Regression models

Validazione dei modelli in Python

Kasey Jones

Data Scientist

Random forests in scikit-learn

from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import RandomForestClassifier

rfr = RandomForestRegressor(random_state=1111)
rfc = RandomForestClassifier(random_state=1111)

Decision trees start with all points and break-off from the top based on different splits. Imagine following various paths across a tree's branches for each data point, based on the characteristics of the data.

When a random forest is completed, it will average the result of the individual decision trees for each data point to get the final prediction for that data point.

Random forest parameters

n_estimators: the number of trees in the forest

max_depth: the maximum depth of the trees

random_state: random seed

from sklearn.ensemble import RandomForestRegressor
rfr = RandomForestRegressor(n_estimators=50, max_depth=10)

rfr = RandomForestRegressor(random_state=1111)
rfr.n_estimators = 50
rfr.max_depth = 10

Feature importance

Print how important each column is to the model

for i, item in enumerate(rfr.feature_importances_):
    print("{0:s}: {1:.2f}".format(X.columns[i], item))

weight: 0.50
height: 0.39
left_handed: 0.72
union_preference: 0.05
eye_color: 0.03

Let's begin

Validazione dei modelli in Python