def setUp(self):
self.SymbolTree = SymbolTree
self.pset = SymbolSet()
from sklearn.datasets import fetch_california_housing
data = fetch_california_housing()
x = data["data"][:100]
y = data["target"][:100]
self.x = x
self.y = y
# self.pset.add_features(x, y, )
self.pset.add_features(x, y, x_group=[[1, 2], [4, 5]])
self.pset.add_constants([6, 3, 4],
c_dim=[dless, dless, dless],
c_prob=None)
self.pset.add_operations(power_categories=(2, 3, 0.5),
categories=("Add", "Mul", "Neg", "Abs"),
self_categories=None)
from sklearn.metrics import r2_score, mean_squared_error
self.cp = CalculatePrecisionSet(self.pset,
scoring=[r2_score, mean_squared_error],
score_pen=[1, -1],
dim_type=None,
filter_warning=True)
def setUp(self):
self.SymbolTree = SymbolTree
self.pset = SymbolSet()
from sklearn.datasets import load_boston
data = load_boston()
x = data["data"]
y = data["target"]
# No = Normalizer()
# y=y/max(y)
# x = No.fit_transform(x)
self.x = x
self.y = y
# self.pset.add_features(x, y, )
self.pset.add_features(x, y, x_group=[[1, 2], [4, 5]])
self.pset.add_constants([6, 3, 4],
c_dim=[dless, dless, dless],
c_prob=None)
self.pset.add_operations(power_categories=(2, 3, 0.5),
categories=("Add", "Mul", "Self", "Abs"),
self_categories=None)
from sklearn.metrics import r2_score, mean_squared_error
self.cp = CalculatePrecisionSet(self.pset,
scoring=[r2_score, mean_squared_error],
score_pen=[1, -1],
filter_warning=True)
#
# plt.show()
X = q1[:, :-1]
y = q1[:, -1]
X = np.concatenate((X, (X[:, 1] / X[:, 0]**2).reshape(-1, 1)), axis=1)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.20,
random_state=0)
store = Store()
# symbolset
pset0 = SymbolSet()
pset0.add_features(X_train, y_train)
pset0.add_constants(c=[
1,
])
pset0.add_operations(
power_categories=(2, ),
categories=("Add", "exp", "Neg"),
)
h_bgp = 3
# stop = None
# This random_state is under Linux system. For others system ,the random_state maybe different。
# try with different random_state.
stop = lambda ind: ind.fitness.values[0] >= 0.99
import numpy as np
import sympy
from bgp.base import SymbolSet, SymbolTree
from bgp.calculation.translate import general_expr_dict, compile_context
if __name__ == "__main__":
x = np.full((10, 4), fill_value=0.1)
y = np.ones((10, ))
height = 2
hbgp = 1
# bgp
group = 2
pset = SymbolSet()
pset.add_features(
x,
y,
x_group=group,
)
pset.add_accumulative_operation(categories=("MAdd", "MMul", "MSub", "MDiv",
"Conv", "Self"),
special_prob={
"MAdd": 0.16,
"MMul": 0.16,
"MSub": 0.16,
"MDiv": 0.16,
"Conv": 0.16,
"Self": 0.16
})
def fit(self,
X=None,
y=None,
c=None,
x_group=None,
x_dim=1,
y_dim=1,
c_dim=1,
x_prob=None,
c_prob=None,
pset=None,
power_categories=(2, 3, 0.5),
categories=("Add", "Mul", "Sub", "Div"),
warm_start=False,
new_gen=None):
"""
Method 1. fit with x, y.
Examples::
sl = SymbolLearning()
sl..fit(x,y,...)
Method 2. fit with customized pset. If need more self-definition, use one defined SymbolSet object to ``pset``.
Examples::
pset = SymbolSet()
pset.add_features_and_constants(...)
pset.add_operations(...)
...
sl = SymbolLearning()
sl..fit(pset=pset)
Parameters
----------
X:np.ndarray
data.
y:np.ndarray
y.
c:list of float, None
constants.
x_dim: 1 or list of Dim
the same size wih x.shape[1], default 1 is dless for all x.
y_dim: 1,Dim
dim of y.
c_dim: 1,list of Dim
the same size wih c.shape, default 1 is dless for all c.
x_prob: None,list of float
the same size wih x.shape[1].
c_prob: None,list of float
the same size wih c.
x_group:list of list
Group of x.
Examples:
x_group=[[1,2],]
or
x_group=2
See Also :py:func:`bgp.base.SymbolSet.add_features`
power_categories: Sized,tuple, None
Examples:(0.5,2,3)
categories: tuple of str
map table:
{"Add": sympy.Add, 'Sub': Sub, 'Mul': sympy.Mul, 'Div': Div}
{"sin": sympy.sin, 'cos': sympy.cos, 'exp': sympy.exp, 'ln': sympy.ln,
{'Abs': sympy.Abs, "Neg": functools.partial(sympy.Mul, -1.0),
"Rec": functools.partial(sympy.Pow, e=-1.0)}
Others: \n
"Rem": f(x)=1-x,if x true \n
"Self": f(x)=x,if x true \n
pset:SymbolSet
See Also SymbolSet.
warm_start: bool
warm start or not.
Note:
If you offer pset in advance by user, please check carefully the feature numbers,especially when use ``re_Tree``.
because the new features are add.
Reference:
CalculatePrecisionSet.update_with_X_y.
new_gen: None,int
warm_start generation.
"""
# try to find pest form args,kwargs
psets = [i for i in self.args if isinstance(i, SymbolSet)]
if len(psets) > 0:
self.args.remove(psets[0])
if "pset" in self.kwargs:
psets.append(self.kwargs["pset"])
del self.kwargs["pset"]
if pset is None:
if len(psets) > 0:
pset = psets[0]
if pset is None:
# one simple pset are generate with no dimension calculation, But just with x_group.\n
if X is not None and y is not None:
pset = SymbolSet()
pset.add_features_and_constants(X,
y,
c,
x_dim=x_dim,
y_dim=y_dim,
c_dim=c_dim,
x_prob=x_prob,
c_prob=c_prob,
x_group=x_group,
feature_name=None)
pset.add_operations(power_categories=power_categories,
categories=categories)
elif hasattr(self.loop, "gen"):
pass
else:
raise ValueError(
"The pset should be defined or the X and Y should be offered."
)
####################################
if warm_start:
assert hasattr(
self.loop,
"gen"), "Before the warm_start, Need fit at least one time"
if X is not None and y is not None:
self.loop.cpset.update_with_X_y(X, y)
elif pset:
# the warm_start are not compacting with "re_Tree"
self.loop.cpset.update(pset)
else:
raise ValueError(
"The pset should be defined or the X and Y should be offered."
)
self.loop.re_fresh_by_name()
hall = self.loop.run(warm_start=True, new_gen=new_gen)
else:
if hasattr(self.loop, "gen"):
loops = self.loop.__class__
self.loop = loops(pset, *self.args, **self.kwargs)
else:
self.loop = self.loop(pset, *self.args, **self.kwargs)
hall = self.loop.run()
self.best_one = hall.items[0]
try:
expr = general_expr(self.best_one.coef_expr, self.loop.cpset)
self.expr_type = "single"
except (RecursionError, RuntimeWarning):
expr = self.best_one.coef_expr
self.expr_type = "group"
self.expr = expr
self.y_dim = self.best_one.y_dim
self.fitness = self.best_one.fitness.values[0]