def draw(test, predic, girlMat, boyMat, girl_train, boy_train, i, j):
actual = transdata(test)
predictions = predic
#得到ROC曲线和曲线下AUC面积
false_positive_rate, true_positive_rate, thresholds = roc_curve(
actual, predictions)
roc_auc = auc(false_positive_rate, true_positive_rate)
#画出ROC曲线
plt.subplot(221)
plt.title('Receiver Operating Characteristic')
plt.plot(false_positive_rate,
true_positive_rate,
lw=1,
label='AUC = %0.2f' % roc_auc)
plt.legend(loc='lower right')
plt.plot([0, 1], [0, 1], '--', color=(0.6, 0.6, 0.6), label='Luck')
plt.xlim([-0.05, 1.05])
plt.ylim([-0.05, 1.05])
plt.ylabel('True Positive Rate')
plt.subplot(222)
w, m1, m2 = calFisher(i, j, girl_train, boy_train)
w0 = gender_prod * m1 + (1 - gender_prod) * m2
x = girlMat.iloc[:, i].append(boyMat.iloc[:, i])
y = girlMat.iloc[:, j].append(boyMat.iloc[:, j])
x_min, x_max = x.min() - 1.5, x.max() + 1.5
y_min, y_max = y.min() - 1.5, y.max() + 1.5
h = 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
z = np.zeros(xx.shape, dtype='int')
for k in range(xx.shape[0]):
for g in range(xx.shape[1]):
data = [xx[k, g], yy[k, g]]
y = (w * np.mat(data).T) - w0
if y > 0:
z[k, g] = 1
Colors = []
#不同性别用不同颜色区分（男：蓝，女：橘）
for t in range(test.shape[0]):
m = test.iloc[t, -2]
if m == 'm':
Colors.append('blue')
if m == 'w':
Colors.append('orange')
cmap_light = ListedColormap(['#AAAAFF', '#F0E68C'])
plt.pcolormesh(xx, yy, z, cmap=cmap_light)
x1 = test.iloc[:, i].tolist()
y1 = test.iloc[:, j].tolist()
plt.scatter(x1, y1, c=Colors)
plt.xlabel('height')
plt.ylabel('weight')
plt.title('boundary line of Fisher')
plt.subplot(223)
z2 = np.zeros(xx.shape, dtype='int')
girl_mean = np.array(bs.calMean(girl_train, i, j))
print(girl_mean)
mean_g = [girl_mean[0, 0], girl_mean[0, 1]]
boy_mean = np.array(bs.calMean(boy_train, i, j))
mean_b = [boy_mean[0, 0], boy_mean[0, 1]]
mean_bg = [mean_g, mean_b]
girl_cov = np.mat(bs.calCov(i, j, girl_train, mean_g))
boy_cov = np.mat(bs.calCov(i, j, girl_train, mean_b))
cov_bg = [girl_cov, boy_cov]
print(mean_bg)
print(cov_bg)
for k in range(xx.shape[0]):
for g in range(xx.shape[1]):
data = pd.DataFrame([xx[k, g], yy[k, g]]).iloc[:, 0]
print(data)
g_r = bs.calGauss(data, mean_bg[0], cov_bg[0])
b_r = bs.calGauss(data, mean_bg[1], cov_bg[1])
if g_r >= b_r:
z2[k, g] = 1
plt.contourf(xx, yy, z2, cmap=cmap_light)
plt.scatter(x1, y1, c=Colors)
plt.xlabel('height')
plt.ylabel('weight')
plt.title('boundary line of Bayes')
plt.subplot(224)
plt.ylim(35, 90)
# plt.contour(xx, yy, z)
x3 = np.arange(x_min + 8, x_max - 8, h)
y4 = (w0 - w[0, 0] * x3) / w[0, 1]
y5 = w[0, 1] / w[0, 0] * x3
plt.plot(x3, y4, color='green')
plt.plot(x3, y5, color='green')
plt.contour(xx, yy, z2, color='y')
plt.scatter(x1, y1, c=Colors)
plt.xlabel('height')
plt.ylabel('weight')
plt.title('boundary line of two classfiers')
plt.show()
