def test_SymbolicFeatures_pickle(data):
exponents = [1]
operators = {}
sym = sf.SymbolicFeatures(exponents, operators)
assert pickle.loads(pickle.dumps(sym)).__dict__ == sym.__dict__
sym.fit(data)
assert pickle.loads(
pickle.dumps(sym)).get_feature_names() == sym.get_feature_names()
def test_SymbolicFeatures_remove_id(data):
"""ProductFeature x_i * x_i**2 == x_i**3
"""
operators = {}
exponents = [1, 2, 3]
sym = sf.SymbolicFeatures(exponents, operators).fit(data)
# simple * 2 + products - excluded
assert len(sym.get_feature_names()) == 2 * 3 + 15 - 2
def test_SymbolicFeatures(data):
operators = {"log": np.log}
exponents = [2]
sym = sf.SymbolicFeatures(exponents, operators)
features = sym.fit_transform(data)
names = sym.get_feature_names()
assert len(names) == features.shape[1]
assert features.shape[0] == data.shape[0]
from sklearn.datasets import load_boston
from sklearn.linear_model import Lasso
import matplotlib.pyplot as plt
import numpy as np
import sparsereg.preprocessing.symfeat as sf
from sparsereg.model import STRidge
from sparsereg.util.net import net
data = load_boston()
x, y = data.data, data.target
exponents = [1]
operators = {}
sym = sf.SymbolicFeatures(exponents=exponents, operators=operators)
features = sym.fit_transform(x)
ests = [Lasso, STRidge]
attrs = ["alpha", "threshold"]
names = ["Lasso", "STRidge"]
for est, attr, name in zip(ests, attrs, names):
models = net(est,
features,
y,
attr,
filter=True,
max_coarsity=5,
r_max=1e5)
def test_SymbolicFeatures_redundant_data():
data = np.ones(shape=(10, 10))
exponents = [1, 2]
operators = {}
sym = sf.SymbolicFeatures(exponents, operators).fit(data)
assert len(sym.get_feature_names()) == 1