diff --git a/docs/index.html b/docs/index.html index c1e862d..c144133 100644 --- a/docs/index.html +++ b/docs/index.html @@ -157,19 +157,19 @@
  • - 9  Visualization (experimental πŸ› ) + 9  Visualization (too be deprecated πŸ› )
  • - 10  Statistical Visualization (experimental πŸ› ) + 10  Statistical Visualization (to be depracated πŸ› )
  • - 11  More visualization examples (experimental πŸ› ) + 11  More visualization examples (to be deprecated πŸ› )
  • @@ -255,9 +255,9 @@

    Datasets

  • Python (experimental πŸ› )

  • Statistics (experimental πŸ› )

    • -

  • Visualization (experimental πŸ› )

    • -

  • Statistical Visualization (experimental πŸ› )

    • -

  • More visualization examples (experimental πŸ› )

    • +

  • Visualization (too be deprecated πŸ› )

    • +

  • Statistical Visualization (to be depracated πŸ› )

    • +

  • More visualization examples (to be deprecated πŸ› )

  • Visualizing correlation matrices (experimental πŸ› ) - DRAFT

  • Known Issues ❗

    • diff --git a/docs/noj_book.automl.html b/docs/noj_book.automl.html index dda4eb9..833d572 100644 --- a/docs/noj_book.automl.html +++ b/docs/noj_book.automl.html @@ -192,19 +192,19 @@
  • - 9  Visualization (experimental πŸ› ) + 9  Visualization (too be deprecated πŸ› )
  • - 10  Statistical Visualization (experimental πŸ› ) + 10  Statistical Visualization (to be depracated πŸ› )
  • - 11  More visualization examples (experimental πŸ› ) + 11  More visualization examples (to be deprecated πŸ› )
  • @@ -329,7 +329,7 @@ 

    ctx-after-train
    -

    {

    +

    {

    @@ -354,63 +354,63 @@

    -

    + - - + + - + + + - - - + - + - + - + - - + + - + - + - - - + + + - - + + @@ -420,21 +420,21 @@

    ...

    + - - - + + - + - + @@ -450,38 +450,38 @@

    0.0

    - + - + + + - - - + - + - + - - + + - + @@ -492,20 +492,20 @@

    :metamorph/mode :fit
    #uuid "eebbb257-124a-4edc-b5da-878650af4c82" {:model-data {:majority-class 1.0, :distinct-labels (0.0 1.0)}, :options {:model-type :metamorph.ml/dummy-classifier}, :id #uuid "2dd95fc5-096f-46c2-9d20-3ef230c97dc3", :feature-columns [:sex :pclass :embarked], :target-columns [:survived], :target-categorical-maps {:survived #tech.v3.dataset.categorical.CategoricalMap{:lookup-table {"no" 0, "yes" 1}, :src-column :survived, :result-datatype :float64}}, :scicloj.metamorph.ml/unsupervised? nil}

    }

    +
    :metamorph/mode :fit
    #uuid "d82acc8b-934d-46e2-bafc-2c786f4d35d2" {:model-data {:majority-class 1.0, :distinct-labels (0.0 1.0)}, :options {:model-type :metamorph.ml/dummy-classifier}, :id #uuid "ad1a8ebd-6247-47a4-991f-49bb45043570", :feature-columns [:sex :pclass :embarked], :target-columns [:survived], :target-categorical-maps {:survived #tech.v3.dataset.categorical.CategoricalMap{:lookup-table {"no" 0, "yes" 1}, :src-column :survived, :result-datatype :float64}}, :scicloj.metamorph.ml/unsupervised? nil}

    }

    (keys ctx-after-train)
    (:metamorph/data
  :metamorph/mode
- #uuid "eebbb257-124a-4edc-b5da-878650af4c82")
    + #uuid "d82acc8b-934d-46e2-bafc-2c786f4d35d2")

    This context map has the β€œdata”, the β€œmode” and an UUID for each operation (we had only one in this pipeline)

    (vals ctx-after-train)
    -

    (

    Group: 0 [711 4]:

    +

    (

    Group: 0 [711 4]:

    1.00.0 3.0 0.0 0.0
    1.01.00.03.0 0.0 1.0
    1.00.0 3.0 0.0 0.0
    1.02.0 0.03.00.00.01.0
    0.01.0 3.0 0.0 0.0
    0.03.02.0 0.0 0.0
    1.00.0 3.01.01.00.00.0
    0.01.0 3.00.02.0 1.0
    1.03.00.00.01.02.01.0
    0.03.00.02.02.0 0.0
    0.0 1.01.02.01.00.00.0
    1.0 1.00.02.0 1.0
    0.0 2.02.00.0 0.0
    1.00.0 3.0 0.01.00.0
    1.01.0 0.03.00.00.01.0
    0.02.03.0 0.0 0.0
    0.0 3.01.00.0 0.0
    1.02.0 0.0 1.00.00.0
    0.03.02.0 0.0 0.0
    @@ -517,63 +517,63 @@

    -

    + - - + + - + + + - - - + - + - + - + - - + + - + - + - - - + + + - - + + @@ -583,21 +583,21 @@

    ...

    + - - - + + - + - + @@ -613,38 +613,38 @@

    0.0

    - + - + + + - - - + - + - + - - + + - + @@ -653,7 +653,7 @@

    :fit 
    {:model-data {:majority-class 1.0, :distinct-labels (0.0 1.0)},
  :options {:model-type :metamorph.ml/dummy-classifier},
- :id #uuid "2dd95fc5-096f-46c2-9d20-3ef230c97dc3",
+ :id #uuid "ad1a8ebd-6247-47a4-991f-49bb45043570",
  :feature-columns [:sex :pclass :embarked],
  :target-columns [:survived],
  :target-categorical-maps
@@ -674,7 +674,7 @@ 
    
 
    ctx-after-predict
    -

    {

    +

    {

    1.00.0 3.0 0.0 0.0
    1.01.00.03.0 0.0 1.0
    1.00.0 3.0 0.0 0.0
    1.02.0 0.03.00.00.01.0
    0.01.0 3.0 0.0 0.0
    0.03.02.0 0.0 0.0
    1.00.0 3.01.01.00.00.0
    0.01.0 3.00.02.0 1.0
    1.03.00.00.01.02.01.0
    0.03.00.02.02.0 0.0
    0.0 1.01.02.01.00.00.0
    1.0 1.00.02.0 1.0
    0.0 2.02.00.0 0.0
    1.00.0 3.0 0.01.00.0
    1.01.0 0.03.00.00.01.0
    0.02.03.0 0.0 0.0
    0.0 3.01.00.0 0.0
    1.02.0 0.0 1.00.00.0
    0.03.02.0 0.0 0.0
    @@ -777,12 +777,12 @@

    - - + + + - - + + - - + + - + - + @@ -848,24 +848,24 @@

    0.0

    - - + + + - - - + + - - + + @@ -873,44 +873,44 @@

    ...

    - - + + - + - + - + + - - + - - - + + + - + - + + - @@ -919,13 +919,13 @@

    - + - - + +
    -
    #uuid "eebbb257-124a-4edc-b5da-878650af4c82"
    +
    #uuid "d82acc8b-934d-46e2-bafc-2c786f4d35d2"

    {

    -
    +
    :feature-columns [:sex :pclass :embarked]
    @@ -818,28 +818,28 @@

    -

    		0.02.00.01.03.01.0
    0.02.01.03.0 0.0
    0.03.0 1.02.00.0
    0.0 1.02.00.0
    1.01.02.0 0.0
    1.02.0 0.03.01.0
    0.0 1.03.0 0.0
    0.03.00.02.02.0
    1.03.0 0.03.02.0
    ...
    1.01.00.03.0 0.0
    1.00.0 3.0 0.0
    0.0 3.01.00.0
    0.01.01.0 2.00.0
    1.00.0 1.0 2.0
    0.03.00.01.01.02.0
    1.01.0 2.00.0
    0.01.01.0 2.00.0
    0.00.02.03.0 0.0
    1.03.0 0.03.01.0
    @@ -938,7 +938,7 @@

    :model-data {:majority-class 1.0, :distinct-labels (0.0 1.0)}

    -
    :id #uuid "2dd95fc5-096f-46c2-9d20-3ef230c97dc3"
    +
    :id #uuid "ad1a8ebd-6247-47a4-991f-49bb45043570"
    @@ -961,18 +961,12 @@

    -

    + - - - - - - @@ -991,10 +985,16 @@

    1.0

    + + + + + + - + @@ -1009,13 +1009,13 @@

    1.0

    - + - + @@ -1024,7 +1024,7 @@

    0.0

    - +
    0.01.0
    0.0
    0.0
    1.0
    1.0
    1.0
    0.0
    ...
    1.00.0
    0.0
    0.01.0
    1.0
    0.01.0
    1.0
    1.00.0
    @@ -1072,7 +1072,7 @@ 

    train-ctx

    -

    {

    +

    {

    @@ -1235,7 +1235,7 @@

    :metamorph/mode :fit
    #uuid "d83cc103-fecd-4898-b572-f1cb01e53941" {:model-data {:majority-class 1, :distinct-labels (0.0 1.0)}, :options {:model-type :metamorph.ml/dummy-classifier}, :id #uuid "15400fca-c6e8-443e-8fa8-9ce6c6d8607b", :feature-columns [:sex :pclass :embarked], :target-columns [:survived], :target-categorical-maps {:survived #tech.v3.dataset.categorical.CategoricalMap{:lookup-table {"no" 0, "yes" 1}, :src-column :survived, :result-datatype :float64}}, :scicloj.metamorph.ml/unsupervised? nil}

    }

    +
    :metamorph/mode :fit
    #uuid "eb9c001e-e4cf-405b-afc5-e870c16d9baf" {:model-data {:majority-class 1, :distinct-labels (0.0 1.0)}, :options {:model-type :metamorph.ml/dummy-classifier}, :id #uuid "a5f7d69b-991d-4b9c-83a0-6743f07c25d7", :feature-columns [:sex :pclass :embarked], :target-columns [:survived], :target-categorical-maps {:survived #tech.v3.dataset.categorical.CategoricalMap{:lookup-table {"no" 0, "yes" 1}, :src-column :survived, :result-datatype :float64}}, :scicloj.metamorph.ml/unsupervised? nil}

    }

    To show the power of pipelines, I start with doing the simplest possible pipeline, and expand then on it.

    we can already chain train and test with usual functions:

    @@ -1514,108 +1514,108 @@

    - + + + + + + - + - + - + - + - + - + - + - - - - - - - - - - - + - + - + - + - + - + - + - + - - + + + + + + +
    [:sex :pclass :embarked] 0.81107726{:model-type :scicloj.ml.tribuo/classification,{:model-type :smile.classification/ada-boost}
    [:sex :pclass :embarked]0.81107726{:model-type :scicloj.ml.tribuo/classification,
    :tribuo-components
    [{:name trainer,
    :type org.tribuo.classification.dtree.CARTClassificationTrainer,
    :properties
    {:maxDepth 8,
    :useRandomSplitPoints false,
    :fractionFeaturesInSplit 0.5}}],
    :tribuo-trainer-name trainer}
    [:sex :pclass :embarked]0.81107726{:model-type :smile.classification/ada-boost}
    [:sex] 0.78633276{:model-type :smile.classification/logistic-regression}
    [:sex]0.78633276 {:model-type :scicloj.ml.tribuo/classification,
    :tribuo-components
    [{:name trainer,
    :type org.tribuo.classification.dtree.CARTClassificationTrainer,
    :properties
    {:maxDepth 8,
    :useRandomSplitPoints false,
    :fractionFeaturesInSplit 0.5}}],
    :tribuo-trainer-name trainer}
    [:sex :embarked]
    [:sex] 0.78633276 {:model-type :smile.classification/ada-boost}
    [:sex :pclass]0.78633276{:model-type :smile.classification/logistic-regression}
    diff --git a/docs/noj_book.datasets.html b/docs/noj_book.datasets.html index e3f5ea4..6869f39 100644 --- a/docs/noj_book.datasets.html +++ b/docs/noj_book.datasets.html @@ -192,19 +192,19 @@
  • - 9  Visualization (experimental πŸ› ) + 9  Visualization (too be deprecated πŸ› )
  • - 10  Statistical Visualization (experimental πŸ› ) + 10  Statistical Visualization (to be depracated πŸ› )
  • - 11  More visualization examples (experimental πŸ› ) + 11  More visualization examples (to be deprecated πŸ› )
  • diff --git a/docs/noj_book.interactions_ols.html b/docs/noj_book.interactions_ols.html index 04d4050..6432a2c 100644 --- a/docs/noj_book.interactions_ols.html +++ b/docs/noj_book.interactions_ols.html @@ -221,19 +221,19 @@
  • - 9  Visualization (experimental πŸ› ) + 9  Visualization (too be deprecated πŸ› )
  • - 10  Statistical Visualization (experimental πŸ› ) + 10  Statistical Visualization (to be depracated πŸ› )
  • - 11  More visualization examples (experimental πŸ› ) + 11  More visualization examples (to be deprecated πŸ› )
  • @@ -354,19 +354,19 @@

    Residuals: Min 1Q Median 3Q Max - -10.6724 -0.9853 0.3437 1.3688 3.3646 + -10.3718 -1.1724 0.3073 1.4592 3.4121 Coefficients: Estimate Std. Error t value Pr(>|t|) -Intercept 3.0177 0.4392 6.8710 0.0000 *** -youtube 0.0458 0.0017 27.1238 0.0000 *** -facebook 0.2007 0.0102 19.7122 0.0000 *** +Intercept 3.4422 0.4584 7.5095 0.0000 *** +youtube 0.0463 0.0018 26.0892 0.0000 *** +facebook 0.1854 0.0105 17.6748 0.0000 *** --------------------------------------------------------------------- Significance codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 -Residual standard error: 2.0553 on 130 degrees of freedom -Multiple R-squared: 0.9012, Adjusted R-squared: 0.8997 -F-statistic: 592.9311 on 3 and 130 DF, p-value: 4.546e-66

    • +Residual standard error: 2.1542 on 130 degrees of freedom +Multiple R-squared: 0.8901, Adjusted R-squared: 0.8884 +F-statistic: 526.3674 on 3 and 130 DF, p-value: 4.663e-63

    We have the following metrics:

    \(RMSE\)

    @@ -374,14 +374,14 @@ 

    (-> evaluations flatten first :test-transform :metric)

    -
    1.9921201677612856
    +
    1.727635715123888

    \(R^2\)

    (-> evaluations flatten first :test-transform :other-metrices first :metric)
    -
    0.8911583564973837
    +
    0.9138890196777525
    @@ -413,20 +413,20 @@

    Residuals: Min 1Q Median 3Q Max - -7.5306 -0.4764 0.2023 0.7802 1.8088 + -7.4013 -0.4475 0.2177 0.7023 1.9540 Coefficients: Estimate Std. Error t value Pr(>|t|) -Intercept 8.0091 0.3883 20.6246 0.0000 *** -youtube 0.0194 0.0020 9.7621 0.0000 *** -facebook 0.0292 0.0117 2.4924 0.0140 * -youtube*facebook 0.0009 0.0001 15.6348 0.0000 *** +Intercept 8.0881 0.3944 20.5092 0.0000 *** +youtube 0.0189 0.0019 10.0111 0.0000 *** +facebook 0.0248 0.0111 2.2471 0.0263 * +youtube*facebook 0.0009 0.0001 17.5637 0.0000 *** --------------------------------------------------------------------- Significance codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 -Residual standard error: 1.2763 on 129 degrees of freedom -Multiple R-squared: 0.9605, Adjusted R-squared: 0.9596 -F-statistic: 1046.6937 on 4 and 129 DF, p-value: 2.533e-90 +Residual standard error: 1.1898 on 129 degrees of freedom +Multiple R-squared: 0.9668, Adjusted R-squared: 0.9660 +F-statistic: 1252.9014 on 4 and 129 DF, p-value: 3.551e-95

    As the multiplcation of youtube*facebook is as well statistically relevant, it suggests that there is indeed an interaction between these 2 predictor variables youtube and facebook.

    \(RMSE\)

    @@ -434,14 +434,14 @@ 

    (-> evaluations flatten first :test-transform :metric)
    -
    0.788376113686339
    +
    1.02489232563229

    \(R^2\)

    (-> evaluations flatten first :test-transform :other-metrices first :metric)
    -
    0.9837989524603392
    +
    0.9711197427339897

    \(RMSE\) and \(R^2\) of the intercation model are sligtly better.

    These results suggest that the model with the interaction term is better than the model that contains only main effects. So, for this specific data, we should go for the model with the interaction model.

    diff --git a/docs/noj_book.known_issues.html b/docs/noj_book.known_issues.html index 0dfc069..bff9e33 100644 --- a/docs/noj_book.known_issues.html +++ b/docs/noj_book.known_issues.html @@ -157,19 +157,19 @@
  • - 9  Visualization (experimental πŸ› ) + 9  Visualization (too be deprecated πŸ› )
  • - 10  Statistical Visualization (experimental πŸ› ) + 10  Statistical Visualization (to be depracated πŸ› )
  • - 11  More visualization examples (experimental πŸ› ) + 11  More visualization examples (to be deprecated πŸ› )
  • diff --git a/docs/noj_book.ml_basic.html b/docs/noj_book.ml_basic.html index 7ab9389..abe1030 100644 --- a/docs/noj_book.ml_basic.html +++ b/docs/noj_book.ml_basic.html @@ -192,19 +192,19 @@
  • - 9  Visualization (experimental πŸ› ) + 9  Visualization (too be deprecated πŸ› )
  • - 10  Statistical Visualization (experimental πŸ› ) + 10  Statistical Visualization (to be depracated πŸ› )
  • - 11  More visualization examples (experimental πŸ› ) + 11  More visualization examples (to be deprecated πŸ› )
  • @@ -1013,7 +1013,7 @@ 

    split
    -

    {

    +

    {

    @@ -1433,9 +1433,9 @@

    reverse)
    -
    ({:predictor :sex, :importance 38.00092227487106}
- {:predictor :pclass, :importance 9.935574733566305}
- {:predictor :embarked, :importance 1.7041266006411997})
    +
    ({:predictor :sex, :importance 44.857553708981115}
+ {:predictor :pclass, :importance 10.038066598506147}
+ {:predictor :embarked, :importance 1.7612673493626976})

    we can see that :sex is more important to predict :survived then :pclass and :embark

    diff --git a/docs/noj_book.more_visualization.html b/docs/noj_book.more_visualization.html index f8d2254..c8beb27 100644 --- a/docs/noj_book.more_visualization.html +++ b/docs/noj_book.more_visualization.html @@ -7,7 +7,7 @@ -Noj Documentation – 11  More visualization examples (experimental πŸ› ) +Noj Documentation – 11  More visualization examples (to be deprecated πŸ› )