【程序媛晒83行代码】云栖社区聚能聊专家，背后83行代码的故事

在中国程序媛中，他们的代码有什么样的魅力，Aone联合云栖社区、饿了么、钉钉、阿里云、天猫、口碑发起首届程序媛比码活动——不秀大长腿，秀高智商；不秀美图照，秀代码图，参与晒码互动游戏赢“83行代码”T恤！

我们来说说这群女工程师的第83行代码及代码背后的故事：

平时习惯于用Jupyter Notebook写代码，以至于很多代码像是这样：

# 分块计算缺失程度(23块）
block_list = [1,5,6,20,24,28,32,36,48,52,54,64,72,76,102,107,111,155,161,166,211,254,278,298]

for i in tqdm(range(len(block_list)-1)):
    tmp_df = train_test.iloc[:,block_list[i]-1:block_list[i+1]-1]
    print(tmp_df.columns)
    tmp_df_T = tmp_df.T
    tmp_df['count'] = tmp_df_T.count()
    train_test['count_f' + str(block_list[i]) + '_f' +str(block_list[i+1])] = tmp_df['count']
    train_test['count_label_f' + str(block_list[i]) + '_f' +str(block_list[i+1]-1)]=np.where(train_test['count_f' + str(block_list[i]) + '_f' +str(block_list[i+1])] > 0,0,1)

# 计算占比(基于date）
for i in tqdm(r_list):
    df_dratio = pd.DataFrame()
    for j in date_list:
        df_tmp = train_test[train_test['date'] == j]
        f_ratio = pd.DataFrame(df_tmp[i].value_counts())
        f_ratio['date'] = j
        f_ratio[i + '_rcount'] = f_ratio[i]
        f_ratio[i + '_ratio'] = f_ratio[i]/len(df_tmp)
        f_ratio[i] = f_ratio.index
        f_ratio = f_ratio.reset_index(drop = True)
        df_dratio = pd.concat([df_dratio, f_ratio], axis = 0)
        df_dratio = df_dratio.reset_index(drop = True)
    train_test = train_test.merge(df_dratio,on = ['date',i],how = 'left')

import copy
def cal_all_altcol_1(col_, labelcol = None, error_corr = False):  
    
#     if labelcol is not None:
#         print("pcsing by groups")
        
    col = copy.deepcopy(col_)
    colname = col.columns[0]

    if(error_corr == True):
        if labelcol is not None:
            mean = pd.DataFrame(calmean(col, labelcol))
            alt_col = [col, 1 / col, col-mean, np.fabs(col-mean)]
            alt_col_name = [colname + "_X", colname + "_1/X", colname + "_Xerr", colname + "_Xerr_abs"]
        else:
            mean = calmean(col, labelcol)
            alt_col = [col, 1 / col, np.fabs(col-mean)]
            alt_col_name = [colname + "_X", colname + "_1/X", colname + "_Xerr_abs"]
    elif(error_corr == False):
        alt_col = [col , 1 / col]
        alt_col_name = [colname + "_X", colname + "_1/X"]
    
    alt_list = pd.concat(alt_col, axis = 1)
    alt_list.columns = alt_col_name
    return alt_list

def cal_all_altcol_1_base(col_, labelcol = None, error_corr = False):  
    # 只取正负列
    
#     if labelcol is not None:
#         print("pcsing by groups")
        
    col = copy.deepcopy(col_)
    colname = col.columns[0]
    
    if(error_corr == True):
        if labelcol is not None:
            mean = pd.DataFrame(calmean(col, labelcol))
            alt_col = [col, np.fabs(col-mean), col-mean, ]
            alt_col_name = [colname + "_X", colname + "_Xerr_abs", colname + "_Xerr"]
        else:
            mean = pd.DataFrame(calmean(col, labelcol))
            print(mean)
            alt_col = [col, np.fabs(col-mean)]
            alt_col_name = [colname + "_X", colname + "_Xerr_abs"]
    elif(error_corr == False):
        alt_col = [col]
        alt_col_name = [colname + "_X"]
    
    alt_list = pd.concat(alt_col, axis = 1)
#     print (alt_list)
    alt_list.columns = alt_col_name
    return alt_list


def cal_all_altcol_2(col_i, col_j, labelcol = None, error_corr = False):
    
#     if labelcol is not None:
#         print("pcsing by groups")
    coli = copy.deepcopy(col_i)
    colj = copy.deepcopy(col_j)
    coliname = coli.columns[0]
    coljname = colj.columns[0]
    colbet = coliname + "_" + coljname
    coli.columns, colj.columns = [colbet], [colbet] # 需要把列名统一不然不能直接减
    
    Plus = coli + colj
    Minus = coli - colj
    Multiply = coli * colj
    Divide_1 = coli / colj
    Divide_2 = colj / coli
    everynum_perpart = 5
    
    if(error_corr == True):
        P_mean = pd.DataFrame(calmean(Plus, labelcol))
        Mi_mean = pd.DataFrame(calmean(Minus, labelcol))
        Mu_mean = pd.DataFrame(calmean(Multiply, labelcol))
        D1_mean = pd.DataFrame(calmean(Divide_1, labelcol))
        D2_mean = pd.DataFrame(calmean(Divide_2, labelcol))
        if labelcol is not None:
            alt_col =  [Plus, Minus, Multiply, Divide_1, Divide_2,
                        np.fabs(Plus - P_mean), np.fabs(Minus - Mi_mean), np.fabs(Multiply - Mu_mean),
                        np.fabs(Divide_1 - D1_mean), np.fabs(Divide_2 - D2_mean),
                        Plus - P_mean, Minus - Mi_mean, Multiply - Mu_mean,Divide_1 - D1_mean, Divide_2 - D2_mean]
            alt_col_name = [colbet + "_X+Y", colbet + "_X-Y", colbet + "_X*Y", colbet + "_X/Y", colbet + "_Y/X",
                            colbet + "_X+Yerr_abs", colbet + "_X-Yerr_abs", colbet + "_X*Yerr_abs",
                            colbet + "_X/Yerr_abs", colbet + "_Y/Xerr_abs",
                            colbet + "_X+Yerr", colbet + "_X-Yerr", colbet + "_X*Yerr",
                            colbet + "_X/Yerr", colbet + "_Y/Xerr",]
        elif labelcol is None:
            alt_col = [Plus, Minus, Multiply, Divide_1, Divide_2, 
                       np.fabs(Plus - P_mean), np.fabs(Minus - Mi_mean), np.fabs(Multiply - Mu_mean),
                       np.fabs(Divide_1 - D1_mean), np.fabs(Divide_2 - D2_mean)]
            alt_col_name = [colbet + "_X+Y", colbet + "_X-Y", colbet + "_X*Y", colbet + "_X/Y", colbet + "_Y/X",
                            colbet + "_X+Yerr_abs", colbet + "_X-Yerr_abs", colbet + "_X*Yerr_abs",
                            colbet + "_X/Yerr_abs", colbet + "_Y/Xerr_abs"]
    elif(error_corr == False):
        alt_col = [Plus, Minus, Multiply, Divide_1, Divide_2]
        alt_col_name = [colbet + "_X+Y", colbet + "_X-Y", colbet + "_X*Y", colbet + "_X/Y", colbet + "_Y/X"]
    
    alt_list = pd.concat(alt_col, axis = 1)
    alt_list.columns = alt_col_name
#     print(alt_list)
    return alt_list
# def cal_all_alt2tol(coli, colj, )
# cal_all_altcol_2(test, test2)

与海洋的云小姐姐互动，为她打call——>点击进去晒码