from read_PLAID_data import read_processed_data
from linear import SingleLayerModel, DoubleLayerModel, MultiLayerModer
def confusion_matrix(preds, labels, conf_matrix):
for p, l in zip(preds, labels):
conf_matrix[p, l] += 1
return conf_matrix
process_start_time = time.time()
label_transformer = {'I': 0, 'R': 1, 'NL': 0}
feature_select = ['i_pp_rms', 'P_F', 'i_hp1', 'i_hm3', 'i_hp3', 'z_hp3']
x, y = read_processed_data('load',
feature_select=feature_select,
direaction=1,
offset=30,
Transformer=label_transformer)
print('finished reading data, cost %2.2f s' %
(time.time() - process_start_time))
x_mean = np.mean(x, axis=0)
x_std = np.std(x, axis=0)
for i in range(len(x)):
for j in range(len(x[0])):
if x_std[j] != 0:
x[i][j] = (x[i][j] - x_mean[j]) / x_std[j]
x_train = torch.tensor(x).float()
y_train = torch.tensor(y.astype(float)).float()
dataset = Data.TensorDataset(x_train, y_train)
import sys
from sklearn import tree
from sklearn.model_selection import train_test_split
sys.path.append('data/')
from read_PLAID_data import read_processed_data, get_feature_name
x, y, index = read_processed_data('type',
selected_label=[
'Fridge',
'Air Conditioner',
],
direaction=1,
offset=30,
each_lenth=1,
source='submetered_process/training/')
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.5,
random_state=0)
x_train = x_train[:, 1:]
x_test = x_test[:, 1:]
feature_select = get_feature_name(
'/home/chaofan/powerknowledge/data/source/submetered_process/training/')
for md in range(1, 10):
for msl in [1, 5, 10, 15, 20, 25, 50, 100]:
decision_tree = tree.DecisionTreeClassifier(max_depth=md,
min_samples_leaf=msl)
decision_tree.fit(x_train, y_train)
score = decision_tree.score(x_test, y_test)
print('[max_depth:%02d,min_samples_leaf:%02d] score %.6f' %
(md, msl, score))
import sys
import time
from sklearn.model_selection import train_test_split
from sklearn import tree
import numpy as np
import joblib
sys.path.append('data/')
sys.path.append('data/source/')
sys.path.append('data/model/deep_learning_model')
sys.path.append('data/model/knowledge_model')
from read_PLAID_data import read_processed_data
start_reading_time = time.time()
x_is_cool, y_is_cool = read_processed_data('is_cool',
type_header='extra label',
direaction=1,
offset=30)
x_is_cool = x_is_cool[:, 1:]
x_is_heat, y_is_heat = read_processed_data('is_heat',
type_header='extra label',
direaction=1,
offset=30)
x_is_heat = x_is_heat[:, 1:]
x_is_light, y_is_light = read_processed_data('is_light',
type_header='extra label',
direaction=1,
offset=30)
x_is_light = x_is_light[:, 1:]
y_epoch.numpy())
epoch_loss += loss.item()
train_time = time.time() - train_start_time
return epoch_acc, train_time
def confusion_matrix(preds, labels, conf_matrix):
for p, l in zip(preds, labels):
conf_matrix[p, l] += 1
return conf_matrix
process_start_time = time.time()
label_transformer = {'I': 0, 'R': 1, 'NL': 0}
x, y = read_processed_data('load',
direaction=1,
offset=30,
Transformer=label_transformer)
print('finished reading data, cost %2.2f s' %
(time.time() - process_start_time))
x_mean = np.mean(x, axis=0)
x_std = np.std(x, axis=0)
for i in range(len(x)):
for j in range(len(x[0])):
if x_std[j] != 0:
x[i][j] = (x[i][j] - x_mean[j]) / x_std[j]
feature_len = x.shape[1]
data_len = x.shape[0]
acc_matrix = np.zeros([feature_len, feature_len])
for a in range(feature_len):
import numpy as np
import time
import sys
sys.path.append(r'data/')
from read_PLAID_data import read_processed_data
process_start_time = time.time()
label_transformer = {'0': 0, '1': 1}
x, y = read_processed_data('is_heat',
type_header='extra label',
direaction=1,
offset=30,
Transformer=label_transformer)
print('finished reading data, cost %2.2f s' %
(time.time() - process_start_time))
x = x[:, 1:]
np.savetxt('model/knowledge_model/heater/y_label.csv', y, delimiter=',')
np.savetxt('model/knowledge_model/heater/x.csv', x, delimiter=',')
import sys
from sklearn import tree
from sklearn.model_selection import train_test_split
sys.path.append('data/')
from read_PLAID_data import read_processed_data
x, y = read_processed_data('type',
selected_label=[
'Laptop', 'Compact Fluorescent Lamp',
'Incandescent Light Bulb'
],
direaction=1,
offset=30,
each_lenth=1)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.5,
random_state=0)
for md in range(1, 10):
for msl in [1, 5, 10, 15, 20, 25, 50, 100]:
decision_tree = tree.DecisionTreeClassifier(max_depth=md,
min_samples_leaf=msl)
decision_tree.fit(x_train, y_train)
score = decision_tree.score(x_test, y_test)
print('[max_depth:%02d,min_samples_leaf:%02d] score %.6f' %
(md, msl, score))
y_predict = decision_tree.predict(x_test)
