def logistic_regression_prediction_epoch_lt12(data_version,penalty='l1'):
X = diff_length_csv('temperature_lt12.csv')
X = pad_sequences(X, maxlen=50, padding='post', truncating='post', value=0, dtype=float)
X = np.array(X, dtype=float)
X2 = same_length_csv('cap_feature_lt12.csv')
# nb_x_train = read_case_nb(f_in='nb_x_train_%d.dat'%(data_version))
# nb_x_test = read_case_nb(f_in='nb_x_test_%d.dat'%(data_version))
nb_x_train =read_case_nb(f_in ='nb_train_lt12_cv%d.dat'%(data_version))
nb_x_test =read_case_nb(f_in ='nb_test_lt12_cv%d.dat'%(data_version))
y = same_length_csv('number_category_lt12.csv')
X_con = np.concatenate((X2, X), axis=1)
X_train, X_test, y_train, y_test, = get_train_test_data(X_con, y, nb_x_train, nb_x_test, )
acc_list = []
for i in range(nb_epochs):
lr = LogisticRegression(penalty=penalty, fit_intercept=True, max_iter=i, warm_start=True)
lr = lr.fit(X_train, y_train, )
score = lr.score(X_test, y_test)
acc_list.append(score)
plot(range(0, nb_epochs), acc_list, label='temp_acc')
acc_list_100_110 = acc_list[99:109]
acc_list_200 = acc_list[0:200]
print(len(acc_list_200))
acc_list_210 = acc_list[200:]
print(acc_list_210)
print(len(acc_list_210))
acc_list_sored = sorted(acc_list_200, reverse=True)
print(acc_list)
title('temp_study_%d' % (data_version))
print('temp_study_%d\n' % (data_version))
print("top-10 mean: %.3f" % np.mean(np.array(acc_list_sored[:10])))
print("top-50 mean: %.3f" % np.mean(np.array(acc_list_sored[:50])))
# print("last-10 mean: %.3f" % np.mean(np.array(acc_list_210)))
print("acc_100-110 mean: %.3f" % np.mean(np.array(acc_list_100_110)))
def para_prediction(model, data_version):
X = same_length_csv('cap_feature_2.csv')
y = same_length_csv('number_category.csv')
nb_x_train = read_case_nb(f_in='nb_x_train_%d.dat' % data_version)
nb_x_test = read_case_nb(f_in='nb_x_test_%d.dat' % data_version)
x_train, x_test, y_train, y_test = get_train_test_data(
X,
y,
nb_x_train,
nb_x_test,
)
probability_test = (sum(y_test) - len(y_test)) / len(y_test)
print('probability_test:', probability_test)
y_train = category_to_target(y_train)
y_test = category_to_target(y_test)
model = model
print('Train...')
acc_list = []
train_loss_list = []
test_loss_list = []
for epoch in range(nb_epochs):
# print('Train...')
model.fit(x_train,
y_train,
batch_size=batch_size,
nb_epoch=1,
validation_split=0.05)
train_score, train_acc = model.evaluate(x_train,
y_train,
batch_size=batch_size)
score, acc = model.evaluate(x_test, y_test, batch_size=batch_size)
acc_list.append(acc)
train_loss_list.append(train_score)
test_loss_list.append(score)
print('Test score:', score)
print('Test accuracy:', acc)
results = ""
for i, acc in enumerate(acc_list):
if acc > 0.72:
if acc > 0.74:
results += '\033[1;31m' + str(i + 1) + ':' + str(
acc) + '\033[0m' + '; '
else:
results += '\033[1;34m' + str(i + 1) + ':' + str(
acc) + '\033[0m' + '; '
else:
results += str(i + 1) + ':' + str(acc) + '; '
plot(range(0, nb_epochs), acc_list, label='feature')
plot(range(0, nb_epochs), train_loss_list, label='train_loss')
plot(range(0, nb_epochs), test_loss_list, label='test_loss')
acc_list = sorted(acc_list, reverse=True)
print(acc_list)
print("top-10 mean: %.3f" % np.mean(np.array(acc_list[:10])))
print("top-50 mean: %.3f" % np.mean(np.array(acc_list[:50])))
def gbdt_feature_prediction_lt12(data_version):
X2 = same_length_csv('cap_feature_lt12.csv')
nb_x_train = read_case_nb(f_in='nb_train_lt12_cv%d.dat' % (data_version))
nb_x_test = read_case_nb(f_in='nb_test_lt12_cv%d.dat' % (data_version))
y = same_length_csv('number_category_lt12.csv')
X_train, X_test, y_train, y_test, = get_train_test_data(X2, y, nb_x_train, nb_x_test, )
lr = GradientBoostingClassifier(n_estimators=100,learning_rate=0.01,max_depth=3)
lr = lr.fit(X_train, y_train, )
score = lr.score(X_test, y_test)
print(score)
return score
def logistic_regression_feature_prediction_lt12(data_version,penalty ='l1'):
X2 = same_length_csv('cap_feature_lt12.csv')
nb_x_train =read_case_nb(f_in ='nb_train_lt12_cv%d.dat'%(data_version))
nb_x_test =read_case_nb(f_in ='nb_test_lt12_cv%d.dat'%(data_version))
y = same_length_csv('number_category_lt12.csv')
X_train, X_test, y_train, y_test, = get_train_test_data(X2, y, nb_x_train, nb_x_test, )
lr = LogisticRegression(penalty=penalty, fit_intercept=True, max_iter=200, warm_start=True,tol=0.0001)
lr = lr.fit(X_train, y_train, )
# print(lr.coef_)
score = lr.score(X_test, y_test)
print(score)
return score
def temp_mutilstm_study(model):
X = diff_length_csv('temperature.csv')
X = pad_sequences(X,
maxlen=time_steps,
padding='post',
truncating='post',
value=padding_value,
dtype=float)
print(X.shape)
y = same_length_csv('number_category.csv')
nb_x_train = read_case_nb(f_in='nb_x_train_%d.dat' % (data_version))
nb_x_test = read_case_nb(f_in='nb_x_test_%d.dat' % (data_version))
x_train, x_test, y_train, y_test, = get_train_test_data(
X,
y,
nb_x_train,
nb_x_test,
)
y_train = category_to_target(y_train)
y_test = category_to_target(y_test)
x_train = step_change_5(x_train)
x_test = step_change_5(x_test)
model = model
# test
acc_list = []
train_score_list = []
test_score_list = []
for epoch in range(nb_epochs):
print('Train...')
model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=1,
shuffle=True,
verbose=1)
train_score, train_acc = model.evaluate(x_train,
y_train,
batch_size=batch_size)
score, acc = model.evaluate(x_test, y_test, batch_size=batch_size)
acc_list.append(acc)
train_score_list.append(train_score)
test_score_list.append(score)
print('Test score:', score)
print('Test accuracy:', acc)
# subplot(2,3,data_version)
plot(range(0, nb_epochs), acc_list, label='temp_acc')
plot(range(0, nb_epochs), train_score_list, label='train_loss')
plot(range(0, nb_epochs), test_score_list, label='test_loss')
acc_list_100_110 = acc_list[99:109]
acc_list = sorted(acc_list, reverse=True)
print(acc_list)
title('temp_study_%d' % (data_version))
print('temp_study_%d\n' % (data_version))
print("top-10 mean: %.3f" % np.mean(np.array(acc_list[:10])))
print("top-50 mean: %.3f" % np.mean(np.array(acc_list[:50])))
print("acc_100-110 mean: %.3f" % np.mean(np.array(acc_list_100_110)))
def gbdt_merge_prediction_lt12(data_version):
X = diff_length_csv('temperature_lt12.csv')
X = pad_sequences(X, maxlen=50, padding='post', truncating='post', value=0, dtype=float)
X = np.array(X, dtype=float)
X2 = same_length_csv('cap_feature_lt12.csv')
# nb_x_train = read_case_nb(f_in='nb_x_train_%d.dat'%(data_version))
# nb_x_test = read_case_nb(f_in='nb_x_test_%d.dat'%(data_version))
nb_x_train =read_case_nb(f_in ='nb_train_lt12_cv%d.dat'%(data_version))
nb_x_test =read_case_nb(f_in ='nb_test_lt12_cv%d.dat'%(data_version))
y = same_length_csv('number_category_lt12.csv')
X_con = np.concatenate((X2, X), axis=1)
X_train, X_test, y_train, y_test, = get_train_test_data(X_con, y, nb_x_train, nb_x_test, )
lr = GradientBoostingClassifier(n_estimators=100,learning_rate=0.01,max_depth=3)
lr = lr.fit(X_train, y_train, )
score = lr.score(X_test, y_test)
print(score)
return score
def logistic_regression_prediction_lt12(data_version,penalty='l1'):
X = diff_length_csv('temperature_lt12.csv')
X = pad_sequences(X, maxlen=50, padding='post', truncating='post', value=0, dtype=float)
X = np.array(X, dtype=float)
X2 = same_length_csv('cap_feature_lt12.csv')
# nb_x_train = read_case_nb(f_in='nb_x_train_%d.dat'%(data_version))
# nb_x_test = read_case_nb(f_in='nb_x_test_%d.dat'%(data_version))
nb_x_train =read_case_nb(f_in ='nb_train_lt12_cv%d.dat'%(data_version))
nb_x_test =read_case_nb(f_in ='nb_test_lt12_cv%d.dat'%(data_version))
y = same_length_csv('number_category_lt12.csv')
X_con = np.concatenate((X2, X), axis=1)
X_train, X_test, y_train, y_test, = get_train_test_data(X_con, y, nb_x_train, nb_x_test, )
lr =LogisticRegression(penalty=penalty,fit_intercept=True,max_iter=200,tol=0.00005)
lr =lr.fit(X_train,y_train,)
# print(lr.coef_)
score =lr.score(X_test,y_test)
print(score)
return score
def gbdt_lstm():
temp_x, temp_y = get_train_fun()
X = same_length_csv('cap_feature.csv')
print(X.shape)
y = same_length_csv('number_category.csv')
# nb_x_train = read_case_nb(f_in='nb_x_train_%d.dat'%(data_version))
# nb_x_test = read_case_nb(f_in='nb_x_test_%d.dat'%(data_version))
nb_x_train = read_case_nb(f_in='nb_train_cv%d.dat' % (data_version))
nb_x_test = read_case_nb(f_in='nb_test_cv%d.dat' % (data_version))
X_train, X_test, y_train, y_test, = get_train_test_data(
X,
y,
nb_x_train,
nb_x_test,
)
# y_train = category_to_target(y_train)
# y_test = category_to_target(y_test)
temp_1_10_train, temp_1_10_test, temp_2_11_train, temp_2_11_test = get_train_test_data(
temp_x, temp_y, nb_x_train, nb_x_test)
temp_1_10_train = reshape_dataset(np.array(temp_1_10_train))
temp_2_11_train = reshape_dataset(temp_2_11_train)
temp_1_10_test = reshape_dataset(temp_1_10_test)
temp_2_11_test = reshape_dataset(temp_2_11_test)
input_temp = Input(shape=(10, 1), name='input_temp')
lstm_temp = LSTM(16, return_sequences=True, name='lstm_temp')(input_temp)
lstm_temp = Dropout(0.25)(lstm_temp)
dense_temp = Dense(1, name='dense_temp', activation='relu')(lstm_temp)
model = Model(inputs=input_temp, outputs=dense_temp)
model.compile(
loss={'dense_temp': 'mse'},
optimizer=Adam(lr=0.0003, clipnorm=1.),
metrics={'dense_temp': 'mse'},
)
model.summary()
intermediate_layer_model = Model(
input=model.input, output=model.get_layer('dense_temp').output)
score_list = []
for epoch in range(nb_epochs):
print('Train...')
model.fit([temp_1_10_train], [temp_2_11_train],
batch_size=batch_size,
epochs=1,
shuffle=True,
verbose=True)
train_temp = intermediate_layer_model.predict(temp_1_10_train)
test_temp = intermediate_layer_model.predict(temp_1_10_test)
train_temp = np.reshape(
train_temp,
newshape=(train_temp.shape[0],
train_temp.shape[1] * train_temp.shape[2]))
test_temp = np.reshape(
test_temp,
newshape=(test_temp.shape[0],
test_temp.shape[1] * test_temp.shape[2]))
x_epoch_train = np.concatenate([train_temp, X_train], axis=1)
x_epoch_test = np.concatenate([test_temp, X_test], axis=1)
print(x_epoch_train.shape)
lr = GradientBoostingClassifier(n_estimators=100,
learning_rate=0.01,
max_depth=3)
lr = lr.fit(
x_epoch_train,
y_train,
)
score = lr.score(x_epoch_test, y_test)
print(score)
score_list.append(score)
plot(range(0, nb_epochs), score_list, label='temp_acc')
acc_list_100_110 = score_list[99:109]
acc_list = sorted(score_list, reverse=True)
print(acc_list)
title('temp_study_%d' % (data_version))
print('temp_study_%d\n' % (data_version))
print("top-10 mean: %.3f" % np.mean(np.array(acc_list[:10])))
print("top-50 mean: %.3f" % np.mean(np.array(acc_list[:50])))
print("acc_100-110 mean: %.3f" % np.mean(np.array(acc_list_100_110)))
loss_weights={
'dense_softmax': 0.1,
'dense_temp': 1
})
model.summary()
return model
if __name__ == '__main__':
# model =merge_predict_next_temp_model()
model = new_merge_predict_next_temp_model()
temp_x, temp_y = get_train_fun()
X = same_length_csv('cap_feature.csv')
print(X.shape)
y = same_length_csv('number_category.csv')
# nb_x_train = read_case_nb(f_in='nb_x_train_%d.dat'%(data_version))
# nb_x_test = read_case_nb(f_in='nb_x_test_%d.dat'%(data_version))
nb_x_train = read_case_nb(f_in='nb_train_cv%d.dat' % (data_version))
nb_x_test = read_case_nb(f_in='nb_test_cv%d.dat' % (data_version))
X_train, X_test, y_train, y_test, = get_train_test_data(
X,
y,
nb_x_train,
nb_x_test,
)
print(X_train.shape)