mirror of
https://github.com/gsi-upm/sitc
synced 2024-11-24 23:42:29 +00:00
113 lines
5.2 KiB
Python
113 lines
5.2 KiB
Python
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
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.neighbors import KNeighborsClassifier
|
|
from sklearn.svm import SVC
|
|
from sklearn.tree import DecisionTreeClassifier
|
|
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
|
|
from sklearn.naive_bayes import GaussianNB
|
|
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
|
|
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
|
|
from sklearn.dummy import DummyClassifier
|
|
|
|
# Taken from http://scikit-learn.org/stable/auto_examples/classification/plot_classifier_comparison.html#example-classification-plot-classifier-comparison-py
|
|
|
|
def plot_classifiers():
|
|
"""
|
|
Plot classifiers in synthetic datasets, taken from http://scikit-learn.org/stable/auto_examples/classification/plot_classifier_comparison.html
|
|
A comparison of a several classifiers in scikit-learn on synthetic datasets. The point of this example is to illustrate the nature of decision boundaries of different classifiers. This should be taken with a grain of salt, as the intuition conveyed by these examples does not necessarily carry over to real datasets.
|
|
Particularly in high-dimensional spaces, data can more easily be separated linearly and the simplicity of classifiers such as naive Bayes and linear SVMs might lead to better generalization than is achieved by other classifiers.
|
|
The plots show training points in solid colors and testing points semi-transparent. The lower right shows the classification accuracy on the test set.
|
|
"""
|
|
h = .02 # step size in the mesh
|
|
|
|
names = ["DummyClassifier", "Nearest Neighbors", "Decision Tree", "Naive Bayes", "Linear SVM", "RBF SVM",
|
|
"Random Forest"]
|
|
classifiers = [
|
|
DummyClassifier(strategy="prior"),
|
|
KNeighborsClassifier(3),
|
|
DecisionTreeClassifier(max_depth=5),
|
|
GaussianNB(),
|
|
SVC(kernel="linear", C=0.025),
|
|
SVC(gamma=2, C=1),
|
|
RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1)
|
|
]
|
|
|
|
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]
|
|
ds_names = ["Dataset moons", "Dataset circles", "Dataset linearly_separable"]
|
|
|
|
figure = plt.figure(figsize=(27, 9))
|
|
i = 1
|
|
# iterate over datasets
|
|
for ds_name, ds in zip(ds_names, datasets):
|
|
# 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)
|
|
|
|
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)
|
|
ax.set_title(ds_name)
|
|
# Plot the training points
|
|
ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
|
|
# and testing points
|
|
ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6)
|
|
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):
|
|
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, m_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=.8)
|
|
|
|
# Plot also the training points
|
|
ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
|
|
# and testing points
|
|
ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
|
|
alpha=0.6)
|
|
|
|
ax.set_xlim(xx.min(), xx.max())
|
|
ax.set_ylim(yy.min(), yy.max())
|
|
ax.set_xticks(())
|
|
ax.set_yticks(())
|
|
ax.set_title(name)
|
|
ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),
|
|
size=15, horizontalalignment='right')
|
|
i += 1
|
|
|
|
figure.subplots_adjust(left=.02, right=.98)
|
|
plt.suptitle("Comparison of Classifiers in synthetic datasets", fontsize=18)
|
|
plt.show()
|