spark处理大数据实例

    def get_debt_rank(self):
        '''
        统计各年龄段债务情况（严重/不严重）
        :return:
        '''
        all_list=[]
        bin = [0, 30, 45, 60, 75, 100]
        df_age_debt = df.select(df['age'], df['DebtRatio'])
        age_debt_y = []
        for i in range(5):
            y0 = df_age_debt.filter(df['age'].between(bin[i], bin[i + 1])). \
                filter(df['DebtRatio'] < 1).count()
            print(y0)
            y1 = df_age_debt.filter(df['age'].between(bin[i], bin[i + 1])). \
                filter(df['DebtRatio'] >= 1).count()
            print(y1)
            age_debt_y.append([y0, y1])
        all_list.append(age_debt_y)
        # 数据可视化data_web.py
        return all_list

统计各年龄情况

    def XiangGuanXing(self):
        feature=['y','age','30-59days','DebtRatio&#