fd-update

Author: tlienart

Manifest.toml

@@ -47,9 +47,9 @@ version = "1.0.6+1"
 
 [[CSV]]
 deps = ["CategoricalArrays", "DataFrames", "Dates", "FilePathsBase", "Mmap", "Parsers", "PooledArrays", "Tables", "Unicode", "WeakRefStrings"]
-git-tree-sha1 = "177e58c6965e6a0f544593b490c38a6c267bd8ce"
+git-tree-sha1 = "dd7861a31c6a2a9404186a80e5dec919a25b3abb"
 uuid = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
-version = "0.5.24"
+version = "0.5.25"
 
 [[CategoricalArrays]]
 deps = ["Compat", "DataAPI", "Future", "JSON", "Missings", "Printf", "Reexport", "Statistics", "Unicode"]
@@ -319,10 +319,10 @@ uuid = "38e38edf-8417-5370-95a0-9cbb8c7f171a"
 version = "1.3.7"
 
 [[GR]]
-deps = ["Base64", "DelimitedFiles", "LinearAlgebra", "Printf", "Random", "Serialization", "Sockets", "Test"]
-git-tree-sha1 = "10633436bc2fc836347bda5073b7b6f06dcdc5e6"
+deps = ["Base64", "DelimitedFiles", "LinearAlgebra", "Printf", "Random", "Serialization", "Sockets", "Test", "UUIDs"]
+git-tree-sha1 = "41dd1395d4dc559f1c2cb558cba784ef37b561fe"
 uuid = "28b8d3ca-fb5f-59d9-8090-bfdbd6d07a71"
-version = "0.46.0"
+version = "0.47.0"
 
 [[GaussianMixtures]]
 deps = ["Arpack", "Clustering", "Compat", "DelimitedFiles", "Distributed", "Distributions", "FileIO", "JLD2", "LinearAlgebra", "Logging", "PDMats", "Printf", "RDatasets", "Random", "ScikitLearnBase", "SpecialFunctions", "Statistics", "StatsBase", "Test"]
@@ -338,15 +338,15 @@ version = "0.11.2"
 
 [[GeometryTypes]]
 deps = ["ColorTypes", "FixedPointNumbers", "LinearAlgebra", "StaticArrays"]
-git-tree-sha1 = "62344139ee47be1fe862a946d41ead9314b1fb21"
+git-tree-sha1 = "480f30bd8e67240636e6d64e062c83745ee45b88"
 uuid = "4d00f742-c7ba-57c2-abde-4428a4b178cb"
-version = "0.7.8"
+version = "0.7.9"
 
 [[HTTP]]
 deps = ["Base64", "Dates", "IniFile", "MbedTLS", "Sockets"]
-git-tree-sha1 = "003d2e773b019fccb93a447bb0517256fda1a71e"
+git-tree-sha1 = "8d9bdd55c9d0d6ddf08f8b5229f90b7f274b6777"
 uuid = "cd3eb016-35fb-5094-929b-558a96fad6f3"
-version = "0.8.10"
+version = "0.8.12"
 
 [[IRTools]]
 deps = ["InteractiveUtils", "MacroTools", "Test"]
@@ -435,10 +435,9 @@ uuid = "b1bec4e5-fd48-53fe-b0cb-9723c09d164b"
 version = "0.4.0"
 
 [[LaTeXStrings]]
-deps = ["Compat"]
-git-tree-sha1 = "7ab9b8788cfab2bdde22adf9004bda7ad9954b6c"
+git-tree-sha1 = "de44b395389b84fd681394d4e8d39ef14e3a2ea8"
 uuid = "b964fa9f-0449-5b57-a5c2-d3ea65f4040f"
-version = "1.0.3"
+version = "1.1.0"
 
 [[LearnBase]]
 deps = ["LinearAlgebra", "SparseArrays", "StatsBase", "Test"]
@@ -549,10 +548,16 @@ deps = ["Base64"]
 uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
 
 [[MbedTLS]]
-deps = ["BinaryProvider", "Dates", "Libdl", "Random", "Sockets"]
-git-tree-sha1 = "85f5947b53c8cfd53ccfa3f4abae31faa22c2181"
+deps = ["Dates", "MbedTLS_jll", "Random", "Sockets"]
+git-tree-sha1 = "709797fadd2d3b7e3f040a9f6e12726a6d6d2bf5"
 uuid = "739be429-bea8-5141-9913-cc70e7f3736d"
-version = "0.7.0"
+version = "1.0.0"
+
+[[MbedTLS_jll]]
+deps = ["Libdl", "Pkg"]
+git-tree-sha1 = "066a4467008745eed36dad973ceb66405785a621"
+uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
+version = "2.16.0+1"
 
 [[Measures]]
 git-tree-sha1 = "e498ddeee6f9fdb4551ce855a46f54dbd900245f"
@@ -698,9 +703,9 @@ version = "0.6.3"
 
 [[Plots]]
 deps = ["Base64", "Contour", "Dates", "FFMPEG", "FixedPointNumbers", "GR", "GeometryTypes", "JSON", "LinearAlgebra", "Measures", "NaNMath", "Pkg", "PlotThemes", "PlotUtils", "Printf", "REPL", "Random", "RecipesBase", "Reexport", "Requires", "Showoff", "SparseArrays", "Statistics", "StatsBase", "UUIDs"]
-git-tree-sha1 = "5655c2e4d1296448afbec71a1b1c8716c83420cc"
+git-tree-sha1 = "305a6ceea7c6bf063fce224e4bcc0e0e6ce10ced"
 uuid = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
-version = "0.29.2"
+version = "0.29.3"
 
 [[PooledArrays]]
 deps = ["DataAPI"]
@@ -796,10 +801,16 @@ uuid = "ae029012-a4dd-5104-9daa-d747884805df"
 version = "1.0.1"
 
 [[Rmath]]
-deps = ["BinaryProvider", "Libdl", "Random", "Statistics"]
-git-tree-sha1 = "2bbddcb984a1d08612d0c4abb5b4774883f6fa98"
+deps = ["Random", "Rmath_jll"]
+git-tree-sha1 = "86c5647b565873641538d8f812c04e4c9dbeb370"
 uuid = "79098fc4-a85e-5d69-aa6a-4863f24498fa"
-version = "0.6.0"
+version = "0.6.1"
+
+[[Rmath_jll]]
+deps = ["Libdl", "Pkg"]
+git-tree-sha1 = "1660f8fefbf5ab9c67560513131d4e933012fc4b"
+uuid = "f50d1b31-88e8-58de-be2c-1cc44531875f"
+version = "0.2.2+0"
 
 [[SHA]]
 uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
@@ -962,9 +973,9 @@ version = "0.6.2"
 
 [[WoodburyMatrices]]
 deps = ["LinearAlgebra", "SparseArrays"]
-git-tree-sha1 = "bbb9f7fd6fbdd9582e77c0b698312c543de5eb71"
+git-tree-sha1 = "68f000f67654d07318d734b364a31233e465f49a"
 uuid = "efce3f68-66dc-5838-9240-27a6d6f5f9b6"
-version = "0.5.0"
+version = "0.5.1"
 
 [[XGBoost]]
 deps = ["BinaryProvider", "Libdl", "Printf", "Random", "SparseArrays", "Statistics", "Test"]

__site/assets/end-to-end/HouseKingCounty/code/ex10.jl

@@ -1,2 +1,7 @@
 # This file was generated, do not modify it. # hide
-select!(df, Not([:yr_renovated, :sqft_basement, :zipcode]));
+plt.figure(figsize=(8,6))
+plt.hist(df.price, color = "blue", edgecolor = "white", bins=50,
+         density=true, alpha=0.5)
+plt.xlabel("Price", fontsize=14)
+plt.ylabel("Frequency", fontsize=14)
+plt.savefig(joinpath(@OUTPUT, "hist_price.svg")) # hide

__site/assets/end-to-end/HouseKingCounty/code/ex11.jl

@@ -1,7 +1,10 @@
 # This file was generated, do not modify it. # hide
 plt.figure(figsize=(8,6))
-plt.hist(df.price, color = "blue", edgecolor = "white", bins=50,
-         density=true)
+plt.hist(df.price[df.isrenovated .== true], color="blue", density=true,
+        edgecolor="white", bins=50, label="renovated", alpha=0.5)
+plt.hist(df.price[df.isrenovated .== false], color="red", density=true,
+        edgecolor="white", bins=50, label="unrenovated", alpha=0.5)
 plt.xlabel("Price", fontsize=14)
 plt.ylabel("Frequency", fontsize=14)
-plt.savefig(joinpath(@OUTPUT, "hist_price.svg")) # hide
+plt.legend(fontsize=12)
+plt.savefig(joinpath(@OUTPUT, "hist_price2.svg")) # hide

__site/assets/end-to-end/HouseKingCounty/code/ex12.jl

@@ -1,10 +1,9 @@
 # This file was generated, do not modify it. # hide
-plt.figure(figsize=(8,6))
-plt.hist(df.price[df.isrenovated .== true], color="blue", density=true,
-        edgecolor="white", bins=50, label="renovated", alpha=0.5)
-plt.hist(df.price[df.isrenovated .== false], color="red", density=true,
-        edgecolor="white", bins=50, label="unrenovated", alpha=0.5)
-plt.xlabel("Price", fontsize=14)
-plt.ylabel("Frequency", fontsize=14)
-plt.legend(fontsize=12)
-plt.savefig(joinpath(@OUTPUT, "hist_price2.svg")) # hide
+@load DecisionTreeRegressor
+
+y, X = unpack(df, ==(:price), col -> true)
+train, test = partition(eachindex(y), 0.7, shuffle=true, rng=5)
+
+tree = machine(DecisionTreeRegressor(), X, y)
+
+fit!(tree, rows=train);

__site/assets/end-to-end/HouseKingCounty/code/ex13.jl

@@ -1,9 +1,2 @@
 # This file was generated, do not modify it. # hide
-@load DecisionTreeRegressor
-
-y, X = unpack(df, ==(:price), col -> true)
-train, test = partition(eachindex(y), 0.7, shuffle=true, rng=5)
-
-tree = machine(DecisionTreeRegressor(), X, y)
-
-fit!(tree, rows=train);
+rms(y[test], predict(tree, rows=test))

__site/assets/end-to-end/HouseKingCounty/code/ex14.jl

@@ -1,2 +1,2 @@
 # This file was generated, do not modify it. # hide
-rms(y[test], predict(tree, rows=test))
+@load RandomForestRegressor pkg=ScikitLearn

__site/assets/end-to-end/HouseKingCounty/code/ex15.jl

@@ -1,2 +1,2 @@
 # This file was generated, do not modify it. # hide
-@load RandomForestRegressor pkg=ScikitLearn
+coerce!(X, Finite => Count);

__site/assets/end-to-end/HouseKingCounty/code/ex16.jl

@@ -1,2 +1,6 @@
 # This file was generated, do not modify it. # hide
-coerce!(X, Finite => Count);
+rf_mdl = RandomForestRegressor()
+rf = machine(rf_mdl, X, y)
+fit!(rf, rows=train)
+
+rms(y[test], predict(rf, rows=test))

__site/assets/end-to-end/HouseKingCounty/code/ex17.jl

@@ -1,6 +1,4 @@
 # This file was generated, do not modify it. # hide
-rf_mdl = RandomForestRegressor()
-rf = machine(rf_mdl, X, y)
-fit!(rf, rows=train)
-
-rms(y[test], predict(rf, rows=test))
+cv3 = CV(; nfolds=3)
+res = evaluate(rf_mdl, X, y, resampling=CV(shuffle=true),
+               measure=rms, verbosity=0)

__site/assets/end-to-end/HouseKingCounty/code/ex18.jl

@@ -1,4 +1,2 @@
 # This file was generated, do not modify it. # hide
-cv3 = CV(; nfolds=3)
-res = evaluate(rf_mdl, X, y, resampling=CV(shuffle=true),
-               measure=rms, verbosity=0)
+@load XGBoostRegressor

__site/assets/end-to-end/HouseKingCounty/code/ex19.jl

@@ -1,2 +1,8 @@
 # This file was generated, do not modify it. # hide
-@load XGBoostRegressor
+coerce!(X, Count => Continuous)
+
+xgb  = XGBoostRegressor()
+xgbm = machine(xgb, X, y)
+fit!(xgbm, rows=train)
+
+rms(y[test], predict(xgbm, rows=test))

__site/assets/end-to-end/HouseKingCounty/code/ex20.jl

@@ -1,8 +1,3 @@
 # This file was generated, do not modify it. # hide
-coerce!(X, Count => Continuous)
-
-xgb  = XGBoostRegressor()
-xgbm = machine(xgb, X, y)
-fit!(xgbm, rows=train)
-
-rms(y[test], predict(xgbm, rows=test))
+r1 = range(xgb, :max_depth, lower=3, upper=10)
+r2 = range(xgb, :num_round, lower=1, upper=25);

__site/assets/end-to-end/HouseKingCounty/code/ex21.jl

@@ -1,3 +1,8 @@
 # This file was generated, do not modify it. # hide
-r1 = range(xgb, :max_depth, lower=3, upper=10)
-r2 = range(xgb, :num_round, lower=1, upper=25);
+tm = TunedModel(model=xgb, tuning=Grid(resolution=7),
+                resampling=CV(rng=11), ranges=[r1,r2],
+                measure=rms)
+mtm = machine(tm, X, y)
+fit!(mtm, rows=train)
+
+rms(y[test], predict(mtm, rows=test))

__site/assets/end-to-end/HouseKingCounty/code/ex22.jl

@@ -1,8 +1,2 @@
 # This file was generated, do not modify it. # hide
-tm = TunedModel(model=xgb, tuning=Grid(resolution=7),
-                resampling=CV(rng=11), ranges=[r1,r2,r3,r4,r5,r6,r7],
-                measure=rms)
-mtm = machine(tm, X, y)
-fit!(mtm, rows=train)
-
-rms(y[test], predict(mtm, rows=test))
+PyPlot.close_figs() # hide

__site/assets/end-to-end/HouseKingCounty/code/ex3.jl

@@ -1,5 +1,5 @@
 # This file was generated, do not modify it. # hide
 coerce!(df, :zipcode => Multiclass)
-df.isrenovated  = @. !ismissing(df.yr_renovated)
-df.has_basement = @. !ismissing(df.sqft_basement)
+df.isrenovated  = @. !iszero(df.yr_renovated)
+df.has_basement = @. !iszero(df.sqft_basement)
 schema(df)

__site/assets/end-to-end/HouseKingCounty/code/ex9.jl

@@ -1,7 +1,2 @@
 # This file was generated, do not modify it. # hide
-for col in names(df)
-    nmissings = sum(ismissing, df[!,col])
-    if nmissings > 0
-        println(rpad("$col has ", 25), nmissings, " missings")
-    end
-end
+select!(df, Not([:yr_renovated, :sqft_basement, :zipcode]));

__site/assets/end-to-end/HouseKingCounty/code/output/ex13.res

@@ -1 +1 @@
-nothing
+179.70137523672759

__site/assets/end-to-end/HouseKingCounty/code/output/ex14.res

@@ -1 +1,16 @@
-179.96112573828466
+RandomForestRegressor(
+    n_estimators = 100,
+    criterion = "mse",
+    max_depth = nothing,
+    min_samples_split = 2,
+    min_samples_leaf = 1,
+    min_weight_fraction_leaf = 0.0,
+    max_features = "auto",
+    max_leaf_nodes = nothing,
+    min_impurity_decrease = 0.0,
+    bootstrap = true,
+    oob_score = false,
+    n_jobs = nothing,
+    random_state = nothing,
+    verbose = 0,
+    warm_start = false) @ 8…80

__site/assets/end-to-end/HouseKingCounty/code/output/ex15.res

@@ -1,16 +1 @@
-RandomForestRegressor(
-    n_estimators = 100,
-    criterion = "mse",
-    max_depth = nothing,
-    min_samples_split = 2,
-    min_samples_leaf = 1,
-    min_weight_fraction_leaf = 0.0,
-    max_features = "auto",
-    max_leaf_nodes = nothing,
-    min_impurity_decrease = 0.0,
-    bootstrap = true,
-    oob_score = false,
-    n_jobs = nothing,
-    random_state = nothing,
-    verbose = 0,
-    warm_start = false) @ 4…24
+nothing

__site/assets/end-to-end/HouseKingCounty/code/output/ex16.res

@@ -1 +1 @@
-nothing
+137.22983495128528

__site/assets/end-to-end/HouseKingCounty/code/output/ex17.res

@@ -1 +1,6 @@
-137.65885615237326
+┌───────────┬───────────────┬────────────────────────────────────────────┐
+│ _.measure │ _.measurement │ _.per_fold                                 │
+├───────────┼───────────────┼────────────────────────────────────────────┤
+│ rms       │ 133.0         │ [134.0, 125.0, 126.0, 144.0, 132.0, 140.0] │
+└───────────┴───────────────┴────────────────────────────────────────────┘
+_.per_observation = [missing]

__site/assets/end-to-end/HouseKingCounty/code/output/ex18.res

@@ -1,6 +1,36 @@
-┌───────────┬───────────────┬────────────────────────────────────────────┐
-│ _.measure │ _.measurement │ _.per_fold                                 │
-├───────────┼───────────────┼────────────────────────────────────────────┤
-│ rms       │ 136.0         │ [148.0, 138.0, 123.0, 127.0, 143.0, 134.0] │
-└───────────┴───────────────┴────────────────────────────────────────────┘
-_.per_observation = [missing]
+XGBoostRegressor(
+    num_round = 1,
+    booster = "gbtree",
+    disable_default_eval_metric = 0,
+    eta = 0.3,
+    gamma = 0.0,
+    max_depth = 6,
+    min_child_weight = 1.0,
+    max_delta_step = 0.0,
+    subsample = 1.0,
+    colsample_bytree = 1.0,
+    colsample_bylevel = 1.0,
+    lambda = 1.0,
+    alpha = 0.0,
+    tree_method = "auto",
+    sketch_eps = 0.03,
+    scale_pos_weight = 1.0,
+    updater = "auto",
+    refresh_leaf = 1,
+    process_type = "default",
+    grow_policy = "depthwise",
+    max_leaves = 0,
+    max_bin = 256,
+    predictor = "cpu_predictor",
+    sample_type = "uniform",
+    normalize_type = "tree",
+    rate_drop = 0.0,
+    one_drop = 0,
+    skip_drop = 0.0,
+    feature_selector = "cyclic",
+    top_k = 0,
+    tweedie_variance_power = 1.5,
+    objective = "reg:linear",
+    base_score = 0.5,
+    eval_metric = "rmse",
+    seed = 0) @ 8…21