def load_german():
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
g = pd.read_csv("./datasets/german/german.data.txt", header=-1, sep='\s+')
g = g.as_matrix()
g = np.array(g, dtype='str')
g = LabelEncoder().fit_transform(g.ravel()).reshape(*g.shape)
list_of_cat = [0, 2, 3, 5, 6, 8, 9, 11, 13, 14, 16, 18]
for i in range(len(g[1, :])):
if len(set(g[:, i])) > 2:
list_of_cat.append(i)
val19_0 = np.min(g[:, 19]) # Foreign\not foreign feature
val19_1 = np.max(g[:, 19])
for idx, ex in enumerate(g):
g[idx, 19] = -1.0 if g[idx, 19] == val19_0 else 1.0
list_of_cat = sorted(list(set(list_of_cat)))
enc = OneHotEncoder(n_values='auto',
categorical_features=list_of_cat,
sparse=False,
handle_unknown='error')
enc.fit(g)
g = enc.transform(g)
ytrue_value = g[0, -1]
y = -np.array([1.0 if yy == ytrue_value else -1.0 for yy in g[:, -1]])
x = g[:, :-1]
dataset = namedtuple('_', 'data, target')(x, y)
return dataset
def getAnova(self, X, y):
# y = y[:200]
# X = X[:200]
X = LabelEncoder().fit_transform(X.ravel()).reshape(*X.shape)
# transform to binary
# X = OneHotEncoder().fit_transform(X_int).toarray()
n_samples = len(y)
X = X.reshape((n_samples, -1))
# add 200 non-informative features
X = np.hstack((X, 2 * np.random.random((n_samples, 200))))
transform = feature_selection.SelectPercentile(
feature_selection.f_classif)
clf = Pipeline([('anova', transform), ('svc', svm.SVC(C=1.0))])
# #############################################################################
# Plot the cross-validation score as a function of percentile of features
score_means = list()
score_stds = list()
percentiles = (5, 10, 20, 40, 60, 80, 100)
for percentile in percentiles:
clf.set_params(anova__percentile=percentile)
# Compute cross-validation score using 1 CPU
this_scores = cross_val_score(clf,
X,
y,
n_jobs=1,
verbose=10,
cv=3)
score_means.append(this_scores.mean())
score_stds.append(this_scores.std())
plt.errorbar(percentiles, score_means, np.array(score_stds))
plt.title(
'Performance of the SVM-Anova varying the percentile of features selected'
)
plt.xlabel('Percentile')
plt.ylabel('Prediction rate')
plt.axis('tight')
plt.show()
x1_max, x2_max = x.max()
t1 = np.linspace(x1_min, x1_max, N)
t2 = np.linspace(x2_min, x2_max, M)
x1, x2 = np.meshgrid(t1, t2) # 生成网格采样点
x_show = np.stack((x1.flat, x2.flat), axis=1) # 测试点
print x_show.shape
cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF'])
cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
y_show_hat = model.predict(x_show) # 预测值
y_show_hat = y_show_hat.reshape(x1.shape) # 使之与输入的形状相同
plt.figure(facecolor='w')
plt.pcolormesh(x1, x2, y_show_hat, cmap=cm_light) # 预测值的显示
plt.contour(x1, x2, y_show_hat, levels=(0,1), colors='r', linestyles='-.')
plt.scatter(x_test[0], x_test[1], c=y_test.ravel(), edgecolors='k', s=150, zorder=10, cmap=cm_dark, marker='*') # 测试数据
plt.scatter(x[0], x[1], c=y.ravel(), edgecolors='k', s=40, cmap=cm_dark) # 全部数据
plt.xlabel(iris_feature[0], fontsize=15)
plt.ylabel(iris_feature[1], fontsize=15)
plt.xlim(x1_min, x1_max)
plt.ylim(x2_min, x2_max)
plt.grid(True)
plt.title(u'鸢尾花数据的决策树分类', fontsize=17)
plt.show()
# 训练集上的预测结果
y_test = y_test.reshape(-1)
print y_test_hat
print y_test
result = (y_test_hat == y_test) # True则预测正确，False则预测错误
acc = np.mean(result)
print u'准确度: %.2f%%' % (100 * acc)
y_show_hat = model.predict(x_show) # 预测值
print(y_show_hat.shape)
print(y_show_hat)
y_show_hat = y_show_hat.reshape(x1.shape) # 使之与输入的形状相同
print(y_show_hat)
plt.figure(facecolor='w')
plt.pcolormesh(x1, x2, y_show_hat, cmap=cm_light) # 预测值的显示
plt.scatter(x_test[0],
x_test[1],
c=y_test.ravel(),
edgecolors='k',
s=100,
zorder=10,
cmap=cm_dark,
marker='*') # 测试数据
plt.scatter(x[0], x[1], c=y.ravel(), edgecolors='k', s=20,
cmap=cm_dark) # 全部数据
plt.xlabel(iris_feature[0], fontsize=13)
plt.ylabel(iris_feature[1], fontsize=13)
plt.xlim(x1_min, x1_max)
plt.ylim(x2_min, x2_max)
plt.grid(b=True, ls=':', color='#606060')
plt.title('鸢尾花数据的决策树分类', fontsize=15)
plt.show()
# 训练集上的预测结果
y_test = y_test.reshape(-1)
print(y_test_hat)
print(y_test)
result = (y_test_hat == y_test) # True则预测正确，False则预测错误
acc = np.mean(result)
score_best = score
print('p: {}, {}, {}'.format(p_lower, p, p_upper))
print('score: {}'.format(score_best))
print()
return AffinityPropagation(preference=p_best).fit(y)
if __name__ == '__main__':
y_train = np.load('y_train.npy')
c_train = np.load('c_train.npy').ravel()
y_test = np.load('y_test.npy')
c_test = np.load('c_test.npy').ravel()
c_train = LabelEncoder().fit_transform(c_train)
c_test = LabelEncoder().fit_transform(c_test)
K = 40
# K = len(np.unique(c_train))
y = y_train[c_train.ravel() < K]
c = c_train[c_train < K]
# y = y_test[c_test.ravel() < K]
# c = c_test[c_test < K]
ap = ap_cluster_k(y, K, preference_init=-1.0, c=c, iter_finetune=30)
c_pred = ap.predict(y)
print(normalized_mutual_info_score(c, c_pred))
plt.plot(np.vstack((c_pred, c)).T)
plt.show()
# print f1_score(c, c_pred)
t2 = np.linspace(x2_min, x2_max, M)
x1, x2 = np.meshgrid(t1, t2) # 生成网格采样点
x_show = np.stack((x1.flat, x2.flat), axis=1) # 测试点
print x_show.shape
cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF'])
cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b'])
y_show_hat = model.predict(x_show) # 预测值
print y_show_hat.shape
print y_show_hat
y_show_hat = y_show_hat.reshape(x1.shape) # 使之与输入的形状相同
print y_show_hat
plt.figure(facecolor='w')
plt.pcolormesh(x1, x2, y_show_hat, cmap=cm_light) # 预测值的显示
plt.scatter(x_test[0], x_test[1], c=y_test.ravel(), edgecolors='k', s=150, zorder=10, cmap=cm_dark, marker='*') # 测试数据
plt.scatter(x[0], x[1], c=y.ravel(), edgecolors='k', s=40, cmap=cm_dark) # 全部数据
plt.xlabel(iris_feature[0], fontsize=15)
plt.ylabel(iris_feature[1], fontsize=15)
plt.xlim(x1_min, x1_max)
plt.ylim(x2_min, x2_max)
plt.grid(True)
plt.title(u'鸢尾花数据的决策树分类', fontsize=17)
plt.show()
# 训练集上的预测结果
y_test = y_test.reshape(-1)
print y_test_hat
print y_test
result = (y_test_hat == y_test) # True则预测正确，False则预测错误
acc = np.mean(result)
print u'准确度: %.2f%%' % (100 * acc)
