Our study aims at discover and create a new method of how inductively to reason effective attack patterns by using much amounts of log data in RoboCup soccer simulation 2D. The inductive reasoning of those patterns makes it feasible to implement a RoboCup soccer team easier, and also to predict results of soccer games more precisely than before. This paper presents an experiment to reason effective attack patterns from a collection of simple actions of ball-holder soccer players. As a result, some of effective attack patterns can be handled successfully, but sequences of actions which are of importance in soccer game analysis cannot properly. This suggests sampling method should be improved when reasoning inductively.