def run_aifeynman(pathdir,filename,BF_try_time,BF_ops_file_type, polyfit_deg=4, NN_epochs=4000, vars_name=[],test_percentage=20):
# If the variable names are passed, do the dimensional analysis first
filename_orig = filename
try:
if vars_name!=[]:
dimensionalAnalysis(pathdir,filename,vars_name)
DR_file = filename + "_dim_red_variables.txt"
filename = filename + "_dim_red"
else:
DR_file = ""
except:
DR_file = ""
# Split the data into train and test set
input_data = np.loadtxt(pathdir+filename)
sep_idx = np.random.permutation(len(input_data))
train_data = input_data[sep_idx[0:(100-test_percentage)*len(input_data)//100]]
test_data = input_data[sep_idx[test_percentage*len(input_data)//100:len(input_data)]]
np.savetxt(pathdir+filename+"_train",train_data)
if test_data.size != 0:
np.savetxt(pathdir+filename+"_test",test_data)
PA = ParetoSet()
# Run the code on the train data
PA = run_AI_all(pathdir,filename+"_train",BF_try_time,BF_ops_file_type, polyfit_deg, NN_epochs, PA=PA)
PA_list = PA.get_pareto_points()
# Run bf snap on the resulted equations
for i in range(len(PA_list)):
try:
PA = add_bf_on_numbers_on_pareto(pathdir,filename,PA,PA_list[i][-1])
except:
continue
PA_list = PA.get_pareto_points()
np.savetxt("results/solution_before_snap_%s.txt" %filename,PA_list,fmt="%s")
# Run zero, integer and rational snap on the resulted equations
for j in range(len(PA_list)):
PA = add_snap_expr_on_pareto(pathdir,filename,PA_list[j][-1],PA, "")
PA_list = PA.get_pareto_points()
np.savetxt("results/solution_first_snap_%s.txt" %filename,PA_list,fmt="%s")
# Run gradient descent on the data one more time
for i in range(len(PA_list)):
try:
gd_update = final_gd(pathdir,filename,PA_list[i][-1])
PA.add(Point(x=gd_update[1],y=gd_update[0],data=gd_update[2]))
except:
continue
PA_list = PA.get_pareto_points()
for j in range(len(PA_list)):
PA = add_snap_expr_on_pareto(pathdir,filename,PA_list[j][-1],PA, DR_file)
list_dt = np.array(PA.get_pareto_points())
data_file_len = len(np.loadtxt(pathdir+filename))
log_err = []
log_err_all = []
for i in range(len(list_dt)):
log_err = log_err + [np.log2(float(list_dt[i][1]))]
log_err_all = log_err_all + [data_file_len*np.log2(float(list_dt[i][1]))]
log_err = np.array(log_err)
log_err_all = np.array(log_err_all)
# Try the found expressions on the test data
if DR_file=="" and test_data.size != 0:
test_errors = []
for i in range(len(list_dt)):
test_errors = test_errors + [get_symbolic_expr_error(pathdir,filename+"_test",str(list_dt[i][-1]))]
test_errors = np.array(test_errors)
# Save all the data to file
save_data = np.column_stack((test_errors,log_err,log_err_all,list_dt))
else:
save_data = np.column_stack((log_err,log_err_all,list_dt))
np.savetxt("results/solution_%s" %filename_orig,save_data,fmt="%s")
def run_bf_polyfit(pathdir,pathdir_transformed,filename,BF_try_time,BF_ops_file_type, PA, polyfit_deg=4, output_type=""):
#############################################################################################################################
# run BF on the data (+)
print("Checking for brute force + \n")
brute_force(pathdir_transformed,filename,BF_try_time,BF_ops_file_type,"+")
try:
# load the BF output data
bf_all_output = np.loadtxt("results.dat", dtype="str")
express = bf_all_output[:,2]
prefactors = bf_all_output[:,1]
prefactors = [str(i) for i in prefactors]
# Calculate the complexity of the bf expression the same way as for gradient descent case
complexity = []
errors = []
eqns = []
for i in range(len(prefactors)):
try:
if output_type=="":
eqn = prefactors[i] + "+" + RPN_to_eq(express[i])
elif output_type=="acos":
eqn = "cos(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
elif output_type=="asin":
eqn = "sin(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
elif output_type=="atan":
eqn = "tan(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
elif output_type=="cos":
eqn = "acos(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
elif output_type=="exp":
eqn = "log(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
elif output_type=="inverse":
eqn = "1/(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
elif output_type=="log":
eqn = "exp(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
elif output_type=="sin":
eqn = "acos(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
elif output_type=="sqrt":
eqn = "(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")**2"
elif output_type=="squared":
eqn = "sqrt(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
elif output_type=="tan":
eqn = "atan(" + prefactors[i] + "+" + RPN_to_eq(express[i]) + ")"
eqns = eqns + [eqn]
errors = errors + [get_symbolic_expr_error(pathdir,filename,eqn)]
expr = parse_expr(eqn)
is_atomic_number = lambda expr: expr.is_Atom and expr.is_number
numbers_expr = [subexpression for subexpression in preorder_traversal(expr) if is_atomic_number(subexpression)]
compl = 0
for j in numbers_expr:
try:
compl = compl + get_number_DL(float(j))
except:
compl = compl + 1000000
# Add the complexity due to symbols
n_variables = len(expr.free_symbols)
n_operations = len(count_ops(expr,visual=True).free_symbols)
if n_operations!=0 or n_variables!=0:
compl = compl + (n_variables+n_operations)*np.log2((n_variables+n_operations))
complexity = complexity + [compl]
except:
continue
for i in range(len(complexity)):
PA.add(Point(x=complexity[i], y=errors[i], data=eqns[i]))
# run gradient descent of BF output parameters and add the results to the Pareto plot
for i in range(len(express)):
try:
bf_gd_update = RPN_to_pytorch(pathdir+filename,eqns[i])
PA.add(Point(x=bf_gd_update[1],y=bf_gd_update[0],data=bf_gd_update[2]))
except:
continue
except:
pass
#############################################################################################################################
# run BF on the data (*)
print("Checking for brute force * \n")
brute_force(pathdir_transformed,filename,BF_try_time,BF_ops_file_type,"*")
try:
# load the BF output data
bf_all_output = np.loadtxt("results.dat", dtype="str")
express = bf_all_output[:,2]
prefactors = bf_all_output[:,1]
prefactors = [str(i) for i in prefactors]
# Calculate the complexity of the bf expression the same way as for gradient descent case
complexity = []
errors = []
eqns = []
for i in range(len(prefactors)):
try:
if output_type=="":
eqn = prefactors[i] + "*" + RPN_to_eq(express[i])
elif output_type=="acos":
eqn = "cos(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
elif output_type=="asin":
eqn = "sin(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
elif output_type=="atan":
eqn = "tan(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
elif output_type=="cos":
eqn = "acos(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
elif output_type=="exp":
eqn = "log(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
elif output_type=="inverse":
eqn = "1/(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
elif output_type=="log":
eqn = "exp(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
elif output_type=="sin":
eqn = "acos(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
elif output_type=="sqrt":
eqn = "(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")**2"
elif output_type=="squared":
eqn = "sqrt(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
elif output_type=="tan":
eqn = "atan(" + prefactors[i] + "*" + RPN_to_eq(express[i]) + ")"
eqns = eqns + [eqn]
errors = errors + [get_symbolic_expr_error(pathdir,filename,eqn)]
expr = parse_expr(eqn)
is_atomic_number = lambda expr: expr.is_Atom and expr.is_number
numbers_expr = [subexpression for subexpression in preorder_traversal(expr) if is_atomic_number(subexpression)]
compl = 0
for j in numbers_expr:
try:
compl = compl + get_number_DL(float(j))
except:
compl = compl + 1000000
# Add the complexity due to symbols
n_variables = len(expr.free_symbols)
n_operations = len(count_ops(expr,visual=True).free_symbols)
if n_operations!=0 or n_variables!=0:
compl = compl + (n_variables+n_operations)*np.log2((n_variables+n_operations))
complexity = complexity + [compl]
except:
continue
# add the BF output to the Pareto plot
for i in range(len(complexity)):
PA.add(Point(x=complexity[i], y=errors[i], data=eqns[i]))
# run gradient descent of BF output parameters and add the results to the Pareto plot
for i in range(len(express)):
try:
bf_gd_update = RPN_to_pytorch(pathdir+filename,eqns[i])
PA.add(Point(x=bf_gd_update[1],y=bf_gd_update[0],data=bf_gd_update[2]))
except:
continue
except:
pass
#############################################################################################################################
# run polyfit on the data
print("Checking polyfit \n")
polyfit_result = polyfit(polyfit_deg, pathdir_transformed+filename)
eqn = str(polyfit_result[0])
# Calculate the complexity of the polyfit expression the same way as for gradient descent case
if output_type=="":
eqn = eqn
elif output_type=="acos":
eqn = "cos(" + eqn + ")"
elif output_type=="asin":
eqn = "sin(" + eqn + ")"
elif output_type=="atan":
eqn = "tan(" + eqn + ")"
elif output_type=="cos":
eqn = "acos(" + eqn + ")"
elif output_type=="exp":
eqn = "log(" + eqn + ")"
elif output_type=="inverse":
eqn = "1/(" + eqn + ")"
elif output_type=="log":
eqn = "exp(" + eqn + ")"
elif output_type=="sin":
eqn = "acos(" + eqn + ")"
elif output_type=="sqrt":
eqn = "(" + eqn + ")**2"
elif output_type=="squared":
eqn = "sqrt(" + eqn + ")"
elif output_type=="tan":
eqn = "atan(" + eqn + ")"
polyfit_err = get_symbolic_expr_error(pathdir,filename,eqn)
expr = parse_expr(eqn)
is_atomic_number = lambda expr: expr.is_Atom and expr.is_number
numbers_expr = [subexpression for subexpression in preorder_traversal(expr) if is_atomic_number(subexpression)]
complexity = 0
for j in numbers_expr:
complexity = complexity + get_number_DL(float(j))
try:
# Add the complexity due to symbols
n_variables = len(polyfit_result[0].free_symbols)
n_operations = len(count_ops(polyfit_result[0],visual=True).free_symbols)
if n_operations!=0 or n_variables!=0:
complexity = complexity + (n_variables+n_operations)*np.log2((n_variables+n_operations))
except:
pass
#run zero snap on polyfit output
PA_poly = ParetoSet()
PA_poly.add(Point(x=complexity, y=polyfit_err, data=str(eqn)))
PA_poly = add_snap_expr_on_pareto_polyfit(pathdir, filename, str(eqn), PA_poly)
for l in range(len(PA_poly.get_pareto_points())):
PA.add(Point(PA_poly.get_pareto_points()[l][0],PA_poly.get_pareto_points()[l][1],PA_poly.get_pareto_points()[l][2]))
print("Complexity RMSE Expression")
for pareto_i in range(len(PA.get_pareto_points())):
print(PA.get_pareto_points()[pareto_i])
return PA