TypeError: unsupported operand type(s) for -: ‘str‘ and ‘float‘

背景：

读一个文件中的数据，用来训练一个小模型，发现数据中有异常值，如下：

使用pandas读数据，然后对数值类型特征，进行归一化，报错：

def minmax_norm(df):
    return (df - df.min()) / (df.max() - df.min())

if __name__=='__main__':

    train_data_path = 'train_1205_shanghai.txt'
    test_data_path = 'test_1206_shanghai.txt'
    # load_data_to_df(path)
    col_name = ['a','b','c']

    train_data = pd.read_table(train_data_path, header=None)
    train_data.columns = col_name
    test_data = pd.read_table(test_data_path, header=None)
    test_data.columns = col_name

    # print(data.head(3)) 'avg_rider_done_ord_cnt'
    number_feat = ['a','b']
    for i in range(len(number_feat)):
        train_data[[number_feat[i]]] = minmax_norm(train_data[[number_feat[i]]])
        test_data[[number_feat[i]]] = minmax_norm(test_data[[number_feat[i]]])

报错：

Traceback (most recent call last):
  File "/Users/alsc/.conda/envs/algoTest/lib/python3.6/site-packages/pandas/core/ops/array_ops.py", line 143, in na_arithmetic_op
    result = expressions.evaluate(op, left, right)
  File "/Users/alsc/.conda/envs/algoTest/lib/python3.6/site-packages/pandas/core/computation/expressions.py", line 233, in evaluate
    return _evaluate(op, op_str, a, b)  # type: ignore
  File "/Users/alsc/.conda/envs/algoTest/lib/python3.6/site-packages/pandas/core/computation/expressions.py", line 68, in _evaluate_standard
    return op(a, b)
TypeError: unsupported operand type(s) for -: 'str' and 'float'

排查：

这个错误的意思：类型有错误，不能将str和float类型的数据进行相减‘-’。

划重点，终于知道了【for -:】是什么意思，就是在减号处，出现了类型不匹配的问题，想修复问题，就去减号附近看看有没有涉及到不同类型计算的。

解决：

删除数据中的异常值。