trainNN.py 文件源码

def load_csv(self):
    file_name = "data/jra_race_resultNN.csv"
    df = pd.read_csv(file_name)
    ## ???????
    labelEncoder = preprocessing.LabelEncoder()
    df['area_name'] = labelEncoder.fit_transform(df['area_name'])
    df['race_name'] = labelEncoder.fit_transform(df['race_name'])
    df['track'] = labelEncoder.fit_transform(df['track'])
    df['run_direction'] = labelEncoder.fit_transform(df['run_direction'])
    df['track_condition'] = labelEncoder.fit_transform(df['track_condition'])
    df['horse_name'] = labelEncoder.fit_transform(df['horse_name'])
    df['horse_sex'] = labelEncoder.fit_transform(df['horse_sex'])
    df['jockey_name'] = labelEncoder.fit_transform(df['jockey_name'])
    df['margin'] = labelEncoder.fit_transform(df['margin'])
    df['is_blinkers'] = labelEncoder.fit_transform(df['is_blinkers'])
    df['trainer_name'] = labelEncoder.fit_transform(df['trainer_name'])
    df['comments_by_trainer'] = labelEncoder.fit_transform(df['comments_by_trainer'])
    df['evaluation_by_trainer'] = labelEncoder.fit_transform(df['evaluation_by_trainer'])
    df['dhorse_weight'] = labelEncoder.fit_transform(df['dhorse_weight'])
    x_np = np.array(df[['area_name', 'race_number', 'race_name', 'track', 'run_direction',
                       'distance', 'track_condition', 'purse', 'heads_count', 
                       'post_position', 'horse_number', 'horse_name', 'horse_sex', 'horse_age', 
                       'jockey_name', 'time', 'margin', 'time3F', 
                       'load_weight', 'horse_weight', 'dhorse_weight', 'odds_order', 
                       'odds', 'is_blinkers', 'trainer_name', 'comments_by_trainer', 
                        'evaluation_by_trainer'
    ]].fillna(0))
    # ??
    d = df[['finish_order']].to_dict('record')
    self.vectorizer = DictVectorizer(sparse=False)
    y_np = self.vectorizer.fit_transform(d)
    self.n_classes = len(self.vectorizer.get_feature_names())
    self.train_size =   int(len(df[['finish_order']]) / 5)
    self.batch_size = self.train_size

    # ????????????????????
    [self.x_train, self.x_test] = np.vsplit(x_np, [self.train_size]) 
    [self.y_train, self.y_test] = np.vsplit(y_np, [self.train_size])

  # Create model