Question

我在python中有以下代码，在其中尝试实现线性回归。我尝试通过具有功能computeCost来计算成本，作为第一步。这是向量化的实现，因此我尝试通过定义矩阵X，y和theta来实现成本函数的公式。

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from sklearn.preprocessing import MinMaxScaler

def loadData():
    dataset = pd.read_csv('datasets/Folds5x2_pp.csv')
    X = dataset[['AT','V','AP','RH']]
    y = dataset['PE']
    #print(X)
    scaler = MinMaxScaler()
    scaler.fit(X)
    X_nor = scaler.transform(X) 
    ones = np.ones([X.shape[0],1])
    X_nor = np.hstack((ones,X_nor))
    #print(X_nor)
    y_nor = (y - min(y)) / (max(y) - min(y))

   return X_nor, y_nor

def computeCost(X,y,theta):
   tobesummed = np.power(((X @ theta.T)-y),2)
   return np.sum(tobesummed)/(2 * len(X))


if __name__ == "__main__":
   X,y = loadData()

   theta = np.ones([1,5])
   alpha = 0.01
   iters = 1000

   computeCost(X,y,theta)

当我运行computeCost时，出现以下错误，该数据必须是一维的。我不确定1维是什么意思。

Exception                                 Traceback (most recent call last)
<ipython-input-64-7bd696e0edc3> in <module>
 32     iters = 1000
 33 
---> 34     computeCost(X,y,theta)
 35 
 36 

<ipython-input-64-7bd696e0edc3> in computeCost(X, y, theta)
 21 
 22 def computeCost(X,y,theta):
---> 23     tobesummed = np.power(((X @ theta.T)-y),2)
 24     return np.sum(tobesummed)/(2 * len(X))
 25 

~\Anaconda3\lib\site-packages\pandas\core\ops.py in wrapper(left, right)
   1583         result = safe_na_op(lvalues, rvalues)
   1584         return construct_result(left, result,
-> 1585                                 index=left.index, name=res_name, dtype=None)
   1586 
   1587     wrapper.__name__ = op_name

~\Anaconda3\lib\site-packages\pandas\core\ops.py in _construct_result(left, result, index, name,
 dtype)
   1472     not be enough; we still need to override the name attribute.
   1473     """
-> 1474     out = left._constructor(result, index=index, dtype=dtype)
   1475 
   1476     out.name = name

~\Anaconda3\lib\site-packages\pandas\core\series.py in __init__(self, data, index, dtype, name,
copy, fastpath)
260             else:
261                 data = sanitize_array(data, index, dtype, copy,
--> 262                                       raise_cast_failure=True)
263 
264                 data = SingleBlockManager(data, index, fastpath=True)

~\Anaconda3\lib\site-packages\pandas\core\internals\construction.py in sanitize_array(data,            
index, dtype, copy, raise_cast_failure)
656     elif subarr.ndim > 1:
657         if isinstance(data, np.ndarray):
--> 658             raise Exception('Data must be 1-dimensional')
659         else:
660             subarr = com.asarray_tuplesafe(data, dtype=dtype)

Exception: Data must be 1-dimensional

数据在Python中必须为一维

0 个答案: