Skip to content

Feat/reorganize core bits #18

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
eschmidt42 merged 4 commits into from
Aug 17, 2025
Merged

Feat/reorganize core bits #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
28f50c6
feat: added inline-snapshot and dirty-equals as dependencies to simpl…
eschmidt42 Aug 17, 2025
4b4ecfd
feat: migrated components from decisiontree.py to a sub-package. also…
eschmidt42 Aug 17, 2025
3faf8bc
chore: migrated test dependencies to test group
eschmidt42 Aug 17, 2025
87fa59d
fix: updated notebooks
eschmidt42 Aug 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 9 additions & 5 deletions nbs/core/decision-tree.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,11 @@
"import seaborn as sns\n",
"import sklearn.datasets as sk_datasets\n",
"\n",
"import random_tree_models.decisiontree as dtree\n",
"from random_tree_models.decisiontree import (\n",
" DecisionTreeClassifier,\n",
" DecisionTreeRegressor,\n",
")\n",
"from random_tree_models.decisiontree.visualize import show_tree\n",
"from random_tree_models.scoring import MetricNames"
]
},
Expand Down Expand Up @@ -111,7 +115,7 @@
"metadata": {},
"outputs": [],
"source": [
"model = dtree.DecisionTreeClassifier(measure_name=MetricNames.gini, max_depth=4)"
"model = DecisionTreeClassifier(measure_name=MetricNames.gini, max_depth=4)"
]
},
{
Expand All @@ -138,7 +142,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model)"
"show_tree(model)"
]
},
{
Expand Down Expand Up @@ -216,7 +220,7 @@
"metadata": {},
"outputs": [],
"source": [
"model = dtree.DecisionTreeRegressor(measure_name=MetricNames.variance, max_depth=2)"
"model = DecisionTreeRegressor(measure_name=MetricNames.variance, max_depth=2)"
]
},
{
Expand All @@ -234,7 +238,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model)"
"show_tree(model)"
]
},
{
Expand Down
8 changes: 4 additions & 4 deletions nbs/core/extra-trees.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,10 +41,10 @@
"import seaborn as sns\n",
"import sklearn.datasets as sk_datasets\n",
"\n",
"import random_tree_models.decisiontree as dtree\n",
"import random_tree_models.extratrees as et\n",
"from random_tree_models.scoring import MetricNames\n",
"from random_tree_models.utils import ThresholdSelectionMethod"
"from random_tree_models.params import ThresholdSelectionMethod\n",
"from random_tree_models.decisiontree.visualize import show_tree"
]
},
{
Expand Down Expand Up @@ -143,7 +143,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down Expand Up @@ -249,7 +249,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down
6 changes: 3 additions & 3 deletions nbs/core/gradient-boosted-trees.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@
"import seaborn as sns\n",
"import sklearn.datasets as sk_datasets\n",
"\n",
"import random_tree_models.decisiontree as dtree\n",
"from random_tree_models.decisiontree.visualize import show_tree\n",
"import random_tree_models.gradientboostedtrees as gbtree\n",
"from random_tree_models.scoring import MetricNames"
]
Expand Down Expand Up @@ -160,7 +160,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down Expand Up @@ -256,7 +256,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down
7 changes: 3 additions & 4 deletions nbs/core/isolation-forest.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,9 +56,9 @@
"import seaborn as sns\n",
"import sklearn.datasets as sk_datasets\n",
"\n",
"import random_tree_models.decisiontree as dtree\n",
"from random_tree_models.decisiontree.visualize import show_tree\n",
"import random_tree_models.isolationforest as iforest\n",
"from random_tree_models.utils import ColumnSelectionMethod, ThresholdSelectionMethod"
"from random_tree_models.params import ColumnSelectionMethod, ThresholdSelectionMethod"
]
},
{
Expand Down Expand Up @@ -111,7 +111,6 @@
"source": [
"frac_subsamples = 2 / 3\n",
"frac_features = 1 # math.sqrt(X.shape[1]) / X.shape[1]\n",
"frac_subsamples, frac_features, X.shape[1]\n",
"\n",
"# threshold_method = ThresholdSelectionMethod.uniform # selects a random threshold from the linear space between the min and max values in X\n",
"threshold_method = (\n",
Expand Down Expand Up @@ -167,7 +166,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down
8 changes: 4 additions & 4 deletions nbs/core/random-forest.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,9 +41,9 @@
"import seaborn as sns\n",
"import sklearn.datasets as sk_datasets\n",
"\n",
"import random_tree_models.decisiontree as dtree\n",
"from random_tree_models.decisiontree.visualize import show_tree\n",
"import random_tree_models.randomforest as rf\n",
"from random_tree_models.scoring import MetricNames"
"from random_tree_models.params import MetricNames"
]
},
{
Expand Down Expand Up @@ -135,7 +135,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down Expand Up @@ -238,7 +238,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down
6 changes: 3 additions & 3 deletions nbs/core/robust-random-cut-forest.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,9 +55,9 @@
"import seaborn as sns\n",
"import sklearn.datasets as sk_datasets\n",
"\n",
"import random_tree_models.decisiontree as dtree\n",
"from random_tree_models.decisiontree.visualize import show_tree\n",
"import random_tree_models.isolationforest as iforest\n",
"from random_tree_models.utils import ColumnSelectionMethod, ThresholdSelectionMethod"
"from random_tree_models.params import ColumnSelectionMethod, ThresholdSelectionMethod"
]
},
{
Expand Down Expand Up @@ -164,7 +164,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down
21 changes: 10 additions & 11 deletions nbs/core/xgboost.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"$$ \\text{loss}^{(t)} = \\sum_{i=1}^n l(y_i, \\hat{y}^{(t-1)}_i + f^{(t)}(x_i) ) + \\Omega \\left( f^{(t)} \\right) $$ "
"$$ \\text{loss} ^ {(t)} = \\sum_{i=1}^n l(y_i, \\hat{y}^{(t-1)}_i + f^{(t)}(x_i) ) + \\Omega \\left( f^{(t)} \\right) $$"
]
},
{
Expand All @@ -97,7 +97,7 @@
"metadata": {},
"source": [
"For the regularization the authors use\n",
"$$ \\Omega (f_t) = \\gamma N^{(t)}_\\text{leafs} + \\frac{1}{2} \\lambda \\sum^{N^{(t)}_\\text{leafs}}_j w_j^2$$\n",
"$$ \\Omega (f_t) = \\gamma N^{(t)}_\\text{leafs} + \\frac{1}{2} \\lambda \\sum^{N^{(t)}_\\text{leafs}}_j w_j^2 $$\n",
"\n",
"where $\\gamma$ is some constant and $w_j$ is a leaf weight (seems like the $\\gamma_{jm}$ from Friedman et al. but isn't clarified)"
]
Expand Down Expand Up @@ -284,10 +284,9 @@
"import sklearn.datasets as sk_datasets\n",
"from scipy import stats\n",
"\n",
"import random_tree_models.decisiontree as dtree\n",
"import random_tree_models.gradientboostedtrees as gbtree\n",
"from random_tree_models.decisiontree.visualize import show_tree\n",
"import random_tree_models.xgboost as xgboost\n",
"from random_tree_models.scoring import MetricNames"
"from random_tree_models.params import MetricNames"
]
},
{
Expand Down Expand Up @@ -355,7 +354,7 @@
"outputs": [],
"source": [
"model = xgboost.XGBoostClassifier(\n",
" measure_name=\"xgboost\", max_depth=2, n_trees=3, lam=0.0\n",
" measure_name=MetricNames.xgboost, max_depth=2, n_trees=3, lam=0.0\n",
")"
]
},
Expand All @@ -374,7 +373,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down Expand Up @@ -449,7 +448,7 @@
"outputs": [],
"source": [
"model = xgboost.XGBoostRegressor(\n",
" measure_name=\"xgboost\", max_depth=2, n_trees=3, lam=0.0\n",
" measure_name=MetricNames.xgboost, max_depth=2, n_trees=3, lam=0.0\n",
")"
]
},
Expand All @@ -468,7 +467,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down Expand Up @@ -610,7 +609,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down Expand Up @@ -719,7 +718,7 @@
"metadata": {},
"outputs": [],
"source": [
"dtree.show_tree(model.trees_[0])"
"show_tree(model.trees_[0])"
]
},
{
Expand Down
10 changes: 3 additions & 7 deletions nbs/dev/xgboost-profiling-histogramming-yay-or-nay.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,9 +165,7 @@
"metadata": {},
"outputs": [],
"source": [
"execution_stats_reg_vanilla = get_class_stats(\n",
" False, None, n_samples_arr, n_features_arr\n",
")"
"execution_stats_reg_vanilla = get_class_stats(False, 256, n_samples_arr, n_features_arr)"
]
},
{
Expand Down Expand Up @@ -363,9 +361,7 @@
"metadata": {},
"outputs": [],
"source": [
"execution_stats_class_vanilla = get_reg_stats(\n",
" False, None, n_samples_arr, n_features_arr\n",
")"
"execution_stats_class_vanilla = get_reg_stats(False, 256, n_samples_arr, n_features_arr)"
]
},
{
Expand Down Expand Up @@ -499,7 +495,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
"version": "3.13.3"
}
},
"nbformat": 4,
Expand Down
6 changes: 4 additions & 2 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,8 @@ build-backend = "maturin"
[dependency-groups]
test = [
"pytest>=7.3.1",
"dirty-equals>=0.9.0",
"inline-snapshot>=0.27.2",
]
nb = [
"ipywidgets>=8.0.6",
Expand All @@ -44,6 +46,6 @@ dev = [
"snakeviz>=2.2.0",
"pip-audit>=2.9.0",
"pytest-cov>=6.2.1",
{include-group = "nb"},
{include-group = "test"},
{include-group = "nb"},
{include-group = "test"},
]
Loading
Loading