add chapter 8

Manifest.toml

@@ -11,13 +11,19 @@ version = "1.1.0"
 
 [[deps.Adapt]]
 deps = ["LinearAlgebra"]
-git-tree-sha1 = "9faf218ea18c51fcccaf956c8d39614c9d30fe8b"
+git-tree-sha1 = "af92965fb30777147966f58acb05da51c5616b5f"
 uuid = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
-version = "3.3.2"
+version = "3.3.3"
 
 [[deps.ArgTools]]
 uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
 
+[[deps.ArnoldiMethod]]
+deps = ["LinearAlgebra", "Random", "StaticArrays"]
+git-tree-sha1 = "62e51b39331de8911e4a7ff6f5aaf38a5f4cc0ae"
+uuid = "ec485272-7323-5ecc-a04f-4719b315124d"
+version = "0.2.0"
+
 [[deps.Artifacts]]
 uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
 
@@ -49,9 +55,9 @@ version = "1.0.8+0"
 
 [[deps.CSV]]
 deps = ["CodecZlib", "Dates", "FilePathsBase", "InlineStrings", "Mmap", "Parsers", "PooledArrays", "SentinelArrays", "Tables", "Unicode", "WeakRefStrings"]
-git-tree-sha1 = "49f14b6c56a2da47608fe30aed711b5882264d7a"
+git-tree-sha1 = "9519274b50500b8029973d241d32cfbf0b127d97"
 uuid = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
-version = "0.9.11"
+version = "0.10.2"
 
 [[deps.Cairo_jll]]
 deps = ["Artifacts", "Bzip2_jll", "Fontconfig_jll", "FreeType2_jll", "Glib_jll", "JLLWrappers", "LZO_jll", "Libdl", "Pixman_jll", "Pkg", "Xorg_libXext_jll", "Xorg_libXrender_jll", "Zlib_jll", "libpng_jll"]
@@ -65,11 +71,16 @@ git-tree-sha1 = "c308f209870fdbd84cb20332b6dfaf14bf3387f8"
 uuid = "324d7699-5711-5eae-9e2f-1d82baa6b597"
 version = "0.10.2"
 
+[[deps.Chain]]
+git-tree-sha1 = "339237319ef4712e6e5df7758d0bccddf5c237d9"
+uuid = "8be319e6-bccf-4806-a6f7-6fae938471bc"
+version = "0.4.10"
+
 [[deps.ChainRulesCore]]
 deps = ["Compat", "LinearAlgebra", "SparseArrays"]
-git-tree-sha1 = "4c26b4e9e91ca528ea212927326ece5918a04b47"
+git-tree-sha1 = "54fc4400de6e5c3e27be6047da2ef6ba355511f8"
 uuid = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
-version = "1.11.2"
+version = "1.11.6"
 
 [[deps.ChangesOfVariables]]
 deps = ["ChainRulesCore", "LinearAlgebra", "Test"]
@@ -91,9 +102,9 @@ version = "0.7.0"
 
 [[deps.ColorSchemes]]
 deps = ["ColorTypes", "Colors", "FixedPointNumbers", "Random"]
-git-tree-sha1 = "a851fec56cb73cfdf43762999ec72eff5b86882a"
+git-tree-sha1 = "6b6f04f93710c71550ec7e16b650c1b9a612d0b6"
 uuid = "35d6a980-a343-548e-a6ea-1d62b119f2f4"
-version = "3.15.0"
+version = "3.16.0"
 
 [[deps.ColorTypes]]
 deps = ["FixedPointNumbers", "Random"]
@@ -135,9 +146,9 @@ uuid = "587fd27a-f159-11e8-2dae-1979310e6154"
 version = "0.2.7"
 
 [[deps.Crayons]]
-git-tree-sha1 = "3f71217b538d7aaee0b69ab47d9b7724ca8afa0d"
+git-tree-sha1 = "249fe38abf76d48563e2f4556bebd215aa317e15"
 uuid = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
-version = "4.0.4"
+version = "4.1.1"
 
 [[deps.DataAPI]]
 git-tree-sha1 = "cc70b17275652eb47bc9e5f81635981f13cea5c8"
@@ -152,9 +163,15 @@ version = "0.7.7"
 
 [[deps.DataFrames]]
 deps = ["Compat", "DataAPI", "Future", "InvertedIndices", "IteratorInterfaceExtensions", "LinearAlgebra", "Markdown", "Missings", "PooledArrays", "PrettyTables", "Printf", "REPL", "Reexport", "SortingAlgorithms", "Statistics", "TableTraits", "Tables", "Unicode"]
-git-tree-sha1 = "cfdfef912b7f93e4b848e80b9befdf9e331bc05a"
+git-tree-sha1 = "ae02104e835f219b8930c7664b8012c93475c340"
 uuid = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
-version = "1.3.1"
+version = "1.3.2"
+
+[[deps.DataFramesMeta]]
+deps = ["Chain", "DataFrames", "MacroTools", "OrderedCollections", "Reexport"]
+git-tree-sha1 = "ab4768d2cc6ab000cd0cec78e8e1ea6b03c7c3e2"
+uuid = "1313f7d8-7da2-5740-9ea0-a2ca25f37964"
+version = "0.10.0"
 
 [[deps.DataStructures]]
 deps = ["Compat", "InteractiveUtils", "OrderedCollections"]
@@ -193,9 +210,9 @@ uuid = "8ba89e20-285c-5b6f-9357-94700520ee1b"
 
 [[deps.Distributions]]
 deps = ["ChainRulesCore", "DensityInterface", "FillArrays", "LinearAlgebra", "PDMats", "Printf", "QuadGK", "Random", "SparseArrays", "SpecialFunctions", "Statistics", "StatsBase", "StatsFuns", "Test"]
-git-tree-sha1 = "6a8dc9f82e5ce28279b6e3e2cea9421154f5bd0d"
+git-tree-sha1 = "5863b0b10512ed4add2b5ec07e335dc6121065a5"
 uuid = "31c24e10-a181-5473-b8eb-7969acd0382f"
-version = "0.25.37"
+version = "0.25.41"
 
 [[deps.DocStringExtensions]]
 deps = ["LibGit2"]
@@ -291,21 +308,21 @@ version = "3.3.5+1"
 
 [[deps.GLM]]
 deps = ["Distributions", "LinearAlgebra", "Printf", "Reexport", "SparseArrays", "SpecialFunctions", "Statistics", "StatsBase", "StatsFuns", "StatsModels"]
-git-tree-sha1 = "f564ce4af5e79bb88ff1f4488e64363487674278"
+git-tree-sha1 = "fb764dacfa30f948d52a6a4269ae293a479bbc62"
 uuid = "38e38edf-8417-5370-95a0-9cbb8c7f171a"
-version = "1.5.1"
+version = "1.6.1"
 
 [[deps.GR]]
-deps = ["Base64", "DelimitedFiles", "GR_jll", "HTTP", "JSON", "Libdl", "LinearAlgebra", "Pkg", "Printf", "Random", "Serialization", "Sockets", "Test", "UUIDs"]
-git-tree-sha1 = "30f2b340c2fff8410d89bfcdc9c0a6dd661ac5f7"
+deps = ["Base64", "DelimitedFiles", "GR_jll", "HTTP", "JSON", "Libdl", "LinearAlgebra", "Pkg", "Printf", "Random", "RelocatableFolders", "Serialization", "Sockets", "Test", "UUIDs"]
+git-tree-sha1 = "4a740db447aae0fbeb3ee730de1afbb14ac798a1"
 uuid = "28b8d3ca-fb5f-59d9-8090-bfdbd6d07a71"
-version = "0.62.1"
+version = "0.63.1"
 
 [[deps.GR_jll]]
 deps = ["Artifacts", "Bzip2_jll", "Cairo_jll", "FFMPEG_jll", "Fontconfig_jll", "GLFW_jll", "JLLWrappers", "JpegTurbo_jll", "Libdl", "Libtiff_jll", "Pixman_jll", "Pkg", "Qt5Base_jll", "Zlib_jll", "libpng_jll"]
-git-tree-sha1 = "f97acd98255568c3c9b416c5a3cf246c1315771b"
+git-tree-sha1 = "aa22e1ee9e722f1da183eb33370df4c1aeb6c2cd"
 uuid = "d2c73de3-f751-5644-a686-071e5b155ba9"
-version = "0.63.0+0"
+version = "0.63.1+0"
 
 [[deps.GeometryBasics]]
 deps = ["EarCut_jll", "IterTools", "LinearAlgebra", "StaticArrays", "StructArrays", "Tables"]
@@ -331,6 +348,12 @@ git-tree-sha1 = "344bf40dcab1073aca04aa0df4fb092f920e4011"
 uuid = "3b182d85-2403-5c21-9c21-1e1f0cc25472"
 version = "1.3.14+0"
 
+[[deps.Graphs]]
+deps = ["ArnoldiMethod", "Compat", "DataStructures", "Distributed", "Inflate", "LinearAlgebra", "Random", "SharedArrays", "SimpleTraits", "SparseArrays", "Statistics"]
+git-tree-sha1 = "d727758173afef0af878b29ac364a0eca299fc6b"
+uuid = "86223c79-3864-5bf0-83f7-82e725a168b6"
+version = "1.5.1"
+
 [[deps.Grisu]]
 git-tree-sha1 = "53bb909d1151e57e2484c3d1b53e19552b887fb2"
 uuid = "42e2da0e-8278-4e71-bc24-59509adca0fe"
@@ -350,9 +373,14 @@ version = "2.8.1+1"
 
 [[deps.Impute]]
 deps = ["BSON", "CSV", "DataDeps", "Distances", "IterTools", "LinearAlgebra", "Missings", "NamedDims", "NearestNeighbors", "Random", "Statistics", "StatsBase", "TableOperations", "Tables"]
-git-tree-sha1 = "4baf7c1120d33f925259c98dce84c35cd107aae3"
+git-tree-sha1 = "d3fb6342d94030706ad31f05c23514962c29296c"
 uuid = "f7bf1975-0170-51b9-8c5f-a992d46b9575"
-version = "0.6.7"
+version = "0.6.8"
+
+[[deps.Inflate]]
+git-tree-sha1 = "f5fc07d4e706b84f72d54eedcc1c13d92fb0871c"
+uuid = "d25df0c9-e2be-5dd7-82c8-3ad0b3e990b9"
+version = "0.1.2"
 
 [[deps.IniFile]]
 deps = ["Test"]
@@ -398,9 +426,9 @@ version = "1.0.0"
 
 [[deps.JLLWrappers]]
 deps = ["Preferences"]
-git-tree-sha1 = "642a199af8b68253517b80bd3bfd17eb4e84df6e"
+git-tree-sha1 = "22df5b96feef82434b07327e2d3c770a9b21e023"
 uuid = "692b3bcd-3c85-4b1f-b108-f13ce0eb3210"
-version = "1.3.0"
+version = "1.4.0"
 
 [[deps.JSON]]
 deps = ["Dates", "Mmap", "Parsers", "Unicode"]
@@ -608,9 +636,9 @@ uuid = "05823500-19ac-5b8b-9628-191a04bc5112"
 
 [[deps.OpenSSL_jll]]
 deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
-git-tree-sha1 = "15003dcb7d8db3c6c857fda14891a539a8f2705a"
+git-tree-sha1 = "648107615c15d4e09f7eca16307bc821c1f718d8"
 uuid = "458c3c95-2e84-50aa-8efc-19380b2a3a95"
-version = "1.1.10+0"
+version = "1.1.13+0"
 
 [[deps.OpenSpecFun_jll]]
 deps = ["Artifacts", "CompilerSupportLibraries_jll", "JLLWrappers", "Libdl", "Pkg"]
@@ -643,9 +671,9 @@ version = "0.11.5"
 
 [[deps.Parsers]]
 deps = ["Dates"]
-git-tree-sha1 = "d7fa6237da8004be601e19bd6666083056649918"
+git-tree-sha1 = "92f91ba9e5941fc781fecf5494ac1da87bdac775"
 uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
-version = "2.1.3"
+version = "2.2.0"
 
 [[deps.Pixman_jll]]
 deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
@@ -665,15 +693,15 @@ version = "2.0.1"
 
 [[deps.PlotUtils]]
 deps = ["ColorSchemes", "Colors", "Dates", "Printf", "Random", "Reexport", "Statistics"]
-git-tree-sha1 = "68604313ed59f0408313228ba09e79252e4b2da8"
+git-tree-sha1 = "6f1b25e8ea06279b5689263cc538f51331d7ca17"
 uuid = "995b91a9-d308-5afd-9ec6-746e21dbc043"
-version = "1.1.2"
+version = "1.1.3"
 
 [[deps.Plots]]
 deps = ["Base64", "Contour", "Dates", "Downloads", "FFMPEG", "FixedPointNumbers", "GR", "GeometryBasics", "JSON", "Latexify", "LinearAlgebra", "Measures", "NaNMath", "PlotThemes", "PlotUtils", "Printf", "REPL", "Random", "RecipesBase", "RecipesPipeline", "Reexport", "Requires", "Scratch", "Showoff", "SparseArrays", "Statistics", "StatsBase", "UUIDs", "UnicodeFun", "Unzip"]
-git-tree-sha1 = "7eda8e2a61e35b7f553172ef3d9eaa5e4e76d92e"
+git-tree-sha1 = "db7393a80d0e5bef70f2b518990835541917a544"
 uuid = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
-version = "1.25.3"
+version = "1.25.6"
 
 [[deps.PooledArrays]]
 deps = ["DataAPI", "Future"]
@@ -728,20 +756,26 @@ version = "1.2.1"
 
 [[deps.RecipesPipeline]]
 deps = ["Dates", "NaNMath", "PlotUtils", "RecipesBase"]
-git-tree-sha1 = "7ad0dfa8d03b7bcf8c597f59f5292801730c55b8"
+git-tree-sha1 = "37c1631cb3cc36a535105e6d5557864c82cd8c2b"
 uuid = "01d81517-befc-4cb6-b9ec-a95719d0359c"
-version = "0.4.1"
+version = "0.5.0"
 
 [[deps.Reexport]]
 git-tree-sha1 = "45e428421666073eab6f2da5c9d310d99bb12f9b"
 uuid = "189a3867-3050-52da-a836-e630ba90ab69"
 version = "1.2.2"
 
+[[deps.RelocatableFolders]]
+deps = ["SHA", "Scratch"]
+git-tree-sha1 = "cdbd3b1338c72ce29d9584fdbe9e9b70eeb5adca"
+uuid = "05181044-ff0b-4ac5-8273-598c1e38db00"
+version = "0.1.3"
+
 [[deps.Requires]]
 deps = ["UUIDs"]
-git-tree-sha1 = "8f82019e525f4d5c669692772a6f4b0a58b06a6a"
+git-tree-sha1 = "838a3a4188e2ded87a4f9f184b4b0d78a1e91cb7"
 uuid = "ae029012-a4dd-5104-9daa-d747884805df"
-version = "1.2.0"
+version = "1.3.0"
 
 [[deps.Rmath]]
 deps = ["Random", "Rmath_jll"]
@@ -766,9 +800,9 @@ version = "1.1.0"
 
 [[deps.SentinelArrays]]
 deps = ["Dates", "Random"]
-git-tree-sha1 = "244586bc07462d22aed0113af9c731f2a518c93e"
+git-tree-sha1 = "15dfe6b103c2a993be24404124b8791a09460983"
 uuid = "91c51154-3ec4-41a3-a24f-3f23e20d615c"
-version = "1.3.10"
+version = "1.3.11"
 
 [[deps.Serialization]]
 uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
@@ -788,6 +822,12 @@ git-tree-sha1 = "91eddf657aca81df9ae6ceb20b959ae5653ad1de"
 uuid = "992d4aef-0814-514b-bc4d-f2e9a6c4116f"
 version = "1.0.3"
 
+[[deps.SimpleTraits]]
+deps = ["InteractiveUtils", "MacroTools"]
+git-tree-sha1 = "5d7e3f4e11935503d3ecaf7186eac40602e7d231"
+uuid = "699a6c99-e7fa-54fc-8d76-47d257e15c1d"
+version = "0.9.4"
+
 [[deps.Sockets]]
 uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
 
@@ -803,15 +843,15 @@ uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
 
 [[deps.SpecialFunctions]]
 deps = ["ChainRulesCore", "IrrationalConstants", "LogExpFunctions", "OpenLibm_jll", "OpenSpecFun_jll"]
-git-tree-sha1 = "f0bccf98e16759818ffc5d97ac3ebf87eb950150"
+git-tree-sha1 = "e08890d19787ec25029113e88c34ec20cac1c91e"
 uuid = "276daf66-3868-5448-9aa4-cd146d93841b"
-version = "1.8.1"
+version = "2.0.0"
 
 [[deps.StaticArrays]]
 deps = ["LinearAlgebra", "Random", "Statistics"]
-git-tree-sha1 = "3c76dde64d03699e074ac02eb2e8ba8254d428da"
+git-tree-sha1 = "2884859916598f974858ff01df7dfc6c708dd895"
 uuid = "90137ffa-7385-5640-81b9-e52037218182"
-version = "1.2.13"
+version = "1.3.3"
 
 [[deps.Statistics]]
 deps = ["LinearAlgebra", "SparseArrays"]
@@ -842,9 +882,9 @@ version = "0.6.28"
 
 [[deps.StructArrays]]
 deps = ["Adapt", "DataAPI", "StaticArrays", "Tables"]
-git-tree-sha1 = "2ce41e0d042c60ecd131e9fb7154a3bfadbf50d3"
+git-tree-sha1 = "d21f2c564b21a202f4677c0fba5b5ee431058544"
 uuid = "09ab397b-f2b6-538f-b94a-2f83cf4a842a"
-version = "0.6.3"
+version = "0.6.4"
 
 [[deps.StructTypes]]
 deps = ["Dates", "UUIDs"]
@@ -1071,6 +1111,12 @@ git-tree-sha1 = "79c31e7844f6ecf779705fbc12146eb190b7d845"
 uuid = "c5fb5394-a638-5e4d-96e5-b29de1b5cf10"
 version = "1.4.0+3"
 
+[[deps.ZipFile]]
+deps = ["Libdl", "Printf", "Zlib_jll"]
+git-tree-sha1 = "3593e69e469d2111389a9bd06bac1f3d730ac6de"
+uuid = "a5390f91-8eb1-5f08-bee0-b1d1ffed6cea"
+version = "0.9.4"
+
 [[deps.Zlib_jll]]
 deps = ["Libdl"]
 uuid = "83775a58-1f1d-513f-b197-d71354ab007a"
@@ -1105,9 +1151,9 @@ version = "1.6.38+0"
 
 [[deps.libvorbis_jll]]
 deps = ["Artifacts", "JLLWrappers", "Libdl", "Ogg_jll", "Pkg"]
-git-tree-sha1 = "c45f4e40e7aafe9d086379e5578947ec8b95a8fb"
+git-tree-sha1 = "b910cb81ef3fe6e78bf6acee440bda86fd6ae00c"
 uuid = "f27f6e37-5d2b-51aa-960f-b287f2bc3b7a"
-version = "1.3.7+0"
+version = "1.3.7+1"
 
 [[deps.nghttp2_jll]]
 deps = ["Artifacts", "Libdl"]

Project.toml

@@ -1,10 +1,13 @@
 [deps]
 BenchmarkTools = "6e4b80f9-dd63-53aa-95a3-0cdb28fa8baf"
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
+CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"
 CodecBzip2 = "523fee87-0ab8-5b00-afb7-3ecf72e48cfd"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
+DataFramesMeta = "1313f7d8-7da2-5740-9ea0-a2ca25f37964"
 FreqTables = "da1fdf0e-e0ff-5433-a45f-9bb5ff651cb1"
 GLM = "38e38edf-8417-5370-95a0-9cbb8c7f171a"
+Graphs = "86223c79-3864-5bf0-83f7-82e725a168b6"
 HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
 Impute = "f7bf1975-0170-51b9-8c5f-a992d46b9575"
 InlineStrings = "842dd82b-1e85-43dc-bf29-5d0ee9dffc48"
@@ -14,3 +17,4 @@ Missings = "e1d29d7a-bbdc-5cf2-9ac0-f12de2c33e28"
 Plots = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
 PooledArrays = "2dfb63ee-cc39-5dd5-95bd-886bf059d720"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
+ZipFile = "a5390f91-8eb1-5f08-bee0-b1d1ffed6cea"

appB.jl

@@ -155,3 +155,37 @@ proptable([walk_unique_2ahead() for _ in 1:10^5])
 
 @time wide = DataFrame(ones(1, 10_000), :auto);
 @time Tables.columntable(wide);
+
+# Code for exercise 8.1
+
+cg = complete_graph(37700)
+Base.summarysize(cg)
+@time deg_class(cg, classes_df.ml_target);
+
+# Code for exercise 8.2
+
+scatter(log1p.(agg_df.deg_ml),
+        log1p.(agg_df.deg_web);
+        zcolor=agg_df.web_mean,
+        xlabel="degree ml", ylabel="degree web",
+        markersize=2, markerstrokewidth=0, markeralpha=0.8,
+        legend=:topleft, labels = "fraction web",
+        xticks=gen_ticks(maximum(classes_df.deg_ml)),
+        yticks=gen_ticks(maximum(classes_df.deg_web)))
+
+# Code for exercise 8.3
+
+glm(@formula(ml_target~log1p(deg_ml)+log1p(deg_web)),
+    classes_df, Binomial(), ProbitLink())
+
+# Code for exercise 8.4
+
+df = DataFrame()
+df.a = [1, 2, 3]
+df.b = df.a
+df.b === df.a
+df.b = df[:, "b"]
+df.b === df.a
+df.b == df.a
+df[1:2, "a"] .= 10
+df

ch08.jl

@@ -0,0 +1,284 @@
+# Bogumił Kamiński, 2022
+
+# Codes for chapter 8
+
+# Codes for section 8.1
+
+# Code for listing 8.1
+
+import Downloads
+using SHA
+git_zip = "git_web_ml.zip"
+if !isfile(git_zip)
+    Downloads.download("https://snap.stanford.edu/data/" *
+                       "git_web_ml.zip",
+                       git_zip)
+end
+isfile(git_zip)
+open(sha256, git_zip) == [0x56, 0xc0, 0xc1, 0xc2,
+                          0xc4, 0x60, 0xdc, 0x4c,
+                          0x7b, 0xf8, 0x93, 0x57,
+                          0xb1, 0xfe, 0xc0, 0x20,
+                          0xf4, 0x5e, 0x2e, 0xce,
+                          0xba, 0xb8, 0x1d, 0x13,
+                          0x1d, 0x07, 0x3b, 0x10,
+                          0xe2, 0x8e, 0xc0, 0x31]
+
+# Code for opeining a zip archive
+
+import ZipFile
+git_archive = ZipFile.Reader(git_zip)
+
+# Code for listing 8.2
+
+function ingest_to_df(archive::ZipFile.Reader, filename::AbstractString)
+    idx = only(findall(x -> x.name == filename, archive.files))
+    return CSV.read(read(archive.files[idx]), DataFrame)
+end
+
+# Code for working with zip archive
+
+git_archive.files
+
+git_archive.files[2].name
+
+findall(x -> x.name == "git_web_ml/musae_git_edges.csv", git_archive.files)
+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
+
+using CSV
+using DataFrames
+edges_df = ingest_to_df(git_archive, "git_web_ml/musae_git_edges.csv");
+classes_df = ingest_to_df(git_archive, "git_web_ml/musae_git_target.csv");
+close(git_archive)
+summary(edges_df)
+describe(edges_df, :min, :max, :mean, :nmissing, :eltype)
+summary(classes_df)
+describe(classes_df, :min, :max, :mean, :nmissing, :eltype)
+
+# Code for updating data frame columns using broadcasting
+
+edges_df .+= 1
+classes_df.id .+= 1
+
+# Code for examples of data frame broadcasting
+
+df = DataFrame(a=1:3, b=[4, missing, 5])
+df .^ 2
+coalesce.(df, 0)
+df .+ [10, 11, 12]
+
+# Code for checking the order of :id column in a data frame
+
+classes_df.id == axes(classes_df, 1)
+
+# Code for the difference between ! and : in broadcasting assignment
+
+df = DataFrame(a=1:3, b=1:3)
+df[!, :a] .= "x"
+df[:, :b] .= "x"
+df
+
+# Code for the difference between ! and : in assignment
+
+df = DataFrame(a=1:3, b=1:3, c=1:3)
+df[!, :a] = ["x", "y", "z"]
+df[:, :b] = ["x", "y", "z"]
+df[:, :c] = [11, 12, 13]
+df
+
+# Codes for section 8.2
+
+# Code from listing 8.4
+
+using Graphs
+gh = SimpleGraph(nrow(classes_df))
+for (from, to) in eachrow(edges_df)
+    add_edge!(gh, from, to)
+end
+gh
+ne(gh)
+nv(gh)
+
+# Code for iterator destruction in iteration specification
+
+mat = [1 2; 3 4; 5 6]
+for (x1, x2) in eachrow(mat)
+    @show x1, x2
+end
+
+# Code for getting degrees of nodes in the graph
+
+degree(gh)
+
+# Code for adding a column to a data frame
+
+classes_df.deg = degree(gh)
+
+# Code for the difference between ! and : when adding a column
+
+df = DataFrame()
+x = [1, 2, 3]
+df[!, :x1] = x
+df[:, :x2] = x
+df
+df.x1 === x
+df.x2 === x
+df.x2 == x
+
+# Code for creating a column using broadcasting
+
+df.x3 .= 1
+df
+
+# Code for edge iterator of a graph
+
+edges(gh)
+
+e1 = first(edges(gh))
+dump(e1)
+e1.src
+e1.dst
+
+# Code for listing 8.5
+
+function deg_class(gh, class)
+    deg_ml = zeros(Int, length(class))
+    deg_web = zeros(Int, length(class))
+    for edge in edges(gh)
+        a, b = edge.src, edge.dst
+        if class[b] == 1
+            deg_ml[a] += 1
+        else
+            deg_web[a] += 1
+        end
+        if class[a] == 1
+            deg_ml[b] += 1
+        else
+            deg_web[b] += 1
+        end
+    end
+    return (deg_ml, deg_web)
+end
+
+# Code for computing machine learning and web neighbors for gh graph
+
+classes_df.deg_ml, classes_df.deg_web =
+deg_class(gh, classes_df.ml_target)
+
+# Code for checking type stability of deg_class function
+
+@time deg_class(gh, classes_df.ml_target);
+@code_warntype deg_class(gh, classes_df.ml_target)
+
+# Code for checking the classes_df summary statistics
+
+describe(classes_df, :min, :max, :mean, :std)
+
+# Code for average degree of node in the graph
+
+2 * ne(gh) / nv(gh)
+
+# Code for checking correctness of computations
+
+classes_df.deg_ml + classes_df.deg_web == classes_df.deg
+
+# Code for showing that DataFrames.jl checks consistency of stored objects
+
+df = DataFrame(a=1, b=11)
+push!(df.a, 2)
+df
+
+# Codes for section 8.3
+
+# Code for computing groupwise means of columns
+
+using Statistics
+for type in [0, 1], col in ["deg_ml", "deg_web"]
+    println((type, col, mean(classes_df[classes_df.ml_target .== type, col])))
+end
+
+gdf = groupby(classes_df, :ml_target)
+combine(gdf,
+        :deg_ml => mean => :mean_deg_ml,
+        :deg_web => mean => :mean_deg_web)
+
+using DataFramesMeta
+@combine(gdf,
+         :mean_deg_ml = mean(:deg_ml),
+         :mean_deg_web = mean(:deg_web))
+
+# Code for simple plotting of relationship between developer degree and type
+
+using Plots
+scatter(classes_df.deg_ml, classes_df.deg_web;
+        color=[x == 1 ? "black" : "gray" for x in classes_df.ml_target],
+        xlabel="degree ml", ylabel="degree web", labels=false)
+
+# Code for aggregation of degree data
+
+agg_df = combine(groupby(classes_df, [:deg_ml, :deg_web]),
+                 :ml_target => (x -> 1 - mean(x)) => :web_mean)
+
+# Code for comparison how Julia parses expressions
+
+:ml_target => (x -> 1 - mean(x)) => :web_mean
+:ml_target => x -> 1 - mean(x) => :web_mean
+
+# Code for aggregation using DataFramesMeta.jl
+
+@combine(groupby(classes_df, [:deg_ml, :deg_web]),
+         :web_mean = 1 - mean(:ml_target))
+
+# Code for getting summary information about the aggregated data frame
+
+describe(agg_df)
+
+# Code for log1p function
+
+log1p(0)
+
+# Code for listing 8.6
+
+function gen_ticks(maxv)
+    max2 = round(Int, log2(maxv))
+    tick = [0; 2 .^ (0:max2)]
+    return (log1p.(tick), tick)
+end
+
+log1pjitter(x) = log1p(x) - 0.05 + rand() / 10
+
+using Random
+Random.seed!(1234);
+scatter(log1pjitter.(agg_df.deg_ml),
+        log1pjitter.(agg_df.deg_web);
+        zcolor=agg_df.web_mean,
+        xlabel="degree ml", ylabel="degree web",
+        markersize=2, markerstrokewidth=0, markeralpha=0.8,
+        legend=:topleft, labels = "fraction web",
+        xticks=gen_ticks(maximum(classes_df.deg_ml)),
+        yticks=gen_ticks(maximum(classes_df.deg_web)))
+
+# Code for fitting logistic regression model
+
+using GLM
+glm(@formula(ml_target~log1p(deg_ml)+log1p(deg_web)), classes_df, Binomial(), LogitLink())
+
+# Code for inspecting @formula result
+
+@formula(ml_target~log1p(deg_ml)+log1p(deg_web))
+
+# Code for inserting columns to a data frame
+
+df = DataFrame(x=1:3)
+insertcols!(df, :y => 4:6)
+insertcols!(df, :y => 4:6)
+insertcols!(df, :z => 1)
+
+insertcols!(df, 1, :a => 0)
+insertcols!(df, :x, :pre_x => 2)
+insertcols!(df, :x, :post_x => 3, after=true)