def leave_target_out():
global data
classifier = LogisticRegression()
mean_tpr = 0.0
mean_fpr = np.linspace(0, 1, 100)
all_tpr = []
targets = list(data.keys())
#added to try and fix legend
fig = plt.figure()
ax = plt.subplot(111)
for i in range (len(targets)):
test_x, test_y, train_x, train_y = pd.leave_one_target_out(data, i)
probs = classifier.fit(train_x, train_y).predict_proba(test_x)
fpr, tpr, thresholds = roc_curve(test_y, probs[:, 1])
mean_tpr += interp(mean_fpr, fpr, tpr)
mean_tpr[0] = 0.0
roc_auc = auc(fpr, tpr)
ax.plot(fpr, tpr, lw=1, label='%s (area = %0.2f)' % (targets[i], roc_auc))
ax.plot([0, 1], [0, 1], '--', color=(0.6, 0.6, 0.6), label='Luck')
mean_tpr /= len(targets)
mean_tpr[-1] = 1.0
mean_auc = auc(mean_fpr, mean_tpr)
ax.plot(mean_fpr, mean_tpr, 'k--',
label='Mean ROC (area = %0.2f)' % mean_auc, lw=2)
plt.xlim([-0.05, 1.05])
plt.ylim([-0.05, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Leave one (target) out (SCOREDATA.vina.balanced)')
box = ax.get_position()
ax.set_position([box.x0, box.y0, box.width * 0.8, box.height])
ax.legend(loc='center left', bbox_to_anchor=(1, 0.5), ncol=4)
#plt.legend(loc="lower right")
plt.show()
def leave_target_out_dist():
global data
classifier = LogisticRegression()
rocs = []
targets = list(data.keys())
for i in range (len(targets)):
# for i in range (3):
test_x, test_y, train_x, train_y = pd.leave_one_target_out(data, i)
probs = classifier.fit(train_x, train_y).predict_proba(test_x)
fpr, tpr, thresholds = roc_curve(test_y, probs[:, 1])
# rocs.append((targets[i], auc(fpr, tpr)))
rocs.append(auc(fpr, tpr))
# sorted_rocs = sorted(rocs, key=lambda x: x[1])
# for tuple in sorted_rocs:
# print tuple
plt.hist(rocs)
plt.title("Target AUC distribution")
plt.xlabel("AUC")
plt.ylabel("Frequency")
plt.show()
def plot(i):
test_x, test_y, train_x, train_y = pd.leave_one_target_out(data, i)
predictions = clf.fit(train_x, train_y).predict(test_x)
fpr, tpr, thresholds = roc_curve(test_y, predictions)
return {'name': targets[i], 'fpr': fpr, 'tpr': tpr, 'auc': auc(fpr, tpr)}
