Search⌘ K
Home
Courses
A Beginner's Guide to Deep Learning

Regression Models

Explore how to build regression models in Keras by working with a real-world hourly wage dataset. Learn data preparation, model architecture specification, compiling, fitting, and evaluating regression models without output activation functions. Understand practical regression modeling steps to predict continuous values effectively.

We'll cover the following...

The Predict Hourly Wage dataset is taken from Kaggle. Make a model to predict wages per hour. The dataset contains the following columns:

Read and explore the data

Read the data from the given hourly_wages_data.csv and check for any missing values.

Python 3.8
import pandas as pd
import keras
# read in data using pandas
train_df = pd.read_csv('hourly_wages_data.csv')
print("Training data:\n", train_df.head())
# sum the missing values in each column
null_values = train_df.isnull().sum()
print("Checking for null values:\n", null_values)

Line - 4: Reads the data in train_df using the read_csv method.

train_df =
...