Spaces:
Running
Running
File size: 3,239 Bytes
ac2928c 7e72d81 ac2928c c88fbe0 ac2928c c88fbe0 ac2928c c88fbe0 ac2928c c88fbe0 ac2928c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 |
import numpy as np
import csv
class Problem:
"""
Problem API to work with PySR.
Should be able to call pysr(problem.X, problem.y, var_names=problem.var_names) and have it work
"""
def __init__(self, X, y, variable_names=None):
self.X = X
self.y = y
self.variable_names = variable_names
class FeynmanProblem(Problem):
"""
Stores the data for the problems from the 100 Feynman Equations on Physics.
This is the benchmark used in the AI Feynman Paper
"""
def __init__(self, row, gen=False, dp=500):
"""
row: a row read as a dict from the FeynmanEquations dataset provided in the datasets folder of the repo
gen: If true the problem will have dp X and y values randomly generated else they will be None
"""
self.eq_id = row['Filename']
self.form = row['Formula']
self.n_vars = int(row['# variables'])
super(FeynmanProblem, self).__init__(None, None,
variable_names=[row[f'v{i + 1}_name'] for i in range(self.n_vars)])
#self.var_names = [row[f'v{i+1}_name'] for i in range(self.n_vars)]
self.low = [float(row[f'v{i+1}_low']) for i in range(self.n_vars)]
self.high = [float(row[f'v{i+1}_high']) for i in range(self.n_vars)]
self.dp = dp#int(row[f'datapoints'])
#self.X = None
#self.Y = None
if gen:
self.X = np.random.uniform(0.01, 25, size=(self.dp, self.n_vars))
d = {}
for var in range(len(self.var_names)):
d[self.var_names[var]] = self.X[:, var]
d['exp'] = np.exp
d['sqrt'] = np.sqrt
d['pi'] = np.pi
d['cos'] = np.cos
d['sin'] = np.sin
d['tan'] = np.tan
d['tanh'] = np.tanh
d['ln'] = np.log
d['log'] = np.log # Quite sure the Feynman dataset has no base 10 logs
d['arcsin'] = np.arcsin
self.y = eval(self.form,d)
return
def __str__(self):
return f"Feynman Equation: {self.eq_id}|Form: {self.form}"
def __repr__(self):
return str(self)
def mk_problems(first=100, gen=False, dp=500, data_dir="datasets/FeynmanEquations.csv"):
"""
first: the first "first" equations from the dataset will be made into problems
data_dir: the path pointing to the Feynman Equations csv
returns: list of FeynmanProblems
"""
ret = []
with open(data_dir) as csvfile:
ind = 0
reader = csv.DictReader(csvfile)
for i, row in enumerate(reader):
if ind > first:
break
if row['Filename'] == '': continue
try:
p = FeynmanProblem(row, gen=gen, dp=dp)
ret.append(p)
except Exception as e:
#traceback.print_exc()
#print(row)
print(f"FAILED ON ROW {i}")
ind += 1
return ret
if __name__ == "__main__":
ret = FeynmanProblem.mk_problems(first=100, gen=True)
print(ret) |