result_file(string):存储最终预测结果的文件名
'''
m = len(prediction)
n = len(data_test[0])
f_result = open(result_file, "w")
for i in xrange(m):
tmp = []
for j in xrange(n - 1):
tmp.append(str(data_test[i][j]))
tmp.append(str(prediction[i]))
f_result.writelines("\t".join(tmp) + "\n")
f_result.close()
if __name__ == "__main__":
# 1、导入测试数据集
print "--------- 1、load test data --------"
data_test = load_data("test_data.txt")
# 2、导入随机森林模型
print "--------- 2、load random forest model ----------"
trees_result, trees_feature = load_model("result_file", "feature_file")
# 3、预测
print "--------- 3、get prediction -----------"
prediction = get_predict(trees_result, trees_feature, data_test)
# 4、保存最终的预测结果
print "--------- 4、save result -----------"
save_result(data_test, prediction, "final_result")
def main():
data_test = load_data('test_data.txt')
trees_result, trees_feature = load_model('result_file', 'feature_file')
prediction = get_predict(trees_result, trees_feature, data_test)
print(prediction)
save_result(data_test, prediction, "final_result")
result_file(string):存储最终预测结果的文件名
'''
m = len(prediction)
n = len(data_test[0])
f_result = open(result_file, "w")
for i in xrange(m):
tmp = []
for j in xrange(n -1):
tmp.append(str(data_test[i][j]))
tmp.append(str(prediction[i]))
f_result.writelines("\t".join(tmp) + "\n")
f_result.close()
if __name__ == "__main__":
# 1、导入测试数据集
print "--------- 1、load test data --------"
data_test = load_data("test_data.txt")
# 2、导入随机森林模型
print "--------- 2、load random forest model ----------"
trees_result, trees_feature = load_model("result_file", "feature_file")
# 3、预测
print "--------- 3、get prediction -----------"
prediction = get_predict(trees_result, trees_feature, data_test)
# 4、保存最终的预测结果
print "--------- 4、save result -----------"
save_result(data_test, prediction, "final_result")