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 randomForest_fit(self, known_data, parameter_list, bit_string="1111111"):
"""
03-17-06
2006-10-302006-10-30, add avg_degree(vertex_gradient) and unknown_cut_off
"""
if self.debug:
sys.stderr.write("Fitting randomForest...\n")
mty = parameter_list[0]
from rpy import r
r._libPaths(
os.path.join(lib_path, "R")
) # better than r.library("randomForest", lib_loc=os.path.join(lib_path, "R")) (see plone doc)
r.library("randomForest")
coeff_name_list = [
"p_value",
"recurrence",
"connectivity",
"cluster_size",
"gradient",
"avg_degree",
"unknown_ratio",
] # 2006-10-30
formula_list = []
for i in range(len(bit_string)):
if bit_string[i] == "1":
formula_list.append(coeff_name_list[i])
formula = r("is_correct~%s" % "+".join(formula_list))
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],
"avg_degree": known_data[:, 5],
"unknown_ratio": known_data[:, 6],
"is_correct": r.factor(known_data[:, -1]),
}
) # 03-17-06, watch r.factor #2006-10-30
if mty > 0:
fit = r.randomForest(formula, data=data_frame, mty=mty)
else:
fit = r.randomForest(formula, data=data_frame)
del data_frame
if self.debug:
sys.stderr.write("Done fitting randomForest.\n")
return fit
