LogisticRegression.py 文件源码

def readData(self):
        vector = []
        labels = []
        indice = 0
        for elem in gson:
            actors = gson.get(elem).get("actors")
            directors = gson.get(elem).get("director")
            writers = gson.get(elem).get("writer")
            imdbRating = int(float(gson.get(elem).get("imdbRating")))
            mediaAct, mediaDir, mediaWri = self.calcolaMedie(actors, directors, writers)
            vect = [1,mediaAct, mediaDir, mediaWri]
            vector.append(vect)
            labels.append(int(imdbRating))  ## CAST PER CLASSI DISCRETE ##
        data = np.array(vector)
        labels = np.array(labels)
        train_data,test_data,train_labels,test_labels = train_test_split(data,labels, train_size= 0.1)
        return train_data, train_labels,test_data,test_labels