Recap: Forest Ranger

Part of the Supervised Learning section of Coddy's Machine Learning journey. Lesson 44 of 58.

Challenge

Medium

Race this chapter's two teams of trees. A park ranger wants to know which campsites bears will visit, and what draws them; the starter loads campsites.csv.

Cross-validate a forest of 100 trees and boosting with default settings, cv=5, both random_state=0. Print each mean and std.
Print the winner by mean, and fit it on all the rows.
Draw its importances as sideways bars, smallest first, titled What Brings Bears, x label Importance.

Another park, about raccoons:

Forest: mean 0.780, std 0.086
Boosting: mean 0.787, std 0.075
Winner: boosting

Sideways bars titled What Brings Raccoons, smallest at the bottom: oaks about 0.06, visitors 0.16, bins 0.21, tables 0.24 and creek_m 0.33 on top

Coddy then describes your chart.

Try it yourself

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier

# 200 campsites: distance to a stream, bear-proof food lockers (1 or 0), trash bins,
# altitude, berry bushes nearby, campers a week, and whether a bear visited (1 or 0)
sites = pd.read_csv("campsites.csv")
features = ["stream_m", "lockers", "bins", "altitude_m", "berries", "campers"]

# Write your code below