Fixing get_leaves function and better documentation

mmerce · mmerce · commit 5e055e070aa4 · 2024-09-09T18:44:39.000+02:00
diff --git a/.readthedocs.yaml b/.readthedocs.yaml
@@ -1,9 +1,22 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
 version: 2
 
+# Set the version of Python and other tools you might need
 build:
   os: ubuntu-22.04
   tools:
-    python: "3.10"
+    python: "3.11"
 
+# Build documentation in the docs/ directory with Sphinx
 sphinx:
   configuration: docs/conf.py
+
+# We recommend specifying your dependencies to enable reproducible builds:
+# https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+  install:
+  - requirements: docs/requirements.txt
diff --git a/HISTORY.rst b/HISTORY.rst
@@ -3,6 +3,12 @@
 History
 -------
 
+9.8.0 (2024-09-09)
+------------------
+
+- Fixing the get_leaves function for local decision trees.
+- Changing documentation templates.
+
 9.8.0.dev1 (2024-02-28)
 -----------------------
 
diff --git a/bigml/generators/model.py b/bigml/generators/model.py
@@ -135,8 +135,9 @@ def get_leaves(model, path=None, filter_function=None):
 
     offsets = model.offsets
 
-    def get_tree_leaves(tree, fields, path, leaves, filter_function=None):
+    def get_tree_leaves(tree, fields, path, filter_function=None):
 
+        leaves = []
         node = get_node(tree)
         predicate = get_predicate(tree)
         if isinstance(predicate, list):
@@ -149,10 +150,12 @@ def get_tree_leaves(tree, fields, path, leaves, filter_function=None):
 
         if children:
             for child in children:
+
                 leaves += get_tree_leaves(child, fields,
-                                          path[:], leaves,
+                                          path[:],
                                           filter_function=filter_function)
         else:
+            print("id:", node[offsets["id"]])
             leaf = {
                 'id': node[offsets["id"]],
                 'confidence': node[offsets["confidence"]],
@@ -171,7 +174,7 @@ def get_tree_leaves(tree, fields, path, leaves, filter_function=None):
                     or filter_function(leaf)):
                 leaves += [leaf]
         return leaves
-    return get_tree_leaves(model.tree, model.fields, path, leaves,
+    return get_tree_leaves(model.tree, model.fields, path,
                            filter_function)
 
 
diff --git a/bigml/tests/create_model_steps.py b/bigml/tests/create_model_steps.py
@@ -31,6 +31,7 @@
 from bigml.deepnet import Deepnet
 from bigml.fusion import Fusion
 from bigml.ensemble import Ensemble
+from bigml.generators.model import get_leaves
 
 
 from .read_resource_steps import wait_until_status_code_is
@@ -690,3 +691,8 @@ def the_cloned_logistic_regression_is(step, logistic_regression):
 def check_deepnet_id_local_id(step):
     """Checking that deepnet ID and local deepnet ID match"""
     eq_(world.deepnet["resource"], step.bigml["local_deepnet"].resource_id)
+
+
+def check_leaves_number(step, leaves_number):
+    """Checking the number of leaves in a tree local model"""
+    eq_(len(get_leaves(step.bigml["local_model"])), leaves_number)
diff --git a/bigml/tests/test_40_local_from_file.py b/bigml/tests/test_40_local_from_file.py
@@ -66,17 +66,18 @@ def test_scenario1(self):
             When I create a local model from the file "<exported_file>"
             Then the model ID and the local model ID match
             And the prediction for "<input_data>" is "<prediction>"
+            And the number of leaves is "<leaves#>"
         """
         show_doc(self.test_scenario1)
         headers = ["data", "source_wait", "dataset_wait", "model_wait",
                    "pmml", "exported_file", "input_data", "prediction",
-                   "model_conf"]
+                   "model_conf", 'leaves#']
         examples = [
             ['data/iris.csv', '10', '10', '10', False,
-             './tmp/model.json', {}, "Iris-setosa", '{}'],
+             './tmp/model.json', {}, "Iris-setosa", '{}', 9],
             ['data/iris.csv', '10', '10', '10', False,
              './tmp/model_dft.json', {}, "Iris-versicolor",
-             '{"default_numeric_value": "mean"}']]
+             '{"default_numeric_value": "mean"}', 9]]
         for example in examples:
             example = dict(zip(headers, example))
             show_method(self, self.bigml["method"], example)
@@ -97,6 +98,7 @@ def test_scenario1(self):
             model_create.check_model_id_local_id(self)
             model_create.local_model_prediction_is(
                 self, example["input_data"], example["prediction"])
+            model_create.check_leaves_number(self, example["leaves#"])
 
     def test_scenario2(self):
         """
diff --git a/bigml/version.py b/bigml/version.py
@@ -1 +1 @@
-__version__ = '9.8.0.dev1'
+__version__ = '9.8.0'
diff --git a/docs/101_anomaly.rst b/docs/101_anomaly.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using an anomaly detector
-===============================================
+101 - Anomaly detector usage
+============================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_association.rst b/docs/101_association.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using Association Discovery
-=================================================
+101 - Association Discovery usage
+=================================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_cluster.rst b/docs/101_cluster.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using a Cluster
-=====================================
+101 - Cluster Usage
+===================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_deepnet.rst b/docs/101_deepnet.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using a Deepnet Model
-===========================================
+101 - Deepnet usage
+===================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_ensemble.rst b/docs/101_ensemble.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using an Ensemble
-=======================================
+101 - Ensemble usage
+====================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_fusion.rst b/docs/101_fusion.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using a Fusion Model
-==========================================
+101 - Fusion usage
+==================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_images_classification.rst b/docs/101_images_classification.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Images Classification
-===========================================
+101 - Images Classification
+===========================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_images_feature_extraction.rst b/docs/101_images_feature_extraction.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Images Feature Extraction
-===============================================
+101 - Images Feature Extraction
+===============================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_linear_regression.rst b/docs/101_linear_regression.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using a Linear Regression
-=================================================
+101 - Linear Regression usage
+=============================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_logistic_regression.rst b/docs/101_logistic_regression.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using a Logistic Regression
-=================================================
+101 - Logistic Regression usage
+===============================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_model.rst b/docs/101_model.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using a Decision Tree Model
-=================================================
+101 - Decision Tree usage
+=========================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_object_detection.rst b/docs/101_object_detection.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Images Object Detection
-=============================================
+101 - Images Object Detection
+=============================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_optiml.rst b/docs/101_optiml.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using an OptiML
-=====================================
+101 - OptiML usage
+==================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_pca.rst b/docs/101_pca.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using a PCA
-=================================
+101 - PCA usage
+===============
 
 The PCA model is used to find the linear combination of your original
 features that best describes your data. In that sense, the goal of the model
diff --git a/docs/101_scripting.rst b/docs/101_scripting.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Creating and executing scripts
-====================================================
+101 - Creating and executing scripts
+====================================
 
 The bindings offer methods to create and execute `WhizzML <https://bigml.com/whizzml>`_
 scripts in the platform.
diff --git a/docs/101_topic_model.rst b/docs/101_topic_model.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using a Topic Model
-=========================================
+101 - Topic Model usage
+=======================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/101_ts.rst b/docs/101_ts.rst
@@ -1,8 +1,8 @@
 .. toctree::
    :hidden:
 
-BigML Bindings: 101 - Using a Time Series
-=========================================
+101 - Time Series usage
+=======================
 
 Following the schema described in the `prediction workflow <api_sketch.html>`_,
 document, this is the code snippet that shows the minimal workflow to
diff --git a/docs/conf.py b/docs/conf.py
@@ -30,7 +30,9 @@
 
 # Add any Sphinx extension module names here, as strings. They can be extensions
 # coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
-extensions = []
+extensions = [
+    'sphinx_rtd_theme'
+]
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -46,7 +48,7 @@
 
 # General information about the project.
 project = u'BigML'
-copyright = u'2011 - 2020, The BigML Team'
+copyright = u'2011 - 2024, The BigML Team'
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -101,7 +103,8 @@
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
-html_theme = 'default'
+# a list of builtin themes.
+html_theme = 'sphinx_rtd_theme'
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
diff --git a/docs/index.rst b/docs/index.rst
diff --git a/docs/ml_resources.rst b/docs/ml_resources.rst
diff --git a/docs/quick_start.rst b/docs/quick_start.rst
diff --git a/docs/reading_resources.rst b/docs/reading_resources.rst
diff --git a/docs/requirements.txt b/docs/requirements.txt

Original file line number	Diff line number	Diff line change
`@@ -1 +1 @@`
`1`		`-__version__ = '9.8.0.dev1'`
	`1`	`+__version__ = '9.8.0'`