How to fix value error broadcasting in python loop?-CodePudding

I am having trouble fixing my broadcasting error, the current error i am getting is ValueError: operands could not be broadcast together with shapes (10,) (5,)

preprocessing data:

data1 = pd.DataFrame({"cust_id": ['x111'], #customer data
                      "state": ['B'],
                      "amount": [1000],
                      "year":[3],
                      "group":[10],
                      "loan_rate":[0.12]})

data1['state'] = pd.Categorical(data1['state'], 
                                        categories=state_list, 
                                        ordered=True).codes

state_list = ['A','B','C','D','E'] #possible states


lookup1 = pd.DataFrame({'year': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
                       'lim %': [0.1, 0.1, 0.1, 0.1, 0.1,0.1, 0.1, 0.1, 0.1, 0.1]}).set_index(['year'])

matrix_data = np.arange(250).reshape(10,5,5) #3d matrix by state(A-E) and year(1-10)

results={}
for cust_id, state, amount, start, group, loan_rate in data1.itertuples(name=None, index=False):
    res = [amount * matrix_data[start-1, state, :]]
    for year in range(start 1, len(matrix_data) 1,):
        temp = np.array([lookup1.loc[year].iat[0]]*len(matrix_data))
        temp[3] = temp[4] = 1
        res.append(temp * np.array(res[-1])) #trying to edit this line
        res.append(res[-1] * loan_rate)
        res.append(res[-1]  60)
        res.append([res[-1] @ matrix_data[year-1]])
        results[cust_id] = res

expected output:

{'x111': [array([55000, 56000, 57000, 58000, 59000]),
  array([ 5500.,  5600.,  5700., 58000., 59000.]),...

related to this question How to use append with np.where in nested loop?

CodePudding user response：

See if below code snippet works for you, and make changes as per your convenience:

import pandas as pd
import numpy as np

state_list = ['A','B','C','D','E'] #possible states

data1 = pd.DataFrame({"cust_id": ['x111'], #customer data
                    "state": ['B'],
                    "amount": [1000],
                    "year":[3],
                    "group":[10],
                    "loan_rate":[0.12]})

data1['state'] = pd.Categorical(data1['state'], 
                                        categories=state_list, 
                                        ordered=True).codes




lookup1 = pd.DataFrame({'year': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
                    'lim %': [0.1, 0.1, 0.1, 0.1, 0.1,0.1, 0.1, 0.1, 0.1, 0.1]}).set_index(['year'])

matrix_data = np.arange(250).reshape(10,5,5) #3d matrix by state(A-E) and year(1-10)

results={}
for cust_id, state, amount, start, group, loan_rate in data1.itertuples(name=None, index=False):
    print(cust_id, state, amount, start, group, loan_rate)
    res = [amount * matrix_data[start-1, state, :]]
    for year in range(start 1, len(matrix_data) 1,):
        temp = np.array([lookup1.loc[year].iat[0]]*len(matrix_data))
        temp[3] = temp[4] = 1
        res.append(temp[:5] * np.array(res[-1])) #trying to edit this line
        res.append(res[-1] * loan_rate)
        res.append(res[-1]  60)
        res.append([res[-1] @ matrix_data[year-1]])
        results[cust_id] = res

print(results)