My goal is to create a DataFrame with unique name as Col A and a sumif of the original DataFrame from type, and the current iloc of the new DataFrame.

OLD_DF
| Type | nameDest | Column A | Column B |
| Payment | A | —— | ———|
| Debt | A | —— | ———|
| Payment | A | —— | ———|
| Payment | A | —— | ———|
| Payment | B | —— | ———|
| Debt | B | —— | ———|
| Debt | B | —— | ———|
| Payment | B | —— | ———|

New DF
| NameDest | Payment | Debt |
| A | 3 | 1 |
| B | 2 | 2 |

I tried to stay away from loops, but kept getting an error (error below the code)

def exercise_custom(df):
    cust_df = pd.DataFrame(df.nameDest.dropna().unique(), columns=['DestName'])
    cust_df['Payment_Count'] = len(df[(df['type']=='PAYMENT') & (df['nameDest']==cust_df.DestName)])
    display(cust_df.head(5))

return cust_df
pass     

The Traceback gives me

ValueError                                Traceback (most recent call last)
Cell In[72], line 56
     52     return "TODO"
     54     pass
---> 56 visual_custom(df)

Cell In[72], line 40, in visual_custom(df)
     38 def visual_custom(df):
---> 40     exercise_custom(df)
     43     fig, axs = plt.subplots(1, figsize=(6,10))
     44     #updated to show bottom labels correctly & chg color

Cell In[72], line 6, in exercise_custom(df)
      1 def exercise_custom(df):
      2     #X
      3     #for index, row in df:
      4         #cust_df = df['nameDest'].unique()
      5     cust_df = pd.DataFrame(df.nameDest.dropna().unique(), columns=['DestName'])
----> 6     cust_df['Payment_Count'] = len(df[(df['type']=='PAYMENT') & (df['nameDest']==cust_df.DestName)])
      7     display(cust_df.head(5))
     13         #X= pd.DataFrame(df['nameDest'].unique())
     14         #df[df_payment_count] = len(df[(df['type']=='PAYMENT') & (df['isFraud']==1)])
     15     
   (...)
     32              #              'Cash In':len(df[(df['type']=='CASH_IN') & (df['isFraud']==1)])}
     33             #    }

File ~/anaconda3/envs/forageenv/lib/python3.9/site-packages/pandas/core/ops/common.py:76, in _unpack_zerodim_and_defer.<locals>.new_method(self, other)
     72             return NotImplemented
     74 other = item_from_zerodim(other)
---> 76 return method(self, other)

File ~/anaconda3/envs/forageenv/lib/python3.9/site-packages/pandas/core/arraylike.py:40, in OpsMixin.__eq__(self, other)
     38 @unpack_zerodim_and_defer("__eq__")
     39 def __eq__(self, other):
---> 40     return self._cmp_method(other, operator.eq)

File ~/anaconda3/envs/forageenv/lib/python3.9/site-packages/pandas/core/series.py:6105, in Series._cmp_method(self, other, op)
   6102 res_name = ops.get_op_result_name(self, other)
   6104 if isinstance(other, Series) and not self._indexed_same(other):
-> 6105     raise ValueError("Can only compare identically-labeled Series objects")
   6107 lvalues = self._values
   6108 rvalues = extract_array(other, extract_numpy=True, extract_range=True)

ValueError: Can only compare identically-labeled Series objects

One way I thought about fixing this is by looping, but its so slow and this needs to be quicker. (this was my last option cause all I was able to find was ‘Loops are bad’).

def exercise_custom(df):
    payment_counts=[]
    cust_df = pd.DataFrame(df.nameDest.dropna().unique(), columns=['DestName'])
    for name in cust_df['DestName']:
        filtered_df = df[(df['type'] == 'PAYMENT') & (df['nameDest'] == name)].dropna().reset_index(drop=True)
        if len(filtered_df) == 0:
            payment_count =0
        else:
            payment_count=len(filtered_df)
        payment_count=len(filtered_df)
        payment_counts.append(payment_count)
    cust_df['Payment_Count'] = payment_counts
    display(cust_df.head(5))
    
    
    pass