Fixing the get_leaves function and setup issues for Python 3.12

.github/workflows/tests_01.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python: [3.11]
+        python: [3.12]
     env:
         BIGML_USERNAME: ${{ secrets.BIGML_USERNAME }}
         BIGML_API_KEY: ${{ secrets.BIGML_API_KEY }}

.github/workflows/tests_05.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python: [3.11]
+        python: [3.12]
     env:
         BIGML_USERNAME: ${{ secrets.BIGML_USERNAME }}
         BIGML_API_KEY: ${{ secrets.BIGML_API_KEY }}

.github/workflows/tests_22.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python: [3.11]
+        python: [3.12]
     env:
         BIGML_USERNAME: ${{ secrets.BIGML_USERNAME }}
         BIGML_API_KEY: ${{ secrets.BIGML_API_KEY }}

.github/workflows/tests_23.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python: [3.11]
+        python: [3.12]
     env:
         BIGML_USERNAME: ${{ secrets.BIGML_USERNAME }}
         BIGML_API_KEY: ${{ secrets.BIGML_API_KEY }}

.github/workflows/tests_36.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python: [3.11]
+        python: [3.12]
     env:
         BIGML_USERNAME: ${{ secrets.BIGML_USERNAME }}
         BIGML_API_KEY: ${{ secrets.BIGML_API_KEY }}

.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

HISTORY.rst

@@ -3,6 +3,13 @@
 History
 -------
 
+9.8.0 (2024-10-02)
+------------------
+
+- Fixing the get_leaves function for local decision trees.
+- Fixing setup issues in Python3.12
+- Changing documentation templates.
+
 9.8.0.dev1 (2024-02-28)
 -----------------------
 

bigml/dataset.py

@@ -20,7 +20,6 @@
 """
 import os
 import logging
-import warnings
 import subprocess
 
 from bigml.fields import Fields, sorted_headers, get_new_fields
@@ -40,12 +39,13 @@
 
 #pylint: disable=locally-disabled,bare-except,ungrouped-imports
 try:
-    # avoiding tensorflow info logging
-    warnings.filterwarnings("ignore", category=DeprecationWarning)
-    os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
+    # bigml-sensenet should be installed for image processing
+    logging.disable(logging.WARNING)
+    os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
     import tensorflow as tf
-    tf.get_logger().setLevel('ERROR')
     tf.autograph.set_verbosity(0)
+    logging.getLogger("tensorflow").setLevel(logging.ERROR)
+    import sensenet
     from bigml.images.featurizers import ImageFeaturizer as Featurizer
 except:
     pass

bigml/deepnet.py

@@ -62,20 +62,15 @@
 import bigml.laminar.preprocess_np as pp
 
 try:
-    # avoiding tensorflow info logging
-    warnings.filterwarnings("ignore", category=DeprecationWarning)
-    os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
+    logging.disable(logging.WARNING)
+    os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
+    logging.getLogger("tensorflow").setLevel(logging.ERROR)
     import tensorflow as tf
-    tf.get_logger().setLevel('ERROR')
     tf.autograph.set_verbosity(0)
-    LAMINAR_VERSION = False
-except Exception:
-    LAMINAR_VERSION = True
-
-try:
     from sensenet.models.wrappers import create_model
     from bigml.images.utils import to_relative_coordinates
     from bigml.constants import IOU_REMOTE_SETTINGS
+    LAMINAR_VERSION = False
 except Exception:
     LAMINAR_VERSION = True
 

bigml/ensemble.py

@@ -214,7 +214,6 @@ def __init__(self, ensemble, api=None, max_models=None, cache_get=None,
                 # avoid checking fields because of old ensembles
                 ensemble = retrieve_resource(self.api, self.resource_id,
                                              no_check_fields=True)
-
             self.parent_id = ensemble.get('object', {}).get('dataset')
             self.name = ensemble.get('object', {}).get('name')
             self.description = ensemble.get('object', {}).get('description')

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)
 
 

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)

bigml/tests/test_14_create_evaluations.py

@@ -194,7 +194,7 @@ def test_scenario4(self):
                    "evaluation_wait", "metric", "value"]
         examples = [
             ['data/iris.csv', '50', '50', '800', '80', 'average_phi',
-             '0.97007']]
+             '0.98029']]
         for example in examples:
             example = dict(zip(headers, example))
             show_method(self, self.bigml["method"], example)

bigml/tests/test_36_compare_predictions.py

@@ -77,7 +77,7 @@ def test_scenario1(self):
              'Iris-versicolor', '{}'],
             ['data/iris_missing2.csv', '30', '50', '60', '{}', '000004',
              'Iris-versicolor', '{}'],
-            ['data/grades.csv', '30', '50', '60', '{}', '000005', 55.6560,
+            ['data/grades.csv', '30', '50', '60', '{}', '000005', 47.04852,
              '{}'],
             ['data/spam.csv', '30', '50', '60', '{}', '000000', 'ham', '{}']]
         show_doc(self.test_scenario1)

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):
         """
@@ -211,7 +213,7 @@ def test_scenario4(self):
             ['data/iris.csv', '10', '10', '500', './tmp/deepnet.json', {},
              'Iris-versicolor', '{}'],
             ['data/iris.csv', '10', '10', '500', './tmp/deepnet_dft.json', {},
-             'Iris-virginica', '{"default_numeric_value": "maximum"}']]
+             'Iris-versicolor', '{"default_numeric_value": "maximum"}']]
         for example in examples:
             example = dict(zip(headers, example))
             show_method(self, self.bigml["method"], example)

bigml/tests/test_49_local_pipeline.py

@@ -210,28 +210,28 @@ def test_scenario4(self):
         examples = [
             ['data/dates2.csv', '20', '45', '160',
              '{"time-1": "1910-05-08T19:10:23.106", "cat-0":"cat2"}',
-             '000002', -0.02616, "pipeline1"],
+             '000002', -0.4264, "pipeline1"],
             ['data/dates2.csv', '20', '45', '160',
              '{"time-1": "2011-04-01T00:16:45.747", "cat-0":"cat2"}',
-             '000002', 0.13352, "pipeline2"],
+             '000002', 0.11985, "pipeline2"],
             ['data/dates2.csv', '20', '45', '160',
              '{"time-1": "1969-W29-1T17:36:39Z", "cat-0":"cat1"}',
-             '000002', 0.10071, "pipeline3"],
+             '000002', -0.08211, "pipeline3"],
             ['data/dates2.csv', '20', '45', '160',
              '{"time-1": "1920-06-45T20:21:20.320", "cat-0":"cat1"}',
-             '000002', 0.10071, "pipeline4"],
+             '000002', -0.08211, "pipeline4"],
             ['data/dates2.csv', '20', '45', '160',
              '{"time-1": "2001-01-05T23:04:04.693", "cat-0":"cat2"}',
-             '000002', 0.15235, "pipeline5"],
+             '000002', 0.00388, "pipeline5"],
             ['data/dates2.csv', '20', '45', '160',
              '{"time-1": "1950-11-06T05:34:05.602", "cat-0":"cat1"}',
-             '000002', -0.07686, "pipeline6"],
+             '000002', -0.04976, "pipeline6"],
             ['data/dates2.csv', '20', '45', '160',
              '{"time-1": "1932-01-30T19:24:11.440",  "cat-0":"cat2"}',
-             '000002', 0.0017, "pipeline7"],
+             '000002', -0.36264, "pipeline7"],
             ['data/dates2.csv', '20', '45', '160',
              '{"time-1": "Mon Jul 14 17:36 +0000 1969", "cat-0":"cat1"}',
-             '000002', 0.10071, "pipeline8"]]
+             '000002', -0.08211, "pipeline8"]]
         show_doc(self.test_scenario4)
         for example in examples:
             example = dict(zip(headers, example))

bigml/version.py

@@ -1 +1 @@
-__version__ = '9.8.0.dev1'
+__version__ = '9.8.0'

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

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

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

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

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

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

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

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

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

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