8、特征離散化
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.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import KBinsDiscretizer
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.utils._testing import ignore_warnings
from sklearn.exceptions import ConvergenceWarning
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
h = .02? # 設(shè)置網(wǎng)格的補(bǔ)不長(zhǎng)
def get_name(estimator):
? ? name = estimator.__class__.__name__
? ? if name == 'Pipeline':
? ? ? ? name = [get_name(est[1]) for est in estimator.steps]
? ? ? ? name = ' + '.join(name)
? ? return name
# （estimator，param_grid）的列表，其中在GridSearchCV中使用param_grid
classifiers = [
? ? (LogisticRegression(random_state=0), {
? ? ? ? 'C': np.logspace(-2, 7, 10)
? ? }),
? ? (LinearSVC(random_state=0), {
? ? ? ? 'C': np.logspace(-2, 7, 10)
? ? }),
? ? (make_pipeline(
? ? ? ? KBinsDiscretizer(encode='onehot'),
? ? ? ? LogisticRegression(random_state=0)), {
? ? ? ? ? ? 'kbinsdiscretizer__n_bins': np.arange(2, 10),
? ? ? ? ? ? 'logisticregression__C': np.logspace(-2, 7, 10),
? ? ? ? }),
? ? (make_pipeline(
? ? ? ? KBinsDiscretizer(encode='onehot'), LinearSVC(random_state=0)), {
? ? ? ? ? ? 'kbinsdiscretizer__n_bins': np.arange(2, 10),
? ? ? ? ? ? 'linearsvc__C': np.logspace(-2, 7, 10),
? ? ? ? }),
? ? (GradientBoostingClassifier(n_estimators=50, random_state=0), {
? ? ? ? 'learning_rate': np.logspace(-4, 0, 10)
? ? }),
? ? (SVC(random_state=0), {
? ? ? ? 'C': np.logspace(-2, 7, 10)
? ? }),
]
names = [get_name(e) for e, g in classifiers]
n_samples = 100
datasets = [
? ? make_moons(n_samples=n_samples, noise=0.2, random_state=0),
? ? make_circles(n_samples=n_samples, noise=0.2, factor=0.5, random_state=1),
? ? make_classification(n_samples=n_samples, n_features=2, n_redundant=0,
? ? ? ? ? ? ? ? ? ? ? ? n_informative=2, random_state=2,
? ? ? ? ? ? ? ? ? ? ? ? n_clusters_per_class=1)
]
fig, axes = plt.subplots(nrows=len(datasets), ncols=len(classifiers) + 1,
? ? ? ? ? ? ? ? ? ? ? ? figsize=(21, 9))
cm = plt.cm.PiYG
cm_bright = ListedColormap(['#b30065', '#178000'])
# 在數(shù)據(jù)集上迭代
for ds_cnt, (X, y) in enumerate(datasets):
? ? print('\ndataset %d\n---------' % ds_cnt)
? ? # 預(yù)處理數(shù)據(jù)集，分為訓(xùn)練和測(cè)試部分
? ? X = StandardScaler().fit_transform(X)
? ? X_train, X_test, y_train, y_test = train_test_split(
? ? ? ? X, y, test_size=.5, random_state=42)
? ? # 為背景顏色創(chuàng)建網(wǎng)格
? ? 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))
? ? # 首先繪制數(shù)據(jù)集
? ? ax = axes[ds_cnt, 0]
? ? if ds_cnt == 0:
? ? ? ? ax.set_title("Input data")
? ? # 規(guī)劃訓(xùn)練要點(diǎn)
? ? ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,
? ? ? ? ? ? ? edgecolors='k')
? ? # 檢測(cè)點(diǎn)
? ? ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6,
? ? ? ? ? ? ? edgecolors='k')
? ? ax.set_xlim(xx.min(), xx.max())
? ? ax.set_ylim(yy.min(), yy.max())
? ? ax.set_xticks(())
? ? ax.set_yticks(())
? ? # 在分類(lèi)器上迭代
? ? for est_idx, (name, (estimator, param_grid)) in \
? ? ? ? ? ? enumerate(zip(names, classifiers)):
? ? ? ? ax = axes[ds_cnt, est_idx + 1]
? ? ? ? clf = GridSearchCV(estimator=estimator, param_grid=param_grid)
? ? ? ? with ignore_warnings(category=ConvergenceWarning):
? ? ? ? ? ? clf.fit(X_train, y_train)
? ? ? ? score = clf.score(X_test, y_test)
? ? ? ? print('%s: %.2f' % (name, score))
? ? ? ? # 繪制決策邊界。
? ? ? ? # 將網(wǎng)格[x_min，x_max] * [y_min，y_max]中的每個(gè)點(diǎn)分配顏色。
? ? ? ? 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]
? ? ? ? # 將結(jié)果放入顏色圖
? ? ? ? Z = Z.reshape(xx.shape)
? ? ? ? ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)
? ? ? ? # 繪制訓(xùn)練點(diǎn)
? ? ? ? ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,
? ? ? ? ? ? ? ? ? edgecolors='k')
? ? ? ? # 以及測(cè)試點(diǎn)
? ? ? ? ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
? ? ? ? ? ? ? ? ? edgecolors='k', alpha=0.6)
? ? ? ? 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.replace(' + ', '\n'))
? ? ? ? ax.text(0.95, 0.06, ('%.2f' % score).lstrip('0'), size=15,
? ? ? ? ? ? ? ? bbox=dict(boxstyle='round', alpha=0.8, facecolor='white'),
? ? ? ? ? ? ? ? transform=ax.transAxes, horizontalalignment='right')
plt.tight_layout()
# 在圖像上增加標(biāo)題
plt.subplots_adjust(top=0.90)
suptitles = [
? ? '線性分類(lèi)器',
? ? '特征離散化與線性分類(lèi)器',
? ? '非線性分類(lèi)器',
]
for i, suptitle in zip([1, 3, 5], suptitles):
? ? ax = axes[0, i]
? ? ax.text(1.05, 1.25, suptitle, transform=ax.transAxes,
? ? ? ? ? ? horizontalalignment='center', size='x-large')
plt.show()
