Comparing classifiers (including Bayesian networks) with scikit-learn¶
In this notebook, we use the skbn module to insert bayesian networks into some examples from the scikit-learn documentation (that we refer).
In [1]:
import pyAgrum as gum
import pyAgrum.lib.notebook as gnb
from pyAgrum.skbn import BNClassifier
Binary classifiers¶
In [2]:
# From https://scikit-learn.org/stable/auto_examples/classification/plot_classifier_comparison.html)
# Code source: Gael Varoquaux
# Andreas Muller
# Modified for documentation by Jaques Grobler
# License: BSD 3 clause
In [3]:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patheffects as pe
from matplotlib.colors import ListedColormap
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.neural_network import MLPClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.gaussian_process import GaussianProcessClassifier
from sklearn.gaussian_process.kernels import RBF
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
In [4]:
# the data
X, y = make_classification(n_features=2, n_redundant=0, n_informative=2,
random_state=1, n_clusters_per_class=1)
rng = np.random.RandomState(2)
X += 2 * rng.uniform(size=X.shape)
linearly_separable = (X, y)
datasets = [make_moons(noise=0.3, random_state=0),
make_circles(noise=0.2, factor=0.5, random_state=1),
linearly_separable
]
datasets_name=['Moons ',
'Circle',
'LinSep']
In [5]:
def showComparison(names,classifiers,datasets,datasets_name):# the results
bnres=[None]*len(datasets_name)
h = .02 # step size in the mesh
fs=6
figure = plt.figure(figsize=(12, 4))
i = 1
# iterate over datasets
for ds_cnt, ds in enumerate(datasets):
print(datasets_name[ds_cnt]+' : ',end='')
# preprocess dataset, split into training and test part
X, y = ds
X = StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=.4, random_state=42)
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
# just plot the dataset first
cm = plt.cm.RdBu
cm_bright = ListedColormap(['#FF0000', '#0000FF'])
ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
if ds_cnt == 0:
ax.set_title("Input data",fontsize=fs)
ax.set_ylabel(datasets_name[ds_cnt])
# Plot the training points
ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,
edgecolors='k',marker=".")
# Plot the testing points
ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6,
edgecolors='k',marker=".")
ax.set_xlim(xx.min(), xx.max())
ax.set_ylim(yy.min(), yy.max())
ax.set_xticks(())
ax.set_yticks(())
i += 1
# iterate over classifiers
for name, clf in zip(names, classifiers):
print(".",end="",flush=True)
ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]x[y_min, y_max].
if hasattr(clf, "decision_function"):
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
else:
Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
# Put the result into a color plot
Z = Z.reshape(xx.shape)
ax.contourf(xx, yy, Z, cmap=cm, alpha=.7)
# Plot the training points
#ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,
# edgecolors='k', alpha=0.2,marker='.')
# Plot the testing points
ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
edgecolors='k',marker='.')
ax.set_xlim(xx.min(), xx.max())
ax.set_ylim(yy.min(), yy.max())
ax.set_xticks(())
ax.set_yticks(())
if ds_cnt == 0:
ax.set_title(name,fontsize=fs)
ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),
size=12, horizontalalignment='right',color="white",
path_effects=[pe.withStroke(linewidth=2, foreground="black")])
i += 1
bnres[ds_cnt]=gum.BayesNet(classifiers[-1].bn)
print()
plt.tight_layout()
plt.show()
return bnres
In [6]:
# the classifiers
names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Gaussian Process",
"Decision Tree", "Random Forest", "Neural Net", "AdaBoost",
"Naive Bayes", "QDA","BNClassifier"
]
classifiers = [
KNeighborsClassifier(3),
SVC(kernel="linear", C=0.025),
SVC(gamma=2, C=1),
GaussianProcessClassifier(1.0 * RBF(1.0)),
DecisionTreeClassifier(max_depth=5),
RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
MLPClassifier(alpha=1, max_iter=1000),
AdaBoostClassifier(),
GaussianNB(),
QuadraticDiscriminantAnalysis(),
BNClassifier(learningMethod='MIIC', prior='Smoothing', priorWeight=0.01, discretizationNbBins=5,
discretizationStrategy="kmeans", # 'kmeans', 'uniform', 'quantile', 'NML', 'MDLP', 'CAIM', 'NoDiscretization'
usePR=False)
]
bnres=showComparison(names,classifiers,datasets,datasets_name)
Moons : .
.
.
.
.
.
.
.
.
.
.
/Users/phw/.virtualenvs/devAgrum/lib/python3.12/site-packages/sklearn/ensemble/_weight_boosting.py:527: FutureWarning: The SAMME.R algorithm (the default) is deprecated and will be removed in 1.6. Use the SAMME algorithm to circumvent this warning. warnings.warn(
Circle : .
.
.
.
.
.
.
.
.
.
.
/Users/phw/.virtualenvs/devAgrum/lib/python3.12/site-packages/sklearn/ensemble/_weight_boosting.py:527: FutureWarning: The SAMME.R algorithm (the default) is deprecated and will be removed in 1.6. Use the SAMME algorithm to circumvent this warning. warnings.warn(
LinSep : .
.
.
.
.
.
.
.
.
.
.
/Users/phw/.virtualenvs/devAgrum/lib/python3.12/site-packages/sklearn/ensemble/_weight_boosting.py:527: FutureWarning: The SAMME.R algorithm (the default) is deprecated and will be removed in 1.6. Use the SAMME algorithm to circumvent this warning. warnings.warn(