def getdata_test(df, chunk_size_x, chunk_size_y):
list = df['Unnamed: 0'].tolist()
data_set = df.iloc[:, 15:].values
data_set = data_set.astype('float64')
#归一化
scaler = StandardScaler()
train_data_set = np.array(data_set)
#得到数据集
reframed_train_data_set = np.array(
getDataSet(train_data_set, chunk_size_x, chunk_size_y, True,
list).values)
reframed_train_data_set = reframed_train_data_set[:, :16 * chunk_size_x +
1]
data = reframed_train_data_set[:, :-chunk_size_y]
scaler.fit(data)
data = scaler.transform(data)
test_x = data
data_y = reframed_train_data_set[:, -chunk_size_y:]
label = np.zeros_like(data_y)
label[data_y > 0] = 1
label[data_y > 0.5] = 2
label[data_y > 1.5] = 3
test_y = label
test_x = test_x.reshape((test_x.shape[0], 16))
return test_x, test_y, scaler
def getdata_test(df, chunk_size_x, chunk_size_y):
list = df['Unnamed: 0'].tolist()
data_set = df.iloc[:, 15:].values
data_set = data_set.astype('float64')
#归一化
scaler = StandardScaler()
train_data_set = np.array(data_set)
#得到数据集
reframed_train_data_set = np.array(
getDataSet(train_data_set, chunk_size_x, chunk_size_y, True,
list).values)
reframed_train_data_set = reframed_train_data_set[:, :16 * chunk_size_x +
1]
data = reframed_train_data_set[:, :-chunk_size_y]
scaler.fit(data)
data = scaler.transform(data)
test_x = data
data_y = reframed_train_data_set[:, -chunk_size_y:]
label = np.zeros_like(data_y)
label[data_y > 0] = 1
label[data_y > 0.5] = 2
label[data_y > 1.5] = 3
# label = to_categorical(label, num_classes=4)
test_y = label.reshape(-1)
# 将数据集重构为符合LSTM要求的数据格式,即 [样本，时间步，特征维度：16]
test_x = test_x.reshape((test_x.shape[0], chunk_size_x, 16))
return test_x, test_y, scaler
def getdata_2(df, chunk_size_x, chunk_size_y):
list = df['Unnamed: 0'].tolist()
data_set = df.iloc[:, 15:].values
data_set = data_set.astype('float64')
#归一化
scaler = StandardScaler()
# scaler = MinMaxScaler()
train_data_set = np.array(data_set)
#得到数据集
reframed_train_data_set = np.array(
getDataSet(train_data_set, chunk_size_x, chunk_size_y, True,
list).values)
reframed_train_data_set = reframed_train_data_set[:, :16 * chunk_size_x +
1]
# 数据集划分,选取前60%天的数据作为训练集,中间20%天作为验证集,其余的作为测试集
data_y = reframed_train_data_set[:, -chunk_size_y:]
label = np.zeros_like(data_y)
idx = data_y > 0
# label[data_y > 0] = 1
label[data_y > 0.5] = 1
label[data_y > 1.5] = 2
label = label[idx]
train_days = int(len(label) * 0.6)
valid_days = int(len(label) * 0.2)
label = to_categorical(label, num_classes=3)
train_y = label[:train_days]
valid_y = label[train_days:train_days + valid_days]
test_y = label[train_days + valid_days:]
data = reframed_train_data_set[:, :-chunk_size_y]
scaler.fit(data)
data = scaler.transform(data)
idx = idx.reshape(-1)
data = data[idx]
train_x = data[:train_days, :]
valid_x = data[train_days:train_days + valid_days, :]
test_x = data[train_days + valid_days:, :]
# 将数据集重构为符合LSTM要求的数据格式,即 [样本，时间步，特征维度：16]
train_x = train_x.reshape((train_x.shape[0], chunk_size_x, 16))
valid_x = valid_x.reshape((valid_x.shape[0], chunk_size_x, 16))
test_x = test_x.reshape((test_x.shape[0], chunk_size_x, 16))
return train_x, train_y, valid_x, valid_y, test_x, test_y, scaler
def getdata(df, chunk_size_x, chunk_size_y):
list = df['Unnamed: 0'].tolist()
data_set = df.iloc[:, 15:].values
data_set = data_set.astype('float64')
train_data_set = np.array(data_set)
#得到数据集
reframed_train_data_set = np.array(
getDataSet(train_data_set, chunk_size_x, chunk_size_y, True,
list).values)
reframed_train_data_set = reframed_train_data_set[:, :16 * chunk_size_x +
1]
# 数据集划分,选取前70%天的数据作为训练集,中间20%天作为验证集,其余的作为测试集
train_days = int(len(reframed_train_data_set) * 0.7)
valid_days = int(len(reframed_train_data_set) * 0.2)
# 归一化
scaler = StandardScaler()
data = reframed_train_data_set[:, :-chunk_size_y]
scaler.fit(data)
data = scaler.transform(data)
train_x = data[:train_days, :]
valid_x = data[train_days:train_days + valid_days, :]
test_x = data[train_days + valid_days:, :]
data_y = reframed_train_data_set[:, -chunk_size_y:]
label = np.zeros_like(data_y)
label[data_y > 0] = 1
label[data_y > 0.5] = 2
label[data_y > 1.5] = 3
# label = to_categorical(label, num_classes=4)
train_y = label[:train_days]
valid_y = label[train_days:train_days + valid_days]
test_y = label[train_days + valid_days:]
train_x = train_x.reshape((train_x.shape[0], 16))
valid_x = valid_x.reshape((valid_x.shape[0], 16))
test_x = test_x.reshape((test_x.shape[0], 16))
return train_x, train_y, valid_x, valid_y, test_x, test_y, scaler
def gettrain_rand(df, chunk_size_x, chunk_size_y):
list = df['Unnamed: 0'].tolist()
trainsize = int(df.shape[0] * 0.9)
data_set = df.iloc[:trainsize, 15:].values
data_set = data_set.astype('float64')
# 归一化
scaler = StandardScaler()
train_data_set = np.array(data_set)
# 得到数据集
reframed_train_data_set = np.array(
getDataSet(train_data_set, chunk_size_x, chunk_size_y, True,
list).values)
reframed_train_data_set = reframed_train_data_set[:, :16 * chunk_size_x +
1]
data = reframed_train_data_set[:, :-chunk_size_y]
scaler.fit(data)
data = scaler.transform(data)
data_y = reframed_train_data_set[:, -chunk_size_y:]
label = np.zeros_like(data_y)
label[data_y > 0] = 1
label[data_y > 0.5] = 2
label[data_y > 1.5] = 3
label = to_categorical(label, num_classes=4)
train_x, rest_x, train_y, rest_y = train_test_split(data,
label,
test_size=0.2,
random_state=0)
valid_x, test_x, valid_y, test_y = train_test_split(rest_x,
rest_y,
test_size=0.5,
random_state=0)
train_x = train_x.reshape((train_x.shape[0], chunk_size_x, 16))
valid_x = valid_x.reshape((valid_x.shape[0], chunk_size_x, 16))
test_x = test_x.reshape((test_x.shape[0], chunk_size_x, 16))
return train_x, train_y, valid_x, valid_y, test_x, test_y
