add synthetic data generator, refactor project modules

WHY/WHY.egg-info/PKG-INFO

+Metadata-Version: 2.1
+Name: WHY
+Version: 0.0.1.dev0+5059977
+Summary: Explainable AI system
+Home-page: https://gitlab.cci.drexel.edu/pjm363/why-senior-project
+Author: Philip Monaco, Abdullah Shah, Ibrahim Elsaid, Jashanpreet Singh, William Lu, Songheng Li
+License: LICENSE.md
+Description: # WHY Senior Project
+        
+        ## Installing WHY
+        
+        There are two way in which the `WHY` package can be installed.
+        First, follow the [prerequisite](#prerequisites) instructions.
+        IF you do not need to rebuild documentation or make modifications to the library, follow the instructions under [User Installation](#user-installation).
+        Otherwise, follow the instructions under [Developer Installation](#developer-installation).
+        
+        ### Prerequisites
+        
+        The `WHY` requires at least `python3.8` and makes use of a number of third-party libraries. The bare minimum packages are automatically installed when you install `WHY` using `pip`. Additional dependencies for developers are contained in `requirements.txt` file. See the
+        
+        It's recommended that you use `WHY` within a python virtual environment. 
+        Virtual environments are now included natively with Python 3 using `venv`. Instructions to create a virtual environment can be found [here](https://docs.python.org/3/library/venv.html).  
+        
+        API documentation requires the use of `sphinx` which will require installing `Cmake`.  Installation instructions can be found [here](https://cmake.org/install/).
+        
+        ### User Installation
+        
+        First you must clone the repository using the following bash command.
+        ```bash
+        pip clone git@gitlab.cci.drexel.edu:pjm363/why-senior-project.git
+        ```
+        
+        From the root path of the repository (the folder where `setup.py` is located) `WHY` can be installed using `pip` using the following command. 
+        
+        ```bash
+        pip install .
+        ```
+        
+        ### Developer Installation
+        Developers need an additional tool, `clang-format` in order to run the precommit script. 
+        
+        Install via Ubuntu.
+        ```bash 
+        apt-get install clang-format
+        ```
+        Install via MacOSX with homebrew.
+        ```bash
+        brew install clang-format
+        ```
+        Install via [installer](https://llvm.org/builds/) or using chocolatey via.
+        ```bash
+        choco install llvm
+        ```
+        
+        ## Building API Documentation
+        
+        To build the API Documentation in HTML format for local browsing, execute the following from the root of the repository.
+        ```
+        cd docs/
+        make html
+        ```
+        
+        This will also cause any examples contained in `examples` to be generated in the example gallery.  
+        All documentation is also built automatically when the `./precommit.sh` script is run.
+        
+Platform: UNKNOWN
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Provides-Extra: lint
+Provides-Extra: docs
+Provides-Extra: all

WHY/WHY.egg-info/SOURCES.txt

+README.md
+setup.py
+src/WHY.egg-info/PKG-INFO
+src/WHY.egg-info/SOURCES.txt
+src/WHY.egg-info/dependency_links.txt
+src/WHY.egg-info/not-zip-safe
+src/WHY.egg-info/requires.txt
+src/WHY.egg-info/top_level.txt
\ No newline at end of file

WHY/WHY.egg-info/dependency_links.txt

+

WHY/WHY.egg-info/not-zip-safe

+

WHY/WHY.egg-info/requires.txt

+numpy>=1.21
+pandas>=1.3.5
+bokeh>=2.4.2
+matplotlib>=3.5.0
+scikit-learn>=1.0.2
+
+[all]
+numpy>=1.21
+pandas>=1.3.5
+bokeh>=2.4.2
+matplotlib>=3.5.0
+scikit-learn>=1.0.2
+black==21.12b0
+isort==5.10.1
+flake8==4.0.1
+mypy
+Sphinx
+sphinx-gallery
+sphinx-rtd-theme
+m2r2
+
+[docs]
+Sphinx
+sphinx-gallery
+sphinx-rtd-theme
+m2r2
+
+[lint]
+black==21.12b0
+isort==5.10.1
+flake8==4.0.1
+mypy

WHY/WHY.egg-info/top_level.txt

+

WHY/config.py

+"""
+This is a docstring for config.
+"""
+from bokeh.models import Select, Slider, Row, Column
+from bokeh.layouts import column, row
+
+x = 0 
+y = 0
+
+spectral = 0
+source = 0
+
+datasets_names = [
+    "Make Classification",
+    "Multilabel Classification",
+    "Blobs",
+    "Noisy Moons", 
+    "Noisy Circles"
+]
+
+dataset_select = Select(value='Make Classification',
+                        title='Select Dataset',
+                        width=200,
+                        options=datasets_names)
+
+samples_slider = Slider(title="Number of samples",
+                        value=1500.0,
+                        start=200.0,
+                        end=3000.0,
+                        step=100,
+                        width=400)
+
+classes_slider = Slider(title="Number of Classes",
+                        value = 3,
+                        start=2,
+                        end=20,
+                        step=1,
+                        width=400)
+
+features_slider = Slider(title="Number of Features",
+                         value = 3,
+                         start=2,
+                         end=1000,
+                         step=1,
+                         width=400)
+
+inf_slider = Slider(title='Informative Classes',
+                    value=3,
+                    start=2,
+                    end=100,
+                    step=1,
+                    width=400)
+
+
+selects = Row(dataset_select, width=420)
+inputs = Column(selects, samples_slider, classes_slider, inf_slider, features_slider)

WHY/data_vis.py

+"""
+This is a docstrings for datavis
+"""
+from bokeh.models import ColumnDataSource, Select, Slider, Plot, Scatter, Row, Column
+from bokeh.plotting import figure
+import config as config
+
+def vis_synthetic():
+    """This is a docstring for datavis
+
+    Returns:
+        _type_: _description_
+    """
+    b = figure(
+    title="Dataset", width=400, height=400, min_border=0)
+
+    glyph = Scatter(x="x", y="y", size=5, fill_color="colors")
+
+    b.add_glyph(config.source, glyph)
+    
+    return b
\ No newline at end of file

WHY/synthetic.py

+"""
+Synthetic data generation class, with callbacks and visualizations
+"""
+
+import numpy as np
+from sklearn import datasets
+from bokeh.models import Select, Slider, Row, Column
+from bokeh.io import curdoc
+from bokeh.layouts import column, row
+import math
+from bokeh.palettes import Spectral6
+import config as config
+from data_vis import vis_synthetic
+
+class SyntheticData:
+    """Class for creating a synthetic data object with default parameters.
+    """
+    def __init__(self, 
+                 dataset='Make Classification', 
+                 n_samples=1500, 
+                 n_features=4, 
+                 n_classes=3, 
+                 n_inf=2):
+        self.dataset = dataset
+        self.n_samples = n_samples
+        self.n_features = n_features
+        self.n_classes = n_classes
+        self.n_inf = n_inf
+    
+    
+    def generator(self):
+        """Engine that creates synthetic data.
+        
+        Takes advantage the synthetic data generator provided by sklearn.
+        The generator makes 5 data shapes available.
+
+        Returns:
+            X: ndarray of shape(n_samples, 2) The generated samples.
+            y: ndarray of shape(n_samples,) The integer labels for class membership of each sample.
+        """
+        if self.dataset == 'Blobs':
+            #sliders: samples, classes, features
+            return datasets.make_blobs(n_samples=self.n_samples,
+                                       centers=self.n_classes,
+                                       n_features=self.n_features,
+                                       random_state=8
+                                       )
+            
+        elif self.dataset == 'Make Classification':
+            #sliders: samples, features, informative features, classes
+            return datasets.make_classification(n_samples=self.n_samples,
+                                                n_features=self.n_features, 
+                                                n_informative=self.n_inf, 
+                                                n_redundant=0,
+                                                n_clusters_per_class=1, 
+                                                n_classes=self.n_classes,
+                                                random_state=8
+                                                )
+            
+        elif self.dataset == 'Noisy Circles':
+            #sliders: samples
+            return datasets.make_circles(n_samples=self.n_samples,
+                                        factor=0.5,
+                                        noise=0.05
+                                        )
+
+        elif self.dataset == 'Noisy Moons':
+            #sliders: samples
+            return datasets.make_moons(n_samples=self.n_samples,
+                                       noise=0.05
+                                       )
+
+        elif self.dataset == 'Multilabel Classification':
+            #sliders: samples, features, classes
+            return datasets.make_multilabel_classification(n_samples=self.n_samples, 
+                                                           n_features=self.n_features,
+                                                           n_classes=self.n_classes,
+                                                           random_state=8
+                                                           )
+
+        elif self.dataset == "No Structure":
+            return np.random.rand(self.n_samples, 2), None
+        
+def update_samples_or_dataset(attrname, old, new):
+    """Callback function that updates samples as values are scrubbed with sliders.
+
+    Args:
+        attrname (_type_): _description_
+        old (_type_): _description_
+        new (_type_): _description_
+    """
+
+    if config.dataset_select.value == 'Blobs':
+        dataset = config.dataset_select.value
+        n_samples = int(config.samples_slider.value)
+        n_classes = int(config.classes_slider.value)
+        n_features = int(config.features_slider.value)
+        
+        data = SyntheticData(dataset, n_samples, n_features, n_classes)
+        config.x, config.y = data.generator()
+        colors = [config.spectral[i] for i in config.y]
+
+        config.source.data = dict(colors=colors, x=config.x[:, 0], y=config.x[:, 1])
+        
+    elif config.dataset_select.value == 'Make Classification':
+        dataset = config.dataset_select.value
+        n_samples = int(config.samples_slider.value)
+        n_classes = int(config.classes_slider.value)
+        n_features = int(config.features_slider.value)
+        n_inf = int(config.inf_slider.value)
+        
+        if n_inf > n_features:
+            n_features = n_inf
+            config.features_slider.update(value=n_inf)
+        
+        if n_classes > 2**n_inf:
+            n_inf = (math.ceil(math.log2(n_classes)))
+            n_features = n_inf
+            config.inf_slider.update(value=n_inf)
+            config.features_slider.update(value=n_features)
+            
+        data = SyntheticData(dataset, n_samples, n_features, n_classes, n_inf)
+        config.x, config.y = data.generator()
+        colors = [config.spectral[i]  for i in config.y]
+
+        config.source.data = dict(colors=colors, x=config.x[:, 0], y=config.x[:, 1])
+        
+    elif config.dataset_select.value == 'Noisy Circles':
+        dataset = config.dataset_select.value
+        n_samples = int(config.samples_slider.value)
+        
+        data = SyntheticData(dataset, n_samples)
+        config.x, config.y = data.generator()
+        colors = [config.spectral[i]  for i in config.y]
+
+        config.source.data = dict(colors=colors, x=config.x[:, 0], y=config.x[:, 1])
+        
+    elif config.dataset_select.value == 'Noisy Moons':
+        dataset = config.dataset_select.value
+        n_samples = int(config.samples_slider.value)
+        
+        data = SyntheticData(dataset, n_samples)
+        config.x, config.y = data.generator()
+        colors = [config.spectral[i]  for i in config.y]
+
+        config.source.data = dict(colors=colors, x=config.x[:, 0], y=config.x[:, 1])
+        
+    elif config.dataset_select.value == 'Multilabel Classification':
+        dataset = config.dataset_select.value
+        n_samples = int(config.samples_slider.value)
+        n_features = int(config.features_slider.value)
+        n_classes = int(config.classes_slider.value)
+                
+        data = SyntheticData(dataset, n_samples, n_features, n_classes)
+        config.x, config.y = data.generator()
+        colors = [config.spectral[i]  for i in config.y]
+
+        config.source.data = dict(colors=colors, x=config.x[:, 0], y=config.x[:, 1])
+    
+
+def update_layout(attrname, old, new):
+    """Callback function that updates the sliders layout as datasets change.
+
+    Args:
+        attrname (_type_): _description_
+        old (_type_): _description_
+        new (_type_): _description_
+    """
+    if config.dataset_select.value == 'Blobs' or config.dataset_select.value == 'Multilabel Classification':
+        inputs = Column(config.selects, config.samples_slider, config.classes_slider, config.features_slider)
+        b = vis_synthetic()
+        curdoc().clear()
+        curdoc().add_root(Row(inputs, b))
+
+    elif config.dataset_select.value == 'Make Classification':
+        inputs = Column(config.selects, config.samples_slider, config.classes_slider, config.features_slider, config.inf_slider)
+        b = vis_synthetic()
+        curdoc().clear()
+        curdoc().add_root(Row(inputs, b))
+        
+    elif config.dataset_select.value == 'Noisy Circles' or config.dataset_select.value == 'Noisy Moons':
+        inputs = Column(config.selects, config.samples_slider)
+        b = vis_synthetic()
+        curdoc().clear()
+        curdoc().add_root(Row(inputs,b))
+
+config.dataset_select.on_change('value', update_samples_or_dataset)
+config.samples_slider.on_change('value_throttled', update_samples_or_dataset)
+config.classes_slider.on_change('value_throttled', update_samples_or_dataset)
+config.features_slider.on_change('value', update_samples_or_dataset)
+config.inf_slider.on_change('value', update_samples_or_dataset)
+
+config.dataset_select.on_change('value', update_layout)
\ No newline at end of file

docs/Makefile

@@ -3,10 +3,10 @@
 
 # You can set these variables from the command line, and also
 # from the environment for the first two.
-SPHINXOPTS    =
-SPHINXBUILD   = sphinx-build
-SOURCEDIR     = source
-BUILDDIR      = build
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
 
 # Put it first so that "make" without argument is like "make help".
 help:

docs/WHY.rst

+WHY package
+===========
+
+Submodules
+----------
+
+WHY.config module
+-----------------
+
+.. automodule:: WHY.config
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+WHY.data\_vis module
+--------------------
+
+.. automodule:: WHY.data_vis
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+WHY.synthetic module
+--------------------
+
+.. automodule:: WHY.synthetic
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+Module contents
+---------------
+
+.. automodule:: WHY
+   :members:
+   :undoc-members:
+   :show-inheritance: