HackNight20/hacknight.py at master · avisatna/HackNight20 · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Dropout
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
from sklearn.metrics import mean_squared_error
from math import sqrt

dataset = pd.read_csv('005930.KS.csv', index_col="Date", parse_dates=True)
#clear NAN values
dataset = dataset.dropna()

dataset["Close"] = dataset["Close"].replace(',', '').astype(float)
dataset["Volume"] = dataset["Volume"].replace(',', '').astype(float)

training_set=dataset['Open']
training_set=pd.DataFrame(training_set)

sc = MinMaxScaler(feature_range = (0, 1))
training_set_scaled = sc.fit_transform(training_set)

X_train = []
y_train = []
for i in range(60, len(dataset)):
    X_train.append(training_set_scaled[i-60:i, 0])
    y_train.append(training_set_scaled[i, 0])
X_train, y_train = np.array(X_train), np.array(y_train)

# Reshaping
X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))


#LSTM
regressor = Sequential()

regressor.add(LSTM(units = 50, return_sequences = True, input_shape = (X_train.shape[1], 1)))
regressor.add(Dropout(0.2))

regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))

regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))

regressor.add(LSTM(units = 50))
regressor.add(Dropout(0.2))

regressor.add(Dense(units = 1))

regressor.compile(optimizer = 'adam', loss = 'mean_squared_error')

regressor.fit(X_train, y_train, epochs = 100, batch_size = 32)

dataset_test = pd.read_csv('005930.KS_test.csv',index_col="Date",parse_dates=True)
dataset_test = dataset_test.dropna()
real_stock_price = dataset_test.iloc[:, 3:4].values
dataset_test["Volume"] = dataset_test["Volume"].replace(',', '').astype(float)
test_set=dataset_test['Open']
test_set=pd.DataFrame(test_set)

dataset_total = pd.concat((dataset['Open'], dataset_test['Open']), axis = 0)
inputs = dataset_total[len(dataset_total) - len(dataset_test) - 60:].values
inputs = inputs.reshape(-1,1)
inputs = sc.transform(inputs)
X_test = []
for i in range(60, 60+len(dataset_test)):
    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))
predicted_stock_price = regressor.predict(X_test)
predicted_stock_price = sc.inverse_transform(predicted_stock_price)
predicted_stock_price=pd.DataFrame(predicted_stock_price)
plt.plot(real_stock_price, color = 'red', label = 'Real Stock Price')
plt.plot(predicted_stock_price, color = 'blue', label = 'Predicted Stock Price')
plt.title('Stock Price Prediction')
plt.xlabel('Time')
plt.ylabel('Stock Price')
plt.legend()
plt.show()
rms = sqrt(mean_squared_error(real_stock_price, predicted_stock_price))