def crossData(data_list,
alpha=0.0,
rank_weight=False,
stop_criterion_mis_rate=None,
stop_criterion_min_node=1,
stop_criterion_gain=0.0,
prune_criteria=0):
results = {}
for data_train in data_list:
results[data_train] = {}
for data_test in data_list:
if data_test == data_train:
continue
x_train, y_tr = LogR.dataClean(data_train)
y_train = label2Rank(y_tr.tolist())
x_test, y_te = LogR.dataClean(data_test)
y_test = label2Rank(y_te.tolist())
tree = DecisionTree().buildtree(
x_train,
y_train,
weights=None,
stop_criterion_mis_rate=stop_criterion_mis_rate,
stop_criterion_min_node=stop_criterion_min_node,
stop_criterion_gain=stop_criterion_gain)
y_pred = tree.predict(x_test, alpha)
results[data_train][data_test] = LogR.perfMeasure(y_pred,
y_test,
rankopt=True)
return results
if nocross:
break
for key in results.keys():
item = np.array(results[key])
mean = np.nanmean(item, axis=0)
std = np.nanstd(item, axis=0)
results[key] = [mean, std]
return results
if __name__ == "__main__":
x,y = LogR.dataClean("data/posts_Feature_Emotion.txt")
y = label2Rank(y)
# x,y = dataSimulated(100,3,5)
# for j in range(1,6):
# stop_criterion_mis_rate = 0.22 - 0.04*j
# for m in range(10):
# ITER_MAX = 10 + m*10
result = crossValidate(x,y, nocross = False, iter_max=ITER_MAX, cost = cost)
print result
with open("result_boost.txt","a") as f:
f.write("Nsamp: %d\n" % x.shape[0])
f.write("iter_max "+str(ITER_MAX)+"\n")
f.write("stop misclassification rate %f\n" %stop_criterion_mis_rate)
f.write("cost: AdaC2.M1\n")
f.write("cost_level %s" % str(COST_LEVEL))
f.write(str(result)+"\n")