Which code can be used directly to predict prices for new HDB resale cases using a trained Linear Regression model?

Question

BlackTom AI · Accepted Answer

Question restatement: Which code can be used directly to predict prices for new HDB resale cases using a trained Linear Regression model?

Option A: lr.predict([[3, 'Ang Mo Kio', '4-room'], [4, 'Bedok', '5-room']])
- This input uses categorical data like location names ('Ang Mo Kio', 'Bedok') and room labels ('4-room', '5-room') directly, which is inconsistent with a trained Linear Regression model that typically expects numerical feature values. Unless those categories have been encoded numerically beforehand, this would not be appropriate.

Option B: lr.predict([[1200, 30, 1, 0, 0], [980, 12, 0, 1, 0]])
- This input provides numerical feature vectors, matching a common structure for a trained linear model. Each inner list represents a new observation with features in the learned order (e.g., size, age, binary indicators for categories, etc.). If the model was trained with exactly these feature positions, this code can be used directly to produce price predictions for new cases.

Option C: df.predict(y_test)
- This attempts to call predict on a DataFrame object with y_test as input, which is conceptually incorrect. predict should be called on a trained model, not on a raw DataFrame, and the argument should be new feature data, not the test labels. This misuse would raise an error or yield meaningless results.

Option D: df.fit(X_test, y_test)
- This represents fitting or training a model using X_test and y_test, typically from a test set, which is improper for predicting new prices. You should fit a model on training data, not fit it again on test data. Additionally, df suggests a DataFrame object, which does not provide a fit method unless it wraps a model, making this option unlikely to directly produce predictions for new cases.

Summary of reasoning:
- The core requirement for predicting with a trained Linear Regression model is to pass numeric feature arrays that align with the model’s learned feature order.
- Option A uses non-numeric/categorical inputs in raw form, which is not compatible unless preprocessed; it is therefore unreliable for direct prediction.
- Option B supplies numeric feature vectors in the expected shape, aligning with standard practice for calling model.predict on new data.
- Options C and D describe incorrect usage: predicting with a DataFrame method or retraining on test data, neither of which yields direct, valid price predictions for new cases.

Which code can be used directly to predict prices for new HDB resale cases using a trained Linear Regression model?

查看解析

登录即可查看完整答案

类似问题

神经网络中需要有多少个神经元才能解决一维的线性回归任务？ How many neurons are necessary in a neural network to solve a linear regression task in one dimension?

The linear regression method for supervised learning assumes that the true regression function is a linear function.

In a consumer society, many adults channel creativity into buying things

Economic stress and unpredictable times have resulted in a booming industry for self-help products

更多留学生实用工具

考试浏览器助手

风格化写作助手

论文查重助手

文献引用助手

课堂转译助手

课堂笔记助手

Quiz搜索助手

学校历年真题

智能刷题助手

智能匹配练习

希望你的学习变得更简单