def rpart_fit(self, known_data, parameter_list, bit_string="11111"):
"""
11-09-05
1st use known_data to get the fit model
2nd use the fit model to do prediction on all_data, result is prob for each class
11-09-05 add rpart_cp
11-17-05
add loss_matrix, prior_prob
return two pred
11-23-05
split fit and predict. rpart_fit_and_predict() is split into rpart_fit() and rpart_predict()
11-27-05
r cleanup
03-17-06
use parameter_list instead
"""
if self.debug:
sys.stderr.write("Doing rpart_fit...\n")
# 03-17-06
rpart_cp, loss_matrix, prior_prob = parameter_list
# 11-27-05 r cleanup
from rpy import r
r.library("rpart")
coeff_name_list = ["p_value", "recurrence", "connectivity", "cluster_size", "gradient"]
formula_list = []
for i in range(len(bit_string)):
if bit_string[i] == "1":
formula_list.append(coeff_name_list[i])
# 11-17-05 transform into array
known_data = array(known_data)
set_default_mode(NO_CONVERSION)
data_frame = r.as_data_frame(
{
"p_value": known_data[:, 0],
"recurrence": known_data[:, 1],
"connectivity": known_data[:, 2],
"cluster_size": known_data[:, 3],
"gradient": known_data[:, 4],
"is_correct": known_data[:, -1],
}
)
if prior_prob:
prior_prob = [prior_prob, 1 - prior_prob] # get the full list
fit = r.rpart(
r("is_correct~%s" % "+".join(formula_list)),
data=data_frame,
method="class",
control=r.rpart_control(cp=rpart_cp),
parms=r.list(prior=prior_prob, loss=r.matrix(loss_matrix)),
)
else:
fit = r.rpart(
r("is_correct~%s" % "+".join(formula_list)),
data=data_frame,
method="class",
control=r.rpart_control(cp=rpart_cp),
parms=r.list(loss=r.matrix(loss_matrix)),
)
del data_frame
if self.debug:
sys.stderr.write("Done rpart_fit.\n")
return fit
def rpart_fit_and_predict(self, all_data, known_data, rpart_cp, loss_matrix, prior_prob, bit_string='11111'):
"""
11-09-05
1st use known_data to get the fit model
2nd use the fit model to do prediction on all_data, result is prob for each class
11-09-05 add rpart_cp
11-17-05
add loss_matrix, prior_prob
return two pred
"""
sys.stderr.write("rpart fitting and predicting...\n")
r.library("rpart")
coeff_name_list = ['p_value', 'recurrence', 'connectivity', 'cluster_size', 'gradient']
formula_list = []
for i in range(len(bit_string)):
if bit_string[i] == '1':
formula_list.append(coeff_name_list[i])
#11-17-05 transform into array
all_data = array(all_data)
known_data = array(known_data)
set_default_mode(NO_CONVERSION)
data_frame = r.as_data_frame({"p_value":known_data[:,0], "recurrence":known_data[:,1], "connectivity":known_data[:,2], \
"cluster_size":known_data[:,3], "gradient":known_data[:,4], "is_correct":known_data[:,-1]})
if prior_prob:
prior_prob = [prior_prob, 1-prior_prob] #get the full list
fit = r.rpart(r("is_correct~%s"%'+'.join(formula_list)), data=data_frame, method="class", control=r.rpart_control(cp=rpart_cp),\
parms=r.list(prior=prior_prob, loss=r.matrix(loss_matrix) ) )
else:
fit = r.rpart(r("is_correct~%s"%'+'.join(formula_list)), data=data_frame, method="class", control=r.rpart_control(cp=rpart_cp),\
parms=r.list(loss=r.matrix(loss_matrix) ) )
set_default_mode(BASIC_CONVERSION)
pred_training = r.predict(fit, data_frame, type=["class"])
del data_frame
set_default_mode(NO_CONVERSION)
all_data_frame = r.as_data_frame({"p_value":all_data[:,0], "recurrence":all_data[:,1], "connectivity":all_data[:,2], \
"cluster_size":all_data[:,3], "gradient":all_data[:,4], "is_correct":all_data[:,-1]})
set_default_mode(BASIC_CONVERSION)
pred = r.predict(fit, all_data_frame, type=["class"]) #11-17-05 type=c("class")
del all_data_frame
sys.stderr.write("Done rpart fitting and predicting.\n")
return pred, pred_training