under0tech

import numpy as np
import time as tm
import datetime as dt
import tensorflow as tf

# Data preparation
from yahoo_fin import stock_info as yf
from sklearn.preprocessing import MinMaxScaler
from collections import deque

under0tech

!pip install yahoo_fin

under0tech

# SETTINGS

# Window size or the sequence length, 7 (1 week)
N_STEPS = 7

# Lookup steps, 1 is the next day, 3 = after tomorrow
LOOKUP_STEPS = [1, 2, 3]

# Stock ticker, GOOGL
STOCK = 'GOOGL'

under0tech

# LOAD DATA 
# from yahoo_fin 
# for 1104 bars with interval = 1d (one day)
init_df = yf.get_data(
    STOCK, 
    start_date=date_3_years_back, 
    end_date=date_now, 
    interval='1d')

under0tech

# remove columns which our neural network will not use
init_df = init_df.drop(['open', 'high', 'low', 'adjclose', 'ticker', 'volume'], axis=1)
# create the column 'date' based on index column
init_df['date'] = init_df.index

under0tech

# Scale data for ML engine
scaler = MinMaxScaler()
init_df['close'] = scaler.fit_transform(np.expand_dims(init_df['close'].values, axis=1))

under0tech

# Let's preliminary see our data on the graphic
plt.style.use(style='ggplot')
plt.figure(figsize=(16,10))
plt.plot(init_df['close'][-200:])
plt.xlabel("days")
plt.ylabel("price")
plt.legend([f'Actual price for {STOCK}'])
plt.show()

under0tech

def PrepareData(days):
  df = init_df.copy()
  df['future'] = df['close'].shift(-days)
  last_sequence = np.array(df[['close']].tail(days))
  df.dropna(inplace=True)
  sequence_data = []
  sequences = deque(maxlen=N_STEPS)

  for entry, target in zip(df[['close'] + ['date']].values, df['future'].values):
      sequences.append(entry)

under0tech

def GetTrainedModel(x_train, y_train):
  model = Sequential()
  model.add(LSTM(60, return_sequences=True, input_shape=(N_STEPS, len(['close']))))
  model.add(Dropout(0.3))
  model.add(LSTM(120, return_sequences=False))
  model.add(Dropout(0.3))
  model.add(Dense(20))
  model.add(Dense(1))

  BATCH_SIZE = 8

under0tech

# GET PREDICTIONS
predictions = []

for step in LOOKUP_STEPS:
  df, last_sequence, x_train, y_train = PrepareData(step)
  x_train = x_train[:, :, :len(['close'])].astype(np.float32)

  model = GetTrainedModel(x_train, y_train)

  last_sequence = last_sequence[-N_STEPS:]