Recurrent Neural Network#

References#

What is it?#

Load data#

[1]:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

plt.style.use("fivethirtyeight")

[2]:

df = pd.read_csv("/opt/datasetsRepo/stock.csv")
df.head()

[2]:

	Date	Open	High	Low	Close	Volume
0	1/3/2012	325.25	332.83	324.97	663.59	7,380,500
1	1/4/2012	331.27	333.87	329.08	666.45	5,749,400
2	1/5/2012	329.83	330.75	326.89	657.21	6,590,300
3	1/6/2012	328.34	328.77	323.68	648.24	5,405,900
4	1/9/2012	322.04	322.29	309.46	620.76	11,688,800

[3]:

df = df[['Date', 'Open']]

[4]:

df.shape

[4]:

(1258, 2)

[5]:

df['Date'] = df['Date'].apply(pd.to_datetime)

How the data looks like#

[6]:

fig, ax = plt.subplots(1, 1, figsize=(15,5))

ax.plot(df['Date'], df['Open'], '.-k')

plt.show()

Data Preparation#

[7]:

test_size = 0.1
test_len = int(df.shape[0] * test_size)

[8]:

train_df = df.iloc[:df.shape[0]-test_len]
test_df = df.iloc[df.shape[0]-test_len:]

[9]:

fig, ax = plt.subplots(1, 1, figsize=(15,5))

ax.plot(train_df['Date'], train_df['Open'], '.-k', label='train_data')
ax.plot(test_df['Date'], test_df['Open'], '.-r', label='test_data')

plt.legend(loc='best')
plt.show()

Simple RNN#

[ ]: