for i in pdata_nearest_neigh:
(kx, kd) = k_nearest_cluster(nxs, nds, i)
train_x = train_x.join(kx)
test_x = test_x.join(kd)
if configure_verbose_mode:
print("Finished: algorithm nearest")
if pdata_regression_sgd:
nxs = dtrain[args_x[1:]].as_matrix()
nds = dtest[args_x[1:]].as_matrix()
weights = dtrain[args_y[0]].as_matrix()
aux_end = int(len(nxs)*0.9)#0.9 is the best value!
new_feature_train = regression_sgd(nxs[:aux_end,:],weights[:aux_end],nxs)
new_feature_test = regression_sgd(nxs,weights,nds)
new_feature_train = ps.DataFrame([i for i in new_feature_train],columns = ["Mnew_sgd"])
new_feature_test = ps.DataFrame(([i for i in new_feature_test]),columns = ["Mnew_sgd"])
train_x = train_x.join(new_feature_train)
test_x = test_x.join(new_feature_test)
if configure_verbose_mode:
print("Finished: regression sgd")
if pdata_additional:
train_x = add_features(train_x)
test_x = add_features(test_x)
if configure_verbose_mode:
print("Finished: feature engeneering")
#if exclude_sth:
###
if pdata_add_features:
train_x = add_features(train_x)
test_x = add_features(test_x)
if add_column_as_regression_sgd:
#with all data
#nxs = train_x.as_matrix()
#nds = test_x.as_matrix()
#or not
nxs = dtrain[args_x[1:]].as_matrix()
nds = dtest[args_x[1:]].as_matrix()
weights = dtrain[args_y[0]].as_matrix()
aux_end = int(len(nxs)*pdata_sgd)
new_feature_train = regression_sgd(nxs[:aux_end,:],weights[:aux_end],nxs)
new_feature_test = regression_sgd(nxs,weights,nds)
new_feature_train = ps.DataFrame([i for i in new_feature_train],columns = ["Mnew_sgd"])
new_feature_test = ps.DataFrame(([i for i in new_feature_test]),columns = ["Mnew_sgd"])
train_x = train_x.join(new_feature_train)
test_x = test_x.join(new_feature_test)
#xs = np.append(xs, new_feature_train, 1)
#ds = np.append(ds, new_feature_test, 1)
#Jet_num
#New_sum_jet_pt
#new_frac_lep_pt
#if threshold_filter_features>0:
# fs = ps.read_csv(feature_importance_file,',',header=0)
# print(len(fs.columns.values))
# fs = fs.dropna(axis=1,how='all')
import sys, os #is necessary for relative import
sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'components')) #is necessary for relative import
from reading_train_data import txs, tys
from reading_test_data import tds, tis
from write_results import write_predictions,write_predictions2
from funcs import get_threshold, regression_sgd
from sklearn import metrics
from sklearn.linear_model import *
import numpy as np
predicted = regression_sgd(txs,tys[:,0],tds,False)
threshold = get_threshold(tys[:,0],tys[:,1])
write_predictions2("regression_sgd.csv",tis,predicted,threshold)
#############################
exit()
#############################
#logical EOF
model = LogisticRegression()
model.fit(txs, tys[:,1])
#print(model)
# make predictions
#expected = train_data_y[:,1]
#predicted = model.predict(test_data[:,1:])
#probability = model.decision_function(test_data[:,1:])
##with all features result is 2.01342 ~ 1508 place
#write_predictions("regression.csv",test_data[:,0],probability,predicted)