Merge pull request #265 from FluxML/dev

Update docs
FluxML · Jun 12, 2024 · aea9436 · aea9436
2 parents 3766e44 + 3427fcb
commit aea9436
Show file tree

Hide file tree

Showing 33 changed files with 629 additions and 174 deletions.
diff --git a/README.md b/README.md
@@ -34,7 +34,7 @@ Grab some data and split into features and target:
 
 ```julia
 iris = RDatasets.dataset("datasets", "iris");
-y, X = unpack(iris, ==(:Species), colname -> true, rng=123);
+y, X = unpack(iris, ==(:Species), rng=123);
 X = Float32.(X);      # To optmise for GPUs
 ```
 
@@ -83,17 +83,16 @@ Train the wrapped model:
 julia> mach = machine(iterated_model, X, y)
 julia> fit!(mach)
 
-[ Info: Training machine(ProbabilisticIteratedModel(model = NeuralNetworkClassifier(builder = MLP(hidden = (5, 4), …), …), …), …).
-[ Info: No iteration parameter specified. Using `iteration_parameter=:(epochs)`.
-[ Info: final loss: 0.10431026246922499
-[ Info: final training loss: 0.046286315
-[ Info: Stop triggered by Patience(4) stopping criterion.
-[ Info: Total of 349 iterations.
+[ Info: No iteration parameter specified. Using `iteration_parameter=:(epochs)`. 
+[ Info: final loss: 0.1284184007796247
+[ Info: final training loss: 0.055630706
+[ Info: Stop triggered by NumberSinceBest(5) stopping criterion. 
+[ Info: Total of 811 iterations. 
 ```
 Inspect results:
 
 ```julia-repl
-julia> plot(train_losses, label="Validation Loss", linewidth=2, size=(800,400))
+julia> plot(train_losses, label="Training Loss")
 julia> plot!(validation_losses, label="Validation Loss", linewidth=2, size=(800,400))
 ```
 

diff --git a/docs/src/common_workflows/architecture_search/notebook.ipynb b/docs/src/common_workflows/architecture_search/notebook.ipynb
@@ -95,7 +95,7 @@
    "cell_type": "code",
    "source": [
     "iris = RDatasets.dataset(\"datasets\", \"iris\");\n",
-    "y, X = unpack(iris, ==(:Species), colname -> true, rng = 123);\n",
+    "y, X = unpack(iris, ==(:Species), rng = 123);\n",
     "X = Float32.(X);      # To be compatible with type of network network parameters\n",
     "first(X, 5)"
    ],
@@ -130,7 +130,7 @@
     {
      "output_type": "execute_result",
      "data": {
-      "text/plain": "NeuralNetworkClassifier(\n  builder = MLP(\n        hidden = (1, 1, 1), \n        σ = NNlib.relu), \n  finaliser = NNlib.softmax, \n  optimiser = Adam(0.01, (0.9, 0.999), 1.0e-8), \n  loss = Flux.Losses.crossentropy, \n  epochs = 10, \n  batch_size = 8, \n  lambda = 0.0, \n  alpha = 0.0, \n  rng = 42, \n  optimiser_changes_trigger_retraining = false, \n  acceleration = ComputationalResources.CPU1{Nothing}(nothing))"
+      "text/plain": "NeuralNetworkClassifier(\n  builder = MLP(\n        hidden = (1, 1, 1), \n        σ = NNlib.relu), \n  finaliser = NNlib.softmax, \n  optimiser = Adam(0.01, (0.9, 0.999), 1.0e-8), \n  loss = Flux.Losses.crossentropy, \n  epochs = 10, \n  batch_size = 8, \n  lambda = 0.0, \n  alpha = 0.0, \n  rng = 42, \n  optimiser_changes_trigger_retraining = false, \n  acceleration = CPU1{Nothing}(nothing))"
      },
      "metadata": {},
      "execution_count": 4
@@ -306,7 +306,7 @@
     {
      "output_type": "execute_result",
      "data": {
-      "text/plain": "NeuralNetworkClassifier(\n  builder = MLP(\n        hidden = (21, 57, 25), \n        σ = NNlib.relu), \n  finaliser = NNlib.softmax, \n  optimiser = Adam(0.01, (0.9, 0.999), 1.0e-8), \n  loss = Flux.Losses.crossentropy, \n  epochs = 10, \n  batch_size = 8, \n  lambda = 0.0, \n  alpha = 0.0, \n  rng = 42, \n  optimiser_changes_trigger_retraining = false, \n  acceleration = ComputationalResources.CPU1{Nothing}(nothing))"
+      "text/plain": "NeuralNetworkClassifier(\n  builder = MLP(\n        hidden = (45, 49, 21), \n        σ = NNlib.relu), \n  finaliser = NNlib.softmax, \n  optimiser = Adam(0.01, (0.9, 0.999), 1.0e-8), \n  loss = Flux.Losses.crossentropy, \n  epochs = 10, \n  batch_size = 8, \n  lambda = 0.0, \n  alpha = 0.0, \n  rng = 42, \n  optimiser_changes_trigger_retraining = false, \n  acceleration = CPU1{Nothing}(nothing))"
      },
      "metadata": {},
      "execution_count": 8
@@ -341,9 +341,9 @@
     {
      "output_type": "execute_result",
      "data": {
-      "text/plain": "\u001b[1m10×2 DataFrame\u001b[0m\n\u001b[1m Row \u001b[0m│\u001b[1m mlp                           \u001b[0m\u001b[1m measurement \u001b[0m\n     │\u001b[90m MLP…                          \u001b[0m\u001b[90m Float64     \u001b[0m\n─────┼────────────────────────────────────────────\n   1 │ MLP(hidden = (21, 57, 25), …)    0.0867019\n   2 │ MLP(hidden = (45, 17, 13), …)    0.0929803\n   3 │ MLP(hidden = (33, 13, 49), …)    0.0973896\n   4 │ MLP(hidden = (21, 41, 61), …)    0.0981502\n   5 │ MLP(hidden = (57, 49, 61), …)    0.100331\n   6 │ MLP(hidden = (25, 25, 29), …)    0.101083\n   7 │ MLP(hidden = (29, 61, 21), …)    0.101466\n   8 │ MLP(hidden = (29, 61, 5), …)     0.107513\n   9 │ MLP(hidden = (21, 61, 17), …)    0.107874\n  10 │ MLP(hidden = (45, 49, 61), …)    0.111292",
+      "text/plain": "\u001b[1m10×2 DataFrame\u001b[0m\n\u001b[1m Row \u001b[0m│\u001b[1m mlp                           \u001b[0m\u001b[1m measurement \u001b[0m\n     │\u001b[90m MLP…                          \u001b[0m\u001b[90m Float64     \u001b[0m\n─────┼────────────────────────────────────────────\n   1 │ MLP(hidden = (45, 49, 21), …)    0.0860875\n   2 │ MLP(hidden = (25, 45, 33), …)    0.0877367\n   3 │ MLP(hidden = (29, 17, 53), …)    0.0970372\n   4 │ MLP(hidden = (61, 9, 29), …)     0.0970978\n   5 │ MLP(hidden = (49, 49, 9), …)     0.0971594\n   6 │ MLP(hidden = (21, 33, 61), …)    0.0984172\n   7 │ MLP(hidden = (57, 61, 61), …)    0.099232\n   8 │ MLP(hidden = (41, 13, 25), …)    0.101498\n   9 │ MLP(hidden = (53, 29, 21), …)    0.105323\n  10 │ MLP(hidden = (57, 33, 45), …)    0.110168",
       "text/html": [
-       "<div><div style = \"float: left;\"><span>10×2 DataFrame</span></div><div style = \"clear: both;\"></div></div><div class = \"data-frame\" style = \"overflow-x: scroll;\"><table class = \"data-frame\" style = \"margin-bottom: 6px;\"><thead><tr class = \"header\"><th class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">Row</th><th style = \"text-align: left;\">mlp</th><th style = \"text-align: left;\">measurement</th></tr><tr class = \"subheader headerLastRow\"><th class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\"></th><th title = \"MLJFlux.MLP{3}\" style = \"text-align: left;\">MLP…</th><th title = \"Float64\" style = \"text-align: left;\">Float64</th></tr></thead><tbody><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">1</td><td style = \"text-align: left;\">MLP(hidden = (21, 57, 25), …)</td><td style = \"text-align: right;\">0.0867019</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">2</td><td style = \"text-align: left;\">MLP(hidden = (45, 17, 13), …)</td><td style = \"text-align: right;\">0.0929803</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">3</td><td style = \"text-align: left;\">MLP(hidden = (33, 13, 49), …)</td><td style = \"text-align: right;\">0.0973896</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">4</td><td style = \"text-align: left;\">MLP(hidden = (21, 41, 61), …)</td><td style = \"text-align: right;\">0.0981502</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">5</td><td style = \"text-align: left;\">MLP(hidden = (57, 49, 61), …)</td><td style = \"text-align: right;\">0.100331</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">6</td><td style = \"text-align: left;\">MLP(hidden = (25, 25, 29), …)</td><td style = \"text-align: right;\">0.101083</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">7</td><td style = \"text-align: left;\">MLP(hidden = (29, 61, 21), …)</td><td style = \"text-align: right;\">0.101466</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">8</td><td style = \"text-align: left;\">MLP(hidden = (29, 61, 5), …)</td><td style = \"text-align: right;\">0.107513</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">9</td><td style = \"text-align: left;\">MLP(hidden = (21, 61, 17), …)</td><td style = \"text-align: right;\">0.107874</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">10</td><td style = \"text-align: left;\">MLP(hidden = (45, 49, 61), …)</td><td style = \"text-align: right;\">0.111292</td></tr></tbody></table></div>"
+       "<div><div style = \"float: left;\"><span>10×2 DataFrame</span></div><div style = \"clear: both;\"></div></div><div class = \"data-frame\" style = \"overflow-x: scroll;\"><table class = \"data-frame\" style = \"margin-bottom: 6px;\"><thead><tr class = \"header\"><th class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">Row</th><th style = \"text-align: left;\">mlp</th><th style = \"text-align: left;\">measurement</th></tr><tr class = \"subheader headerLastRow\"><th class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\"></th><th title = \"MLJFlux.MLP{3}\" style = \"text-align: left;\">MLP…</th><th title = \"Float64\" style = \"text-align: left;\">Float64</th></tr></thead><tbody><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">1</td><td style = \"text-align: left;\">MLP(hidden = (45, 49, 21), …)</td><td style = \"text-align: right;\">0.0860875</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">2</td><td style = \"text-align: left;\">MLP(hidden = (25, 45, 33), …)</td><td style = \"text-align: right;\">0.0877367</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">3</td><td style = \"text-align: left;\">MLP(hidden = (29, 17, 53), …)</td><td style = \"text-align: right;\">0.0970372</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">4</td><td style = \"text-align: left;\">MLP(hidden = (61, 9, 29), …)</td><td style = \"text-align: right;\">0.0970978</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">5</td><td style = \"text-align: left;\">MLP(hidden = (49, 49, 9), …)</td><td style = \"text-align: right;\">0.0971594</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">6</td><td style = \"text-align: left;\">MLP(hidden = (21, 33, 61), …)</td><td style = \"text-align: right;\">0.0984172</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">7</td><td style = \"text-align: left;\">MLP(hidden = (57, 61, 61), …)</td><td style = \"text-align: right;\">0.099232</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">8</td><td style = \"text-align: left;\">MLP(hidden = (41, 13, 25), …)</td><td style = \"text-align: right;\">0.101498</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">9</td><td style = \"text-align: left;\">MLP(hidden = (53, 29, 21), …)</td><td style = \"text-align: right;\">0.105323</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">10</td><td style = \"text-align: left;\">MLP(hidden = (57, 33, 45), …)</td><td style = \"text-align: right;\">0.110168</td></tr></tbody></table></div>"
       ]
      },
      "metadata": {},

diff --git a/docs/src/common_workflows/architecture_search/notebook.jl b/docs/src/common_workflows/architecture_search/notebook.jl
@@ -25,7 +25,7 @@ import Optimisers       # native Flux.jl optimisers no longer supported
 # ### Loading and Splitting the Data
 
 iris = RDatasets.dataset("datasets", "iris");
-y, X = unpack(iris, ==(:Species), colname -> true, rng = 123);
+y, X = unpack(iris, ==(:Species), rng = 123);
 X = Float32.(X);      # To be compatible with type of network network parameters
 first(X, 5)
 

diff --git a/docs/src/common_workflows/architecture_search/notebook.md b/docs/src/common_workflows/architecture_search/notebook.md
@@ -28,7 +28,7 @@ import Optimisers       # native Flux.jl optimisers no longer supported
 
 ````@example architecture_search
 iris = RDatasets.dataset("datasets", "iris");
-y, X = unpack(iris, ==(:Species), colname -> true, rng = 123);
+y, X = unpack(iris, ==(:Species), rng = 123);
 X = Float32.(X);      # To be compatible with type of network network parameters
 first(X, 5)
 ````

diff --git a/docs/src/common_workflows/architecture_search/notebook.unexecuted.ipynb b/docs/src/common_workflows/architecture_search/notebook.unexecuted.ipynb
@@ -75,7 +75,7 @@
    "cell_type": "code",
    "source": [
     "iris = RDatasets.dataset(\"datasets\", \"iris\");\n",
-    "y, X = unpack(iris, ==(:Species), colname -> true, rng = 123);\n",
+    "y, X = unpack(iris, ==(:Species), rng = 123);\n",
     "X = Float32.(X);      # To be compatible with type of network network parameters\n",
     "first(X, 5)"
    ],

diff --git a/docs/src/common_workflows/comparison/notebook.ipynb b/docs/src/common_workflows/comparison/notebook.ipynb
@@ -81,7 +81,7 @@
    "cell_type": "code",
    "source": [
     "iris = RDatasets.dataset(\"datasets\", \"iris\");\n",
-    "y, X = unpack(iris, ==(:Species), colname -> true, rng=123);"
+    "y, X = unpack(iris, ==(:Species), rng=123);"
    ],
    "metadata": {},
    "execution_count": 3
@@ -107,7 +107,7 @@
     {
      "output_type": "execute_result",
      "data": {
-      "text/plain": "NeuralNetworkClassifier(\n  builder = MLP(\n        hidden = (5, 4), \n        σ = NNlib.relu), \n  finaliser = NNlib.softmax, \n  optimiser = Adam(0.01, (0.9, 0.999), 1.0e-8), \n  loss = Flux.Losses.crossentropy, \n  epochs = 50, \n  batch_size = 8, \n  lambda = 0.0, \n  alpha = 0.0, \n  rng = 42, \n  optimiser_changes_trigger_retraining = false, \n  acceleration = ComputationalResources.CPU1{Nothing}(nothing))"
+      "text/plain": "NeuralNetworkClassifier(\n  builder = MLP(\n        hidden = (5, 4), \n        σ = NNlib.relu), \n  finaliser = NNlib.softmax, \n  optimiser = Adam(0.01, (0.9, 0.999), 1.0e-8), \n  loss = Flux.Losses.crossentropy, \n  epochs = 50, \n  batch_size = 8, \n  lambda = 0.0, \n  alpha = 0.0, \n  rng = 42, \n  optimiser_changes_trigger_retraining = false, \n  acceleration = CPU1{Nothing}(nothing))"
      },
      "metadata": {},
      "execution_count": 4
@@ -271,9 +271,9 @@
     {
      "output_type": "execute_result",
      "data": {
-      "text/plain": "\u001b[1m4×2 DataFrame\u001b[0m\n\u001b[1m Row \u001b[0m│\u001b[1m mlp                               \u001b[0m\u001b[1m measurement \u001b[0m\n     │\u001b[90m Probabil…                         \u001b[0m\u001b[90m Float64     \u001b[0m\n─────┼────────────────────────────────────────────────\n   1 │ BayesianLDA(method = gevd, …)        0.0610826\n   2 │ NeuralNetworkClassifier(builder …    0.0857014\n   3 │ RandomForestClassifier(max_depth…    0.102881\n   4 │ ProbabilisticTunedModel(model = …    0.221056",
+      "text/plain": "\u001b[1m4×2 DataFrame\u001b[0m\n\u001b[1m Row \u001b[0m│\u001b[1m mlp                               \u001b[0m\u001b[1m measurement \u001b[0m\n     │\u001b[90m Probabil…                         \u001b[0m\u001b[90m Float64     \u001b[0m\n─────┼────────────────────────────────────────────────\n   1 │ BayesianLDA(method = gevd, …)        0.0610826\n   2 │ NeuralNetworkClassifier(builder …    0.0857014\n   3 │ RandomForestClassifier(max_depth…    0.107885\n   4 │ ProbabilisticTunedModel(model = …    0.221056",
       "text/html": [
-       "<div><div style = \"float: left;\"><span>4×2 DataFrame</span></div><div style = \"clear: both;\"></div></div><div class = \"data-frame\" style = \"overflow-x: scroll;\"><table class = \"data-frame\" style = \"margin-bottom: 6px;\"><thead><tr class = \"header\"><th class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">Row</th><th style = \"text-align: left;\">mlp</th><th style = \"text-align: left;\">measurement</th></tr><tr class = \"subheader headerLastRow\"><th class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\"></th><th title = \"MLJModelInterface.Probabilistic\" style = \"text-align: left;\">Probabil…</th><th title = \"Float64\" style = \"text-align: left;\">Float64</th></tr></thead><tbody><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">1</td><td style = \"text-align: left;\">BayesianLDA(method = gevd, …)</td><td style = \"text-align: right;\">0.0610826</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">2</td><td style = \"text-align: left;\">NeuralNetworkClassifier(builder = MLP(hidden = (5, 4), …), …)</td><td style = \"text-align: right;\">0.0857014</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">3</td><td style = \"text-align: left;\">RandomForestClassifier(max_depth = -1, …)</td><td style = \"text-align: right;\">0.102881</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">4</td><td style = \"text-align: left;\">ProbabilisticTunedModel(model = XGBoostClassifier(test = 1, …), …)</td><td style = \"text-align: right;\">0.221056</td></tr></tbody></table></div>"
+       "<div><div style = \"float: left;\"><span>4×2 DataFrame</span></div><div style = \"clear: both;\"></div></div><div class = \"data-frame\" style = \"overflow-x: scroll;\"><table class = \"data-frame\" style = \"margin-bottom: 6px;\"><thead><tr class = \"header\"><th class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">Row</th><th style = \"text-align: left;\">mlp</th><th style = \"text-align: left;\">measurement</th></tr><tr class = \"subheader headerLastRow\"><th class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\"></th><th title = \"Probabilistic\" style = \"text-align: left;\">Probabil…</th><th title = \"Float64\" style = \"text-align: left;\">Float64</th></tr></thead><tbody><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">1</td><td style = \"text-align: left;\">BayesianLDA(method = gevd, …)</td><td style = \"text-align: right;\">0.0610826</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">2</td><td style = \"text-align: left;\">NeuralNetworkClassifier(builder = MLP(hidden = (5, 4), …), …)</td><td style = \"text-align: right;\">0.0857014</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">3</td><td style = \"text-align: left;\">RandomForestClassifier(max_depth = -1, …)</td><td style = \"text-align: right;\">0.107885</td></tr><tr><td class = \"rowNumber\" style = \"font-weight: bold; text-align: right;\">4</td><td style = \"text-align: left;\">ProbabilisticTunedModel(model = XGBoostClassifier(test = 1, …), …)</td><td style = \"text-align: right;\">0.221056</td></tr></tbody></table></div>"
       ]
      },
      "metadata": {},

diff --git a/docs/src/common_workflows/comparison/notebook.jl b/docs/src/common_workflows/comparison/notebook.jl
@@ -23,7 +23,7 @@ import Optimisers       # native Flux.jl optimisers no longer supported
 # ### Loading and Splitting the Data
 
 iris = RDatasets.dataset("datasets", "iris");
-y, X = unpack(iris, ==(:Species), colname -> true, rng=123);
+y, X = unpack(iris, ==(:Species), rng=123);
 
 
 # ### Instantiating the models Now let's construct our model. This follows a similar setup

diff --git a/docs/src/common_workflows/comparison/notebook.md b/docs/src/common_workflows/comparison/notebook.md
@@ -26,7 +26,7 @@ import Optimisers       # native Flux.jl optimisers no longer supported
 
 ````@example comparison
 iris = RDatasets.dataset("datasets", "iris");
-y, X = unpack(iris, ==(:Species), colname -> true, rng=123);
+y, X = unpack(iris, ==(:Species), rng=123);
 nothing #hide
 ````
 

diff --git a/docs/src/common_workflows/comparison/notebook.unexecuted.ipynb b/docs/src/common_workflows/comparison/notebook.unexecuted.ipynb
@@ -73,7 +73,7 @@
    "cell_type": "code",
    "source": [
     "iris = RDatasets.dataset(\"datasets\", \"iris\");\n",
-    "y, X = unpack(iris, ==(:Species), colname -> true, rng=123);"
+    "y, X = unpack(iris, ==(:Species), rng=123);"
    ],
    "metadata": {},
    "execution_count": null