Very easy The goal of this project was to train a linear regression model to predict the price of houses based on numerous features like flat area, no of floors, condition of house, etc. Initially, I looked for the target variable for any missing values and outliers and removed them from the dataset. I used median to fill missing values in the numerical features of dataset. In zipcode attribute, I chose the “most frequent values” for imputing missing values. I performed other data transformations for categorical variables like “date house was sold”, “condition of house”. After this, I tried to analyze the effect of attributes on target variable using bar plots. It became