
+
+# Code for a note on conversion
+
+x = [1.5]
+x[1] = 1
+x
+
+# Code from section 11.1.1
+
+using Serialization
+walk = deserialize("walk.bin")
+
+Matrix(walk)
+Matrix{Any}(walk)
+Matrix{String}(walk)
+
+plot(walk)
+
+plot(Matrix(walk); labels=["x" "y"] , legend=:topleft)
+
+# Code from section 11.1.2
+
+Tables.columntable(walk)
+
+using BenchmarkTools
+function mysum(table)
+           s = 0 #A
+           for v in table.x #B
+               s += v
+           end
+           return s
+       end
+df = DataFrame(x=1:1_000_000);
+@btime mysum($df)
+
+tab = Tables.columntable(df);
+@btime mysum($tab)
+
+@code_warntype mysum(df)
+
+@code_warntype mysum(tab)
+
+typeof(tab)
+
+function barrier_mysum2(x)
+    s = 0
+    for v in x
+        s += v
+    end
+    return s
+end
+mysum2(table) = barrier_mysum2(table.x)
+@btime mysum2($df)
+
+df = DataFrame(a=[1, 1, 2], b=[1, 1, 2])
+unique(df)
+
+tab = Tables.columntable(df)
+unique(tab)
+
+# Code from section 11.1.3
+
+Tables.rowtable(walk)
+
+nti = Tables.namedtupleiterator(walk)
+for v in nti
+    println(v)
+end
+
+er = eachrow(walk)
+er[1]
+er[end]
+ec = eachcol(walk)
+ec[1]
+ec[end]
+
+identity.(eachcol(walk))
+
+df = DataFrame(x=1:2, b=["a", "b"])
+identity.(eachcol(df))

ch12.jl

@@ -1,10 +1,10 @@
 # Bogumił Kamiński, 2022
 
-# Codes for chapter 8
+# Codes for chapter 12
 
-# Codes for section 8.1
+# Codes for section 12.1
 
-# Code for listing 8.1
+# Code for listing 12.1
 
 import Downloads
 using SHA
@@ -29,7 +29,7 @@ open(sha256, git_zip) == [0x56, 0xc0, 0xc1, 0xc2,
 import ZipFile
 git_archive = ZipFile.Reader(git_zip)
 
-# Code for listing 8.2
+# Code for listing 12.2
 
 function ingest_to_df(archive::ZipFile.Reader, filename::AbstractString)
     idx = only(findall(x -> x.name == filename, archive.files))
@@ -48,7 +48,7 @@ findall(x -> x.name == "", git_archive.files)
 only(findall(x -> x.name == "git_web_ml/musae_git_edges.csv", git_archive.files))
 only(findall(x -> x.name == "", git_archive.files))
 
-# Code for listing 8.3
+# Code for listing 12.3
 
 using CSV
 using DataFrames
@@ -91,9 +91,9 @@ df[:, :b] = ["x", "y", "z"]
 df[:, :c] = [11, 12, 13]
 df
 
-# Codes for section 8.2
+# Codes for section 12.2
 
-# Code from listing 8.4
+# Code from listing 12.4
 
 using Graphs
 gh = SimpleGraph(nrow(classes_df))
@@ -144,7 +144,7 @@ dump(e1)
 e1.src
 e1.dst
 
-# Code for listing 8.5
+# Code for listing 12.5
 
 function deg_class(gh, class)
     deg_ml = zeros(Int, length(class))
@@ -193,7 +193,7 @@ df = DataFrame(a=1, b=11)
 push!(df.a, 2)
 df
 
-# Codes for section 8.3
+# Codes for section 12.3
 
 # Code for computing groupwise means of columns
 
@@ -242,7 +242,7 @@ describe(agg_df)
 
 log1p(0)
 
-# Code for listing 8.6
+# Code for listing 12.6
 
 function gen_ticks(maxv)
     max2 = round(Int, log2(maxv))