我尝试进行逻辑回归。
import pandas
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression
import numpy as np
df = pd.read_csv("tested.csv")
df.dropna(inplace=True)
x = df["Age"]
y = df["Survived"]
x_re = x.values.reshape(-1, 1)
reg = LogisticRegression()
reg.fit(x_re, y)
predict = reg.predict(x)
plt.title("Propability to survive")
plt.scatter(x, y, "r")
plt.plot(x, predict, "b")
plt.grid()
plt.show()
但它显示了一个错误，因为我的 x 数据没有正确的维度并且它不是数组。 这里有一个错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[28], line 13
11 reg = LogisticRegression()
12 reg.fit(x_re, y)
---> 13 predict = reg.predict(x)
14 plt.title("Propability to survive")
15 plt.scatter(x, y, "r")
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\sklearn\linear_model\_base.py:451, in LinearClassifierMixin.predict(self, X)
437 """
438 Predict class labels for samples in X.
439
(...)
448 Vector containing the class labels for each sample.
449 """
450 xp, _ = get_namespace(X)
--> 451 scores = self.decision_function(X)
452 if len(scores.shape) == 1:
453 indices = xp.astype(scores > 0, int)
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\sklearn\linear_model\_base.py:432, in LinearClassifierMixin.decision_function(self, X)
429 check_is_fitted(self)
430 xp, _ = get_namespace(X)
--> 432 X = self._validate_data(X, accept_sparse="csr", reset=False)
433 scores = safe_sparse_dot(X, self.coef_.T, dense_output=True) + self.intercept_
434 return xp.reshape(scores, (-1,)) if scores.shape[1] == 1 else scores
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\sklearn\base.py:605, in BaseEstimator._validate_data(self, X, y, reset, validate_separately, cast_to_ndarray, **check_params)
603 out = X, y
604 elif not no_val_X and no_val_y:
--> 605 out = check_array(X, input_name="X", **check_params)
606 elif no_val_X and not no_val_y:
607 out = _check_y(y, **check_params)
File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\sklearn\utils\validation.py:938, in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)
936 # If input is 1D raise error
937 if array.ndim == 1:
--> 938 raise ValueError(
939 "Expected 2D array, got 1D array instead:\narray={}.\n"
940 "Reshape your data either using array.reshape(-1, 1) if "
941 "your data has a single feature or array.reshape(1, -1) "
942 "if it contains a single sample.".format(array)
943 )
945 if dtype_numeric and hasattr(array.dtype, "kind") and array.dtype.kind in "USV":
946 raise ValueError(
947 "dtype='numeric' is not compatible with arrays of bytes/strings."
948 "Convert your data to numeric values explicitly instead."
949 )
ValueError: Expected 2D array, got 1D array instead:
array=[23. 47. 48. 22. 41. 30. 45. 45. 60. 24. 28. 25. 36. 13.
31. 60. 28.5 35. 32.5 55. 67. 27. 76. 43. 18.5 36. 63. 1.
36. 35. 53. 61. 23. 29. 42. 48. 54. 36. 64. 37. 18. 27.
6. 47. 33. 42. 50. 22. 39. 64. 48. 45. 41. 27. 46. 26.
24. 53. 64. 30. 55. 55. 57. 25. 26. 12. 39. 30. 58. 45.
50. 59. 25. 31. 49. 54. 55. 23. 51. 18. 48. 30. 43. 20.
50. 37. 39. ].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.
我尝试使用 array.reshape(-1, 1)、values.reshape(-1, 1) 或仅 reshape(-1, 1) 但它总是显示相同的错误。在 YouTube 上，这个人只是在没有重塑功能的情况下做到了这一点。有人可以帮我吗？
错误来自
predict = reg.predict(x)x使用这个：
predict = reg.predict(x.reshape(-1,1))