Exercise

# Training a linear model in batches

In this exercise, we will train a linear regression model in batches, starting where we left off in the previous exercise. We will do this by stepping through the dataset in batches and updating the model's variables, `intercept`

and `slope`

, after each step. This approach will allow us to train with datasets that are otherwise too large to hold in memory.

Note that the loss function,`loss_function(intercept, slope, targets, features)`

, has been defined for you. Additionally, `keras`

has been imported for you and `numpy`

is available as `np`

. The trainable variables should be entered into `var_list`

in the order in which they appear as loss function arguments.

Instructions

**100 XP**

- Use the
`.Adam()`

optimizer. - Load in the data from
`'kc_house_data.csv'`

in batches with a`chunksize`

of 100. - Extract the
`price`

column from`batch`

, convert it to a`numpy`

array of type 32-bit float, and assign it to`price_batch`

. - Complete the loss function, fill in the list of trainable variables, and perform minimization.