import pandas as pd import numpy as np from sklearn.model_selection import train_test_split pd.set_option('display.max_columns', None) # 所有列 pd.set_option('display.max_rows', None) # 所有行 data = pd.read_excel('半监督数据.xlsx') X = data.drop(columns=['label']) # 特征矩阵 y = data['label'] # 标签列 # 划分数据集 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, stratify=None, shuffle=True, random_state=0) # 划分带标签数据集 labeled_size = 0.3 n_labeled = int(labeled_size * len(X_train)) indices = np.arange(len(X_train)) unlabeled_indices = np.delete(indices, y_train.index[:n_labeled]) X_unlabeled = X_train.iloc[unlabeled_indices] y_unlabeled = y_train.iloc[unlabeled_indices] X_labeled = X_train.iloc[y_train.index[:n_labeled]] y_labeled = y_train.iloc[y_train.index[:n_labeled]] from sklearn import preprocessing pre_transform=preprocessing.StandardScaler() pre_transform.fit(np.vstack([train_datas, test_datas])) train_datas=pre_transform.transform(train_datas) test_datas=pre_transform.transform(train_datas) from LAMDA_SSL.Algorithm.Regression.CoReg import CoReg model=CoReg() model.fit(X=train_datas,y=labeled_y,test_datas=unlabeled_X) pred_y=model.predict(X=test_X) from LAMDA_SSL.Evaluation.Regressor.Mean_Squared_Error import Mean_Squared_Error performance = Mean_Squared_Error().scoring(test_y, pred_y)帮我看一下这段代码有什么问题?怎么修改?
时间: 2023-06-25 12:08:16 浏览: 181
pd_split_train_test.rar_pandas_pandas对数据分类_pd.split_split_数据分类
在代码中,预处理部分中使用了未定义的变量 `train_datas` 和 `test_datas`,应该将其改为 `X_train` 和 `X_test`。
另外,在调用 `CoReg` 模型时,传入的参数名 `test_datas` 应该改为 `unlabeled_X`,因为在之前的代码中,`X_unlabeled` 被赋值给了 `unlabeled_X`。
最后,在计算预测结果时,应该将 `test_X` 改为 `X_test`。
修改后的代码如下:
```
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from LAMDA_SSL.Algorithm.Regression.CoReg import CoReg
from LAMDA_SSL.Evaluation.Regressor.Mean_Squared_Error import Mean_Squared_Error
pd.set_option('display.max_columns', None) # 所有列
pd.set_option('display.max_rows', None) # 所有行
data = pd.read_excel('半监督数据.xlsx')
X = data.drop(columns=['label']) # 特征矩阵
y = data['label'] # 标签列
# 划分数据集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, stratify=None, shuffle=True, random_state=0)
# 划分带标签数据集
labeled_size = 0.3
n_labeled = int(labeled_size * len(X_train))
indices = np.arange(len(X_train))
unlabeled_indices = np.delete(indices, y_train.index[:n_labeled])
X_unlabeled = X_train.iloc[unlabeled_indices]
y_unlabeled = y_train.iloc[unlabeled_indices]
X_labeled = X_train.iloc[y_train.index[:n_labeled]]
y_labeled = y_train.iloc[y_train.index[:n_labeled]]
# 数据预处理
pre_transform=preprocessing.StandardScaler()
pre_transform.fit(np.vstack([X_train, X_test]))
X_train = pre_transform.transform(X_train)
X_test = pre_transform.transform(X_test)
# 构建和训练模型
model = CoReg()
model.fit(X=X_train, y=y_labeled, test_datas=X_unlabeled)
pred_y = model.predict(X=X_test)
# 计算性能指标
performance = Mean_Squared_Error().scoring(y_test, pred_y)
```
阅读全文