python - Pandas 根据列的值创建新列

Question

希望你能帮助我 我有一个像这样的数据框:

df = pd.DataFrame   (   {   'voucher_id': ['ugp_0008', 'ugp_0008', 'ugp_0008', 'ugp_0001', 'ugp_0009', 'ugp_0002', 'ugp_0003', 'ugp_0004', 'ugp_0005', 'ugp_0006', 'ugp_0007', 'ugp_0007'],
                        'status': ['REDEEMED', 'REDEEMED', 'REDEEMED', 'REDEEMED', 'AVAILABLE', 'AVAILABLE', 'REDEEMED', 'EXPIRED', 'EXPIRED', 'REDEEMED', 'REDEEMED', 'REDEEMED'],
                        'redeem_type': ['OTHERS', 'VOUCHER', 'VOUCHER', 'BILLER', 'exp_or_avail', 'exp_or_avail', 'VOUCHER', 'exp_or_avail', 'exp_or_avail', 'VOUCHER', 'OTHERS', 'DIRECT-MERCHANT'],
                        'nominal': [200000, 200000, 200000, 100000, 100000, 100000, 500000, 100000, 100000, 100000, 100000, 100000],
                        'value_used': [10000, 30000, 150000, 20000, 0, 0, 500000, 0, 0, 20000, 20000, 80000],
                    }
                )

预期结果是:

df_expect = pd.DataFrame   (   {   'voucher_id': ['ugp_0008', 'ugp_0001', 'ugp_0009', 'ugp_0002', 'ugp_0003', 'ugp_0004', 'ugp_0005', 'ugp_0006', 'ugp_0007'],
                        'status': ['REDEEMED', 'REDEEMED', 'AVAILABLE', 'AVAILABLE', 'REDEEMED', 'EXPIRED', 'EXPIRED', 'REDEEMED', 'REDEEMED'],
                        'nominal': [200000, 100000, 100000, 100000, 500000, 100000, 100000, 100000, 100000],
                        'VOUCHER' : [180000, 0,0,0, 5000000,0,0,20000,0],
                        'BILLER' : [0,20000,0,0,0,0,0,0,0],
                        'OTHERS' : [10000,0,0,0,0,0,0,0,20000],
                        'DIRECT-MERCHANT' : [0,0,0,0,0,0,0,0,80000]
                        ,'remaining_nominal' : [10000, 80000, 100000, 100000, 0, 100000, 100000, 80000, 0]
                        }
                )

我希望voucher_id分组，并且redeem_type值根据条件成为新列

我尝试使用 np.where

df2 = df.copy()
df2['BILLER'] = np.where(df['redeem_type'] == 
'BILLER', df['value_used'], 0)

df2['VOUCHER'] = np.where(df['redeem_type'] 
== 'VOUCHER', df['value_used'], 0)

df2['OTHERS'] = np.where(df['redeem_type'] == 
'OTHERS', df['value_used'], 0)

df2['DIRECT-MERCHANT'] = 
np.where(df['redeem_type'] == 'DIRECT- 
MERCHANT', df['value_used'], 0)

df2['exp_or_avail'] = 
np.where(df['redeem_type'] == 'exp_or_avail', 
df['value_used'], 0)

我就这样了

然后我使用枢轴:

ss=df.groupby(['voucher_id','redeem_type']).sum().reset_index()
ss.pivot(index='voucher_id',columns='redeem_type',values='value_used').fillna(0)

我得到了相同的结果(voucher_id 未分组)

希望大家能帮帮我，谢谢!祝大家度过愉快的一天

Answer 1

聚合数据帧以计算每张优惠券和状态的名义值(value)之和

keys = ['voucher_id', 'status']
nominal = df.groupby(keys)['nominal'].sum()

# voucher_id  status   
# ugp_0001    REDEEMED     100000
# ugp_0002    AVAILABLE    100000
# ugp_0003    REDEEMED     500000
# ugp_0004    EXPIRED      100000
# ugp_0005    EXPIRED      100000
# ugp_0006    REDEEMED     100000
# ugp_0007    REDEEMED     200000
# ugp_0008    REDEEMED     600000
# ugp_0009    AVAILABLE    100000
# Name: nominal, dtype: int64

透视数据框以计算每张优惠券的 value_used、状态和赎回类型的总和

df1 = df.pivot_table(index=keys, columns='redeem_type', values='value_used', aggfunc='sum', fill_value=0)

# redeem_type           BILLER  DIRECT-MERCHANT  OTHERS  VOUCHER  exp_or_avail
# voucher_id status                                                           
# ugp_0001   REDEEMED    20000                0       0        0             0
# ugp_0002   AVAILABLE       0                0       0        0             0
# ugp_0003   REDEEMED        0                0       0   500000             0
# ugp_0004   EXPIRED         0                0       0        0             0
# ugp_0005   EXPIRED         0                0       0        0             0
# ugp_0006   REDEEMED        0                0       0    20000             0
# ugp_0007   REDEEMED        0            80000   20000        0             0
# ugp_0008   REDEEMED        0                0   10000   180000             0
# ugp_0009   AVAILABLE       0                0       0        0             0

从名义值中减去每行的所有 value_used 的总和，以计算剩余

df1 = df1.assign(nominal=nominal, remaining=nominal - df1.sum(axis=1))

# redeem_type           BILLER  DIRECT-MERCHANT  OTHERS  VOUCHER  exp_or_avail  nominal  remaining
# voucher_id status                                                                               
# ugp_0001   REDEEMED    20000                0       0        0             0   100000      80000
# ugp_0002   AVAILABLE       0                0       0        0             0   100000     100000
# ugp_0003   REDEEMED        0                0       0   500000             0   500000          0
# ugp_0004   EXPIRED         0                0       0        0             0   100000     100000
# ugp_0005   EXPIRED         0                0       0        0             0   100000     100000
# ugp_0006   REDEEMED        0                0       0    20000             0   100000      80000
# ugp_0007   REDEEMED        0            80000   20000        0             0   200000     100000
# ugp_0008   REDEEMED        0                0   10000   180000             0   600000     410000
# ugp_0009   AVAILABLE       0                0       0        0             0   100000     100000