made edits and modifications to for visuals to update for both logit and...

made edits and modifications to for visuals to update for both logit and decision trees, this is not finalized

examples/decision_tree/main.py

@@ -2,10 +2,11 @@ import numpy as np
 # import pandas as pd
 
 from synthetic import *
-from data_vis import *
-#from data_vis import decisionTreemodel
+from data_vis import vis_synthetic
+from data_vis import decisionTreemodel
+from data_vis import logisticRegressionmodel
 import config as config
-# from modelling import *
+from modelling import *
 
 from bokeh.io import curdoc
 from bokeh.models import ColumnDataSource, Row
@@ -18,6 +19,12 @@ data = SyntheticData(shuffle=False)
 config.X_train, config.X_test, config.y_train, config.y_test = data.generator()
 
 #instantiate model here.
+#finalModel = Models()
+
+
+testModel = decisionTreemodel(config.X_train, config.X_test, config.y_train, config.y_test, 9)
+
+#testModel1 = logisticRegressionModel(config.X_train, config.X_test, config.y_train, config.y_test, 9)
 
 #fit model using fit method on the model class
 
@@ -30,5 +37,5 @@ config.source = ColumnDataSource(dict(x=config.X_train[:,0], y=config.X_train[:,
 
 b = vis_synthetic()
 
-curdoc().add_root(Row(config.inputs, b)) #, text_input_widget, stext_output2))
+curdoc().add_root(Row(config.inputs, b, testModel)) #, text_input_widget, stext_output2))
 curdoc().title = "Decision Tree"
\ No newline at end of file

src/config.py

@@ -35,10 +35,15 @@ regularization_names = [
     "elasticnet" #both l1 and l2 combined
 ]
 
+regularization_names_liblinear = [
+    "l2",
+    "l1"
+]
+
 solver_names = [
     "newton-cg", #dependent on l2 or none regularization
     "lbfgs", #dependent on l1 or none regularization
-    "libliniear", #dependent on l1 or l2 regularization
+    "liblinear", #dependent on l1 or l2 regularization
     "sag", #dependent on l2 or none regularization
     "saga" #dependent on elasticnet, l1, l2, or none regularization
 ]
@@ -95,6 +100,11 @@ normalization_select = Select(value='none',
                               width=200,
                               options=regularization_names)
 
+normalization_select_liblinear = Select(value='none',
+                              title='Select Regularization',
+                              width=200,
+                              options=regularization_names_liblinear)
+
 solver_select = Select(value = "newton-cg",
                        title='Select Solver',
                        width=200,
@@ -116,5 +126,5 @@ inputs = Column(selects,
                 classes_slider, 
                 inf_slider, 
                 features_slider, 
-                data_split_slider)
+                data_split_slider, models_select, solver_select, normalization_select, normalization_select_liblinear, index_slider)
     
\ No newline at end of file

src/data_vis.py

@@ -4,8 +4,9 @@ This is a docstrings for datavis
 from bokeh.models import Scatter
 from bokeh.plotting import figure
 import config as config
-
-# import pandas as pd
+import pandas as pd
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.linear_model import LogisticRegression
 # import numpy as np
 # import math
 # import matplotlib.pyplot as plt
@@ -16,9 +17,8 @@ import config as config
 # from sklearn.model_selection import train_test_split
 
 # lime modules
-# from lime import submodular_pick
-# import lime
-# from lime.lime_tabular import LimeTabularExplainer
+import lime
+from lime.lime_tabular import LimeTabularExplainer
 # from lime import submodular_pick
 
 def vis_synthetic():
@@ -36,6 +36,106 @@ def vis_synthetic():
     
     return b
 
+
+def logisticRegressionmodel(X_train, X_test, Y_train, Y_test, record_value):
+    """This is a docstring for decisionTreeVisuals
+
+    Returns:
+        _type_: _description_
+    """
+
+    # instantiating model
+    model_logreg = LogisticRegression(random_state=7)
+
+    # fit model on training set
+    model_logreg.fit(X_train, Y_train)
+
+    # grabbing unique class names
+    class_names=model_logreg.classes_
+
+    # grabbing specific row for model to use to make prediction
+    #ex_specie = X_test[3, ]
+
+    # lime_tabular is a module that contains functions that explain classifiers which use tabular data (matrices).
+    # LimeTabularExplainer is a function that explains predictions of tabular (matrix) data.
+
+    explainer = lime.lime_tabular.LimeTabularExplainer(X_train, feature_names=Y_train, 
+                                                    class_names=class_names, discretize_continuous=True)
+
+    # grab count of columns from feature matrix
+    featureCount = len(X_train)
+
+    # explain_instance is a function that generates explanations for a prediction after using LimeTabularExplainer.
+    exp = explainer.explain_instance(X_test[record_value],model_logreg.predict_proba,num_features=featureCount)
+
+    # converting explainations as list
+    tupleTest = exp.as_list()
+
+    # converting tuples to list
+    NewList = [list(x) for x in tupleTest]
+
+    # separating comparisons from feature scores
+    Labels1 = [item[0] for item in NewList]
+
+   # separating feature scores from comparisons
+    featureNums = [item[1] for item in NewList]
+
+
+    p = figure(x_range = Labels1, plot_height = 400, title = "Feature Importance Scores")
+    p.vbar(x = Labels1, top = featureNums, width = 0.5, color = "#fc8d59")
+
+    return p
+
+
+def decisionTreemodel(X_train, X_test, Y_train, Y_test, record_value):
+    """This is a docstring for decisionTreeVisuals
+
+    Returns:
+        _type_: _description_
+    """
+
+    # instantiating model
+    model_logreg = DecisionTreeClassifier(max_depth=8, random_state=0)
+
+    # fit model on training set
+    model_logreg.fit(X_train, Y_train)
+
+    # grabbing unique class names
+    class_names=model_logreg.classes_
+
+    # grabbing specific row for model to use to make prediction
+    #ex_specie = X_test[3, ]
+
+    # lime_tabular is a module that contains functions that explain classifiers which use tabular data (matrices).
+    # LimeTabularExplainer is a function that explains predictions of tabular (matrix) data.
+
+    explainer = lime.lime_tabular.LimeTabularExplainer(X_train, feature_names=Y_train, 
+                                                    class_names=class_names, discretize_continuous=True)
+
+    # grab count of columns from feature matrix
+    featureCount = len(X_train)
+
+    # explain_instance is a function that generates explanations for a prediction after using LimeTabularExplainer.
+    exp = explainer.explain_instance(X_test[record_value],model_logreg.predict_proba,num_features=featureCount)
+
+    # converting explainations as list
+    tupleTest = exp.as_list()
+
+    # converting tuples to list
+    NewList = [list(x) for x in tupleTest]
+
+    # separating comparisons from feature scores
+    Labels1 = [item[0] for item in NewList]
+
+   # separating feature scores from comparisons
+    featureNums = [item[1] for item in NewList]
+
+
+    p = figure(x_range = Labels1, plot_height = 400, title = "Feature Importance Scores")
+    p.vbar(x = Labels1, top = featureNums, width = 0.5, color = "#fc8d59")
+
+    return p
+
 '''
 def decisionTreemodel():
     """This is a docstring for decisionTreeVisuals

src/modelling.py

@@ -3,6 +3,8 @@ This is a docstrings for decisionTreeVisuals
 """
 import config as config
 import pandas as pd
+from data_vis import vis_synthetic
+from synthetic import *
 # import numpy as np
 # import math
 # import matplotlib.pyplot as plt
@@ -15,6 +17,9 @@ from sklearn.linear_model import LogisticRegression
 # from sklearn.metrics import accuracy_score
 from sklearn.model_selection import train_test_split
 from synthetic import update_samples_or_dataset
+from bokeh.models import Select, Slider, Row, Column
+from data_vis import decisionTreemodel, logisticRegressionmodel
+from bokeh.io import curdoc
 
 # bokeh libraries/modules
 # from bokeh.io import output_file, show
@@ -67,15 +72,84 @@ def model_callback(attrname, old, new):
         new (_type_): _description_
     """
     #controls parameters when solver updates, add more elif statements as needed.
-    if config.solver_select.value == "newton-cg" or config.solver_select.value == "sag", or config.solver_select.value == "lbfgs":
-        solver = "l2"
+
+   # if config.models_select.value == "Logistic Regression":
+
+    if config.models_select.value == "Logistic Regression" and (config.solver_select.value == "newton-cg" or config.solver_select.value == "sag" or config.solver_select.value == "lbfgs") and (config.dataset_select.value == 'Noisy Circles' or config.dataset_select.value == 'Noisy Moons'):
+    # solver = "l2"
+    # config.normalization_select.value = "l2"
+        inputs = Column(config.selects, config.samples_slider, config.data_split_slider, config.models_select, config.solver_select, config.normalization_select, config.index_slider)
+        s = int(config.index_slider.value)
+        testModel = logisticRegressionmodel( config.X_train, config.X_test, config.y_train, config.y_test, s)
+        normalization_selected = "l2"
+        config.normalization_select.value = normalization_selected
+        b = vis_synthetic()
+
+        curdoc().clear()
+        curdoc().add_root(Row(inputs, b, testModel))
+
+# multilabel classification not working
+    
+    elif config.models_select.value == "Decision Tree" and (config.dataset_select.value == "Make Classification" or config.dataset_select.value == "Blobs" or config.dataset_select.value == "Make Classification" or config.dataset_select.value == 'Noisy Circles' or config.dataset_select.value == 'Noisy Moons'):
+        s = int(config.index_slider.value)
+        inputs = Column(config.selects, config.samples_slider, config.data_split_slider, config.models_select, config.solver_select, config.normalization_select, config.index_slider)
+        testModel = decisionTreemodel(config.X_train, config.X_test, config.y_train, config.y_test, s)
+        #normalization_selected =  "l1", "l2"
+        #config.normalization_select.value = list(normalization_selected.values)
+        b = vis_synthetic()
+
+        curdoc().clear()
+        curdoc().add_root(Row(inputs, b, testModel))
+
+    elif config.models_select.value == "Logistic Regression" and (config.solver_select.value == "liblinear") and (config.dataset_select.value == 'Noisy Circles' or config.dataset_select.value == 'Noisy Moons'):
+        s = int(config.index_slider.value)
+        inputs = Column(config.selects, config.samples_slider, config.data_split_slider, config.models_select, config.solver_select, config.normalization_select_liblinear, config.index_slider)
+        testModel = logisticRegressionmodel(config.X_train, config.X_test, config.y_train, config.y_test, s)
+        #normalization_selected =  "l1", "l2"
+        #config.normalization_select.value = list(normalization_selected.values)
+        b = vis_synthetic()
+
+        curdoc().clear()
+        curdoc().add_root(Row(inputs, b, testModel))
+    #if config.models_select.value == "Logistic Regression":
+
+
+        '''
+
+        if config.model_names.value == 'Decision Tree':
+            inputs = Column(config.selects, config.samples_slider, config.data_split_slider, config.models_select, config.solver_select, config.normalization_select, config.index_slider)
+            s = int(config.index_slider.value)
+            testModel = decisionTreemodel( config.X_train, config.X_test, config.y_train, config.y_test, s)
+            b = vis_synthetic()
+
+            curdoc().clear()
+            curdoc().add_root(Row(inputs, b, testModel))
+        '''
+
+        
+    
     
     #control statements for selecting the appropriate dataset needs to:
     # 1. update the dataset ( this will automatically update the layout)
     #have to figure out how to update the dataset from here.
     #probably need to update the selector to only show binary datasets. So make 2 separate dataset selectors: binary and multiclass 
 
+# add more call backs for each selector
+#config.models_select.on_change('value', model_callback)
+
+config.dataset_select.on_change('value', model_callback)
+
+config.solver_select.on_change('value', model_callback)
 
+config.normalization_select.on_change('value', model_callback)
+
+config.index_slider.on_change('value', model_callback)
+
+
+
+#config.index_slider.on_change('value', model_callback)
+
+'''
 def decisionTreemodel(X, Y, indexValue):
     """This is a docstring for decisionTreeVisuals
 
@@ -163,6 +237,5 @@ def decisionTreemodel(X, Y, indexValue):
     #return (Labels1, featureNums)
     #return dfBokehChart
     return p
+'''
 
-# add more call backs for each selector
-config.models_select.on_change('value', model_callback)

src/synthetic.py

@@ -213,21 +213,28 @@ def update_layout(attrname, old, new):
         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, config.data_split_slider)
+        inputs = Column(config.selects, config.samples_slider, config.classes_slider, config.features_slider, config.data_split_slider, config.models_select, config.solver_select, config.normalization_select, config.index_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, config.data_split_slider)
+        inputs = Column(config.selects, config.samples_slider, config.classes_slider, config.features_slider, config.inf_slider, config.data_split_slider, config.models_select, config.solver_select, config.normalization_select, config.index_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, config.data_split_slider)
+        inputs = Column(config.selects, config.samples_slider, config.data_split_slider, config.models_select, config.solver_select, config.normalization_select, config.index_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') and (config.solver_select.value == "liblinear"):
+        inputs = Column(config.selects, config.samples_slider, config.data_split_slider, config.models_select, config.solver_select, config.normalization_select_liblinear, config.index_slider)
         b = vis_synthetic()
         
         curdoc().clear()