def trainFinalClassifier(db, random_state=0):
clf = ExtraTreesClassifier(n_estimators=100, random_state=random_state, verbose=100, n_jobs=-1)
print("Loading training set...")
loaded = joblib.load(db + ".dump")
print("Fitting...")
clf.fit(loaded[:, 0:-1], loaded[:, -1])
loaded = 0
print("Saving...")
path = "clfs{}/".format(random_state)
if (os.path.exists(path) == False):
os.mkdir(path)
clf.verbose = 0
joblib.dump(clf, path + db)
def roc_precision(db, usecols=None, test="unnamed", random_state=0, show_plots=False):
if (os.path.exists(MAT_PATH) == False):
os.mkdir(MAT_PATH)
random_state = check_random_state(random_state)
clf = 0
if (not os.path.exists("clfs/" + db)):
clf = ExtraTreesClassifier(n_estimators=100, random_state=0, n_jobs=-1)
print("Loading training set...")
loaded = loadClassifiedDB(db + ".train.csv", random_state=random_state, usecols=usecols)#, skipheader=234100)
print("Fitting...")
clf.fit(loaded[:, 0:-1], loaded[:, -1])
loaded = 0
print("Saving...")
if (os.path.exists("clfs/") == False):
os.mkdir("clfs")
clf.verbose = 0
joblib.dump(clf, "clfs/" + db)
else:
print("Loading {}...".format(db))
clf = joblib.load("clfs/" + db)
classes = clf.classes_
print("Loading test set...")
loaded = loadClassifiedDB(db + ".csv", random_state=random_state, usecols=usecols)#, skipheader=232800)
y_true = loaded[:, -1]
print("Predict proba...")
y_score = clf.predict_proba(loaded[:, 0:-1])
loaded = 0
clf = 0
y_score = y_score[:, classes == 1]
print("ROC...")
fpr, tpr, thresholds = roc_curve(y_true, y_score)
sio.savemat(MAT_PATH + test + '.roc.' + db + '.mat', {'fpr':fpr, 'tpr':tpr, 'thresholds':thresholds})
if (show_plots):
plt.plot(fpr, tpr)
plt.title("ROC curve")
plt.xlabel("False Positive Rate")
plt.ylabel("True Positive Rate")
for i in range(0, thresholds.size):
plt.annotate(str(thresholds[i]), xy=(fpr[i], tpr[i]), xytext=(10,10), textcoords='offset points', arrowprops=dict(facecolor='black', shrink=0.025))
plt.show()
print("Precision/Recall...")
precision, recall, thresholds = precision_recall_curve(y_true, y_score)
sio.savemat(MAT_PATH + test + '.precall.' + db + '.mat', {'precision':precision, 'recall':recall, 'thresholds':thresholds})
if (show_plots):
plt.plot(recall, precision)
plt.title("Precision/Recall")
plt.xlabel("Recall (TP / (TP+FN))")
plt.ylabel("Precision (TP / (TP + FP))")
for i in range(0, thresholds.size):
plt.annotate(str(thresholds[i]), xy=(recall[i], precision[i]), xytext=(10,10), textcoords='offset points', arrowprops=dict(facecolor='black', shrink=0.025))
plt.show()
