LinearRegression拟合报错：期望2D数组却得到1D数组的解决方法咨询

我用LinearRegression模型预测年度'Value'数值，从CSV导入的数据如下（df.head()结果）：

LOCATION    INDICATOR   SUBJECT MEASURE FREQUENCY   TIME    Value   Flag Codes
0   IRL LTINT   TOT PC_PA   M   1.167610e+18    4.04    NaN
1   IRL LTINT   TOT PC_PA   M   1.170288e+18    4.07    NaN
2   IRL LTINT   TOT PC_PA   M   1.172707e+18    3.97    NaN
3   IRL LTINT   TOT PC_PA   M   1.175386e+18    4.19    NaN
4   IRL LTINT   TOT PC_PA   M   1.177978e+18    4.32    NaN

原TIME列格式为YYYY-DD-MM，我执行了以下代码处理该列：

df['TIME'] = pd.to_datetime(df['TIME'])
df['TIME'] = pd.to_numeric(df['TIME'])
df['TIME'] = df['TIME'].astype(float)

随后编写拟合代码：

X=df['TIME']
Y=df['Value']
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.4, random_state=101)
lm= LinearRegression()

执行lm.fit(X_train, Y_train)时出现报错：

ValueError                                Traceback (most recent call last)
Cell In[12], line 1
----> 1 lm.fit(X_train, Y_train)
File ~\anaconda3\Lib\site-packages\sklearn\base.py:1151, in _fit_context.<locals>.decorator.<locals>.wrapper(estimator, *args, **kwargs)
   1144     estimator._validate_params()
   1146 with config_context(
   1147     skip_parameter_validation=(
   1148         prefer_skip_nested_validation or global_skip_validation
   1149     )
   1150 ):
-> 1151     return fit_method(estimator, *args, **kwargs)
File ~\anaconda3\Lib\site-packages\sklearn\linear_model\_base.py:678, in LinearRegression.fit(self, X, y, sample_weight)
    674 n_jobs_ = self.n_jobs
    676 accept_sparse = False if self.positive else ["csr", "csc", "coo"]
-> 678 X, y = self._validate_data(
    679     X, y, accept_sparse=accept_sparse, y_numeric=True, multi_output=True
    680 )
    682 has_sw = sample_weight is not None
    683 if has_sw:
File ~\anaconda3\Lib\site-packages\sklearn\base.py:621, in BaseEstimator._validate_data(self, X, y, reset, validate_separately, cast_to_ndarray, **check_params)
    619         y = check_array(y, input_name="y", **check_y_params)
    620     else:
-> 621         X, y = check_X_y(X, y, **check_params)
    622     out = X, y
    624 if not no_val_X and check_params.get("ensure_2d", True):
File ~\anaconda3\Lib\site-packages\sklearn\utils\validation.py:1147, in check_X_y(X, y, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, estimator)
   1142         estimator_name = _check_estimator_name(estimator)
   1143     raise ValueError(
   1144         f"{estimator_name} requires y to be passed, but the target y is None"
   1145     )
-> 1147 X = check_array(
   1148     X,
   1149     accept_sparse=accept_sparse,
   1150     accept_large_sparse=accept_large_sparse,
   1151     dtype=dtype,
   1152     order=order,
   1153     copy=copy,
   1154     force_all_finite=force_all_finite,
   1155     ensure_2d=ensure_2d,
   1156     allow_nd=allow_nd,
   1157     ensure_min_samples=ensure_min_samples,
   1158     ensure_min_features=ensure_min_features,
   1159     estimator=estimator,
   1160     input_name="X",
   1161 )
   1163 y = _check_y(y, multi_output=multi_output, y_numeric=y_numeric, estimator=estimator)
   1165 check_consistent_length(X, y)
File ~\anaconda3\Lib\site-packages\sklearn\utils\validation.py:940, 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)
    938     # If input is 1D raise error
    939     if array.ndim == 1:
-> 940         raise ValueError(
    941             "Expected 2D array, got 1D array instead:\narray={}.\n"
    942             "Reshape your data either using array.reshape(-1, 1) if "
    943             "your data has a single feature or array.reshape(1, -1) "
    944             "if it contains a single sample.".format(array)
    945         )
    947 if dtype_numeric and hasattr(array.dtype, "kind") and array.dtype.kind in "USV":
    948     raise ValueError(
    949         "dtype='numeric' is not compatible with arrays of bytes/strings."
    950         "Convert your data to numeric values explicitly instead."
    951     )
ValueError: Expected 2D array, got 1D array instead:
array=[1.3437792e+18 1.6198272e+18 1.3596768e+18 ... 1.3596768e+18 1.5805152e+18
 1.5751584e+18].
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.

错误核心原因：scikit-learn的LinearRegression要求输入的特征矩阵X必须是二维数组（形状为(n_samples, n_features)），但你传入的X_train是一维的Series（或一维numpy数组）。

以下三种方法可解决问题：

方法1：用双括号选取特征列，直接生成二维DataFrame #

修改X的定义，使用df[['TIME']]代替df['TIME']，双括号会返回二维的DataFrame，符合模型输入要求：

X = df[['TIME']]  # 返回形状为(n,1)的DataFrame
Y = df['Value']
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.4, random_state=101)
lm = LinearRegression()
lm.fit(X_train, Y_train)  # 可正常执行

方法2：用reshape将一维数组转为二维 #

在拟合时或提前对X进行reshape处理：

X = df['TIME']
Y = df['Value']
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.4, random_state=101)
lm = LinearRegression()
# 拟合时对X_train进行reshape
lm.fit(X_train.values.reshape(-1, 1), Y_train)

或提前处理X：

X = df['TIME'].values.reshape(-1, 1)  # 直接转为二维数组
Y = df['Value']
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.4, random_state=101)
lm = LinearRegression()
lm.fit(X_train, Y_train)

方法3：用sklearn转换器确保维度（适合复杂流程） #

如果后续有更多特征处理步骤，可使用FunctionTransformer统一处理维度：

from sklearn.preprocessing import FunctionTransformer

reshape_transformer = FunctionTransformer(lambda x: x.reshape(-1, 1))
X = reshape_transformer.fit_transform(df['TIME'])
Y = df['Value']
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.4, random_state=101)
lm = LinearRegression()
lm.fit(X_train, Y_train)

内容的提问来源于stack exchange，提问作者Najoua