Question

我需要在不使用scikit的情况下对波士顿住房数据集进行线性回归。

这是我到目前为止提出的

import pandas as pd
import numpy as np
import matplotlib.pyplot as mlt
from sklearn.cross_validation import train_test_split 

data = pd.read_csv("housing.csv", delimiter=' ',
                   skipinitialspace=True,
                   names=['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE',
                          'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']
                  )

df_x = data.drop('MEDV', axis = 1)
df_y = data['MEDV']
x_train, x_test, y_train, y_test = train_test_split(df_x, df_y,
                                                    test_size=0.2,
                                                    random_state=4
                                                   )

def hypothesis(x, theta):
    return np.dot(x, theta.T)

def costfn(predictions, y, x):
    a = 1 / (2 * len(x)) * np.sum((prediction - y) ** 2)
    return a

def gradient(theta, alpha, predictions, x, y):
    theta = np.subtract(theta, (alpha / len(x)) * np.dot(np.subtract(predictions, y).T, x))
    return theta

alpha = 0.001
iters = 1000
theta = np.zeros([1, 13])
predictions = hypothesis(x_train, theta)

for i in range(iters):
    predictions = hypothesis(x_train, theta)
    theta = gradient(theta, alpha, predictions, x_train, y_train)

predictions = hypothesis(x_test, theta)
print(predictions)

我接受并输入了测试和培训案例，一切正常。但我收到此错误-

Exception                                 Traceback (most recent call last)
<ipython-input-33-36492e2820ce> in <module>
      6 for i in range(iters):
      7     predictions = hypothesis(x_train, theta)
----> 8     theta = gradient(theta, alpha, predictions, x_train, y_train)
      9 
     10 predictions = hypothesis(x_test, theta)

<ipython-input-32-15d0b5b7bf16> in gradient(theta, alpha, predictions, x, y)
      9 
     10 
---> 11     theta = np.subtract(theta, (alpha / len(x)) * np.dot(np.subtract(predictions, y).T, x))
     12     return theta

/usr/lib/python3/dist-packages/pandas/core/series.py in __array_wrap__(self, result, context)
    502         """
    503         return self._constructor(result, index=self.index,
--> 504                                  copy=False).__finalize__(self)
    505 
    506     def __array_prepare__(self, result, context=None):

/usr/lib/python3/dist-packages/pandas/core/series.py in __init__(self, data, index, dtype, name, copy, fastpath)
    262             else:
    263                 data = _sanitize_array(data, index, dtype, copy,
--> 264                                        raise_cast_failure=True)
    265 
    266                 data = SingleBlockManager(data, index, fastpath=True)

/usr/lib/python3/dist-packages/pandas/core/series.py in _sanitize_array(data, index, dtype, copy, raise_cast_failure)
   3273     elif subarr.ndim > 1:
   3274         if isinstance(data, np.ndarray):
-> 3275             raise Exception('Data must be 1-dimensional')
   3276         else:
   3277             subarr = _asarray_tuplesafe(data, dtype=dtype)

Exception: Data must be 1-dimensional

请帮助。另外，如果我的逻辑错误，请告诉我，因为我是初学者。

Answer 1

pandas对于数据管理非常有用，但是在数学步骤上，我倾向于坚持使用NumPy对象。 pandas试图在这里做些聪明的事情，我不知道该怎么做，但是如果您将df_x.values和df_y.values传递给train_test_split()，您的代码将运行：

x_train, x_test, y_train, y_test = train_test_split(df_x.values,
                                                    df_y.values,
                                                    test_size=0.2,
                                                    random_state=4
                                                   )

如何在线性回归中解决“异常：数据必须为一维”？

1 个答案: