Activity 11.01 – Multiple regression with non-linear models

As part of a research effort to improve metallic-oxide semiconductor sensors for the toxic gas carbon monoxide (CO), you are asked to investigate models of the sensor response for an array of sensors. You will review the data, perform some feature engineering for non-linear features, and then compare a baseline linear regression approach to a random forest model:

1. For this exercise, you will need the pandas and numpy libraries, and three modules from sklearn, matplotlib, and seaborn. Load them in the first cell of the notebook:

   import pandas as pd
   import numpy as np
   from sklearn.linear_model import LinearRegression as OLS
   from sklearn.ensemble import RandomForestRegressor
   from sklearn.preprocessing import StandardScaler
   import matplotlib.pyplot as plt
   import seaborn as sns

2. As we have done before, create a utility function to plot a grid of histograms after being given the data, which variables to plot, the...