RuleFit

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

import japanize_matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.datasets import fetch_openml
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score

dataset = fetch_openml(data_id=42092, as_frame=True)
X = dataset.data.select_dtypes("number").copy()
y = dataset.target.astype(float)

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18

from rulefit import RuleFit
import warnings
warnings.simplefilter("ignore")

rf = RuleFit(max_rules=200, tree_random_state=27)
rf.fit(X_train.values, y_train.values, feature_names=list(X_train.columns))

pred_tr = rf.predict(X_train.values)
pred_te = rf.predict(X_test.values)

def report(y_true, y_pred, name):
    rmse = mean_squared_error(y_true, y_pred, squared=False)
    mae  = mean_absolute_error(y_true, y_pred)
    r2   = r2_score(y_true, y_pred)
    print(f"{name:8s}  RMSE={rmse:,.0f}  MAE={mae:,.0f}  R2={r2:.3f}")

report(y_train, pred_tr, "Train")
report(y_test,  pred_te, "Test")

1
2
3

rules = rf.get_rules()
rules = rules[rules.coef != 0].sort_values(by="importance", ascending=False)
rules.head(10)

1
2
3
4
5
6
7

plt.figure(figsize=(6, 5))
plt.scatter(X_train["sqft_above"], y_train, s=10, alpha=0.5)
plt.xlabel("sqft_above")
plt.ylabel("price")
plt.title("Relationship between sqft_above and price")
plt.grid(alpha=0.3)
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

rule_mask = X["sqft_living"].le(3935.0) & X["lat"].le(47.5315)

applicable_data = np.log(y[rule_mask])
not_applicable  = np.log(y[~rule_mask])

plt.figure(figsize=(8, 5))
plt.boxplot([applicable_data, not_applicable],
            labels=["Rule satisfied", "Rule not satisfied"])
plt.ylabel("log(price)")
plt.title("Price distribution by rule satisfaction")
plt.grid(alpha=0.3)
plt.show()