Python 日期格式的LSTM错误

这是我第一次尝试深入学习，这段代码的目的是预测外汇市场的走向

代码如下：

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from keras.layers.core import Dense, Activation, Dropout
from keras.layers.recurrent import LSTM
from keras.models import Sequential

column_names = ['Date', 'Time', 'Open', 'High', 'Low','Close', 'Volume']

data = pd.read_csv(r"E:\Tutorial\EURUSD60.csv", header=None, names=column_names)

data['DateTime'] = pd.to_datetime(data.Date + ' ' + data.Time)
del data['Date']
del data['Time']

sequence_length = 21
n_features = len(data.columns)
val_ratio = 0.1
n_epochs = 300
batch_size = 512

data = data.as_matrix()
data_processed = []
for index in range(len(data) - sequence_length):
    data_processed.append(data[index: index + sequence_length])
data_processed = np.array(data_processed)

val_split = round((1 - val_ratio) * data_processed.shape[0])
train = data_processed[: int(val_split), :]
val = data_processed[int(val_split):, :]

print('Training data: {}'.format(train.shape))
print('Validation data: {}'.format(val.shape))

train_samples, train_nx, train_ny = train.shape
val_samples, val_nx, val_ny = val.shape

train = train.reshape((train_samples, train_nx * train_ny))
val = val.reshape((val_samples, val_nx * val_ny))

preprocessor = MinMaxScaler().fit(train)
train = preprocessor.transform(train)
val = preprocessor.transform(val)

train = train.reshape((train_samples, train_nx, train_ny))
val = val.reshape((val_samples, val_nx, val_ny))

X_train = train[:, : -1]
y_train = train[:, -1][:, -1]
X_val = val[:, : -1]
y_val = val[:, -1][:, -1]

X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], n_features))
X_val = np.reshape(X_val, (X_val.shape[0], X_val.shape[1], n_features))

model = Sequential()
model.add(LSTM(input_shape=(X_train.shape[1:]), units=128, return_sequences=True))
model.add(Dropout(0.5))
model.add(LSTM(128, return_sequences=False))
model.add(Dropout(0.25))
model.add(Dense(units=1))
model.add(Activation("linear"))

model.compile(loss="mse", optimizer="adam")

history = model.fit(
    X_train,
    y_train,
    batch_size=batch_size,
    epochs=n_epochs,
    verbose=2)

preds_val = model.predict(X_val)
diff = []
for i in range(len(y_val)):
    pred = preds_val[i][0]
    diff.append(y_val[i] - pred)

real_min = preprocessor.data_min_[104]
real_max = preprocessor.data_max_[104]
print(preprocessor.data_min_[104])
print(preprocessor.data_max_[104])

preds_real = preds_val * (real_max - real_min) + real_min
y_val_real = y_val * (real_max - real_min) + real_min

plt.plot(preds_real, label='Predictions')
plt.plot(y_val_real, label='Actual values')
plt.xlabel('test')
plt.legend(loc=0)
plt.show()

以下是错误：

使用TensorFlow后端。2017-12-03 13:26:44.494199:W
C:\tf\u jenkins\home\workspace\rel win\M\windows\PY\36\tensorflow\core\platform\cpu\u feature\u guard.cc:45]tensorflow库未编译为使用AVX指令，但
这些功能在您的计算机上可用，可以加快CPU的速度
计算。2017-12-03 13:26:44.494660:W
C:\tf\u jenkins\home\workspace\rel win\M\windows\PY\36\tensorflow\core\platform\cpu\u feature\u guard.cc:45]tensorflow库未编译为使用AVX2指令，但
这些功能在您的计算机上可用，可以加快CPU的速度
计算。培训数据：（1824,21,6）验证数据：（203,21，
6） 回溯（最近一次调用）：文件“E:/Tutorial/Deep
Learning.py”，第42行，在 preprocessor=MinMaxScaler（）.fit（train）文件“C:\Users\sydgo\Anaconda3\lib\site packages\sklearn\preprocessing\data.py”，
第308行，适合
返回self.partial_fit（X，y）文件“C:\Users\sydgo\Anaconda3\lib\site packages\sklearn\preprocessing\data.py”，
第334行，部分配合
estimator=self，dtype=FLOAT\u DTYPES）文件“C:\Users\sydgo\Anaconda3\lib\site packages\sklearn\utils\validation.py”，
第433行，在check_数组中 array=np.array（array，dtype=dtype，order=order，copy=copy）类型错误：float（）参数必须是字符串或数字，而不是
“时间戳”

---

预期的

dtype

和
实际交付的数据类型：

TypeError:float（）参数必须是字符串或数字，而不是“Timestamp”

最有可能修改的是以下方面的转换：

data['DateTime'] = pd.to_datetime(data.Date + ' ' + data.Time)

---

您必须回到这个概念，作为预期的外汇定量建模功能集，应该向LSTM模型提供什么（如果有的话）。

这是修复错误后的代码

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from keras.layers.core import Dense, Activation, Dropout
from keras.layers.recurrent import LSTM
from keras.models import Sequential

column_names = ['Date', 'Time', 'Open', 'High', 'Low','Close', 'Volume']

df = pd.read_csv(r"E:\Tutorial\EURUSD60.csv", header=None, names=column_names)

df['DateTime'] = pd.to_datetime(df.Date + ' ' + df.Time)
del df['Date']
del df['Time']

df.rename(columns={'DateTime': 'timestamp', 'Open': 'open',
                   'High': 'high', 'Low': 'low', 'Close': 'close', 'Volume': 'volume'}, inplace=True)
df['timestamp'] = pd.to_datetime(df['timestamp'], infer_datetime_format=True)
df.set_index('timestamp', inplace=True)
df = df.astype(float)
df['hour'] = df.index.hour
df['day'] = df.index.weekday
df['week'] = df.index.week


sequence_length = 21
n_features = len(df.columns)
val_ratio = 0.1
n_epochs = 300
batch_size = 512

data = df.as_matrix()
data_processed = []
for index in range(len(data) - sequence_length):
    data_processed.append(data[index: index + sequence_length])
data_processed = np.array(data_processed)

val_split = round((1 - val_ratio) * data_processed.shape[0])
train = data_processed[: int(val_split), :]
val = data_processed[int(val_split):, :]

print('Training data: {}'.format(train.shape))
print('Validation data: {}'.format(val.shape))

train_samples, train_nx, train_ny = train.shape
val_samples, val_nx, val_ny = val.shape

train = train.reshape((train_samples, train_nx * train_ny))
val = val.reshape((val_samples, val_nx * val_ny))

preprocessor = MinMaxScaler().fit(train)
train = preprocessor.transform(train)
val = preprocessor.transform(val)

train = train.reshape((train_samples, train_nx, train_ny))
val = val.reshape((val_samples, val_nx, val_ny))

X_train = train[:, : -1]
y_train = train[:, -1][:, -1]
X_val = val[:, : -1]
y_val = val[:, -1][:, -1]

X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], n_features))
X_val = np.reshape(X_val, (X_val.shape[0], X_val.shape[1], n_features))

model = Sequential()
model.add(LSTM(input_shape=(X_train.shape[1:]), units=128, return_sequences=True))
model.add(Dropout(0.5))
model.add(LSTM(128, return_sequences=False))
model.add(Dropout(0.25))
model.add(Dense(units=1))
model.add(Activation("linear"))

model.compile(loss="mse", optimizer="adam")

history = model.fit(
    X_train,
    y_train,
    batch_size=batch_size,
    epochs=n_epochs,
    verbose=2)

preds_val = model.predict(X_val)
diff = []
for i in range(len(y_val)):
    pred = preds_val[i][0]
    diff.append(y_val[i] - pred)

real_min = preprocessor.data_min_[104]
real_max = preprocessor.data_max_[104]
print(preprocessor.data_min_[:120])
print(preprocessor.data_max_[:120])

preds_real = preds_val * (real_max - real_min) + real_min
y_val_real = y_val * (real_max - real_min) + real_min

plt.plot(preds_real, label='Predictions')
plt.plot(y_val_real, label='Actual values')
plt.xlabel('test')
plt.legend(loc=0)
plt.show()