def rpart_predict(self, fit_model, data):
"""
11-23-05
split from rpart_fit_and_predict()
"""
if self.debug:
sys.stderr.write("Doing rpart_predict...\n")
data = array(data)
set_default_mode(NO_CONVERSION)
data_frame = r.as_data_frame(
{
"p_value": data[:, 0],
"recurrence": data[:, 1],
"connectivity": data[:, 2],
"cluster_size": data[:, 3],
"gradient": data[:, 4],
"is_correct": data[:, -1],
}
)
set_default_mode(BASIC_CONVERSION)
pred = r.predict(fit_model, data_frame, type=["class"]) # 11-17-05 type=c("class")
del data_frame
if self.debug:
sys.stderr.write("Done rpart_predict.\n")
return pred
def randomForest_predict(self, fit_model, data):
"""
03-17-06
2006-10-30, add avg_degree(vertex_gradient) and unknown_cut_off
"""
if self.debug:
sys.stderr.write("Predicting by randomForest...\n")
data = array(data)
set_default_mode(NO_CONVERSION)
data_frame = r.as_data_frame(
{
"p_value": data[:, 0],
"recurrence": data[:, 1],
"connectivity": data[:, 2],
"cluster_size": data[:, 3],
"gradient": data[:, 4],
"avg_degree": data[:, 5],
"unknown_ratio": data[:, 6],
"is_correct": r.factor(data[:, -1]),
}
)
set_default_mode(BASIC_CONVERSION)
pred = r.predict(fit_model, data_frame)
del data_frame
if self.debug:
sys.stderr.write("Done randomForest prediction.\n")
return pred
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
def __call__(self, x, se=False):
"""
Predict new values with smoother
x - new values (must be same dimensions as input; check self.nvar)
se - if True, return standard errors for each value as well (default False)
"""
result = r.predict(self.smoother, x, se=se)
if se:
return nx.asarray(result['fit']), nx.asarray(result['se.fit'])
else:
return nx.asarray(result)
def __call__(self, x, se=False):
"""
Predict new values with smoother
x - new values (must be same dimensions as input; check self.nvar)
se - if True, return standard errors for each value as well (default False)
"""
result = r.predict(self.smoother, x, se=se)
if se:
return nx.asarray(result['fit']), nx.asarray(result['se.fit'])
else:
return nx.asarray(result)
def estimate_pi0(self, lambda_list, pi0_list):
"""
01-19-06
Storey2003, (natural) cubic spline, df=3
"""
sys.stderr.write("Estimating pi0...\n")
rpy.set_default_mode(rpy.NO_CONVERSION)
s = r.smooth_spline(lambda_list, pi0_list, df=3)
rpy.set_default_mode(rpy.BASIC_CONVERSION)
estimated_pi0 = r.predict(s, 1)['y']
print "\t estimated_pi0:", estimated_pi0
sys.stderr.write("Done.\n")
return estimated_pi0
def estimate_pi0(self, lambda_list, pi0_list):
"""
01-19-06
Storey2003, (natural) cubic spline, df=3
"""
sys.stderr.write("Estimating pi0...\n")
rpy.set_default_mode(rpy.NO_CONVERSION)
s = r.smooth_spline(lambda_list, pi0_list, df=3)
rpy.set_default_mode(rpy.BASIC_CONVERSION)
estimated_pi0 = r.predict(s,1)['y']
print "\t estimated_pi0:", estimated_pi0
sys.stderr.write("Done.\n")
return estimated_pi0
def fitPoly(xarray, yarray, order):
r.lm.local_mode(rpy.NO_CONVERSION)
xl=list(xarray)
yl=list(yarray)
modelDef = "y ~ poly(x,%d)" % order
model=r.lm(r(modelDef), data=r.data_frame(x=xl,y=yl))
pred=r.predict(model)
# pred is now a dict with keys from '1' to 'N', where N is the size of xl
predvals = []
for i in range(len(xl)):
predvals.append(pred[str(i+1)])
return(xl, predvals)
