class OfflineLearning():
def __init__(self, data_set_size=-1):
self.data_set_size = data_set_size
self.dh = DataHandler(
data_path='/media/cem/ROSDATA/ros_data/features/csv/')
self.dh.collect_data(self.data_set_size)
def get_best_fit(self, n_try, test_size):
best_trials = []
for a in self.dh.actions:
trials = []
for i in range(n_try):
a.split_train_test(test_size)
a.scale_dataset()
a.offline_train()
print a.get_regression_score(), a.gmm.score(a.y_test)
trials.append(
Trial(a, a.get_regression_score(), a.gmm.score(a.y_test)))
# print trials
trials.sort(key=lambda t: t.cluster_score, reverse=True)
best_trials.append(trials[0])
return best_trials
import numpy as np
from data_handler import DataHandler
import pyprind
import pprint
dh = DataHandler(data_path='/Volumes/ROSDATA/ros_data/features/test_data/')
dh.collect_data()
a = dh.actions[0]
a.load_models()
pp = pprint.PrettyPrinter(indent=2)
clusters = {}
errs = []
for s in a.samples:
obj = s.obj
x = a.object_scaler.transform(s.X.reshape(1, -1)).flatten()
y = a.effect_scaler.transform(s.y.reshape(1, -1)).flatten()[0:3]
y_predicted = a.nn.predict(x.reshape(1, -1)).flatten()
err = np.linalg.norm(y_predicted - y)
errs.append(err)
obj_name = obj.name
obj_pos = str(obj.pose)
obj_id = obj.id
if obj_id in dh.dropped:
obj_pos += '*'
class OnlineLearning():
def __init__(self, data_set_size=-1):
self.data_set_size = data_set_size
self.dh = DataHandler()
self.dh.collect_data(self.data_set_size)
def train(self):
for a in self.dh.actions:
a.split_train_test(0.01)
a.scale_dataset()
print a.name, len(a.X_train), len(a.X_test)
bar = pyprind.ProgBar(len(a.X_train),
track_time=False,
title='Training %s...' % (a.name))
for i in range(len(a.X_train)):
x = a.X_train[i]
y = a.y_train_p[i]
a.nn.fit(x.reshape(1, -1),
y.reshape(1, -1),
verbose=0,
batch_size=1,
epochs=10)
e_min_distance = a.effect_som.get_min_distance(y)
if e_min_distance == -1 or e_min_distance >= 0.08:
a.effect_som.add_neuron(y)
else:
a.effect_som.update(y)
bar.update()
pp = pprint.PrettyPrinter(indent=2)
clusters = {}
for i in range(len(a.X_test)):
x = a.X_test[i]
y = a.y_test_p[i]
obj = a.test_samples[i].obj
y_predicted = a.nn.predict(x.reshape(1, -1)).flatten()
err = np.linalg.norm(y - y_predicted)
obj_name = obj.name
obj_pos = str(obj.pose)
obj_id = obj.id
if obj_id in self.dh.dropped:
obj_pos += '*'
if err > 0.05:
obj_pos += 'H'
cid = a.effect_som.winner(y_predicted)
if cid in clusters:
objs = clusters[cid]
if obj_name in objs:
objs[obj_name].append(obj_pos)
else:
objs[obj_name] = [obj_pos]
else:
clusters[cid] = {obj_name: [obj_pos]}
print "Object:", obj.id
print "Error:", err
print "Cluster:", cid
print "============================"
pp.pprint(clusters)
print "#neurons:", len(a.effect_som.weights)
a.save_models()
import pickle
from sklearn.preprocessing import minmax_scale
from data_handler import DataHandler
import numpy as np
import math
dh = DataHandler(data_path='/media/cem/ROSDATA/ros_data/features/csv/')
dh.collect_data(-1)
for a in dh.actions:
gd = pickle.load(open('/home/cem/learning/models/%s_gradient_descent' % (a.name),'rb'))
a.split_train_test(1)
print gd.get_rmse(a.X_test,a.y_test)
def collect_data(self):
DataHandler.collect_data(self)
