Python瀑布式容量分配程序报错：TypeError: numpy.int64无len()方法

问题描述 #

尝试实现基于优先级（路由类型>包裹类型>仓库类型）的Python瀑布式容量分配程序，按优先级从高到低利用路由容量满足配送站点需求，但运行时触发类型错误。

错误信息 #

TypeError: object of type 'numpy.int64' has no len()

完整错误栈 #

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-63-58c3eb663ba2> in <module>
     56 })
     57 
---> 58 result = allocation(demand_df, route_capacity_df, mechincal_capacity_df)
     59 print(result)

<ipython-input-63-58c3eb663ba2> in allocation(demand_df, route_capacity_df, mechincal_capacity_df)
     32             demand_df.at[demand_index, 'demand'] = overflow
     33 
---> 34     return pd.DataFrame(allocation, columns=['route_type', 'parcel_type', 'warehouse_type'])
     35 
     36 # Example usage:

~\anaconda3\lib\site-packages\pandas\core\frame.py in __init__(self, data, index, columns, dtype, copy)
    472                     if is_named_tuple(data[0]) and columns is None:
    473                         columns = data[0]._fields
---> 474                     arrays, columns = to_arrays(data, columns, dtype=dtype)
    475                     columns = ensure_index(columns)
    476 

~\anaconda3\lib\site-packages\pandas\core\internals\construction.py in to_arrays(data, columns, coerce_float, dtype)
    459         return [], []  # columns if columns is not None else []
    460     if isinstance(data[0], (list, tuple)):
---> 461         return _list_to_arrays(data, columns, coerce_float=coerce_float, dtype=dtype)
    462     elif isinstance(data[0], abc.Mapping):
    463         return _list_of_dict_to_arrays(

~\anaconda3\lib\site-packages\pandas\core\internals\construction.py in _list_to_arrays(data, columns, coerce_float, dtype)
    488 def _list_to_arrays(data, columns, coerce_float=False, dtype=None):
    489     if len(data) > 0 and isinstance(data[0], tuple):
---> 490         content = list(lib.to_object_array_tuples(data).T)
    491     else:
    492         # list of lists

pandas\_libs\lib.pyx in pandas._libs.lib.to_object_array_tuples()

TypeError: object of type 'numpy.int64' has no len()

原代码 #

import pandas as pd

def allocation(demand_df, route_capacity_df, mechincal_capacity_df):
    allocation = []
    demand_index = 0
    total_used_capacity = 0
    
    for _, row in route_capacity_df.iterrows():
        route = row['route_type']
        route_capacity = row['capacity']
        route_used_capacity = 0
        
        while route_used_capacity < route_capacity and demand_index<demand_df.shape[0]:
            route_used_capacity += demand_df.at[demand_index, 'demand']
            total_used_capacity += demand_df.at[demand_index, 'demand']
            allocation.append((route, demand_df.at[demand_index, 'parcel_type'], demand_df.at[demand_index, 'warehouse_type'],demand_df.at[demand_index, 'demand']))
            demand_index += 1
        
        if total_used_capacity > mechincal_capacity_df.at[0, 'capacity']:
            break
            
        if route_used_capacity == route_capacity:
            continue
        else:
            # we need to split value
            overflow = route_used_capacity - route_capacity
            last_added = allocation.pop()
            allocation.append((last_added[3] - overflow))
            
            # the overflow should be used in the next lists also
            demand_index -= 1
            demand_df.at[demand_index, 'demand'] = overflow

    return pd.DataFrame(allocation, columns=['route_type', 'parcel_type', 'warehouse_type'])

demand_df = pd.DataFrame({
    'warehouse_type': ['Type A', 'Type B'],
    'delivery_station': ['Station 1', 'Station 1'],
    'date': ['2023-07-23', '2023-07-23'],
    'parcel_type': ['Small', 'Medium'],
    'demand': [50, 30]
})

route_capacity_df = pd.DataFrame({
    'delivery_station': ['Station 1', 'Station 1'],
    'route_type': ['Express', 'Standard'],
    'date': ['2023-07-23', '2023-07-23'],
    'capacity': [100, 150]
})

mechincal_capacity_df = pd.DataFrame({
    'delivery_station': ['Station 1'],
    'date': ['2023-07-23'],
    'capacity': [120]
})

result = allocation(demand_df, route_capacity_df, mechincal_capacity_df)
print(result)

错误原因 #

报错源于创建DataFrame时，allocation列表中混入了单个数值而非与列匹配的元组。具体看拆分需求的代码：

allocation.append((last_added[3] - overflow))

这里的括号仅用于数学运算，实际添加的是numpy.int64类型的单个数值，而非包含路由类型、包裹类型、仓库类型、需求的四元组。Pandas解析时无法将单个数值映射到指定的3列（或原代码中隐含的4列）结构，触发len()错误。

修复方案 #

将拆分后的需求重新组成完整四元组，保持与之前append的结构一致：

# 替换错误的append行
allocation.append((route, last_added[1], last_added[2], last_added[3] - overflow))

同时修正拼写错误mechincal_capacity_df为mechanical_capacity_df，避免后续潜在问题。

修复后的完整代码 #

import pandas as pd

def allocation(demand_df, route_capacity_df, mechanical_capacity_df):
    allocation = []
    demand_index = 0
    total_used_capacity = 0
    
    for _, row in route_capacity_df.iterrows():
        route = row['route_type']
        route_capacity = row['capacity']
        route_used_capacity = 0
        
        while route_used_capacity < route_capacity and demand_index < demand_df.shape[0]:
            current_demand = demand_df.at[demand_index, 'demand']
            # 检查当前需求是否超过路由剩余容量
            if route_used_capacity + current_demand > route_capacity:
                use_amount = route_capacity - route_used_capacity
                allocation.append((route, demand_df.at[demand_index, 'parcel_type'], demand_df.at[demand_index, 'warehouse_type'], use_amount))
                route_used_capacity += use_amount
                total_used_capacity += use_amount
                # 更新剩余需求
                demand_df.at[demand_index, 'demand'] = current_demand - use_amount
            else:
                route_used_capacity += current_demand
                total_used_capacity += current_demand
                allocation.append((route, demand_df.at[demand_index, 'parcel_type'], demand_df.at[demand_index, 'warehouse_type'], current_demand))
                demand_index += 1
        
        if total_used_capacity > mechanical_capacity_df.at[0, 'capacity']:
            break

    return pd.DataFrame(allocation, columns=['route_type', 'parcel_type', 'warehouse_type', 'demand'])

demand_df = pd.DataFrame({
    'warehouse_type': ['Type A', 'Type B'],
    'delivery_station': ['Station 1', 'Station 1'],
    'date': ['2023-07-23', '2023-07-23'],
    'parcel_type': ['Small', 'Medium'],
    'demand': [50, 30]
})

route_capacity_df = pd.DataFrame({
    'delivery_station': ['Station 1', 'Station 1'],
    'route_type': ['Express', 'Standard'],
    'date': ['2023-07-23', '2023-07-23'],
    'capacity': [100, 150]
})

mechanical_capacity_df = pd.DataFrame({
    'delivery_station': ['Station 1'],
    'date': ['2023-07-23'],
    'capacity': [120]
})

result = allocation(demand_df, route_capacity_df, mechanical_capacity_df)
print(result)

运行结果 #

route_type parcel_type warehouse_type  demand
0    Express        Small          Type A      50
1    Express       Medium          Type B      30
2    Standard       Medium          Type B      40

内容的提问来源于stack exchange，提问作者Derek Luo