Python - 使用 LSTM 递归神经网络和 Keras 进行模式预测
Python - Pattern prediction using LSTM Recurrent Neural Networks with Keras
我正在处理来自格式化 CSV dataset with three columns (time_stamp, X and Y - where Y is the actual value). I wanted to predict the value of X from Y based on time index from past values and here is how I approached the problem with LSTM Recurrent Neural Networks in Python with Keras 的模式预测。
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import LSTM, Dense
from keras.preprocessing.sequence import TimeseriesGenerator
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
np.random.seed(7)
df = pd.read_csv('test32_C_data.csv')
n_features=100
values = df.values
for i in range(0,n_features):
df['X_t'+str(i)] = df['X'].shift(i)
df['X_tp'+str(i)] = (df['X'].shift(i) - df['X'].shift(i+1))/(df['X'].shift(i))
print(df)
pd.set_option('use_inf_as_null', True)
#df.replace([np.inf, -np.inf], np.nan).dropna(axis=1)
df.dropna(inplace=True)
X = df.drop('Y', axis=1)
y = df['Y']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.40)
X_train = X_train.drop('time', axis=1)
X_train = X_train.drop('X_t1', axis=1)
X_train = X_train.drop('X_t2', axis=1)
X_test = X_test.drop('time', axis=1)
X_test = X_test.drop('X_t1', axis=1)
X_test = X_test.drop('X_t2', axis=1)
sc = MinMaxScaler()
X_train = np.array(df['X'])
X_train = X_train.reshape(-1, 1)
X_train = sc.fit_transform(X_train)
y_train = np.array(df['Y'])
y_train=y_train.reshape(-1, 1)
y_train = sc.fit_transform(y_train)
model_data = TimeseriesGenerator(X_train, y_train, 100, batch_size = 10)
# Initialising the RNN
model = Sequential()
# Adding the input layerand the LSTM layer
model.add(LSTM(4, input_shape=(None, 1)))
# Adding the output layer
model.add(Dense(1))
# Compiling the RNN
model.compile(loss='mse', optimizer='rmsprop')
# Fitting the RNN to the Training set
model.fit_generator(model_data)
# evaluate the model
#scores = model.evaluate(X_train, y_train)
#print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
# Getting the predicted values
predicted = X_test
predicted = sc.transform(predicted)
predicted = predicted.reshape((-1, 1, 1))
y_pred = model.predict(predicted)
y_pred = sc.inverse_transform(y_pred)
当我将预测绘制成这样时
plt.figure
plt.plot(y_test, color = 'red', label = 'Actual')
plt.plot(y_pred, color = 'blue', label = 'Predicted')
plt.title('Prediction')
plt.xlabel('Time [INdex]')
plt.ylabel('Values')
plt.legend()
plt.show()
下面的情节是我得到的。
但是，如果我们分别绘制每一列，
groups = [1, 2]
i = 1
# plot each column
plt.figure()
for group in groups:
plt.subplot(len(groups), 1, i)
plt.plot(values[:, group])
plt.title(df.columns[group], y=0.5, loc='right')
i += 1
plt.show()
下面的图就是我们得到的。
我们怎样才能提高预测的准确性？
我会让你从这里开始，但这至少应该让你继续。
注意：我发现您对预测的变量有些混淆。为此，我预测通常是标准的 'Y'。如果那不正确，只需在放入 create_sequences 函数之前交换顺序。代码应该仍然有效，无论如何这只是您的起点，您需要更多地使用它才能获得性能良好的网络。
import numpy as np
from keras.models import Sequential
from keras.layers import LSTM, Dense
from sklearn.preprocessing import MinMaxScaler
import pandas as pd
np.random.seed(7)
df = pd.read_csv('test32_C_data.csv')
n_features = 100
def create_sequences(data, window=14, step=1, prediction_distance=14):
x = []
y = []
for i in range(0, len(data) - window - prediction_distance, step):
x.append(data[i:i + window])
y.append(data[i + window + prediction_distance][0])
x, y = np.asarray(x), np.asarray(y)
return x, y
# Scaling prior to splitting
scaler = MinMaxScaler(feature_range=(0.01, 0.99))
scaled_data = scaler.fit_transform(df.loc[:, ["Y", "X"]].values)
# Build sequences
x_sequence, y_sequence = create_sequences(scaled_data)
# Create test/train split
test_len = int(len(x_sequence) * 0.15)
valid_len = int(len(x_sequence) * 0.15)
train_end = len(x_sequence) - (test_len + valid_len)
x_train, y_train = x_sequence[:train_end], y_sequence[:train_end]
x_valid, y_valid = x_sequence[train_end:train_end + valid_len], y_sequence[train_end:train_end + valid_len]
x_test, y_test = x_sequence[train_end + valid_len:], y_sequence[train_end + valid_len:]
# Initialising the RNN
model = Sequential()
# Adding the input layerand the LSTM layer
model.add(LSTM(4, input_shape=(14, 2)))
# Adding the output layer
model.add(Dense(1))
# Compiling the RNN
model.compile(loss='mse', optimizer='rmsprop')
# Fitting the RNN to the Training set
model.fit(x_train, y_train, epochs=5)
# Getting the predicted values
y_pred = model.predict(x_test)
# Plot results
pd.DataFrame({"y_test": y_test, "y_pred": np.squeeze(y_pred)}).plot()
差异：
使用自定义序列生成器，14 步 window，14 步 "look-forward" 进行预测
自定义train/test/valid拆分，训练时可以使用验证集进行early stopping
更改了输入形状以包含 2 个特征 window 为 14 input_shape=(14,2)
5 个纪元
我正在处理来自格式化 CSV dataset with three columns (time_stamp, X and Y - where Y is the actual value). I wanted to predict the value of X from Y based on time index from past values and here is how I approached the problem with LSTM Recurrent Neural Networks in Python with Keras 的模式预测。
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import LSTM, Dense
from keras.preprocessing.sequence import TimeseriesGenerator
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
np.random.seed(7)
df = pd.read_csv('test32_C_data.csv')
n_features=100
values = df.values
for i in range(0,n_features):
df['X_t'+str(i)] = df['X'].shift(i)
df['X_tp'+str(i)] = (df['X'].shift(i) - df['X'].shift(i+1))/(df['X'].shift(i))
print(df)
pd.set_option('use_inf_as_null', True)
#df.replace([np.inf, -np.inf], np.nan).dropna(axis=1)
df.dropna(inplace=True)
X = df.drop('Y', axis=1)
y = df['Y']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.40)
X_train = X_train.drop('time', axis=1)
X_train = X_train.drop('X_t1', axis=1)
X_train = X_train.drop('X_t2', axis=1)
X_test = X_test.drop('time', axis=1)
X_test = X_test.drop('X_t1', axis=1)
X_test = X_test.drop('X_t2', axis=1)
sc = MinMaxScaler()
X_train = np.array(df['X'])
X_train = X_train.reshape(-1, 1)
X_train = sc.fit_transform(X_train)
y_train = np.array(df['Y'])
y_train=y_train.reshape(-1, 1)
y_train = sc.fit_transform(y_train)
model_data = TimeseriesGenerator(X_train, y_train, 100, batch_size = 10)
# Initialising the RNN
model = Sequential()
# Adding the input layerand the LSTM layer
model.add(LSTM(4, input_shape=(None, 1)))
# Adding the output layer
model.add(Dense(1))
# Compiling the RNN
model.compile(loss='mse', optimizer='rmsprop')
# Fitting the RNN to the Training set
model.fit_generator(model_data)
# evaluate the model
#scores = model.evaluate(X_train, y_train)
#print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
# Getting the predicted values
predicted = X_test
predicted = sc.transform(predicted)
predicted = predicted.reshape((-1, 1, 1))
y_pred = model.predict(predicted)
y_pred = sc.inverse_transform(y_pred)
当我将预测绘制成这样时
plt.figure
plt.plot(y_test, color = 'red', label = 'Actual')
plt.plot(y_pred, color = 'blue', label = 'Predicted')
plt.title('Prediction')
plt.xlabel('Time [INdex]')
plt.ylabel('Values')
plt.legend()
plt.show()
下面的情节是我得到的。
但是，如果我们分别绘制每一列，
groups = [1, 2]
i = 1
# plot each column
plt.figure()
for group in groups:
plt.subplot(len(groups), 1, i)
plt.plot(values[:, group])
plt.title(df.columns[group], y=0.5, loc='right')
i += 1
plt.show()
下面的图就是我们得到的。
我们怎样才能提高预测的准确性？
我会让你从这里开始，但这至少应该让你继续。
注意：我发现您对预测的变量有些混淆。为此，我预测通常是标准的 'Y'。如果那不正确，只需在放入 create_sequences 函数之前交换顺序。代码应该仍然有效，无论如何这只是您的起点，您需要更多地使用它才能获得性能良好的网络。
import numpy as np
from keras.models import Sequential
from keras.layers import LSTM, Dense
from sklearn.preprocessing import MinMaxScaler
import pandas as pd
np.random.seed(7)
df = pd.read_csv('test32_C_data.csv')
n_features = 100
def create_sequences(data, window=14, step=1, prediction_distance=14):
x = []
y = []
for i in range(0, len(data) - window - prediction_distance, step):
x.append(data[i:i + window])
y.append(data[i + window + prediction_distance][0])
x, y = np.asarray(x), np.asarray(y)
return x, y
# Scaling prior to splitting
scaler = MinMaxScaler(feature_range=(0.01, 0.99))
scaled_data = scaler.fit_transform(df.loc[:, ["Y", "X"]].values)
# Build sequences
x_sequence, y_sequence = create_sequences(scaled_data)
# Create test/train split
test_len = int(len(x_sequence) * 0.15)
valid_len = int(len(x_sequence) * 0.15)
train_end = len(x_sequence) - (test_len + valid_len)
x_train, y_train = x_sequence[:train_end], y_sequence[:train_end]
x_valid, y_valid = x_sequence[train_end:train_end + valid_len], y_sequence[train_end:train_end + valid_len]
x_test, y_test = x_sequence[train_end + valid_len:], y_sequence[train_end + valid_len:]
# Initialising the RNN
model = Sequential()
# Adding the input layerand the LSTM layer
model.add(LSTM(4, input_shape=(14, 2)))
# Adding the output layer
model.add(Dense(1))
# Compiling the RNN
model.compile(loss='mse', optimizer='rmsprop')
# Fitting the RNN to the Training set
model.fit(x_train, y_train, epochs=5)
# Getting the predicted values
y_pred = model.predict(x_test)
# Plot results
pd.DataFrame({"y_test": y_test, "y_pred": np.squeeze(y_pred)}).plot()
差异：
使用自定义序列生成器，14 步 window，14 步 "look-forward" 进行预测
自定义train/test/valid拆分，训练时可以使用验证集进行early stopping
更改了输入形状以包含 2 个特征 window 为 14 input_shape=(14,2)
5 个纪元