Training ML models on Melbourne Housing Prices dataset

The Dataset is downloaded from Kaggle, it is collected for housing prices in Melbourne, and includes Address, Type of Real estate, Suburb, Method of Selling, Rooms, Price, Real Estate Agent, Date of Sale and distance from C.B.D for different houses in Melbourne. Our task is to train a machine learning model and tune it for maximum accuracy, so that it can be used to predict the likely price of an unsold house. I use two approaches to solve this problem: Regression and Classification. I explore the data by using the describe and head commands in sklearn, this tells me that some of the features in the data are categorical variables, so they might need to be encoded. The variables Car, YearBuilt, BuildingArea and YearBuilt and Council Area seem to be the only ones with missing values, so we need to either remove the samples with missing values or impute them, since the missing values comprise a relatively large part of the dataset, greater than 10%, I choose to impute the missing values instead.