So, I have been trying to apply LSTM on this csv file CSV File that im trying to train
However, it seems to train it self but after the training, its causing issue on my test file with either Error 1 Or if I modify it a little pit then I get another error which says "Value Error: cannot reshape array of size 1047835 into shape"
Here is the code im implementing:-
import math
import matplotlib.pyplot as plt
import keras
import pandas as pd
import numpy as np
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "-1" #Had to use CPU because of gpus capability was 3.0
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Dropout
from keras.layers import *
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
from sklearn.metrics import mean_absolute_error
from sklearn.model_selection import train_test_split
from keras.callbacks import EarlyStopping
df=pd.read_csv(r'C:\Users\LambertThePrick\Desktop\Databysir\LSTM.csv')
print(df.shape)
print(df.head(5))
#df.head(5)
TrainPart=df.iloc[:800,1:3].values
test_set=df.iloc[800:,1:3].values
scaler=MinMaxScaler(feature_range=(0,1))
Trainpart_scaled=scaler.fit_transform(TrainPart)
print(Trainpart_scaled)
X_Train=[]
Y_Train=[]
for i in range(60,800):
X_Train.append(Trainpart_scaled[i-60:i,0])
Y_Train.append(Trainpart_scaled[i,0])
X_Train,Y_Train=np.array(X_Train),np.array(Y_Train)
X_Train = np.reshape(X_Train, (X_Train.shape[0], X_Train.shape[1], 1))
# print(X_train = np.reshape(X_Train, (X_Train.shape[0], X_Train.shape[1], 1)))
#(740, 60, 1)
model = Sequential()
#Adding the first LSTM layer and some Dropout regularisation
model.add(LSTM(units = 50, return_sequences = True, input_shape = (X_Train.shape[1], 1)))
model.add(Dropout(0.2))
# Adding a second LSTM layer and some Dropout regularisation
model.add(LSTM(units = 50, return_sequences = True))
model.add(Dropout(0.2))
# Adding a third LSTM layer and some Dropout regularisation
model.add(LSTM(units = 50, return_sequences = True))
model.add(Dropout(0.2))
# Adding a fourth LSTM layer and some Dropout regularisation
model.add(LSTM(units = 50))
model.add(Dropout(0.2))
# Adding the output layer
model.add(Dense(units = 1))
# Compiling the RNN
model.compile(optimizer = 'adam', loss = 'mean_squared_error')
# Fitting the RNN to the Training set
model.fit(X_Train, Y_Train, epochs = 100, batch_size = 32)
#THIS IS EXPT AFTER THIS
dataset_train = df.iloc[:800, 1:3]
dataset_test = df.iloc[800:, 1:3]
dataset_total = pd.concat((dataset_train, dataset_test), axis = 0)
inputs = dataset_total[len(dataset_total) - len(dataset_test) - 60:].values
inputs = inputs.reshape(-1,1)
inputs = scaler.transform(inputs)
X_Test = []
for i in range(60, 800):
X_Test.append(inputs[i-60:i, 0])
X_Test = np.array(X_Test)
X_Test = np.reshape(X_Test, (X_Test.shape[0], X_Test.shape[1], 1))
print(X_Test.shape)
predicted_stock_price = model.predict(X_Test)
predicted_stock_price = scaler.inverse_transform(predicted_stock_price)
plt.plot(df.loc[800:, 'Date'],dataset_test.values, color = 'red', label = 'Real ASTL Stock Price')
plt.plot(df.loc[800:, 'Date'],predicted_stock_price, color = 'blue', label = 'Predicted ASTL Stock Price')
plt.xticks(np.arange(0,459,50))
plt.title('ASTL Stock Price Prediction')
plt.xlabel('Time')
plt.ylabel('ASTL Stock Price')
plt.legend()
plt.show()
You have a moment in your reshaping where you end up with a non-integer division. Take this example:
import numpy as np
data = np.zeros(3936)
out = data.reshape((-1,1,24,2))
works well because 3936/24/2 results in an integer, 82 .
But in this example
import numpy as np
data = np.zeros(34345)
out = data.reshape((-1,1,24,2))
you end up with the error message ValueError: cannot reshape array of size 34345 into shape (1,24,2) because the division does not result in an integer.
So, looping the way you do is bound to result in events of that type.