print(str(symplified_best))
# output the top 3 champs
champs = 3
for i in range(champs):
ind = hof[i]
symplified_model = gep.simplify(ind)
print('\nSymplified best individual {}: '.format(i))
print(symplified_model)
print("raw indivudal:")
print(hof[i])
# we want to use symbol labels instead of words in the tree graph
rename_labels = {'add': '+', 'sub': '-', 'mul': '*', 'protected_div': '/'}
gep.export_expression_tree(best_ind, rename_labels,
'numerical_expression_tree.png')
# As we can see from the above simplified expression, the *truth model* has been successfully found.
# Due to the existence of Gaussian noise, the minimum mean absolute error （MAE) is still not zero even the best individual represents the true model.
# ## Visualization
# If you are interested in the expression tree corresponding to the individual, i.e., the genotype/phenotype system, *geppy* supports tree visualization by the `graph` and the `export_expression_tree` functions:
#
# - `graph` only outputs the nodes and links information to describe the tree topology, with which you can render the tree with tools you like;
# - `export_expression_tree` implements tree visualization with data generated by `graph` internally using the `graphviz` package.
#
# **Note**: even if the linear scaling is applied, here only the raw individual in GP (i.e., the one without linear scaling) is visualized.
# show the above image here for convenience
from IPython.display import Image
Image(filename='numerical_expression_tree.png')
print(str(symplified_best))
# output the top 3 champs
champs = 3
for i in range(champs):
ind = hof[i]
symplified_model = gep.simplify(ind)
print('\nSymplified best individual {}: '.format(i))
print(symplified_model)
print("raw indivudal:")
print(hof[i])
# we want to use symbol labels instead of words in the tree graph
rename_labels = {'add': '+', 'sub': '-', 'mul': '*', 'protected_div': '/'}
gep.export_expression_tree(best_ind, rename_labels, 'GEP_MT_ET.png')
# As we can see from the above simplified expression, the *truth model* has been successfully found. Due to the existence of Gaussian noise, the minimum mean absolute error （MAE) is still not zero even the best individual represents the true model.
# ## Visualization
# If you are interested in the expression tree corresponding to the individual, i.e., the genotype/phenotype system, *geppy* supports tree visualization by the `graph` and the `export_expression_tree` functions:
#
# - `graph` only outputs the nodes and links information to describe the tree topology, with which you can render the tree with tools you like;
# - `export_expression_tree` implements tree visualization with data generated by `graph` internally using the `graphviz` package.
#
# **Note**: even if the linear scaling is applied, here only the raw individual in GP (i.e., the one without linear scaling) is visualized.
# show the above image here for convenience
#from IPython.display import Image
#Image(filename='expression_tree.png')
file.close()
# In[68]:
# we want to use symbol labels instead of words in the tree graph
rename_labels = {
'add': '+',
'sub': '-',
'mul': '*',
'protected_div': '/',
'sin': 'sin',
'cos': 'cos',
'tan': 'tan'
}
gep.export_expression_tree(best_ind, rename_labels, 'results/heat_tree.pdf')
# ### Let's eyeball predicted vs actual data:
# In[76]:
#from matplotlib import pyplot
#pyplot.rcParams['figure.figsize'] = [20, 5]
#plotlen=200
#pyplot.plot(predPE.head(plotlen)) # predictions are in blue
#pyplot.plot(holdout.ut.head(plotlen)) # actual values are in orange
#pyplot.show()
#
#best_ind = hof[0]
#for gene in best_ind:
# print(gene.kexpression)
# In this problem, the final solution *best* seems more complicated than the true function $f$. Thus, it would be quite helpful if we can get a simplified version of the model we found by removing all the redundancies for better comparison and verification.*geppy* has provided a convenient function `simplify()` to perform symbolic simplification of the individual (solution) by leveraging the `sympy` package.
# In[14]:
symplified_best = gep.simplify(best)
print('Symplified best individual: ')
print(symplified_best)
# Clearly, after simplification the best individual evolved by GEP is just the ideal function $f$. More importantly, GEP can perform implicit variable (feature) selection effectively: though we provide it with four inputs, GEP only picks the three useful inputs `a, c, d`.
# ## Visualization
# If you are interested in the expression tree corresponding to the individual, i.e., the genotype/phenotype system, *geppy* supports tree visualization by the `graph` and the `export_expression_tree` functions:
#
# - `graph` only outputs the nodes and links information to describe the tree topology, with which you can render the tree with tools you like;
# - `export_expression_tree` implements tree visualization with data generated by `graph` internally using the `graphviz` package.
# In[15]:
rename_labels = {
'and_': '&',
'or_': '|',
'not_': '~'
} # we want use symbol labels instead of words in the tree graph
gep.export_expression_tree(best, rename_labels, 'data/bool_tree.png')
# In[17]:
# show the above image here for convenience
from IPython.display import Image
Image(filename='data/bool_tree.png')
str(datetime.datetime.now()))
print(hof[0])
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#Symbolic simplification of the final solution
# print the best symbolic regression we found:
best_ind = hof[0]
symplified_best = gep.simplify(best_ind)
from sympy import init_printing
init_printing()
#use str(symplified_best) to get the string of the symplified model
symplified_best
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#Visualization
#we want to use symbol labels instead of words in the tree graph
rename_labels = {'add': '+', 'sub': '-', 'mul': '*', 'protected_div': '/'}
gep.export_expression_tree(best_ind, rename_labels,
'F:/GEP-LR/synthetic-data-modeling-tree.png')
#show the above image here for convenience
from IPython.display import Image
Image(filename='F:/GEP-LR/synthetic-data-modeling-tree.png')
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#Plot maximum fitness values
import matplotlib.pyplot as plt
max_Fitness_values = log.select("max")
fig = plt.figure(figsize=(15, 5))
plt.plot(max_Fitness_values, '-bo') # predictions are in red
plt.show()
fig.savefig('F:/GEP-LR/synthetic-data-modeling-maxFitness.eps',
dpi=300,
format='eps')
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#Calculate the final estimated probability
print(hof[0])
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#Symbolic simplification of the final solution
#print the best symbolic regression we found:
best_ind = hof[0]
symplified_best = gep.simplify(best_ind)
from sympy import init_printing
init_printing()
#use str(symplified_best) to get the string of the symplified model
symplified_best
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#Visualization
#use symbol labels instead of words in the tree graph
rename_labels = {'add': '+', 'sub': '-', 'mul': '*', 'protected_div': '/'}
gep.export_expression_tree(best_ind, rename_labels, 'F:/GEP-LR/MPM-tree.png')
#show the above image here for convenience
from IPython.display import Image
Image(filename='F:/GEP-LR/MPM-tree.png')
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#Plot maximum fitness values
import matplotlib.pyplot as plt
max_Fitness_values = log.select("max")
fig = plt.figure(figsize=(15, 5))
plt.plot(max_Fitness_values, '-bo') # predictions are in red
plt.show()
fig.savefig('F:/GEP-LR/MPM-maxFitness.eps', dpi=300, format='eps')
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#Calculate the final estimated probability
