Notebook 1_ Stock Market Models-ARIMA, Fourier, Feature Extraction, LSTM.ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Notebook 1: Stock Market Models-ARIMA, Fourier, Feature Extraction, LSTM.ipynb","version":"0.3.2","provenance":[],"collapsed_sections":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"accelerator":"GPU"},"cells":[{"cell_type":"markdown","metadata":{"id":"_jMBTKtPWTP4","colab_type":"text"},"source":["**TIME SERIES ANALYSIS FOR STOCK MARKET DATA SPECIFICALLY AMAZON. DATA SOURCE IS YAHOO.API AND ALPHADVANTAGE.API**\n","\n","**This notebook is Part 1 of Time series modelling for Amazon Stock Prediction\n","It deals with:**\n","\n","**1.   Data Exploration**\n","\n","**2.   Making a time series window**\n","\n","**3.   Feature engineering from the data**\n","\n","**4. Make an ARIMA model**\n","\n","**5. Make a Fourier series mode**l\n","\n","**6. Make a LSTM model with one feature**\n","\n","**7.Make a LSTM model with multiple features**\n","\n","**8.Conclusion**\n","\n","\n","\n"]},{"cell_type":"markdown","metadata":{"id":"VGNrO7RQor0w","colab_type":"text"},"source":["**Level 0: INSTALLATION**\n","\n","**1.   Set up modules on google colab**\n","\n","**2.  Take in data from yahoo.api**\n","\n","**3. For privacy of my own account I have blocked these links and API keys off**\n","\n","**Hint: Google colab Python 3 version comes with all Python packages and modules. It's easier to use than Anaconda or Ubuntu and has a great GPU drive.** \n","\n","\n","\n"]},{"cell_type":"code","metadata":{"id":"_xc364gbUKMG","colab_type":"code","colab":{}},"source":["!pip install -U -q PyDrive\n","from pydrive.auth import GoogleAuth\n","from pydrive.drive import GoogleDrive\n","from google.colab import auth\n","from oauth2client.client import GoogleCredentials\n","# Authenticate and create the PyDrive client.\n","auth.authenticate_user()\n","gauth = GoogleAuth()\n","gauth.credentials = GoogleCredentials.get_application_default()\n","drive = GoogleDrive(gauth)"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"6xka10QxqrBE","colab_type":"text"},"source":["**Use the code above to set up Drive which will have csv file.**\n","\n","Credit: https://medium.com/paper-club/how-to-set-up-google-colab-colaboratory-for-building-pyro-models-8e51129e772a"]},{"cell_type":"code","metadata":{"id":"FpGd27iPApW9","colab_type":"code","colab":{}},"source":["link = 'https://drive.google.com/open?id=1y394o-wiPqYPaWzVYTPRr8xpE_aM9621'"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"yjpKSbnqtdj8","colab_type":"text"},"source":["**Link to your google drive. This will make your drive public to all so be careful who you give it to.**"]},{"cell_type":"code","metadata":{"id":"1NBd-Hx7Auif","colab_type":"code","outputId":"fe3624bf-6174-4d54-d88f-8a6c33aa72f2","executionInfo":{"status":"ok","timestamp":1565975573593,"user_tz":240,"elapsed":1013,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":34}},"source":["fluff, id = link.split('=')\n","print (id) # Verify that you have everything after '='"],"execution_count":12,"outputs":[{"output_type":"stream","text":["1y394o-wiPqYPaWzVYTPRr8xpE_aM9621\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"9EP87twmttME","colab_type":"text"},"source":["**To check I got data in my file and it's been read**"]},{"cell_type":"code","metadata":{"id":"6vnt8KyUA885","colab_type":"code","colab":{}},"source":["import pandas as pd\n","downloaded = drive.CreateFile({'id':id}) \n","downloaded.GetContentFile('AMZN.csv')\n","# Dataset is now stored in a Pandas Dataframe"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"XeoyRs8hCwTX","colab_type":"code","outputId":"8a36fc84-b64f-4bf7-9025-b34889d034ae","executionInfo":{"status":"ok","timestamp":1565975579812,"user_tz":240,"elapsed":4861,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":151}},"source":["pip install mxnet"],"execution_count":14,"outputs":[{"output_type":"stream","text":["Requirement already satisfied: mxnet in /usr/local/lib/python3.6/dist-packages (1.5.0)\n","Requirement already satisfied: requests<3,>=2.20.0 in /usr/local/lib/python3.6/dist-packages (from mxnet) (2.21.0)\n","Requirement already satisfied: graphviz<0.9.0,>=0.8.1 in /usr/local/lib/python3.6/dist-packages (from mxnet) (0.8.4)\n","Requirement already satisfied: numpy<2.0.0,>1.16.0 in /usr/local/lib/python3.6/dist-packages (from mxnet) (1.16.4)\n","Requirement already satisfied: chardet<3.1.0,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests<3,>=2.20.0->mxnet) (3.0.4)\n","Requirement already satisfied: idna<2.9,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests<3,>=2.20.0->mxnet) (2.8)\n","Requirement already satisfied: urllib3<1.25,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests<3,>=2.20.0->mxnet) (1.24.3)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests<3,>=2.20.0->mxnet) (2019.6.16)\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"Encu5lTtt215","colab_type":"text"},"source":["**install mxnet a python package for time series data great for visualization**"]},{"cell_type":"code","metadata":{"id":"Z-n42rXkBY4x","colab_type":"code","colab":{}},"source":["import time\n","import numpy as np\n","\n","from mxnet import nd, autograd, gluon\n","from mxnet.gluon import nn, rnn\n","import mxnet as mx\n","import datetime\n","import seaborn as sns\n","\n","import matplotlib.pyplot as plt\n","%matplotlib inline\n","from sklearn.decomposition import PCA\n","\n","import math\n","\n","from sklearn.preprocessing import MinMaxScaler\n","from sklearn.metrics import mean_squared_error\n","from sklearn.preprocessing import StandardScaler\n","\n","import xgboost as xgb\n","from sklearn.metrics import accuracy_score"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"nGy43Rr9FAhT","colab_type":"code","colab":{}},"source":["import warnings\n","warnings.filterwarnings(\"ignore\")"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"acikqo6lVWgM","colab_type":"code","colab":{}},"source":["context = mx.cpu(); model_ctx=mx.cpu()\n","mx.random.seed(1719)"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"7qUPd_qSuiaI","colab_type":"text"},"source":["Setting up mxnet model \n","Need this to create an ARIMA model and Fourier series model easily "]},{"cell_type":"code","metadata":{"id":"KuwLSx1BVjK7","colab_type":"code","colab":{}},"source":["def parser(x):\n","    return datetime.datetime.strptime(x,'%m/%d/%Y')"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"oGloNVdKu4ZQ","colab_type":"text"},"source":["**Always sort time and format it properily for time series data. Here sorted out it month-date-year format.** "]},{"cell_type":"code","metadata":{"id":"iIX76FltX8yD","colab_type":"code","colab":{}},"source":["import pandas as pd"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"u33F4vKcHEjU","colab_type":"code","colab":{}},"source":["dataset_ex_df = pd.read_csv(\"AMZN.csv\", header=0, parse_dates=[0], date_parser=parser)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"8pMM2w-cHsv3","colab_type":"code","outputId":"220c2f58-0217-4a5e-f7f5-fc0e286bf7ff","executionInfo":{"status":"ok","timestamp":1565975595063,"user_tz":240,"elapsed":740,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":136}},"source":["dataset_ex_df[['Date', 'Close']].head(3)"],"execution_count":21,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>Date</th>\n","      <th>Close</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>2010-01-04</td>\n","      <td>133.899994</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>2010-01-05</td>\n","      <td>134.690002</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2010-01-06</td>\n","      <td>132.250000</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["        Date       Close\n","0 2010-01-04  133.899994\n","1 2010-01-05  134.690002\n","2 2010-01-06  132.250000"]},"metadata":{"tags":[]},"execution_count":21}]},{"cell_type":"markdown","metadata":{"id":"AVkU6X93veJp","colab_type":"text"},"source":["**Have a good look at closing prices and date. Most time series analysis go with trying to fo find closing prices.** \n","**The reason is because closing prices generally summarize the way business was going better than opening prices or average prices.**\n","**Below is a great article to understand stock markets better**\n","https://medium.com/s/story/predicting-the-stock-market-is-easier-than-you-might-think-4f1e0bc05cfe"]},{"cell_type":"code","metadata":{"id":"6a3PaysYHx2i","colab_type":"code","outputId":"98fdf40f-7abc-4051-bda9-3619bba54020","executionInfo":{"status":"ok","timestamp":1565975597982,"user_tz":240,"elapsed":1158,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":34}},"source":["print('There are {} number of days in the dataset.'.format(dataset_ex_df.shape[0]))"],"execution_count":22,"outputs":[{"output_type":"stream","text":["There are 2265 number of days in the dataset.\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"jDVWPQqQIPSg","colab_type":"code","outputId":"d50a57eb-6b13-41eb-a094-cc22d789f02e","executionInfo":{"status":"ok","timestamp":1565975600441,"user_tz":240,"elapsed":1794,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":480}},"source":["plt.figure(figsize=(14, 5), dpi=100)\n","plt.plot(dataset_ex_df['Date'], dataset_ex_df['Close'], label='Amazon stock')\n","plt.vlines(datetime.date(2016,4,20), 0, 270, linestyles='--', colors='gray', label='Train/Test data cut-off')\n","plt.xlabel('Date')\n","plt.ylabel('USD')\n","plt.title('Figure 2: Amazon stock price')\n","plt.legend()\n","plt.show()\n"],"execution_count":23,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAABJQAAAHPCAYAAAAF24DWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n","text/plain":["<Figure size 1400x500 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"PTLPUwUqxsFn","colab_type":"text"},"source":["**I have divided the stock data after 2010 upto 2019 for Amazon. \n","Amazon business really boomed after 2010 and then peaked after 2015 so the testing will be very interesting since most of the data is in the exponential growth period. What I am going to do it normalize the training data such that similar data points over time are reduced to one single data point so that the model can train in such a way it can expect the exponential growth after 2015.**\n","\n","**Inorder to predict better i NEED TO GENERATOR FEATURES SO I HAVE MORE INDICATORS TO PREDICT THE DATA**"]},{"cell_type":"markdown","metadata":{"id":"JUrq9syJy4FM","colab_type":"text"},"source":["# **FEATURE GENERATION**"]},{"cell_type":"code","metadata":{"id":"Pq8-28ZxITgE","colab_type":"code","colab":{}},"source":["def get_technical_indicators(dataset): #function to generate feature technical indicators\n","    \n","    \n","    # Create 7 and 21 days Moving Average\n","    dataset['ma7'] = dataset['Close'].rolling(window = 7).mean()\n","    dataset['ma21'] = dataset['Close'].rolling(window = 21).mean()\n","    \n","    #Create MACD\n","    dataset['26ema'] = dataset['Close'].ewm(span=26).mean()\n","    dataset['12ema'] = dataset['Close'].ewm(span=12).mean()\n","    dataset['MACD'] = (dataset['12ema']-dataset['26ema'])\n","    \n","    #Create Bollinger Bands\n","    dataset['20sd'] = dataset['Close'].rolling(window = 20).std()\n","    dataset['upper_band'] = (dataset['Close'].rolling(window = 20).mean()) + (dataset['20sd']*2)\n","    dataset['lower_band'] = (dataset['Close'].rolling(window = 20).mean()) - (dataset['20sd']*2)\n","    \n","    \n","    #Create Exponential moving average\n","    dataset['ema'] = dataset['Close'].ewm(com=0.5).mean()\n","    \n","    #Create Momentum\n","    dataset['momentum'] = (dataset['Close']/100)-1\n","    \n","    \n","    \n","    return dataset"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"XfaBgjfrzPJm","colab_type":"text"},"source":["**List of technical indicators and explanation:**\n","\n","\n","**1.   Bollinger bands: Bollinger Bands is used to define the prevailing high and low prices in a market to characterize the trading band of a financial instrument or commodity. Bollinger Bands are a volatility indicator. Bands are consists of Moving Average (MA) line, a upper band and lower band. The upper and lower bands are simply MA adding and subtracting standard deviation.** \n","\n","**2.   EMA: Exponential moving average is a better version of a simple moving average that doesnt have SMAs lag. Moving averages just average out the data for a given time so we know how the company's closing price are trending for a given amount of days. example for 4 days is price was 22,23 ,45,1**\n","**(the company crashed on 4th day) the average would be 23. Now 23 is a below average value so it gives us an idea that 45 was indeed just a fluke and that infact the company was always making losses**\n","**EMA is calculated as:**\n","**EMA(t)EMA(t0)=(1−α)EMA(t−1)+α p(t)=p(t0)**\n","**where** \n","**α=1L+1 and length of window is α=2M+1**\n","**I used the ewm(exponential weighted mean ) function to calculate ema.**\n","\n","\n","\n","**3. Momentum: Momentum is perhaps the simplest and easiest oscillator (financial analysis tool) to understand and use. It is the measurement of the speed or velocity of price changes, or the rate of change in price movement for a particular asset.**\n","\n","**The formula for momentum is:**\n","\n","**Momentum=V−Vx**\n","**where:**\n","\n","**V=Latest price**\n","\n","**Vx=Closing price**\n","\n","**x=Number of days ago**\n","\n","\n","**Other features calculated are**\n","**moving averages of 7 and 21 days and standard deviation.**\n","\n","\n","**Great Links are:**\n","1. https://www.learndatasci.com/tutorials/python-finance-part-3-moving-average-trading-strategy/\n","2. https://towardsdatascience.com/trading-technical-analysis-with-pandas-43e737a17861"]},{"cell_type":"code","metadata":{"id":"vLLcWPw0Ij5w","colab_type":"code","colab":{}},"source":["dataset_TI_df = get_technical_indicators(dataset_ex_df)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"r0dKh8HeImGj","colab_type":"code","outputId":"d54c120f-28f8-489a-91dd-81ff8d10376c","executionInfo":{"status":"ok","timestamp":1565975607000,"user_tz":240,"elapsed":1234,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":299}},"source":["dataset_TI_df.head()"],"execution_count":26,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>Date</th>\n","      <th>Open</th>\n","      <th>High</th>\n","      <th>Low</th>\n","      <th>Adj Close</th>\n","      <th>Volume</th>\n","      <th>ma7</th>\n","      <th>ma21</th>\n","      <th>26ema</th>\n","      <th>12ema</th>\n","      <th>MACD</th>\n","      <th>20sd</th>\n","      <th>upper_band</th>\n","      <th>lower_band</th>\n","      <th>ema</th>\n","      <th>momentum</th>\n","      <th>Fourier</th>\n","      <th>ARIMA</th>\n","      <th>Close</th>\n","      <th>labels</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>2010-01-04</td>\n","      <td>136.250000</td>\n","      <td>136.610001</td>\n","      <td>133.139999</td>\n","      <td>133.899994</td>\n","      <td>7599900</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>133.899994</td>\n","      <td>0.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>0.3390</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>2010-01-05</td>\n","      <td>133.429993</td>\n","      <td>135.479996</td>\n","      <td>131.809998</td>\n","      <td>134.690002</td>\n","      <td>8851900</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>134.310190</td>\n","      <td>134.327915</td>\n","      <td>0.017725</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>134.492500</td>\n","      <td>0.3469</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>134.690002</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2010-01-06</td>\n","      <td>134.600006</td>\n","      <td>134.729996</td>\n","      <td>131.649994</td>\n","      <td>132.250000</td>\n","      <td>7178800</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.569984</td>\n","      <td>133.516904</td>\n","      <td>-0.053080</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.940000</td>\n","      <td>0.3225</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.250000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>2010-01-07</td>\n","      <td>132.009995</td>\n","      <td>132.320007</td>\n","      <td>128.800003</td>\n","      <td>130.000000</td>\n","      <td>11030200</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.571973</td>\n","      <td>132.406755</td>\n","      <td>-0.165217</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>130.955500</td>\n","      <td>0.3000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>130.000000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>2010-01-08</td>\n","      <td>130.559998</td>\n","      <td>133.679993</td>\n","      <td>129.029999</td>\n","      <td>133.520004</td>\n","      <td>9830500</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.791825</td>\n","      <td>132.709221</td>\n","      <td>-0.082604</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.672234</td>\n","      <td>0.3352</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.520004</td>\n","      <td>NaN</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["        Date        Open        High  ...  ARIMA       Close  labels\n","0 2010-01-04  136.250000  136.610001  ...    NaN  133.899994     NaN\n","1 2010-01-05  133.429993  135.479996  ...    NaN  134.690002     NaN\n","2 2010-01-06  134.600006  134.729996  ...    NaN  132.250000     NaN\n","3 2010-01-07  132.009995  132.320007  ...    NaN  130.000000     NaN\n","4 2010-01-08  130.559998  133.679993  ...    NaN  133.520004     NaN\n","\n","[5 rows x 20 columns]"]},"metadata":{"tags":[]},"execution_count":26}]},{"cell_type":"code","metadata":{"id":"WI5YM1L4IoXg","colab_type":"code","colab":{}},"source":["def plot_technical_indicators(dataset, last_days):\n","    plt.figure(figsize=(16, 10), dpi=100)\n","    shape_0 = dataset.shape[0]\n","    xmacd_ = shape_0-last_days\n","    \n","    dataset = dataset.iloc[-last_days:, :]\n","    x_ = range(3, dataset.shape[0])\n","    x_ =list(dataset.index)\n","    \n","    # Plot first subplot\n","    plt.subplot(2, 1, 1)\n","    plt.plot(dataset['ma7'],label='MA 7', color='g',linestyle='--')\n","    plt.plot(dataset['Close'],label='Closing Price', color='b')\n","    plt.plot(dataset['ma21'],label='MA 21', color='r',linestyle='--')\n","    plt.plot(dataset['upper_band'],label='Upper Band', color='c')\n","    plt.plot(dataset['lower_band'],label='Lower Band', color='c')\n","    plt.fill_between(x_, dataset['lower_band'], dataset['upper_band'], alpha=0.35)\n","    plt.title('Technical indicators for Amazon - last {} days.'.format(last_days))\n","    plt.ylabel('USD')\n","    plt.legend()\n","\n","    # Plot second subplot\n","    plt.subplot(2, 1, 2)\n","    plt.title('MACD')\n","    plt.plot(dataset['MACD'],label='MACD', linestyle='-.')\n","    plt.hlines(15, xmacd_, shape_0, colors='g', linestyles='--')\n","    plt.hlines(-15, xmacd_, shape_0, colors='g', linestyles='--')\n","    plt.plot(dataset['momentum'],label='Momentum', color='b',linestyle='-')\n","\n","    plt.legend()\n","    plt.show()"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"aDPdCgs_I711","colab_type":"code","outputId":"091b667f-315a-4b21-d57b-27b89e8b7857","executionInfo":{"status":"ok","timestamp":1565975610674,"user_tz":240,"elapsed":3147,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":838}},"source":["plot_technical_indicators(dataset_TI_df, 400)"],"execution_count":28,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAABTAAAAM1CAYAAABHcN7rAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nd9TdAAAAAElFTkSuQmCC\n","text/plain":["<Figure size 1600x1000 with 2 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"QGDJXjmK_rly","colab_type":"text"},"source":["**PLOT UNDERSTANDING:** \n","\n","**THE FIRST PLOT IS SELF EXPLANATORY**\n","\n","**THE SECOND PLOT IS SHOWING THE THRESHOLD BETWEEN MACD AND MOMENTUM. AS YOU CAN SEE MOMENTUM IS GIVING AN AVERAGE VALUE OF THE MACD IN BETEEEN THE PEAK VALUES AND THE HIGHEST OR LOWEST VALUES. MACD DEPENDS ON THE MOVING AVERAGE FEATURES AS CALCULATED ABOVE**"]},{"cell_type":"markdown","metadata":{"id":"aq3LlT6lAzho","colab_type":"text"},"source":["\n","\n",">  \n","# **ANALYSIS OF TIME SERIES USING FOURIER TRANSFORM**\n","\n","\n"]},{"cell_type":"code","metadata":{"id":"dyNAHsAFI-EO","colab_type":"code","colab":{}},"source":["data_FT = dataset_ex_df[['Date', 'Close']]\n","close_fft = np.fft.fft(np.asarray(data_FT['Close'].tolist()))\n","fft_df = pd.DataFrame({'fft':close_fft})\n","fft_df['absolute'] = fft_df['fft'].apply(lambda x: np.abs(x))\n","fft_df['angle'] = fft_df['fft'].apply(lambda x: np.angle(x))"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"U58-Ziw0Jq_3","colab_type":"code","outputId":"2ec51045-ab8a-42f3-a273-7bd55d9b5c22","executionInfo":{"status":"ok","timestamp":1565975617627,"user_tz":240,"elapsed":1923,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":631}},"source":["plt.figure(figsize=(14, 7), dpi=100)\n","fft_list = np.asarray(fft_df['fft'].tolist())\n","for num_ in [3, 6, 9, 100]:\n","    fft_list_m10= np.copy(fft_list); fft_list_m10[num_:-num_]=0\n","    plt.plot(np.fft.ifft(fft_list_m10), label='Fourier transform with {} components'.format(num_))\n","plt.plot(data_FT['Close'],  label='Real')\n","plt.xlabel('Days')\n","plt.ylabel('USD')\n","plt.title('Figure 3: Amazon (close) stock prices & Fourier transforms')\n","plt.legend()\n","plt.show()\n"],"execution_count":30,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAABJQAAAJmCAYAAAAKINptAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n","text/plain":["<Figure size 1400x700 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"Lx_CZZsMDm0U","colab_type":"text"},"source":["**Fourier Transform uses many spectral components to try and train data. From time domain its converted to frequency domain and then calculated. After that it's reconverted into time domain where it's plotted.**\n","**Fourier Transform as indicator helps to extract predominate cycle from a series of data**\n","\n","**Reference: https://www.metastock.com/customer/resources/taaz/?p=58**\n","\n","**In the above example we can see the spectral component of 100 is closest to the real price so we will move ahead ith 100**\n","\n","\n"]},{"cell_type":"code","metadata":{"id":"S92mKcpwJtak","colab_type":"code","colab":{}},"source":["\n","def get_fourier(dataset):\n","    data_FT = dataset[['Date', 'Close']]\n","    close_fft = np.fft.fft(np.asarray(data_FT['Close'].tolist()))\n","    close_fft = np.fft.ifft(close_fft)\n","    close_fft\n","    fft_df = pd.DataFrame({'fft':close_fft})\n","    fft_df['absolute'] = fft_df['fft'].apply(lambda x: np.abs(x))\n","    fft_df['angle'] = fft_df['fft'].apply(lambda x: np.angle(x))\n","    fft_list = np.asarray(fft_df['fft'].tolist())\n","    fft_list_m10= np.copy(fft_list); fft_list_m10[100:-100]=0\n","    dataset['Fourier'] = pd.DataFrame(fft_list_m10).apply(lambda x: np.abs(x))\n","    #dataset['absolute'] = dataset['Fourier'].apply(lambda x: np.abs(x))\n","    return dataset"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"UxWEoAzIJ0xu","colab_type":"code","colab":{}},"source":["dataset_TI_df = get_fourier(dataset_ex_df)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"zlqkfBlQJ9ZR","colab_type":"code","outputId":"81b16f3e-0866-4c8f-990a-6fa45f91a37f","executionInfo":{"status":"ok","timestamp":1565975621384,"user_tz":240,"elapsed":1756,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":1000}},"source":["dataset_TI_df.head(30)"],"execution_count":33,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>Date</th>\n","      <th>Open</th>\n","      <th>High</th>\n","      <th>Low</th>\n","      <th>Adj Close</th>\n","      <th>Volume</th>\n","      <th>ma7</th>\n","      <th>ma21</th>\n","      <th>26ema</th>\n","      <th>12ema</th>\n","      <th>MACD</th>\n","      <th>20sd</th>\n","      <th>upper_band</th>\n","      <th>lower_band</th>\n","      <th>ema</th>\n","      <th>momentum</th>\n","      <th>Fourier</th>\n","      <th>ARIMA</th>\n","      <th>Close</th>\n","      <th>labels</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>2010-01-04</td>\n","      <td>136.250000</td>\n","      <td>136.610001</td>\n","      <td>133.139999</td>\n","      <td>133.899994</td>\n","      <td>7599900</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>133.899994</td>\n","      <td>0.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>0.3390</td>\n","      <td>133.899994</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>2010-01-05</td>\n","      <td>133.429993</td>\n","      <td>135.479996</td>\n","      <td>131.809998</td>\n","      <td>134.690002</td>\n","      <td>8851900</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>134.310190</td>\n","      <td>134.327915</td>\n","      <td>0.017725</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>134.492500</td>\n","      <td>0.3469</td>\n","      <td>134.690002</td>\n","      <td>NaN</td>\n","      <td>134.690002</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2010-01-06</td>\n","      <td>134.600006</td>\n","      <td>134.729996</td>\n","      <td>131.649994</td>\n","      <td>132.250000</td>\n","      <td>7178800</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.569984</td>\n","      <td>133.516904</td>\n","      <td>-0.053080</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.940000</td>\n","      <td>0.3225</td>\n","      <td>132.250000</td>\n","      <td>NaN</td>\n","      <td>132.250000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>2010-01-07</td>\n","      <td>132.009995</td>\n","      <td>132.320007</td>\n","      <td>128.800003</td>\n","      <td>130.000000</td>\n","      <td>11030200</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.571973</td>\n","      <td>132.406755</td>\n","      <td>-0.165217</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>130.955500</td>\n","      <td>0.3000</td>\n","      <td>130.000000</td>\n","      <td>NaN</td>\n","      <td>130.000000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>2010-01-08</td>\n","      <td>130.559998</td>\n","      <td>133.679993</td>\n","      <td>129.029999</td>\n","      <td>133.520004</td>\n","      <td>9830500</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.791825</td>\n","      <td>132.709221</td>\n","      <td>-0.082604</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.672234</td>\n","      <td>0.3352</td>\n","      <td>133.520004</td>\n","      <td>NaN</td>\n","      <td>133.520004</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>2010-01-11</td>\n","      <td>132.619995</td>\n","      <td>132.800003</td>\n","      <td>129.210007</td>\n","      <td>130.309998</td>\n","      <td>8779400</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.294735</td>\n","      <td>132.126083</td>\n","      <td>-0.168651</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>131.095247</td>\n","      <td>0.3031</td>\n","      <td>130.309998</td>\n","      <td>NaN</td>\n","      <td>130.309998</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>6</th>\n","      <td>2010-01-12</td>\n","      <td>128.990005</td>\n","      <td>129.820007</td>\n","      <td>126.550003</td>\n","      <td>127.349998</td>\n","      <td>9096300</td>\n","      <td>131.717142</td>\n","      <td>NaN</td>\n","      <td>131.415339</td>\n","      <td>131.060317</td>\n","      <td>-0.355022</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>128.597272</td>\n","      <td>0.2735</td>\n","      <td>127.349998</td>\n","      <td>NaN</td>\n","      <td>127.349998</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>7</th>\n","      <td>2010-01-13</td>\n","      <td>127.900002</td>\n","      <td>129.710007</td>\n","      <td>125.750000</td>\n","      <td>129.110001</td>\n","      <td>10723200</td>\n","      <td>131.032858</td>\n","      <td>NaN</td>\n","      <td>131.043892</td>\n","      <td>130.653316</td>\n","      <td>-0.390576</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>128.939143</td>\n","      <td>0.2911</td>\n","      <td>129.110001</td>\n","      <td>NaN</td>\n","      <td>129.110001</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>8</th>\n","      <td>2010-01-14</td>\n","      <td>129.139999</td>\n","      <td>130.380005</td>\n","      <td>126.400002</td>\n","      <td>127.349998</td>\n","      <td>9774900</td>\n","      <td>129.984286</td>\n","      <td>NaN</td>\n","      <td>130.496376</td>\n","      <td>129.999802</td>\n","      <td>-0.496574</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>127.879659</td>\n","      <td>0.2735</td>\n","      <td>127.349998</td>\n","      <td>NaN</td>\n","      <td>127.349998</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>9</th>\n","      <td>2010-01-15</td>\n","      <td>129.179993</td>\n","      <td>129.649994</td>\n","      <td>127.059998</td>\n","      <td>127.139999</td>\n","      <td>15376500</td>\n","      <td>129.254285</td>\n","      <td>NaN</td>\n","      <td>130.033228</td>\n","      <td>129.457870</td>\n","      <td>-0.575358</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>127.386544</td>\n","      <td>0.2714</td>\n","      <td>127.139999</td>\n","      <td>NaN</td>\n","      <td>127.139999</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>10</th>\n","      <td>2010-01-19</td>\n","      <td>126.309998</td>\n","      <td>128.000000</td>\n","      <td>124.330002</td>\n","      <td>127.610001</td>\n","      <td>8892600</td>\n","      <td>128.912857</td>\n","      <td>NaN</td>\n","      <td>129.718935</td>\n","      <td>129.119755</td>\n","      <td>-0.599180</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>127.535516</td>\n","      <td>0.2761</td>\n","      <td>127.610001</td>\n","      <td>NaN</td>\n","      <td>127.610001</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>11</th>\n","      <td>2010-01-20</td>\n","      <td>127.129997</td>\n","      <td>129.199997</td>\n","      <td>125.080002</td>\n","      <td>125.779999</td>\n","      <td>9074700</td>\n","      <td>127.807142</td>\n","      <td>NaN</td>\n","      <td>129.234975</td>\n","      <td>128.525957</td>\n","      <td>-0.709017</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>126.365169</td>\n","      <td>0.2578</td>\n","      <td>125.779999</td>\n","      <td>NaN</td>\n","      <td>125.779999</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>12</th>\n","      <td>2010-01-21</td>\n","      <td>127.260002</td>\n","      <td>128.149994</td>\n","      <td>125.000000</td>\n","      <td>126.620003</td>\n","      <td>9970600</td>\n","      <td>127.280000</td>\n","      <td>NaN</td>\n","      <td>128.928631</td>\n","      <td>128.195011</td>\n","      <td>-0.733620</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>126.535059</td>\n","      <td>0.2662</td>\n","      <td>126.620003</td>\n","      <td>NaN</td>\n","      <td>126.620003</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>13</th>\n","      <td>2010-01-22</td>\n","      <td>125.599998</td>\n","      <td>127.669998</td>\n","      <td>120.760002</td>\n","      <td>121.430000</td>\n","      <td>11568900</td>\n","      <td>126.434286</td>\n","      <td>NaN</td>\n","      <td>128.086446</td>\n","      <td>127.043146</td>\n","      <td>-1.043300</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>123.131685</td>\n","      <td>0.2143</td>\n","      <td>121.430000</td>\n","      <td>NaN</td>\n","      <td>121.430000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>14</th>\n","      <td>2010-01-25</td>\n","      <td>122.099998</td>\n","      <td>122.279999</td>\n","      <td>118.120003</td>\n","      <td>120.309998</td>\n","      <td>12023900</td>\n","      <td>125.177143</td>\n","      <td>NaN</td>\n","      <td>127.245225</td>\n","      <td>125.915228</td>\n","      <td>-1.329996</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>121.250560</td>\n","      <td>0.2031</td>\n","      <td>120.309998</td>\n","      <td>NaN</td>\n","      <td>120.309998</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>15</th>\n","      <td>2010-01-26</td>\n","      <td>120.559998</td>\n","      <td>122.980003</td>\n","      <td>119.059998</td>\n","      <td>119.480003</td>\n","      <td>9559000</td>\n","      <td>124.052858</td>\n","      <td>NaN</td>\n","      <td>126.432919</td>\n","      <td>124.851757</td>\n","      <td>-1.581162</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>120.070189</td>\n","      <td>0.1948</td>\n","      <td>119.480003</td>\n","      <td>NaN</td>\n","      <td>119.480003</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>16</th>\n","      <td>2010-01-27</td>\n","      <td>121.029999</td>\n","      <td>123.330002</td>\n","      <td>118.800003</td>\n","      <td>122.750000</td>\n","      <td>14765300</td>\n","      <td>123.425715</td>\n","      <td>NaN</td>\n","      <td>126.059070</td>\n","      <td>124.508344</td>\n","      <td>-1.550727</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>121.856730</td>\n","      <td>0.2275</td>\n","      <td>122.750000</td>\n","      <td>NaN</td>\n","      <td>122.750000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>17</th>\n","      <td>2010-01-28</td>\n","      <td>124.430000</td>\n","      <td>127.199997</td>\n","      <td>122.800003</td>\n","      <td>126.029999</td>\n","      <td>27293100</td>\n","      <td>123.200000</td>\n","      <td>NaN</td>\n","      <td>126.056198</td>\n","      <td>124.754621</td>\n","      <td>-1.301577</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>124.638909</td>\n","      <td>0.2603</td>\n","      <td>126.029999</td>\n","      <td>NaN</td>\n","      <td>126.029999</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>18</th>\n","      <td>2010-01-29</td>\n","      <td>129.770004</td>\n","      <td>131.850006</td>\n","      <td>124.139999</td>\n","      <td>125.410004</td>\n","      <td>29471300</td>\n","      <td>123.147144</td>\n","      <td>NaN</td>\n","      <td>125.993896</td>\n","      <td>124.859851</td>\n","      <td>-1.134044</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>125.152972</td>\n","      <td>0.2541</td>\n","      <td>125.410004</td>\n","      <td>NaN</td>\n","      <td>125.410004</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>19</th>\n","      <td>2010-02-01</td>\n","      <td>123.180000</td>\n","      <td>124.860001</td>\n","      <td>113.820000</td>\n","      <td>118.870003</td>\n","      <td>37774400</td>\n","      <td>122.040001</td>\n","      <td>NaN</td>\n","      <td>125.322058</td>\n","      <td>123.904519</td>\n","      <td>-1.417540</td>\n","      <td>4.720928</td>\n","      <td>136.437356</td>\n","      <td>117.553645</td>\n","      <td>120.964326</td>\n","      <td>0.1887</td>\n","      <td>118.870003</td>\n","      <td>NaN</td>\n","      <td>118.870003</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>20</th>\n","      <td>2010-02-02</td>\n","      <td>118.790001</td>\n","      <td>118.980003</td>\n","      <td>114.400002</td>\n","      <td>118.120003</td>\n","      <td>23079700</td>\n","      <td>121.567144</td>\n","      <td>126.572857</td>\n","      <td>124.656320</td>\n","      <td>122.987114</td>\n","      <td>-1.669206</td>\n","      <td>4.823779</td>\n","      <td>135.854058</td>\n","      <td>116.558943</td>\n","      <td>119.068111</td>\n","      <td>0.1812</td>\n","      <td>118.120003</td>\n","      <td>NaN</td>\n","      <td>118.120003</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>21</th>\n","      <td>2010-02-03</td>\n","      <td>117.120003</td>\n","      <td>119.610001</td>\n","      <td>116.559998</td>\n","      <td>119.099998</td>\n","      <td>12405900</td>\n","      <td>121.394287</td>\n","      <td>125.868096</td>\n","      <td>124.151970</td>\n","      <td>122.373546</td>\n","      <td>-1.778424</td>\n","      <td>4.636742</td>\n","      <td>134.700485</td>\n","      <td>116.153516</td>\n","      <td>119.089369</td>\n","      <td>0.1910</td>\n","      <td>119.099998</td>\n","      <td>NaN</td>\n","      <td>119.099998</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>22</th>\n","      <td>2010-02-04</td>\n","      <td>118.639999</td>\n","      <td>120.330002</td>\n","      <td>115.739998</td>\n","      <td>115.940002</td>\n","      <td>12784000</td>\n","      <td>120.888573</td>\n","      <td>124.975239</td>\n","      <td>123.418807</td>\n","      <td>121.362079</td>\n","      <td>-2.056729</td>\n","      <td>4.804807</td>\n","      <td>134.221114</td>\n","      <td>115.001887</td>\n","      <td>116.989791</td>\n","      <td>0.1594</td>\n","      <td>115.940002</td>\n","      <td>NaN</td>\n","      <td>115.940002</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>23</th>\n","      <td>2010-02-05</td>\n","      <td>115.879997</td>\n","      <td>117.650002</td>\n","      <td>114.099998</td>\n","      <td>117.389999</td>\n","      <td>11024800</td>\n","      <td>120.122858</td>\n","      <td>124.267620</td>\n","      <td>122.888619</td>\n","      <td>120.739696</td>\n","      <td>-2.148923</td>\n","      <td>4.887152</td>\n","      <td>133.755304</td>\n","      <td>114.206697</td>\n","      <td>117.256596</td>\n","      <td>0.1739</td>\n","      <td>117.389999</td>\n","      <td>NaN</td>\n","      <td>117.389999</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>24</th>\n","      <td>2010-02-08</td>\n","      <td>119.379997</td>\n","      <td>121.000000</td>\n","      <td>116.559998</td>\n","      <td>116.830002</td>\n","      <td>9890200</td>\n","      <td>118.808573</td>\n","      <td>123.640477</td>\n","      <td>122.363097</td>\n","      <td>120.128825</td>\n","      <td>-2.234272</td>\n","      <td>4.588413</td>\n","      <td>132.323326</td>\n","      <td>113.969674</td>\n","      <td>116.972200</td>\n","      <td>0.1683</td>\n","      <td>116.830002</td>\n","      <td>NaN</td>\n","      <td>116.830002</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>25</th>\n","      <td>2010-02-09</td>\n","      <td>118.199997</td>\n","      <td>119.089996</td>\n","      <td>117.000000</td>\n","      <td>118.029999</td>\n","      <td>9223000</td>\n","      <td>117.754287</td>\n","      <td>122.902857</td>\n","      <td>121.991946</td>\n","      <td>119.801678</td>\n","      <td>-2.190268</td>\n","      <td>4.397009</td>\n","      <td>131.326519</td>\n","      <td>113.738482</td>\n","      <td>117.677399</td>\n","      <td>0.1803</td>\n","      <td>118.029999</td>\n","      <td>NaN</td>\n","      <td>118.029999</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>26</th>\n","      <td>2010-02-10</td>\n","      <td>118.000000</td>\n","      <td>118.610001</td>\n","      <td>116.000000</td>\n","      <td>117.360001</td>\n","      <td>6233200</td>\n","      <td>117.538572</td>\n","      <td>122.286191</td>\n","      <td>121.599740</td>\n","      <td>119.421860</td>\n","      <td>-2.177880</td>\n","      <td>4.388361</td>\n","      <td>130.809723</td>\n","      <td>113.256278</td>\n","      <td>117.465800</td>\n","      <td>0.1736</td>\n","      <td>117.360001</td>\n","      <td>NaN</td>\n","      <td>117.360001</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>27</th>\n","      <td>2010-02-11</td>\n","      <td>117.209999</td>\n","      <td>120.419998</td>\n","      <td>116.500000</td>\n","      <td>120.089996</td>\n","      <td>8343500</td>\n","      <td>117.820000</td>\n","      <td>121.940477</td>\n","      <td>121.473245</td>\n","      <td>119.525615</td>\n","      <td>-1.947629</td>\n","      <td>4.075084</td>\n","      <td>129.732168</td>\n","      <td>113.431832</td>\n","      <td>119.215264</td>\n","      <td>0.2009</td>\n","      <td>120.089996</td>\n","      <td>NaN</td>\n","      <td>120.089996</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>28</th>\n","      <td>2010-02-12</td>\n","      <td>118.989998</td>\n","      <td>119.940002</td>\n","      <td>117.500000</td>\n","      <td>119.660004</td>\n","      <td>8073500</td>\n","      <td>117.900000</td>\n","      <td>121.490477</td>\n","      <td>121.322782</td>\n","      <td>119.546454</td>\n","      <td>-1.776327</td>\n","      <td>3.859284</td>\n","      <td>128.916068</td>\n","      <td>113.478933</td>\n","      <td>119.511757</td>\n","      <td>0.1966</td>\n","      <td>119.660004</td>\n","      <td>NaN</td>\n","      <td>119.660004</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>29</th>\n","      <td>2010-02-16</td>\n","      <td>120.059998</td>\n","      <td>120.500000</td>\n","      <td>117.180000</td>\n","      <td>117.529999</td>\n","      <td>8932700</td>\n","      <td>118.127143</td>\n","      <td>121.022858</td>\n","      <td>121.010834</td>\n","      <td>119.234151</td>\n","      <td>-1.776684</td>\n","      <td>3.674285</td>\n","      <td>128.065571</td>\n","      <td>113.368431</td>\n","      <td>118.190585</td>\n","      <td>0.1753</td>\n","      <td>117.529999</td>\n","      <td>NaN</td>\n","      <td>117.529999</td>\n","      <td>NaN</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["         Date        Open        High  ...  ARIMA       Close  labels\n","0  2010-01-04  136.250000  136.610001  ...    NaN  133.899994     NaN\n","1  2010-01-05  133.429993  135.479996  ...    NaN  134.690002     NaN\n","2  2010-01-06  134.600006  134.729996  ...    NaN  132.250000     NaN\n","3  2010-01-07  132.009995  132.320007  ...    NaN  130.000000     NaN\n","4  2010-01-08  130.559998  133.679993  ...    NaN  133.520004     NaN\n","5  2010-01-11  132.619995  132.800003  ...    NaN  130.309998     NaN\n","6  2010-01-12  128.990005  129.820007  ...    NaN  127.349998     NaN\n","7  2010-01-13  127.900002  129.710007  ...    NaN  129.110001     NaN\n","8  2010-01-14  129.139999  130.380005  ...    NaN  127.349998     NaN\n","9  2010-01-15  129.179993  129.649994  ...    NaN  127.139999     NaN\n","10 2010-01-19  126.309998  128.000000  ...    NaN  127.610001     NaN\n","11 2010-01-20  127.129997  129.199997  ...    NaN  125.779999     NaN\n","12 2010-01-21  127.260002  128.149994  ...    NaN  126.620003     NaN\n","13 2010-01-22  125.599998  127.669998  ...    NaN  121.430000     NaN\n","14 2010-01-25  122.099998  122.279999  ...    NaN  120.309998     NaN\n","15 2010-01-26  120.559998  122.980003  ...    NaN  119.480003     NaN\n","16 2010-01-27  121.029999  123.330002  ...    NaN  122.750000     NaN\n","17 2010-01-28  124.430000  127.199997  ...    NaN  126.029999     NaN\n","18 2010-01-29  129.770004  131.850006  ...    NaN  125.410004     NaN\n","19 2010-02-01  123.180000  124.860001  ...    NaN  118.870003     NaN\n","20 2010-02-02  118.790001  118.980003  ...    NaN  118.120003     NaN\n","21 2010-02-03  117.120003  119.610001  ...    NaN  119.099998     NaN\n","22 2010-02-04  118.639999  120.330002  ...    NaN  115.940002     NaN\n","23 2010-02-05  115.879997  117.650002  ...    NaN  117.389999     NaN\n","24 2010-02-08  119.379997  121.000000  ...    NaN  116.830002     NaN\n","25 2010-02-09  118.199997  119.089996  ...    NaN  118.029999     NaN\n","26 2010-02-10  118.000000  118.610001  ...    NaN  117.360001     NaN\n","27 2010-02-11  117.209999  120.419998  ...    NaN  120.089996     NaN\n","28 2010-02-12  118.989998  119.940002  ...    NaN  119.660004     NaN\n","29 2010-02-16  120.059998  120.500000  ...    NaN  117.529999     NaN\n","\n","[30 rows x 20 columns]"]},"metadata":{"tags":[]},"execution_count":33}]},{"cell_type":"code","metadata":{"id":"SejcfAlJJ_qE","colab_type":"code","outputId":"5c12c30e-ac56-420e-bec3-16e3d82caf06","executionInfo":{"status":"ok","timestamp":1565975629929,"user_tz":240,"elapsed":8558,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":490}},"source":["from collections import deque\n","items = deque(np.asarray(fft_df['absolute'].tolist()))\n","items.rotate(int(np.floor(len(fft_df)/2)))\n","plt.figure(figsize=(10, 7), dpi=80)\n","plt.stem(items)\n","plt.title('Figure 4: Components of Fourier transforms')\n","plt.show()"],"execution_count":34,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAArgAAAHZCAYAAABtgEhNAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAMTQAADE0B0s6tTgAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzt3X10XWd55/3vpZfYlp04fiUhsq2Q\nhJRCSwp5o5QknQBT2pkHBloYmBBIeJ2WZ3iWy5ROSls6tCzKtOks2ukACZmQBCikzIL2KdBJIQkU\nCLahQEJL4hDLtoztRJYT25Jjy9I1f5ytcKJItqyXc3RufT9rnWWdfd9772ufvY/80z733icyE0mS\nJKkUbc0uQJIkSZpNBlxJkiQVxYArSZKkohhwJUmSVBQDriRJkopiwJUkSVJRDLiSJEkqigFXahER\n8YyIOBQR65tdi8oWER+KiEeq4+1Zza5nTET8bkR8sdl1zKXqff71iDgQEV9tdj1SqzLgSvNIRNwV\nEUerYDH2+CpAZj6Umcsyc0ez6zyeiLgkIo5FxF3TmDci4tqIuCciDkbEQER8PyJ+LyJOm4NyW0pE\nvDkieud4HS8C3gL8bHW8/csEff4wIkbGHaeHImLRXNaWme/LzJfN9nIj4raIuHm2lztNvwPsBU7P\nzMuaXYzUqgy40vzzwSpYjD0a9p9cRJwyw/mXADcBd01zETcAfwT8GbAuM1cCrwbOAJ4zk9o0ZecA\nezNz9wn6fW3ccbosM4/MRUHVHz4ds7CcaR/fEdEeETHTGqbgHOD7mTk63QVEROcs1iO1JAOu1CIi\n4tyIyIjoqZ5HRPxOROyMiP0R8dGI+GxE3Fi1d1T9rzjOMt4cEb0R8Z8iYjvwcDV9SUR8ICIerJZ9\nd0Q8dwplfgD4InDPNLbvMuBNwL/PzE9n5qMAmfnDzPz1zPxG1W9FRNwYEbsioj8i/i4izqtbzh9W\n9f5RROyJiMci4v0RsTIibq+ePxQR/6ZunrHXYWO13H3VOpbW9VlXzb+3Wu6nIuKMuvbbIuITEfGX\n1fx7IuK947bxp6t6H67W8xcR0VXX3hcR74mIL1VnRLdGxMurtiuAvwDW150xfU1ELIqIj1R1HYyI\nbRHxH4/zOk+6HRHxR8CH69bxvZPdj1N8rf5xgtemLyLeWP08dpxeGxHfB4aAC6p9e1fdPMc9TuuO\nhfdHxI+BLRPU+rvAa4D/UPe6Pj0iXlzV8JqI2FrVsCoi/n1EfCciHo3aMI7PRcSGuuWNHUu/HhHb\nq+Pt0xFxatUe1bHZV+2vvoh4X9XWC7wIuK6q47eq6S+sXrP91f79o6gL69Uyfj8i/k9EHATeWVf/\nq6vjaDAiPh8Ry+Mn741HIuL36pazIiI+E7X31YGIuD8i/t3J7n9pPjDgSq3rGuD/A14JrAG+Dfw/\n01hON/BTwE8DT6+m3QD8HHBZtez/Dfx9RCyfbCER8YvAS4H3TNL+OxHxnePU8SvAjsy8+wT1fhLo\nAZ4HrAceAu6oD4rAzwO7q23718BvAX9P7czwCmoh7uaIWFw3Tze11+CZwHOr5f9JVXsH8AXgSNX+\nLOAU4PMRUf979FXAncBa4FeB90TtI38iYi3wtaqObuCCan1/Om773gz8NnAatf1wS0Qsy8y7gHdU\nr9HYGdNPA9cCzweelZmnVts+4R8YJ9qOzPydceuYyh81J7WOk1zcG4FfBpYB907QPpXj9IXAIHA2\ncOn4BWTm+4BPA5+oe11/XNfl14BLqO2P/cCBqq5VwLOBTuC2cYs9C3gGtffVs4CLqL1XAX4JeD1w\nabW/ngv8XVVLD/BN4P1VHR+M2h+jd1Q1Po3a8fxK4P3j1vk24HerOv+ybvrLqtfoGdQ+BdkE7KR2\nDL4C+P2IuKjq+9vAYmrvr+XVun44/jWTWkJm+vDhY548qH20/zjwaN3j9VXbuUACPXV93z9u/u8C\nN1Y/d1T9r6hrH7+MNwNHgcV1fZ5W9Tln3LK3UTu7OlHdpwI/An6+ev6HwF0nue3/C/j6Cfqsq2p7\ndt20U6gFj1+tW/f94+a7F/gfE2zjs+teh2PAqXV9/i1wmNqJgBdV7cvr2tdWy7iwen4b8H/Grfef\ngN+sfv4tah/r17dfTu3MYFTP+4Dr6tqXV+t4fl2dveOW8Sbg/qrGzhO8flPZjqesY4Ll/GG1nPrj\n9C9PYh3/CLx33DL7gDeOO06vnGC9d031OK367xh7fY+zPbcBN4+b9uKJlj/BvBcBo0BX3es3BHTU\n9fkz4G+rn6+k9knJLwFLJljek14baqF187g+vwYcHPfavW+S+s+sm/bnwA/G9fsX4Deqn98HfJ3a\nH0xtJ/P+9eFjvj08gyvNP3+SmafXPW6dpN9ZwPZx03qnsb49mfl43fNzq3+/XX0M+2hEPEotUHRP\nsow/Az6f1TCCaXr4OMsfs67690djEzLzKLUQU393ifHjRwfHTRus/j21blp/Zh6se76N2tms1dV6\n+zPzsbr1PkztbF79euvP/I2tZ2wd5wGXjHtN/4ZagF47yTImqnO8jwM3UjsT3B8RX4iIn5uk71S3\nYyr+cdxx+utzsI5tx2mb6nHam5l5kuudtIaI+FcR8ZXqI/4DwJeBoHYGeczDmXms7vkTx0Fmfpna\nhWTXAXujdmHplcdZ/zrqjvfKg8CyiFg5WZ1j8sljqce/D55UG7UhRndS+2Ozvxqu8Izj1CbNWwZc\nqXXtAjaMm/bE8+o/2MeBpXXtT+epxl/Msqf696fHBZiuzPyTSWr5JeCaauxeP7AReGH1/Owpbs/f\nURv7ebyL6nZW/54zNqEai7iOWsididURsazueQ+1j9n7q/Wujro7OUTEGmofB091vXuonX2sf02X\nZ+bizNw7xWU85cKjzDyWmf8tMy+mFuy2Ap+bZP7Z2I4Tmco6DlJ3XEbtoqj6gDjmeBdaTfU4ncrF\nWpP2ybqLvaohLX8L/P/AuZl5GrUzslALuVOSmTdk7eLRtdSGc/ztuCE29XZSd7xXzgEOZebAVLbh\nJOoazMz3ZObPUvuDLKiFXanlGHCl1nUr8OaIeH7ULih7M0+908AWasFzcdQu8vm9pyxlnMz8EbX/\nwP8yqnvuRsSpEfHLEfG0SWa7EPgZauNKL6A2NnJL9fOUglNmfhX4GPCpiPi1sXGUEXFeRPx5RPx8\nZu6kGksbEWurUPBB4BC1i9tm6k8joisizgLeC3y8CjjfpDYW8c8j4rSIOB34H9U2Hm9ccb2bgIsj\n4m1RuzgqImJ9VBeRTdEeYE1ErBibUF1M9PwqJD5O7YzcsUnmn43tOJGprGML8IqIODNqd974INB+\nMiuZ5nE6mT3AuRFxohoWUTurP5CZhyKim9rH+lMWtdvovagKy0ephf1k8oB6G/CcqF201hm1Cyr/\nK7X32KyKiJdH7ULIdmrDLA4z+bEkzWsGXKl1/S9qV9V/HngEuJhayKsfbvAfqT4yphYMPz7FZb+G\n2rjVL1dXZf+Q2ljPCWXmnszsG3tQ+0/7SPV8BJ64Sf+Jrsp/C7UQ/i5gV0QMAJ+ldl/QsYuM/gO1\nMYffpRaezwdempmDT13cSemjNpZ1K/D96vGb1fYdo3YR3DJqHw/fTy2UvDyneDunzNxG7QKwl1H7\nOPlR4EvULlSaqjuo7eMHq4/kX03tI/lbqI1Dfhh4AbVbq01Uw4y340SmuI4/Ab5Xtf0Q+Gd+ckb2\nZJzUcXocH6Y2Zr2/el0n+qSDatjFW4E/iIhD1AL2Z05yXacB/53ae3aA2sWirxg3TKh+nduoXbx5\nVTXPHdTe8//lJNc7FedUyz5A7f2wktp7Umo5Yxc2SCpARNxH7azjf2t2La2kOvv9nqxdxS5JanGe\nwZVaWNTuybm4+sj7P1MbN/fXza5LkqRmMuBKre3t1D6+f5jax7X/tvpIU5KkBcshCpIkSSqKZ3Al\nSZJUFAOuJEmSitLR7ALmg0WLFuWaNRPdY1ySJEnzwa5du45m5qKp9DXgAmvWrKGvr6/ZZUiSJGkS\nEfHIVPs6REGSJElFMeBKkiSpKAZcSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJ\nKooBV5IkSUUx4EqSJKkoBlxJkiQVxYArSZKkohhwJUmSVBQDriRJkorS0ewCJEmzJzPZsn0/vf2D\n9KxeyoUbVhARzS5LkhrKgCtJhejbP8TVN21i58AQne1tDI+Msm5lF7dcezHdK7qaXZ4kNYxDFCSp\nAJnJ1TdtYvu+IYZHkqGjIwyPJNv3DfGGmzaRmc0uUZIaxoArSQXYsn0/fQOHGRl9cpAdGU12DAyx\nZfv+JlUmSY1nwJWkAvT2D9LRPvFY2872Nnr7BxtckSQ1jwFXkgrQs3opwyOjE7YNj4zSs3ppgyuS\npOYx4EpSAS7csIJ1K7tob3vyWdz2tmD9yi4u3LCiSZVJUuMZcCWpABHBLddezIZVXdVz6GwPelZ1\nccubLvFWYZIWlPDKWuju7s6+vr5mlyFJM5aZvOiDdzI8MspfvO553gdXUjEiYldmdk+lr/fBlaSC\nRARLOttZ0tnORT0rm12OJDWFQxQkSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqKAVeSJElFMeBKkiSp\nKFMKuBHxoYjojYiMiAuqaYsj4nMR8UBEfC8i7oiIc+vmWRsRX4qIrRFxX0Rc1qw2SZIkLRxTPYP7\n18AvANvHTf8ocH5mPhf4PHBjXdsHgHsy8zzgGuCTEdHZpDZJkiQtEFMKuJn51czsGzft8cz8Qv7k\nq9DuAXrqurwa+HDVdzPwY+DyJrVJkiRpgZjNMbjvpHYWl4hYBXRm5p669l5gfaPbZmG7JEmS1EJm\n5at6I+I64FzgytlY3lyLiI3AxrHny5cvb2I1kiRJmk0zPoMbEe8CXgm8LDOHADJzH3AsIs6o69oD\n7Gh020Q1Z+b1mdk99li2bNnJbrYkSZLmqRkF3OpM6GuBl2Tmo+OabwfeXvW7CDgLuLtJbZIkSVog\npjREISI+AvwKcAbw9xFxELgC+FPgIeDOiAA4kpmXVLO9G7g1IrYCR4GrMnO4SW2SJElaIKYUcDPz\nbZM0xXHm2Qu8dD60SZIkaeHwm8wkSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqKAVeSJElFMeBKkiSp\nKAZcSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJKooBV5IkSUUx4EqSJKkoBlxJ\nkiQVxYArSZKkohhwJUmSVBQDriRJkopiwJUkSVJRDLiSJEkqigFXkiRJRTHgSpIkqSgGXEmSJBXF\ngCtJkqSiGHAlSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqKAVeSJElFMeBKkiSpKAZcSZIkFcWAK0mS\npKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJKooBV5IkSUUx4EqSJKkoBlxJkiQVxYArSZKkohhw\nJUmSVBQDriRJkopiwJUkSVJRDLiSJEkqigFXkiRJRTHgSpIkqSgGXEmSJBXFgCtJkqSiGHAlSZJU\nFAOuJEmSimLAlSRJUlEMuJIkSSrKlAJuRHwoInojIiPigrrp50XENyLigYjYHBHPno9tkiRJWjim\negb3r4FfALaPm/4R4KOZ+Uzgj4Gb52mbJEmSFojIzKl3jugFXpGZ342ItcCDwMrMPBYRAeymFoQP\nzJe2zHzwRNvV3d2dfX19U34dJGk+e8n1dwNwx8bLm1yJJM2eiNiVmd1T6dsxg/WsA3Zn5jGAzMyI\n2AGsBx6bR20nDLiSJEkqx4K8yCwiNkZE39jj0KFDzS5JkiRJs2QmAXcncGZEdABUwwLWAzvmWdtT\nZOb1mdk99li2bNkMXgZJkiTNJ9MOuJn5MPAd4Kpq0quAvsx8cD61TXf7JEmS1JqmdJFZRHwE+BXg\nDGAfcDAzz42I86ndrWAVtQu9rsnMe6t55k3biXiRmaSSeJGZpBLN+kVmmfm2SabfD7xgvrdJkiRp\n4ViQF5lJkiSpXAZcSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJKooBV5IkSUUx\n4EqSJKkoBlxJkiQVxYArSZKkohhwJUmSVBQDriRJkopiwJUkSVJRDLiSJEkqigFXkiRJRTHgSpIk\nqSgGXEmSJBXFgCtJkqSiGHAlSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqKAVeSJElFMeBKkiSpKAZc\nSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJKooBV5IkSUUx4EqSJKkoBlxJkiQV\nxYArSZKkohhwJUmSVBQDriRJkopiwJUkSVJRDLiSJEkqigFXkiRJRTHgSpIkqSgGXEmSJBXFgCtJ\nkqSiGHAlSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqKAVeSJElFMeBKkiSpKAZcSZIkFcWAK0mSpKIY\ncCVJklQUA64kSZKKMisBNyJ+OSK+ExHfjYj7IuIN1fS1EfGliNhaTb+sbp6GtkmSJGlhmHHAjYgA\nbgPemJkXAP8G+EhEnAp8ALgnM88DrgE+GRGd1ayNbpMkSdICMFtDFBI4vfr5NGAfcAR4NfBhgMzc\nDPwYuLzq1+g2SZIkLQAdM11AZmZEvAb43xExCKwAXgmcCnRm5p667r3A+ohY1ci28TVHxEZg49jz\n5cuXn9Q2S5Ikaf6ajSEKHcB7gFdm5gbgSuBWZiE8z5XMvD4zu8cey5Yta3ZJkiRJmiWzMUThAuDp\nmflVeGJoQB/ws8CxiDijrm8PsCMz9zWybcZbKEmSpJYxGwF3J3BmRDwLICLOBc4B7gduB95eTb8I\nOAu4u5qv0W2SJElaAGZjDO7eiHgr8JmIGKUWmt+RmTsi4t3ArRGxFTgKXJWZw9WsjW6TJEnSAjAr\n42Qz81PApyaYvhd46STzNLRNkiRJC4PfZCZJkqSiGHAlSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqK\nAVeSJElFMeBKkiSpKAZcSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJKooBV5Ik\nSUUx4EqSJKkoBlxJkiQVxYArSZKkohhwJUmSVBQDriRJkopiwJUkSVJRDLiSJEkqigFXkiRJRTHg\nSpIkqSgGXEmSJBXFgCtJkqSiGHAlSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqKAVeSJElFMeBKkiSp\nKAZcSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJKooBV5IkSUUx4EqSJKkoBlxJ\nkiQVxYArSZKkohhwJUmSVBQDriRJkopiwJUkSVJRDLiSJEkqigFXkiRJRTHgSpIkqSgGXEmSJBXF\ngCtJkqSiGHAlSZJUFAOuJEmSimLAlSRJUlFmJeBGxKKI+IuI2BoR90bEbdX08yLiGxHxQERsjohn\n183T0DZJkiQtDLN1BvcDQALPzMyfAd5VTf8I8NHMfCbwx8DNdfM0uk2SJEkLQGTmzBYQsRTYDXRn\n5oG66WuBB4GVmXksIqLq9wvAgUa2ZeaDx9uG7u7u7Ovrm9HrIEnzxUuuvxuAOzZe3uRKJGn2RMSu\nzOyeSt/ZOIN7DjAAXBcRWyLiaxFxJbAO2J2ZxwCylqR3AOub0CZJkqQFYjYCbgewAfjnzLwQ+E/A\np6vp81JEbIyIvrHHoUOHml2SJEmSZslsBNwdwCjwCYDM/CdgG7XQe2ZEdABUQwbWV/13NrjtSTLz\n+szsHnssW7ZsFl4GSZIkzQczDriZ2Q98GfjXABFxNnA28HXgO8BVVddXAX2Z+WBmPtzItpluoyRJ\nklrHbA0jeDvwsYj4Y2pnc9+Wmbsi4m3AzRFxHbWLwK6pm6fRbZIkSVoAZiXgZuZDwC9OMP1+4AWT\nzNPQNkmSJC0MfpOZJEmSimLAlSRJUlEMuJIkSSqKAVeSJElFMeBKkiSpKAZcSZIkFcWAK0mSpKIY\ncCVJklQUA64kSZKKYsCVJElSUQy4kiRJKooBV5IkSUUx4EqSJKkoBlxJKsjo6CiPHh5m74HHueWb\nvYyOjja7JElquMjMZtfQdN3d3dnX19fsMiRpRrb0DvDaG+5heOQnv9c724NPveVSLuxZ2cTKJGnm\nImJXZnZPpa9ncCWpAKOjo08JtwDDI8lrb7jHM7mSFhQDriQV4LZv7XhKuB0zPJLc9q0dDa5IkprH\ngCtJBbhv12MzapekkhhwJakAzzlr+YzaJakkBlxJKsBVl6ynsz0mbOtsD666ZH2DK5Kk5jHgSlIB\n2tra+NRbLn1KyO1sD/7qrS+grc1f95IWDm8ThrcJk1SO0dFRnnHdFwH4ry9/Nlddst5wK6kIJ3Ob\nsI65LkaS1DhtbW2MncO9+gU9zSxFkprGP+slSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqKAVeSJElF\nMeBKkiSpKAZcSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJKooBV5IkSUUx4EqS\nJKkoBlxJkiQVxYArSZKkohhwJUmSVBQDriRJkopiwJUkSVJRDLiSJEkqigFXkiRJRTHgSpIkqSgG\nXEmSJBXFgCtJkqSiGHAlSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqKAVeSJElFmdWAGxHXRERGxCuq\n52sj4ksRsTUi7ouIy+r6NrRNkiRJC8OsBdyI6AHeAtxTN/kDwD2ZeR5wDfDJiOhsUpskSZIWgFkJ\nuBHRBtwI/L/AkbqmVwMfBsjMzcCPgcub1CZJkqQFYLbO4G4Evp6Z3x6bEBGrgM7M3FPXrxdY3+i2\nGW6bJEmSWkjHTBcQEc8BXgW0zHjXiNhILZQDsHz58iZWI0mSpNk0G2dwXwT0AFsjohe4FPgoteEC\nxyLijLq+PcCOzNzXyLbxBWfm9ZnZPfZYtmzZSW+0JEmS5qcZB9zM/J+ZeWZm9mRmD7WLzN6amf8T\nuB14O0BEXAScBdxdzdroNkmSJC0AMx6icALvBm6NiK3AUeCqzBxuUpskSZIWgFkPuJl5Rd3Pe4GX\nTtKvoW2SJElaGPwmM0mSJBXFgCtJkqSiGHAlSZJUFAOuJEmSimLAlSRJUlEMuJIkSSqKAVeSJElF\nMeBKkiSpKAZcSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJKooBV5IkSUUx4EqS\nJKkoBlxJKkRmsmnbPhJIqP2c2eyyJKnhwl9+0N3dnX19fc0uQ5KmrW//EK+94R52Dhx+0vT1K7v4\n5FsuoXtFV5Mqk6TZERG7MrN7Kn09gytJLS4zef3HvvWUcAuwY2CIN9y0yTO5khYUA64ktbgt2/dP\nGG7HbN83xJbt+xtYkSQ1lwFXklpcb/8gbTF5e1sEvf2DjStIkprMgCtJLa5n9VJGjjMEYTSTntVL\nG1iRJDWXAVeSWtyFG1awfuXkF5FtWNXFhRtWNLAiSWouA64ktbiI4NY3XcK6lUue0rZhVRe3vOkS\nIo4zhkGSCuNtwvA2YZLKkJm86IN30re/dsHZZ952KRf1rDTcSirCydwmrGOui5EkNUZEsKSz/Ynn\nF5+9qonVSFLzOERBkiRJRTHgSpIkqSgGXEmSJBXFgCtJkqSiGHAlSZJUFAOuJEmSimLAlSRJUlEM\nuJIkSSqKAVeSJElFMeBKkiSpKAZcSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4kiRJ\nKooBV5IkSUUx4EqSJKkoBlxJkiQVxYArSZKkohhwJUmSVBQDriQVIjM5PDzyxPPbt+xkc+8AmdnE\nqiSp8cJffNDd3Z19fX3NLkOSpq1v/xBXf2wTD/UPPml6exusX9nFrW+6hO4VXU2qTpJmLiJ2ZWb3\nVPp6BleSWlxm8robvvWUcAswMgrb+od43Q33eCZX0oJhwJWkFre5d4AdA0PH7bNj4DCbewcaVJEk\nNZcBV5Ja3F33PzKr/SSp1RlwJUmSVJQZB9yIWBwRn4uIByLiexFxR0ScW7WtjYgvRcTWiLgvIi6r\nm6+hbZJUqivOXzOr/SSp1c3WGdyPAudn5nOBzwM3VtM/ANyTmecB1wCfjIjOJrVJUpEu6lnJupVL\njttnw6ouLupZ2aCKJKm5ZhxwM/PxzPxC/uTy3HuAnurnVwMfrvptBn4MXN6kNkkqUkTwqbdcytmr\nn3obsPa24Jw1S/nkWy4lIppQnSQ13lyMwX0n8PmIWAV0ZuaeurZeYH2j22ZlqyRpHute0cVXfvOK\nJ01rbwv+6q2X8g8bL+es049/hleSStIxmwuLiOuAc4ErgXn72zQiNgIbx54vX768idVI0uyICAIY\n+zitPcJhCZIWpFk7gxsR7wJeCbwsM4cycx9wLCLOqOvWA+xodNv4WjPz+szsHnssW7ZsehstSZKk\neWdWAm51RvS1wEsy89G6ptuBt1d9LgLOAu5uUpskSZIWgBkPUYiIbuBPgYeAO6uLGI5k5iXAu4Fb\nI2IrcBS4KjOHq1kb3SZJkqQFYMYBNzP7gAkvzc3MvcBL50ObJEmSFga/yUySJElFMeBKkiSpKAZc\nSZIkFcWAK0mSpKIYcCVJklQUA64kSZKKYsCVJElSUQy4klSIzCTrno9ksrl3gMycdB5JKpEBV5IK\n0Ld/iCuvf/I3k4+MJq+74R6uvP5u+vYPNakySWo8A64ktbjM5OqPbWLbI4NPaRseSXr7B3nDTZs8\nkytpwTDgSlKL+8J9u3mof5DJ4utowvZ9g2zZvr+hdUlSsxhwJamFZSbv/ZsfnLDfyChse+RQAyqS\npOYz4EpSC9uyfT/7B4dP2C+Bx4+Nzn1BkjQPGHAlqYX19g/S2R4n7BfAks72uS9IkuYBA64ktbCe\n1Us5Nnrii8c62oOe1UsbUJEkNZ8BV5Ja2IUbVrBuZRftbZOfxW1vC9av7OLCDSsaWJkkNY8BV5Ja\nWERwy7UXs2FV14Ttne1Bz6oubnnTJUSceCiDJJUgvC8idHd3Z19fX7PLkKRpy0xe9ME76dt/+EnT\nb3/7C7hwwwrDraSWFxG7MrN7Kn075roYSdLci4gJLyK7qGdlE6qRpOZyiIIkSZKKYsCVJElSUQy4\nkiRJKooBV5IkSUUx4EqSJKmDpWa+AAAMPklEQVQoBlxJKkBmcnh45CnTb9+yk829A3hLSEkLibcJ\nk6QW17d/iKtv2vSUe+AC/P7f/IDhkVHWrezilmsvpnvFxF8IIUkl8QyuJLWwzOTqmzaxfd/QhO1D\nR0cYHkm27xviDTdt8kyupAXBgCtJLWzL9v30DRxmZPT4wXVkNNkxMMSW7fsbVJkkNY8BV5JaWG//\nIO1T/E3e3hb09g/ObUGSNA8YcCWphW1Y1cXh4dEp9X18eJQNqxyDK6l8BlxJkiQVxYArSS1ssovL\nJhLgEAVJC4IBV5Ja2ET3vp1MAo8fm9pwBklqZQZcSWphizvaiCn2DWBJZ/tcliNJ84IBV5Ja2Nlr\nlp3EXRSgZ/XSuS1IkuYBA64ktbAzTltExNTO4UYEZ5y2eI4rkqTmM+BKUovKTF5347cYHpnat5MN\njyRX3fgtv81MUvEMuJLUojb3DrBz4PBJzbN9YIjNvQNzVJEkzQ8GXElqUXfd/0hD55OkVmHAlaQW\nNTrqLb8kaSIGXElqUQNDR6c136KOqd5YTJJakwFXklpQZvKFe/dMa95PfGunF5pJKpoBV5Ja0Jbt\n+xk6MvVvMas3MHiULdv3z3JFkjR/GHAlqQVte+QQ0x2Be0pHG739g7NajyTNJwZcSWohmcnm3gG+\n+aN9017GkeERtvUPsrl3wKEKkooU/nKD7u7u7Ovra3YZknRcffuHuPqmTewcGGJ0NJni9ztMqOuU\ndoZHRlm3sotbrr2Y7hVds1eoJM2BiNiVmd1T6esZXElqAZnJ1R/bxLZHBhkemVm4BRg6OsLwSLLt\nkUGu/pjfbiapLAZcSZrnRkdH+Y1PfJuH+geZ7RiawEP9Q3zoyw8YciUVwyEKOERB0vySmWzZvp9t\njxzih7sPcNM3tjdkvV2dbbzzxefxvA0ruXDDCiK8X66k+eNkhigYcDHgSmqesTD70MMHuX/vQf5l\n90Hu3fUYh6Z5C7DZcuqidp5z1nKedtoifm79CrpO6aBn9VKDr6SmMeCeJAOupJMxdieDL//zHr7+\nYD+7Hx3i8HCSbcGqpafw5heezetfsIFv73iUu+5/BIArzl/DRT0riQgyk03b9vHRux7krq37Zjye\ntpHaA97xi+fwzhc/k7a22ii3sdejflufv/50Pv6Nbdz4tV76Dx2hva2Nxae0cf4Zp/HvLng6z1h7\nqmFZ0kkx4J4kA64aaeyMXW//4JTOiE21f33IyEzOXL6YJSc461a/7A2ralfRb983NOE89X27T1/E\nx7/Ryz9u7efIsaSzPRgeTdqAto62J4W87+x8jG2PHOLQ40f57Lf7ePDhQYZHob0N2gKWLurglDYY\nOpZkQveKxZy7ein/vPsg+wePMDScRBucedpinnPWctoiGB0d5UePHKJv/2GODo9CwHBCZC2APT7d\nG8ROoiOgM2rjVWd72QtdG7CkE44eq+3D2dRO7XiIqK0n2oLRgGWLOnjmmmW0t7fRHrWvLv5+3wH2\nDR2lsy1Ye9pili85hSUdsPfgUQYOHaWtI1jUFhweHmHo6CjHqmO4s6ONc1Yv5VXP62bp4k42rOpi\ndHSUT3yzl28+NMCBx4/RFkFE0tYGo9nG4s42Xv7cp/Oy55zJjv2HT/h+O9F7c6L+mcndD/QDT/7j\nary5+n0kzYUFHXAj4jzg48Bq4DHgjZn5g+PN06iAOzo6ys1ff4iP3v0Qew8Nz/rFIpIkSXMtgFPa\ng/PPOJXrXvZTXHLO6ob8obPQA+5XgFsy8+aI+FXg3Zl50fHmaUTA3dI7wK99+JuGWkmSVJTVy07h\nc7/xwjm/n/aCvQ9uRKwFLgRuqyZ9FlgXEec2r6ramVvDrSRJKlH/oaO84aZN8+pWgx3NLmCWrQN2\nZ+YxgMzMiNgBrAcebFZRt31rxxPh9vfvuYkzB6f/FZuSJEnzwe6lq/iDS68F4KH+QbZs389FPSub\nXFVNUWdwpyoiNkZE39jj0KFDc7q++3Y9NqfLlyRJaqqE3v7BZlfxhNLO4O4EzoyIjsw8FrURz+uB\nHfWdMvN64Pqx593d3XN6Tv05Zy3nM1tqY3zH/tKRpJN1zuou1q9ayhXPXM1PnXkaOwYmvgJ/MvVX\nwK9fuYQf7j7AF+7dzXd2PMqwd4eQNBMBPauXNruKJ5R4kdldwM11F5n9dmZeeLx55vois9HRUc65\n7ouOwZU0Ze0Bpy7u4OzVS3nFz53F6y/d8MR9Z2db/X19v/bAw2zrH+Jwc79nQlKLOWfNUv5h4+Vz\nejeFhX4XhfOBm4FVwAHgmsy893jzeBcFSdPR2Vb7etvVpy6me8USFncE39v5GHsODU95/rWnLuLF\nz1rLY4+PcODwMFecv4ar5jDMTtXYl1H81aadPHZ4mMvOW8XI6Cg3fHXblG9z2NEGa5Z2smH1Mo4c\nPUb/4BH2HTzKkOFZKsqaZYv43DteyFmnL5nT9SzogDsd3gdXJWmjdo/CUZizY6y9DU5pC37mrNM4\n8/QuHhs6ytLFnSzpaOPg40f53s7HnnSMB9DRDks723nBOavYsHopOZrs3H+YrXsPMjg8QldHG0eO\njbB/cJjh0eTUxZ2sWLqIn3raUo6OjLKld4CDj49AQltbsLizje4VS1ixdBEdbUHPqi72Hz523JA4\nnZvab+4d4Cv/spcf/PgAne1tUw6gJ3uj/lY0020cGRnh/V/8Id/b+ShPO20xlz1zNc9Yc+JvODvR\nfhzbb3f+8GF2P3qYzGRgaJj2gMWdbTyw9xB7H3uc0dEk2oJsC1Z2dXLl+Wv40SOD3L/nAEeOjZK0\nsbgD1py2hGPHRhg8Nsqpizo5Z81S1q/qIkeT3v5DfONH+zh0NJ/0futsgzXLTuGC9StY0tHGjw8c\nYfjYKKuWdrBjYIite4c4NqNX/8TGjlBHn2i2eR/cFuE3mUmSJM1vC/Y+uJIkSZIBV5IkSUUx4EqS\nJKkoBlxJkiQVxYArSZKkohhwJUmSVBQDriRJkopiwJUkSVJRDLiSJEkqigFXkiRJRTHgSpIkqSgG\nXEmSJBXFgCtJkqSiRGY2u4ami4gjwCMNXOUy4FAD16fmc58vLO7vhcd9vrC4v5tjTWYumkpHA24T\nRERfZnY3uw41jvt8YXF/Lzzu84XF/T3/OURBkiRJRTHgSpIkqSgG3Oa4vtkFqOHc5wuL+3vhcZ8v\nLO7vec4xuJIkSSqKZ3AlSZJUFAOuJEmSimLAbaCIOC8ivhERD0TE5oh4drNr0sxFRG9E3B8R360e\nr6mmT7q/PRZaR0R8qNrHGREX1E2f1v51389/x9nnE77Xqzb3eYuKiMUR8blq/3wvIu6IiHOrtrUR\n8aWI2BoR90XEZXXzTatNDZKZPhr0AL4CvLH6+VeBzc2uyces7Nde4IKT2d8eC63zAC4Dusfv5+nu\nX/f9/H8cZ59P+F53n7f2A1gM/DI/uS7pHcBd1c83Ae+tfr4I6AM6Z9LmozEPLzJrkIhYCzwIrMzM\nYxERwG7gFzLzweZWp5mIiF7gFZn53bppk+5v4MBkbR4L81f9fp7u/j1em/t+/hn/3p7ovV5N9/1e\nkIi4EPjrzOyJiEPAuZm5p2rbBFyXmf8w3bambNQC5BCFxlkH7M7MYwBZ+8tiB7C+qVVpttwSEfdG\nxMciYg3H398eC61vuvvXfd/6xr/XwX1emncCn4+IVdTOuu6pa+sF1k+3bU6r1pMYcKWZuywzfxZ4\nHtAPfLzJ9UiaG77XCxcR1wHnAv+l2bVoZgy4jbMTODMiOgCqj6nWU/tLXi0sM3dU/w4D/x14Ecff\n3x4LrW+6+9d938Imea+D+7wIEfEu4JXAyzJzKDP3Acci4oy6bj3Ajum2zWX9ejIDboNk5sPAd4Cr\nqkmvAvocg9XaImJpRJxeN+m1wD8db397LLS+6e5f933rmuy9DtM/HhpTuaYiIjZS26cvycxH65pu\nB95e9bkIOAu4e4ZtagAvMmugiDgfuBlYRe3Cg2sy896mFqUZiYhnAJ8F2oEAHgLemZm9x9vfHgut\nIyI+AvwKcAawDziYmedOd/+67+e/ifY58FImea9X87jPW1REdFM70/4QtX0NcCQzL4mIpwG3AmcD\nR4F3ZOad1XzTalNjGHAlSZJUFIcoSJIkqSgGXEmSJBXFgCtJkqSiGHAlSZJUFAOuJEmSimLAlSRJ\nUlEMuJIkSSqKAVeSJElFMeBKkiSpKP8X5i5njesiy1UAAAAASUVORK5CYII=\n","text/plain":["<Figure size 800x560 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"hnlVxuAmGF2l","colab_type":"text"},"source":["**Component analysis of Fourier Transform**\n","**Once the spectral part of Fourier transform is removed the magnitude part is quite close to the test series values!** \n","**Fourier transform is working!**"]},{"cell_type":"markdown","metadata":{"id":"awn3X9zu_sQy","colab_type":"text"},"source":["# **ARIMA**"]},{"cell_type":"markdown","metadata":{"id":"FyNX3BWLKQ5W","colab_type":"text"},"source":[" **ARIMA as a feature:**\n","   \n"," **Autoregressive Integrated Moving Average (ARIMA) — This was one of the most popular techniques for predicting future values of time series data (in the pre-neural networks ages). Let’s add it and see if it comes off as an important predictive feature.**\n","   \n","  **ARIMA is a technique for predicting time series data. We will show how to use it, and all though ARIMA will not serve as our final prediction, we will use it as a technique to denoise the stock a little and to (possibly) extract some new patters or features.**\n","  \n","  **ARIMA is an acronym. This acronym is descriptive, capturing the key aspects of the model itself. Briefly, they are:**\n","\n","**1. AR: Autoregression. A model that uses the dependent relationship between an observation and some number of lagged observations.**\n","\n","**2. I: Integrated. The use of differencing of raw observations (e.g. subtracting an observation from an observation at the previous time step) in order to make the time series stationary.**\n","\n","**3. MA: Moving Average. A model that uses the dependency between an observation and a residual error from a moving average model applied to lagged observations.**\n","\n","**The parameters of the ARIMA model are defined as follows:**\n","\n","**p: The number of lag observations included in the model, also called the lag order.**\n","**d: The number of times that the raw observations are differenced, also called the degree of differencing.**\n","**q: The size of the moving average window, also called the order of moving average.**\n","\n","**STEPS FOR ARIMA**\n","\n","**1.Define the model by calling ARIMA() and passing in the p, d, and q parameters.**\n","\n","**2. The model is prepared on the training data by calling the fit() function.**\n","\n","**3.Predictions can be made by calling the predict() function and specifying the index of the time or times to be predicted.**\n"," \n","**First, we fit an ARIMA(5,1,0) model. This sets the lag value to 5 for autoregression, uses a difference order of 1 to make the time series stationary, and uses a moving average model of 0.**\n","\n","**When fitting the model, a lot of debug information is provided about the fit of the linear regression model. We can turn this off by setting the disp argument to 0.**\n","\n","**Running the example prints a summary of the fit model. This summarizes the coefficient values used as well as the skill of the fit on the on the in-sample observations.**\n","\n","\n","\n"]},{"cell_type":"code","metadata":{"id":"y-pnaN4iKUNV","colab_type":"code","outputId":"669909b9-31a7-421d-d26f-cc014b2d6a00","executionInfo":{"status":"ok","timestamp":1565975638248,"user_tz":240,"elapsed":1217,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":487}},"source":["from statsmodels.tsa.arima_model import ARIMA\n","from pandas import DataFrame\n","from pandas import datetime\n","\n","series = data_FT['Close']\n","model = ARIMA(series, order=(5, 1, 0))\n","model_fit = model.fit(disp=0)\n","print(model_fit.summary())\n"],"execution_count":35,"outputs":[{"output_type":"stream","text":["                             ARIMA Model Results                              \n","==============================================================================\n","Dep. Variable:                D.Close   No. Observations:                 2264\n","Model:                 ARIMA(5, 1, 0)   Log Likelihood               -9244.973\n","Method:                       css-mle   S.D. of innovations             14.361\n","Date:                Fri, 16 Aug 2019   AIC                          18503.947\n","Time:                        17:13:56   BIC                          18544.021\n","Sample:                             1   HQIC                         18518.569\n","                                                                              \n","=================================================================================\n","                    coef    std err          z      P>|z|      [0.025      0.975]\n","---------------------------------------------------------------------------------\n","const             0.6074      0.291      2.086      0.037       0.037       1.178\n","ar.L1.D.Close    -0.0270      0.021     -1.287      0.198      -0.068       0.014\n","ar.L2.D.Close    -0.0002      0.021     -0.008      0.993      -0.041       0.041\n","ar.L3.D.Close    -0.0293      0.021     -1.399      0.162      -0.070       0.012\n","ar.L4.D.Close    -0.0431      0.021     -2.055      0.040      -0.084      -0.002\n","ar.L5.D.Close     0.0631      0.021      2.956      0.003       0.021       0.105\n","                                    Roots                                    \n","=============================================================================\n","                  Real          Imaginary           Modulus         Frequency\n","-----------------------------------------------------------------------------\n","AR.1           -1.3201           -0.9742j            1.6406           -0.3988\n","AR.2           -1.3201           +0.9742j            1.6406            0.3988\n","AR.3            0.6678           -1.5865j            1.7213           -0.1866\n","AR.4            0.6678           +1.5865j            1.7213            0.1866\n","AR.5            1.9877           -0.0000j            1.9877           -0.0000\n","-----------------------------------------------------------------------------\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"fsUppGk6HY6m","colab_type":"text"},"source":[" **SUMMARY OF THE ARIMA MODEL**\n"," \n","**A good starting point for the AR parameter of the model may be 5 which we did**\n","\n","**From the summary of the ARIMA we can see that most P-values are greater than 0.05 other than the last two.The model should be great!**\n","\n","**The difference between AIC and BIC is low so this indicates this is a good model**\n","\n","**Running the example, we can see that there is a positive correlation with the first 0-to-500 lags that is perhaps significant for the first 250 lags in the autocorrelation below**\n","\n"]},{"cell_type":"code","metadata":{"id":"NuucJ1WqKMkR","colab_type":"code","outputId":"5ed69ecb-7fba-4dc5-b5e5-8e92c0941832","executionInfo":{"status":"ok","timestamp":1565975641493,"user_tz":240,"elapsed":1275,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":300}},"source":["from pandas.plotting import autocorrelation_plot\n","autocorrelation_plot(series)\n","plt.figure(figsize=(10, 7), dpi=80)\n","plt.show()"],"execution_count":36,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAZQAAAEKCAYAAAA1qaOTAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nwhKKMcaYgLCEYowxJiD+P25BZvk62xoHAAAAAElFTkSuQmCC\n","text/plain":["<Figure size 432x288 with 1 Axes>"]},"metadata":{"tags":[]}},{"output_type":"display_data","data":{"text/plain":["<Figure size 800x560 with 0 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"naxBofp9ehfi","colab_type":"text"},"source":["**Refernce to ARIMA code:**\n","\n","https://towardsdatascience.com/forecasting-exchange-rates-using-arima-in-python-f032f313fc56\n","\n","https://github.com/gmonaci/ARIMA\n","\n","**ARIMA Explantion :**\n","\n","https://towardsdatascience.com/forecasting-exchange-rates-using-arima-in-python-f032f313fc56\n","\n","\n"]},{"cell_type":"code","metadata":{"id":"Okfv_vp_KabM","colab_type":"code","colab":{}},"source":["from pandas import read_csv\n","from pandas import datetime\n","from pandas import DataFrame\n","from statsmodels.tsa.arima_model import ARIMA\n","from sklearn.metrics import mean_squared_error\n","\n","X = series.values\n","size = int(len(X) * 0.66)\n","train, test = X[0:size], X[size:len(X)]\n","history = [x for x in train]\n","predictions = list()\n","for t in range(len(test)):\n","    model = ARIMA(history, order=(5,1,0))\n","    model_fit = model.fit(disp=0)\n","    output = model_fit.forecast()\n","    yhat = output[0]\n","    predictions.append(yhat)\n","    obs = test[t]\n","    history.append(obs)\n","\n","dataset_TI_df['ARIMA'] = pd.DataFrame(predictions)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"DC3et1Z8KhL3","colab_type":"code","outputId":"adada03b-a58b-4ecb-ddd2-4d2014835ea1","executionInfo":{"status":"ok","timestamp":1565975822299,"user_tz":240,"elapsed":178731,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":34}},"source":["error = mean_squared_error(test, predictions)\n","print('Test MSE: %.3f' % error)"],"execution_count":38,"outputs":[{"output_type":"stream","text":["Test MSE: 557.865\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"GJcsXpEndQa8","colab_type":"text"},"source":["MSE issquare root of square of average of difference between actual and predicted prices. In this case they MSE is quite big.(MSE ideally for this data should be between 30 and 100). However I will plot the model and check"]},{"cell_type":"code","metadata":{"id":"q00FzNdSLuPB","colab_type":"code","outputId":"64ccde13-b3bf-4863-934b-de0a2cdd79a4","executionInfo":{"status":"ok","timestamp":1565975823495,"user_tz":240,"elapsed":179049,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":555}},"source":["# Plot the predicted (from ARIMA) and real prices\n","\n","plt.figure(figsize=(12, 6), dpi=100)\n","plt.plot(test, color='black', label='Real')\n","plt.plot(predictions, color='yellow', label='Predicted')\n","plt.xlabel('Days')\n","plt.ylabel('USD')\n","plt.title('Figure 5: ARIMA model on Amazon stock')\n","plt.legend()\n","plt.show()"],"execution_count":39,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAA/oAAAIaCAYAAACQ1TaXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n","text/plain":["<Figure size 1200x600 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"SD9T8ykVHqvJ","colab_type":"text"},"source":["**As we can see from Figure 5 ARIMA gives a very good approximation of the real stock price. We will use the predicted price through ARIMA as an input feature into the LSTM because, as we mentioned before, we want to capture as many features and patterns about Amazon as possible.**"]},{"cell_type":"code","metadata":{"id":"3RN-h8RCLyoa","colab_type":"code","outputId":"29f46fd9-1814-4d2d-8dcd-f62435f71bde","executionInfo":{"status":"ok","timestamp":1565975823498,"user_tz":240,"elapsed":176895,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":438}},"source":["dataset_ex_df.head(8)"],"execution_count":40,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>Date</th>\n","      <th>Open</th>\n","      <th>High</th>\n","      <th>Low</th>\n","      <th>Adj Close</th>\n","      <th>Volume</th>\n","      <th>ma7</th>\n","      <th>ma21</th>\n","      <th>26ema</th>\n","      <th>12ema</th>\n","      <th>MACD</th>\n","      <th>20sd</th>\n","      <th>upper_band</th>\n","      <th>lower_band</th>\n","      <th>ema</th>\n","      <th>momentum</th>\n","      <th>Fourier</th>\n","      <th>ARIMA</th>\n","      <th>Close</th>\n","      <th>labels</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>2010-01-04</td>\n","      <td>136.250000</td>\n","      <td>136.610001</td>\n","      <td>133.139999</td>\n","      <td>133.899994</td>\n","      <td>7599900</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>133.899994</td>\n","      <td>0.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>0.3390</td>\n","      <td>133.899994</td>\n","      <td>678.303785</td>\n","      <td>133.899994</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>2010-01-05</td>\n","      <td>133.429993</td>\n","      <td>135.479996</td>\n","      <td>131.809998</td>\n","      <td>134.690002</td>\n","      <td>8851900</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>134.310190</td>\n","      <td>134.327915</td>\n","      <td>0.017725</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>134.492500</td>\n","      <td>0.3469</td>\n","      <td>134.690002</td>\n","      <td>664.043069</td>\n","      <td>134.690002</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2010-01-06</td>\n","      <td>134.600006</td>\n","      <td>134.729996</td>\n","      <td>131.649994</td>\n","      <td>132.250000</td>\n","      <td>7178800</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.569984</td>\n","      <td>133.516904</td>\n","      <td>-0.053080</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.940000</td>\n","      <td>0.3225</td>\n","      <td>132.250000</td>\n","      <td>663.388476</td>\n","      <td>132.250000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>2010-01-07</td>\n","      <td>132.009995</td>\n","      <td>132.320007</td>\n","      <td>128.800003</td>\n","      <td>130.000000</td>\n","      <td>11030200</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.571973</td>\n","      <td>132.406755</td>\n","      <td>-0.165217</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>130.955500</td>\n","      <td>0.3000</td>\n","      <td>130.000000</td>\n","      <td>640.204421</td>\n","      <td>130.000000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>2010-01-08</td>\n","      <td>130.559998</td>\n","      <td>133.679993</td>\n","      <td>129.029999</td>\n","      <td>133.520004</td>\n","      <td>9830500</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.791825</td>\n","      <td>132.709221</td>\n","      <td>-0.082604</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.672234</td>\n","      <td>0.3352</td>\n","      <td>133.520004</td>\n","      <td>660.576572</td>\n","      <td>133.520004</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>2010-01-11</td>\n","      <td>132.619995</td>\n","      <td>132.800003</td>\n","      <td>129.210007</td>\n","      <td>130.309998</td>\n","      <td>8779400</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.294735</td>\n","      <td>132.126083</td>\n","      <td>-0.168651</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>131.095247</td>\n","      <td>0.3031</td>\n","      <td>130.309998</td>\n","      <td>658.990696</td>\n","      <td>130.309998</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>6</th>\n","      <td>2010-01-12</td>\n","      <td>128.990005</td>\n","      <td>129.820007</td>\n","      <td>126.550003</td>\n","      <td>127.349998</td>\n","      <td>9096300</td>\n","      <td>131.717142</td>\n","      <td>NaN</td>\n","      <td>131.415339</td>\n","      <td>131.060317</td>\n","      <td>-0.355022</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>128.597272</td>\n","      <td>0.2735</td>\n","      <td>127.349998</td>\n","      <td>676.445680</td>\n","      <td>127.349998</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>7</th>\n","      <td>2010-01-13</td>\n","      <td>127.900002</td>\n","      <td>129.710007</td>\n","      <td>125.750000</td>\n","      <td>129.110001</td>\n","      <td>10723200</td>\n","      <td>131.032858</td>\n","      <td>NaN</td>\n","      <td>131.043892</td>\n","      <td>130.653316</td>\n","      <td>-0.390576</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>128.939143</td>\n","      <td>0.2911</td>\n","      <td>129.110001</td>\n","      <td>669.110595</td>\n","      <td>129.110001</td>\n","      <td>NaN</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["        Date        Open        High  ...       ARIMA       Close  labels\n","0 2010-01-04  136.250000  136.610001  ...  678.303785  133.899994     NaN\n","1 2010-01-05  133.429993  135.479996  ...  664.043069  134.690002     NaN\n","2 2010-01-06  134.600006  134.729996  ...  663.388476  132.250000     NaN\n","3 2010-01-07  132.009995  132.320007  ...  640.204421  130.000000     NaN\n","4 2010-01-08  130.559998  133.679993  ...  660.576572  133.520004     NaN\n","5 2010-01-11  132.619995  132.800003  ...  658.990696  130.309998     NaN\n","6 2010-01-12  128.990005  129.820007  ...  676.445680  127.349998     NaN\n","7 2010-01-13  127.900002  129.710007  ...  669.110595  129.110001     NaN\n","\n","[8 rows x 20 columns]"]},"metadata":{"tags":[]},"execution_count":40}]},{"cell_type":"code","metadata":{"id":"lUk-WoQNL2mX","colab_type":"code","outputId":"f4fd88bf-0369-46c7-ce38-4862139882ab","executionInfo":{"status":"ok","timestamp":1565975823500,"user_tz":240,"elapsed":174800,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":34}},"source":["print('Total dataset has {} samples, and {} features.'.format(dataset_ex_df.shape[0], \\\n","                                                              dataset_ex_df.shape[1]))"],"execution_count":41,"outputs":[{"output_type":"stream","text":["Total dataset has 2265 samples, and 20 features.\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"WcgZYHjdJCI1","colab_type":"text"},"source":["# **FINDING IMPORTANT FEATURES USING XGBOOST :**"]},{"cell_type":"markdown","metadata":{"id":"xB0kgHi1L-Hy","colab_type":"text"},"source":["**Having so many features we have to consider whether all of them are really indicative of the direction GS stock will take. For example, we included USD denominated LIBOR rates in the dataset because we think that changes in LIBOR might indicate changes in the economy, that, in turn, might indicate changes in the AMZN stock behavior. But we need to test. There are many ways to test feature importance, but the one we will apply uses XGBoost, because it gives one of the best results in both classification and regression problems.**\n","\n","\n","**Since the features dataset is quite large, for the purpose of the presentation here we’ll use only the technical indicators. During the real features importance testing all selected features proved somewhat important so we won’t exclude anything when training.**\n","\n","\n","**So, after adding all types of data (the correlated assets, technical indicators, fundamental analysis, Fourier, and Arima) we have a total of 20 features for the 2,265 days (as mentioned before, however, only 1,585 days are for training data).**\n","\n","**What is XGBoost?**\n","\n","**XGBoost is a decision-tree-based ensemble Machine Learning algorithm that uses a gradient boosting framework. In prediction problems involving unstructured data (images, text, etc.) artificial neural networks tend to outperform all other algorithms or frameworks. However, when it comes to small-to-medium structured/tabular data, decision tree based algorithms are considered best-in-class right now.**\n","\n","![alt text](https://miro.medium.com/max/1094/1*QJZ6W-Pck_W7RlIDwUIN9Q.jpeg)\n","\n","**WHY DOES XGBOOST WORK SO WELL?\n","XGBoost and Gradient Boosting Machines (GBMs) are both ensemble tree methods that apply the principle of boosting weak learners (CARTs generally) using the gradient descent architecture. However, XGBoost improves upon the base GBM framework through systems optimization and algorithmic enhancements.**\n","\n","![alt text](https://miro.medium.com/max/1094/1*FLshv-wVDfu-i54OqvZdHg.png)\n","\n"]},{"cell_type":"code","metadata":{"id":"0DntZYGaL6ct","colab_type":"code","colab":{}},"source":["def get_feature_importance_data(data_income):\n","    data = data_income.copy()\n","    y = data['Close']\n","    X = data.iloc[:,1:19]\n","    \n","    train_samples = int(X.shape[0] * 0.65)\n"," \n","    X_train = X.iloc[:train_samples]\n","    X_test = X.iloc[train_samples:]\n","\n","    y_train = y.iloc[:train_samples]\n","    y_test = y.iloc[train_samples:]\n","    \n","    return (X_train, y_train), (X_test, y_test)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"JbO2whZDMCnB","colab_type":"code","colab":{}},"source":["# Get training and test data\n","(X_train_FI, y_train_FI), (X_test_FI, y_test_FI) = get_feature_importance_data(dataset_TI_df)\n"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"6713TYO_MG5q","colab_type":"code","colab":{}},"source":["regressor = xgb.XGBRegressor(gamma=0.0,n_estimators=200,base_score=0.7,colsample_bytree=1,learning_rate=0.05)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"1L80xmtDMJT3","colab_type":"code","outputId":"8800f2e6-5a04-4e94-abc2-f98935932fe6","executionInfo":{"status":"ok","timestamp":1565975823971,"user_tz":240,"elapsed":166965,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":34}},"source":["xgbModel = regressor.fit(X_train_FI,y_train_FI, \\\n","                         eval_set = [(X_train_FI, y_train_FI), (X_test_FI, y_test_FI)], \\\n","                         verbose=False)"],"execution_count":45,"outputs":[{"output_type":"stream","text":["[17:17:00] WARNING: /workspace/src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"IJrFL2AnMMBy","colab_type":"code","colab":{}},"source":["eval_result = regressor.evals_result()"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"c-TjzmQqMRBW","colab_type":"code","colab":{}},"source":["training_rounds = range(len(eval_result['validation_0']['rmse']))"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"SohU7-lPMTou","colab_type":"code","outputId":"9ecf131e-c215-45d6-b9d7-9786d85200a7","executionInfo":{"status":"ok","timestamp":1565975823979,"user_tz":240,"elapsed":163908,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":295}},"source":["plt.scatter(x=training_rounds,y=eval_result['validation_0']['rmse'],label='Training Error')\n","plt.scatter(x=training_rounds,y=eval_result['validation_1']['rmse'],label='Validation Error')\n","plt.xlabel('Iterations')\n","plt.ylabel('RMSE')\n","plt.title('Training Vs Validation Error')\n","plt.legend()\n","plt.show()"],"execution_count":48,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAY4AAAEWCAYAAABxMXBSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niEhWFBwiIpIVBYeIiGTl/wOawJn/Jj5xFQAAAABJRU5ErkJggg==\n","text/plain":["<Figure size 432x288 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"kYixeciceYEg","colab_type":"text"},"source":["**THE DIFFERENCE BETWEEN VALIDATION AND TRAINING ERROR SHOWS A UNDERFIT MODEL. EXPECTED AS SAID BEFORE BECAUSE OF THE WAY TRAINING AND TESTING DATA IS SPLIT JUST WHEN AMAZON BOOMS!**"]},{"cell_type":"code","metadata":{"id":"U6LISsSkMWat","colab_type":"code","outputId":"bbea72ef-5f13-40df-baab-647ad72a9df1","executionInfo":{"status":"ok","timestamp":1565975823980,"user_tz":240,"elapsed":161964,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":548}},"source":["fig = plt.figure(figsize=(8,8))\n","plt.xticks(rotation='vertical')\n","plt.bar([i for i in range(len(xgbModel.feature_importances_))], xgbModel.feature_importances_.tolist(), tick_label=X_test_FI.columns)\n","plt.title('Figure 6: Feature importance of the technical indicators.')\n","plt.show()"],"execution_count":49,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAecAAAITCAYAAAA95tTGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n","text/plain":["<Figure size 576x576 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"y3kdzMlIN8bV","colab_type":"text"},"source":["**Not surprisingly (for those with experience in stock trading) that MA7, MA21, and EMA are among the important features.\n","I followed the same logic for performing feature importance over the whole dataset — just the training took longer and results were a little more difficult to read, as compared with just a handful of features.\n","Features like Open and Adj Close are bound to be close to Closing prices\n","So if EMA doesn't works out we will focus on Averaging prices from Open and Adj-CLose prices**\n"]},{"cell_type":"markdown","metadata":{"id":"-2dlboKLMowU","colab_type":"text"},"source":["**Next steps:\n","We know which features are important. I suspect Fourier and ARIMA might be equally important but because of their\n","spectral component Fourier and because ARIMA doesn't produce any other features I won't be consideringthem.**"]},{"cell_type":"markdown","metadata":{"id":"mjFYYdr-f5k9","colab_type":"text"},"source":["Code Ref for XGBoost:\n","1. https://xgboost.readthedocs.io/en/latest/get_started.html\n","2. https://machinelearningmastery.com/develop-first-xgboost-model-python-scikit-learn/"]},{"cell_type":"markdown","metadata":{"id":"xKqOo5rfNM6_","colab_type":"text"},"source":["# **LSTM**"]},{"cell_type":"markdown","metadata":{"id":"9vlHf2osb7LE","colab_type":"text"},"source":["**LSTM is great at predicting stock market data. We are going to try to predict the closing prices using 1 feature Open(It has highest correlation to closing price) initially and then using multiple features(use some sort of one hot encoding) and then try to get a output.**\n","\n","**An LSTM Network has its origin in a RNN. But it can solve the memory loss by changing the neuron architecture.**\n","\n","![alt text](https://miro.medium.com/max/875/1*8nFrwolzTYtUWSaziiJGkg.png)\n","\n","**The new neuron has 3 gates, each with a different goal. The gates are:**\n","\n","**1.Input Gate**\n","\n","**2.Output Gate**\n","\n","**3.Forget Gate**\n","\n","**An LSTM Neuron still receives as input its previous state:**\n","\n","**LSTM Neuron passing as parameter its previous state.**\n","\n","![alt text](https://miro.medium.com/max/875/1*J5W8FrASMi93Z81NlAui4w.png)\n","\n","\n","**Following steps are done:**\n","\n","**1.  Clean up the data-Remove any NAs**\n","\n","**2.   Create a test, train and validate set**\n","\n","**3.   Create train for Open**\n","\n","**4.   Normalize data** \n","\n","**5.Create feature and label set**\n","\n","**6. Train, test data and  check with validation set**\n","\n","**7. Make a prediction**\n","\n","**8. Based on this prediction find if the feature extraction method of LSTM works**\n","\n"]},{"cell_type":"code","metadata":{"id":"S6ylerVkNzKh","colab_type":"code","outputId":"38d3d7d2-4fb6-49b4-98fd-380a1953f44c","executionInfo":{"status":"ok","timestamp":1565975823983,"user_tz":240,"elapsed":133887,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":274}},"source":["#1. take dataframe and drop na\n","dataset_lstm_df = dataset_TI_df.drop(columns='Date')\n","dataset_lstm_df.head(7)"],"execution_count":50,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>Open</th>\n","      <th>High</th>\n","      <th>Low</th>\n","      <th>Adj Close</th>\n","      <th>Volume</th>\n","      <th>ma7</th>\n","      <th>ma21</th>\n","      <th>26ema</th>\n","      <th>12ema</th>\n","      <th>MACD</th>\n","      <th>20sd</th>\n","      <th>upper_band</th>\n","      <th>lower_band</th>\n","      <th>ema</th>\n","      <th>momentum</th>\n","      <th>Fourier</th>\n","      <th>ARIMA</th>\n","      <th>Close</th>\n","      <th>labels</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>136.250000</td>\n","      <td>136.610001</td>\n","      <td>133.139999</td>\n","      <td>133.899994</td>\n","      <td>7599900</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>133.899994</td>\n","      <td>0.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.899994</td>\n","      <td>0.3390</td>\n","      <td>133.899994</td>\n","      <td>678.303785</td>\n","      <td>133.899994</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>133.429993</td>\n","      <td>135.479996</td>\n","      <td>131.809998</td>\n","      <td>134.690002</td>\n","      <td>8851900</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>134.310190</td>\n","      <td>134.327915</td>\n","      <td>0.017725</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>134.492500</td>\n","      <td>0.3469</td>\n","      <td>134.690002</td>\n","      <td>664.043069</td>\n","      <td>134.690002</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>134.600006</td>\n","      <td>134.729996</td>\n","      <td>131.649994</td>\n","      <td>132.250000</td>\n","      <td>7178800</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>133.569984</td>\n","      <td>133.516904</td>\n","      <td>-0.053080</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.940000</td>\n","      <td>0.3225</td>\n","      <td>132.250000</td>\n","      <td>663.388476</td>\n","      <td>132.250000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>132.009995</td>\n","      <td>132.320007</td>\n","      <td>128.800003</td>\n","      <td>130.000000</td>\n","      <td>11030200</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.571973</td>\n","      <td>132.406755</td>\n","      <td>-0.165217</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>130.955500</td>\n","      <td>0.3000</td>\n","      <td>130.000000</td>\n","      <td>640.204421</td>\n","      <td>130.000000</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>130.559998</td>\n","      <td>133.679993</td>\n","      <td>129.029999</td>\n","      <td>133.520004</td>\n","      <td>9830500</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.791825</td>\n","      <td>132.709221</td>\n","      <td>-0.082604</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.672234</td>\n","      <td>0.3352</td>\n","      <td>133.520004</td>\n","      <td>660.576572</td>\n","      <td>133.520004</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>5</th>\n","      <td>132.619995</td>\n","      <td>132.800003</td>\n","      <td>129.210007</td>\n","      <td>130.309998</td>\n","      <td>8779400</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>132.294735</td>\n","      <td>132.126083</td>\n","      <td>-0.168651</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>131.095247</td>\n","      <td>0.3031</td>\n","      <td>130.309998</td>\n","      <td>658.990696</td>\n","      <td>130.309998</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>6</th>\n","      <td>128.990005</td>\n","      <td>129.820007</td>\n","      <td>126.550003</td>\n","      <td>127.349998</td>\n","      <td>9096300</td>\n","      <td>131.717142</td>\n","      <td>NaN</td>\n","      <td>131.415339</td>\n","      <td>131.060317</td>\n","      <td>-0.355022</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>128.597272</td>\n","      <td>0.2735</td>\n","      <td>127.349998</td>\n","      <td>676.445680</td>\n","      <td>127.349998</td>\n","      <td>NaN</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["         Open        High         Low  ...       ARIMA       Close  labels\n","0  136.250000  136.610001  133.139999  ...  678.303785  133.899994     NaN\n","1  133.429993  135.479996  131.809998  ...  664.043069  134.690002     NaN\n","2  134.600006  134.729996  131.649994  ...  663.388476  132.250000     NaN\n","3  132.009995  132.320007  128.800003  ...  640.204421  130.000000     NaN\n","4  130.559998  133.679993  129.029999  ...  660.576572  133.520004     NaN\n","5  132.619995  132.800003  129.210007  ...  658.990696  130.309998     NaN\n","6  128.990005  129.820007  126.550003  ...  676.445680  127.349998     NaN\n","\n","[7 rows x 19 columns]"]},"metadata":{"tags":[]},"execution_count":50}]},{"cell_type":"code","metadata":{"id":"LN2zR8p2NR58","colab_type":"code","outputId":"700d8bd3-5a4f-464c-9b1a-2a1137d249a8","executionInfo":{"status":"ok","timestamp":1565976388705,"user_tz":240,"elapsed":1205,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":34}},"source":["print('Total dataset has {} samples, and {} features.'.format(dataset_lstm_df.shape[0], \\\n","                                                              dataset_lstm_df.shape[1]))"],"execution_count":51,"outputs":[{"output_type":"stream","text":["Total dataset has 2265 samples, and 19 features.\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"4jspfamWQaXs","colab_type":"code","outputId":"c30950a4-0831-49d4-9d96-a8f93722c584","executionInfo":{"status":"ok","timestamp":1565976391569,"user_tz":240,"elapsed":2128,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":34}},"source":["from keras.models import Sequential\n","from keras.layers import Dense\n","from keras.layers import LSTM\n","from keras.layers import Dropout\n","from keras.layers import Flatten"],"execution_count":52,"outputs":[{"output_type":"stream","text":["Using TensorFlow backend.\n"],"name":"stderr"}]},{"cell_type":"code","metadata":{"id":"ZoEiTOswgpvE","colab_type":"code","colab":{}},"source":["#creating test, train and validate trains\n","train, validate, test = np.split(dataset_lstm_df.sample(frac=1), [int(.6*len(dataset_lstm_df)), int(.8*len(dataset_lstm_df))])"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"9Xw3oUy5ghHW","colab_type":"text"},"source":["**Split dataset into train,test and validate sets**"]},{"cell_type":"code","metadata":{"id":"S9J6B42cRFYy","colab_type":"code","colab":{}},"source":["open_training = train.iloc[:, 1:2].values"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"4RQDiGIMt1Wj","colab_type":"text"},"source":["**Normalize data:\n","The data is not normalized and the range for each column varies, especially Volume. Normalizing data helps the algorithm in converging i.e. to find local/ global minimum efficiently. I will use MinMaxScaler from Sci-kit Learn. Use a range to keep values similar for that much range**\n","\n","**Keep a window for the length 2000 for your data between 50 and 500...since our length is slightly more than 2000 ill make it 60 to 450**"]},{"cell_type":"code","metadata":{"id":"1Dik4lFzRJL-","colab_type":"code","colab":{}},"source":["#normalise\n","from sklearn.preprocessing import MinMaxScaler\n","scaler = MinMaxScaler(feature_range = (0, 1))\n","open_training = scaler.fit_transform(open_training)\n","#convert to right shape\n","features_set_1 = []\n","labels_1 = []\n","for i in range(60,450): \n","    features_set_1.append(open_training[i-60:i, 0])\n","    labels_1.append(open_training[i, 0])\n","    \n","#Code ref: https://github.com/LiamConnell/deep-algotrading"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"en50MEmiuIxV","colab_type":"text"},"source":["**Convert feature set and label set into arrays and shape feature set into a 3D input that LSTM network demands**"]},{"cell_type":"code","metadata":{"id":"O2JRCdt8RMIb","colab_type":"code","colab":{}},"source":["features_set_1, labels_1 = np.array(features_set_1), np.array(labels_1)\n","features_set_1 = np.reshape(features_set_1, (features_set_1.shape[0], features_set_1.shape[1], 1))"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"ShsX-jhtRPZr","colab_type":"code","outputId":"7d38c480-1feb-4c16-e83b-01ebd9d1693f","executionInfo":{"status":"ok","timestamp":1565976824282,"user_tz":240,"elapsed":425285,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":1000}},"source":["#training it\n","model = Sequential()\n","model.add(LSTM(units=50, return_sequences=True, input_shape=(features_set_1.shape[1],1)))\n","model.add(Dropout(0.2))\n","model.add(LSTM(units=50, return_sequences=True))\n","model.add(Dropout(0.2))\n","model.add(Flatten())\n","model.add(Dense(units = 1))\n","model.compile(optimizer = 'adam', loss = 'mean_squared_error', metrics = ['mean_absolute_error'])\n","model.fit(features_set_1, labels_1, epochs = 100, batch_size = 32,validation_data = (features_set_1, labels_1))\n"],"execution_count":57,"outputs":[{"output_type":"stream","text":["WARNING: Logging before flag parsing goes to stderr.\n","W0816 17:26:38.344084 139733778487168 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n","\n","W0816 17:26:38.400182 139733778487168 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n","\n","W0816 17:26:38.408069 139733778487168 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n","\n","W0816 17:26:38.632785 139733778487168 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:133: The name tf.placeholder_with_default is deprecated. Please use tf.compat.v1.placeholder_with_default instead.\n","\n","W0816 17:26:38.642064 139733778487168 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3445: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.\n","Instructions for updating:\n","Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.\n","W0816 17:26:38.922153 139733778487168 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n","\n","W0816 17:26:39.289612 139733778487168 deprecation.py:323] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_grad.py:1250: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n","Instructions for updating:\n","Use tf.where in 2.0, which has the same broadcast rule as np.where\n","W0816 17:26:40.771565 139733778487168 deprecation_wrapper.py:119] From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:986: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.\n","\n"],"name":"stderr"},{"output_type":"stream","text":["Train on 390 samples, validate on 390 samples\n","Epoch 1/100\n","390/390 [==============================] - 9s 23ms/step - loss: 0.0847 - mean_absolute_error: 0.2147 - val_loss: 0.0723 - val_mean_absolute_error: 0.1844\n","Epoch 2/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0664 - mean_absolute_error: 0.1909 - val_loss: 0.0704 - val_mean_absolute_error: 0.2252\n","Epoch 3/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0680 - mean_absolute_error: 0.2016 - val_loss: 0.0652 - val_mean_absolute_error: 0.1994\n","Epoch 4/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0649 - mean_absolute_error: 0.1988 - val_loss: 0.0656 - val_mean_absolute_error: 0.2087\n","Epoch 5/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0667 - mean_absolute_error: 0.2093 - val_loss: 0.0656 - val_mean_absolute_error: 0.1939\n","Epoch 6/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0663 - mean_absolute_error: 0.2035 - val_loss: 0.0649 - val_mean_absolute_error: 0.1964\n","Epoch 7/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0649 - mean_absolute_error: 0.2044 - val_loss: 0.0646 - val_mean_absolute_error: 0.1967\n","Epoch 8/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0644 - mean_absolute_error: 0.2021 - val_loss: 0.0643 - val_mean_absolute_error: 0.2029\n","Epoch 9/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0656 - mean_absolute_error: 0.1935 - val_loss: 0.0656 - val_mean_absolute_error: 0.2118\n","Epoch 10/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0660 - mean_absolute_error: 0.2088 - val_loss: 0.0668 - val_mean_absolute_error: 0.1874\n","Epoch 11/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0666 - mean_absolute_error: 0.1977 - val_loss: 0.0639 - val_mean_absolute_error: 0.2040\n","Epoch 12/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0646 - mean_absolute_error: 0.1973 - val_loss: 0.0635 - val_mean_absolute_error: 0.2006\n","Epoch 13/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0638 - mean_absolute_error: 0.2018 - val_loss: 0.0640 - val_mean_absolute_error: 0.1911\n","Epoch 14/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0651 - mean_absolute_error: 0.1947 - val_loss: 0.0641 - val_mean_absolute_error: 0.2075\n","Epoch 15/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0648 - mean_absolute_error: 0.1987 - val_loss: 0.0629 - val_mean_absolute_error: 0.1991\n","Epoch 16/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0646 - mean_absolute_error: 0.2043 - val_loss: 0.0648 - val_mean_absolute_error: 0.1863\n","Epoch 17/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0641 - mean_absolute_error: 0.1994 - val_loss: 0.0626 - val_mean_absolute_error: 0.1934\n","Epoch 18/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0636 - mean_absolute_error: 0.1914 - val_loss: 0.0632 - val_mean_absolute_error: 0.2048\n","Epoch 19/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0642 - mean_absolute_error: 0.1986 - val_loss: 0.0620 - val_mean_absolute_error: 0.1970\n","Epoch 20/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0636 - mean_absolute_error: 0.2031 - val_loss: 0.0630 - val_mean_absolute_error: 0.1868\n","Epoch 21/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0627 - mean_absolute_error: 0.1880 - val_loss: 0.0633 - val_mean_absolute_error: 0.2066\n","Epoch 22/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0650 - mean_absolute_error: 0.2045 - val_loss: 0.0638 - val_mean_absolute_error: 0.1838\n","Epoch 23/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0625 - mean_absolute_error: 0.1903 - val_loss: 0.0639 - val_mean_absolute_error: 0.2108\n","Epoch 24/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0631 - mean_absolute_error: 0.1985 - val_loss: 0.0609 - val_mean_absolute_error: 0.1933\n","Epoch 25/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0622 - mean_absolute_error: 0.2004 - val_loss: 0.0643 - val_mean_absolute_error: 0.1808\n","Epoch 26/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0638 - mean_absolute_error: 0.1852 - val_loss: 0.0658 - val_mean_absolute_error: 0.2167\n","Epoch 27/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0645 - mean_absolute_error: 0.1990 - val_loss: 0.0606 - val_mean_absolute_error: 0.1895\n","Epoch 28/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0609 - mean_absolute_error: 0.1944 - val_loss: 0.0603 - val_mean_absolute_error: 0.1921\n","Epoch 29/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0610 - mean_absolute_error: 0.1926 - val_loss: 0.0601 - val_mean_absolute_error: 0.1933\n","Epoch 30/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0609 - mean_absolute_error: 0.1930 - val_loss: 0.0604 - val_mean_absolute_error: 0.1857\n","Epoch 31/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0610 - mean_absolute_error: 0.1850 - val_loss: 0.0599 - val_mean_absolute_error: 0.1966\n","Epoch 32/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0596 - mean_absolute_error: 0.1942 - val_loss: 0.0593 - val_mean_absolute_error: 0.1881\n","Epoch 33/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0597 - mean_absolute_error: 0.1885 - val_loss: 0.0590 - val_mean_absolute_error: 0.1916\n","Epoch 34/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0601 - mean_absolute_error: 0.1988 - val_loss: 0.0589 - val_mean_absolute_error: 0.1856\n","Epoch 35/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0599 - mean_absolute_error: 0.1836 - val_loss: 0.0590 - val_mean_absolute_error: 0.1951\n","Epoch 36/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0591 - mean_absolute_error: 0.1891 - val_loss: 0.0583 - val_mean_absolute_error: 0.1886\n","Epoch 37/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0590 - mean_absolute_error: 0.1888 - val_loss: 0.0582 - val_mean_absolute_error: 0.1910\n","Epoch 38/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0584 - mean_absolute_error: 0.1940 - val_loss: 0.0577 - val_mean_absolute_error: 0.1872\n","Epoch 39/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0588 - mean_absolute_error: 0.1871 - val_loss: 0.0577 - val_mean_absolute_error: 0.1906\n","Epoch 40/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0578 - mean_absolute_error: 0.1909 - val_loss: 0.0576 - val_mean_absolute_error: 0.1830\n","Epoch 41/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0583 - mean_absolute_error: 0.1902 - val_loss: 0.0577 - val_mean_absolute_error: 0.1820\n","Epoch 42/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0588 - mean_absolute_error: 0.1844 - val_loss: 0.0578 - val_mean_absolute_error: 0.1935\n","Epoch 43/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0602 - mean_absolute_error: 0.1911 - val_loss: 0.0572 - val_mean_absolute_error: 0.1869\n","Epoch 44/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0581 - mean_absolute_error: 0.1903 - val_loss: 0.0569 - val_mean_absolute_error: 0.1870\n","Epoch 45/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0577 - mean_absolute_error: 0.1875 - val_loss: 0.0571 - val_mean_absolute_error: 0.1818\n","Epoch 46/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0582 - mean_absolute_error: 0.1907 - val_loss: 0.0570 - val_mean_absolute_error: 0.1814\n","Epoch 47/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0575 - mean_absolute_error: 0.1826 - val_loss: 0.0569 - val_mean_absolute_error: 0.1894\n","Epoch 48/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0581 - mean_absolute_error: 0.1861 - val_loss: 0.0565 - val_mean_absolute_error: 0.1859\n","Epoch 49/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0590 - mean_absolute_error: 0.1961 - val_loss: 0.0579 - val_mean_absolute_error: 0.1788\n","Epoch 50/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0588 - mean_absolute_error: 0.1808 - val_loss: 0.0579 - val_mean_absolute_error: 0.1949\n","Epoch 51/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0584 - mean_absolute_error: 0.1872 - val_loss: 0.0563 - val_mean_absolute_error: 0.1830\n","Epoch 52/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0598 - mean_absolute_error: 0.1978 - val_loss: 0.0568 - val_mean_absolute_error: 0.1808\n","Epoch 53/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0595 - mean_absolute_error: 0.1814 - val_loss: 0.0561 - val_mean_absolute_error: 0.1844\n","Epoch 54/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0579 - mean_absolute_error: 0.1887 - val_loss: 0.0561 - val_mean_absolute_error: 0.1830\n","Epoch 55/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0567 - mean_absolute_error: 0.1857 - val_loss: 0.0560 - val_mean_absolute_error: 0.1835\n","Epoch 56/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0568 - mean_absolute_error: 0.1895 - val_loss: 0.0564 - val_mean_absolute_error: 0.1801\n","Epoch 57/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0581 - mean_absolute_error: 0.1861 - val_loss: 0.0558 - val_mean_absolute_error: 0.1841\n","Epoch 58/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0564 - mean_absolute_error: 0.1840 - val_loss: 0.0559 - val_mean_absolute_error: 0.1811\n","Epoch 59/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0563 - mean_absolute_error: 0.1830 - val_loss: 0.0555 - val_mean_absolute_error: 0.1824\n","Epoch 60/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0571 - mean_absolute_error: 0.1834 - val_loss: 0.0556 - val_mean_absolute_error: 0.1812\n","Epoch 61/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0569 - mean_absolute_error: 0.1845 - val_loss: 0.0559 - val_mean_absolute_error: 0.1878\n","Epoch 62/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0561 - mean_absolute_error: 0.1818 - val_loss: 0.0555 - val_mean_absolute_error: 0.1800\n","Epoch 63/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0572 - mean_absolute_error: 0.1858 - val_loss: 0.0552 - val_mean_absolute_error: 0.1816\n","Epoch 64/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0573 - mean_absolute_error: 0.1800 - val_loss: 0.0552 - val_mean_absolute_error: 0.1806\n","Epoch 65/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0573 - mean_absolute_error: 0.1893 - val_loss: 0.0551 - val_mean_absolute_error: 0.1807\n","Epoch 66/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0560 - mean_absolute_error: 0.1793 - val_loss: 0.0554 - val_mean_absolute_error: 0.1834\n","Epoch 67/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0554 - mean_absolute_error: 0.1844 - val_loss: 0.0551 - val_mean_absolute_error: 0.1814\n","Epoch 68/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0555 - mean_absolute_error: 0.1782 - val_loss: 0.0550 - val_mean_absolute_error: 0.1827\n","Epoch 69/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0571 - mean_absolute_error: 0.1891 - val_loss: 0.0552 - val_mean_absolute_error: 0.1776\n","Epoch 70/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0563 - mean_absolute_error: 0.1822 - val_loss: 0.0554 - val_mean_absolute_error: 0.1876\n","Epoch 71/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0551 - mean_absolute_error: 0.1850 - val_loss: 0.0548 - val_mean_absolute_error: 0.1781\n","Epoch 72/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0560 - mean_absolute_error: 0.1796 - val_loss: 0.0549 - val_mean_absolute_error: 0.1853\n","Epoch 73/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0563 - mean_absolute_error: 0.1842 - val_loss: 0.0545 - val_mean_absolute_error: 0.1798\n","Epoch 74/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0557 - mean_absolute_error: 0.1840 - val_loss: 0.0546 - val_mean_absolute_error: 0.1780\n","Epoch 75/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0552 - mean_absolute_error: 0.1795 - val_loss: 0.0543 - val_mean_absolute_error: 0.1823\n","Epoch 76/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0546 - mean_absolute_error: 0.1803 - val_loss: 0.0541 - val_mean_absolute_error: 0.1798\n","Epoch 77/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0557 - mean_absolute_error: 0.1831 - val_loss: 0.0541 - val_mean_absolute_error: 0.1788\n","Epoch 78/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0548 - mean_absolute_error: 0.1810 - val_loss: 0.0541 - val_mean_absolute_error: 0.1814\n","Epoch 79/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0567 - mean_absolute_error: 0.1903 - val_loss: 0.0559 - val_mean_absolute_error: 0.1738\n","Epoch 80/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0570 - mean_absolute_error: 0.1749 - val_loss: 0.0547 - val_mean_absolute_error: 0.1868\n","Epoch 81/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0560 - mean_absolute_error: 0.1860 - val_loss: 0.0545 - val_mean_absolute_error: 0.1748\n","Epoch 82/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0542 - mean_absolute_error: 0.1803 - val_loss: 0.0535 - val_mean_absolute_error: 0.1805\n","Epoch 83/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0551 - mean_absolute_error: 0.1836 - val_loss: 0.0535 - val_mean_absolute_error: 0.1771\n","Epoch 84/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0555 - mean_absolute_error: 0.1824 - val_loss: 0.0535 - val_mean_absolute_error: 0.1766\n","Epoch 85/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0545 - mean_absolute_error: 0.1806 - val_loss: 0.0533 - val_mean_absolute_error: 0.1796\n","Epoch 86/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0539 - mean_absolute_error: 0.1777 - val_loss: 0.0531 - val_mean_absolute_error: 0.1781\n","Epoch 87/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0541 - mean_absolute_error: 0.1831 - val_loss: 0.0531 - val_mean_absolute_error: 0.1767\n","Epoch 88/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0544 - mean_absolute_error: 0.1797 - val_loss: 0.0531 - val_mean_absolute_error: 0.1810\n","Epoch 89/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0540 - mean_absolute_error: 0.1798 - val_loss: 0.0531 - val_mean_absolute_error: 0.1751\n","Epoch 90/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0525 - mean_absolute_error: 0.1770 - val_loss: 0.0528 - val_mean_absolute_error: 0.1797\n","Epoch 91/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0545 - mean_absolute_error: 0.1807 - val_loss: 0.0526 - val_mean_absolute_error: 0.1785\n","Epoch 92/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0544 - mean_absolute_error: 0.1779 - val_loss: 0.0529 - val_mean_absolute_error: 0.1812\n","Epoch 93/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0532 - mean_absolute_error: 0.1817 - val_loss: 0.0524 - val_mean_absolute_error: 0.1747\n","Epoch 94/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0539 - mean_absolute_error: 0.1780 - val_loss: 0.0522 - val_mean_absolute_error: 0.1773\n","Epoch 95/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0532 - mean_absolute_error: 0.1794 - val_loss: 0.0523 - val_mean_absolute_error: 0.1739\n","Epoch 96/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0539 - mean_absolute_error: 0.1769 - val_loss: 0.0520 - val_mean_absolute_error: 0.1783\n","Epoch 97/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0526 - mean_absolute_error: 0.1761 - val_loss: 0.0520 - val_mean_absolute_error: 0.1751\n","Epoch 98/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0545 - mean_absolute_error: 0.1800 - val_loss: 0.0519 - val_mean_absolute_error: 0.1775\n","Epoch 99/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0532 - mean_absolute_error: 0.1788 - val_loss: 0.0521 - val_mean_absolute_error: 0.1728\n","Epoch 100/100\n","390/390 [==============================] - 4s 11ms/step - loss: 0.0532 - mean_absolute_error: 0.1799 - val_loss: 0.0525 - val_mean_absolute_error: 0.1713\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/plain":["<keras.callbacks.History at 0x7f15c2020da0>"]},"metadata":{"tags":[]},"execution_count":57}]},{"cell_type":"markdown","metadata":{"id":"H5aWIT43vX27","colab_type":"text"},"source":["**MAE: This means the average difference between input and ouput for all 2265 datapoints is 0.167. \n","However the value is for the days here so the MAE here is pretty bad.(2265 length of dataset will be denominator. Difference between actual and prediced values should be so small that such a large denominator dividing the difference should put MAE in rage of 10^-3 ie 0.00then digits. Since MAE is 167.something*10^-3(0.167) difference is high**\n","\n","\n","**Data is trained for 100 epochs optimizer is adam and loss is mse. This seems to be an average model because mean absolute error is 0.18 and val mean absolute eroor is 0.17 so it indicates overfitting. Since this is a regression problem accuracy is not a good metric. MAE was chosen since the difference between training and testing should be less so we don't need to take the square root of the value.** \n","\n","**We will focus on hyperparameters if this model is good at prediction**"]},{"cell_type":"code","metadata":{"id":"d-5yfE6JRRqD","colab_type":"code","colab":{}},"source":["#TESTING THE MODEL\n","open_testing_processed = test.iloc[:, 1:2].values"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"CHZUOE1uv2i9","colab_type":"text"},"source":["**Test the model on test data**"]},{"cell_type":"code","metadata":{"id":"MKcZZryvKReB","colab_type":"code","colab":{}},"source":["#convert test data to right format\n","open_total = pd.concat((train['Open'], test['Open']), axis=0)"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"gN7qc_6uv9ta","colab_type":"text"},"source":["**Start predictions:\n","Reshape, scale and then oredict the model**"]},{"cell_type":"code","metadata":{"id":"1zjnBY-HKWNN","colab_type":"code","colab":{}},"source":["test_inputs = open_total[len(open_total) - len(test) - 60:].values"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"6Ot9WW7PKZnE","colab_type":"code","colab":{}},"source":["#scaling data\n","test_inputs = test_inputs.reshape(-1,1)\n","test_inputs = scaler.transform(test_inputs)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"xfBTp0XfKd_N","colab_type":"code","colab":{}},"source":["test_features = []\n","for i in range(60, 151):\n","    test_features.append(test_inputs[i-60:i, 0])"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"QwY1URr5KhEo","colab_type":"code","colab":{}},"source":["test_features = np.array(test_features)\n","test_features.shape\n","test_features = np.reshape(test_features, (test_features.shape[0], test_features.shape[1], 1))"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"K_Zthb6IKjuy","colab_type":"code","colab":{}},"source":["#make predictions\n","predictions = model.predict(test_features)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"Gn9GJRFoineD","colab_type":"code","colab":{}},"source":["predictions = scaler.inverse_transform(predictions)"],"execution_count":0,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"PehVpGNAwc70","colab_type":"text"},"source":["**Plot the prediction model for the number of test days and train days**"]},{"cell_type":"code","metadata":{"id":"cPa6q0vVKnX3","colab_type":"code","outputId":"8d6e552a-fb37-411f-a417-998876057386","executionInfo":{"status":"ok","timestamp":1565977303541,"user_tz":240,"elapsed":1034,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":404}},"source":["plt.figure(figsize=(10,6))\n","plt.plot(open_testing_processed, color='pink', label='Actual Stock Price')\n","plt.plot(predictions , color='yellow', label='Predicted Stock Price')\n","plt.title('Actual Value vs Predicted')\n","plt.xlabel('Date')\n","plt.ylabel('Predicted Price')\n","plt.legend()\n","plt.show()\n"],"execution_count":66,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAm4AAAGDCAYAAACSmpzSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEdO2XQcAAAAASUVORK5CYII=\n","text/plain":["<Figure size 720x432 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"QNz7cSfbwyby","colab_type":"text"},"source":["**This wasn't a great result with one feature so let's try using more features and then train them on LSTM model**"]},{"cell_type":"markdown","metadata":{"id":"jlnOEFRAjjPM","colab_type":"text"},"source":["**USING 5FEATURES :**\n","\n","\n","**USING THE BEST 5 FEATURES FROM THE RESULT OF THE XGBOOST. ITS QUITE OBVIOUS THAT A SINGLE FEATURE WILL NOT WORK SO WE USE THE 6 FEATURES THAT\n","COULD GENERATE THE BEST OUTCOME FROM XGBOOST**"]},{"cell_type":"code","metadata":{"id":"4sxE7ubqKuI6","colab_type":"code","colab":{}},"source":["dataset = dataset_ex_df[['Open', 'Close','High','Adj Close','Low']]"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"CMVCWkeJjrb5","colab_type":"code","outputId":"16d65690-6c7f-4264-e12b-c8d9cda9dbfb","executionInfo":{"status":"ok","timestamp":1565977308091,"user_tz":240,"elapsed":296,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":195}},"source":["dataset.head()"],"execution_count":68,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>Open</th>\n","      <th>Close</th>\n","      <th>High</th>\n","      <th>Adj Close</th>\n","      <th>Low</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>136.250000</td>\n","      <td>133.899994</td>\n","      <td>136.610001</td>\n","      <td>133.899994</td>\n","      <td>133.139999</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>133.429993</td>\n","      <td>134.690002</td>\n","      <td>135.479996</td>\n","      <td>134.690002</td>\n","      <td>131.809998</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>134.600006</td>\n","      <td>132.250000</td>\n","      <td>134.729996</td>\n","      <td>132.250000</td>\n","      <td>131.649994</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>132.009995</td>\n","      <td>130.000000</td>\n","      <td>132.320007</td>\n","      <td>130.000000</td>\n","      <td>128.800003</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>130.559998</td>\n","      <td>133.520004</td>\n","      <td>133.679993</td>\n","      <td>133.520004</td>\n","      <td>129.029999</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["         Open       Close        High   Adj Close         Low\n","0  136.250000  133.899994  136.610001  133.899994  133.139999\n","1  133.429993  134.690002  135.479996  134.690002  131.809998\n","2  134.600006  132.250000  134.729996  132.250000  131.649994\n","3  132.009995  130.000000  132.320007  130.000000  128.800003\n","4  130.559998  133.520004  133.679993  133.520004  129.029999"]},"metadata":{"tags":[]},"execution_count":68}]},{"cell_type":"code","metadata":{"id":"IcdIP_gtw9DB","colab_type":"code","colab":{}},"source":["# FUNCTION TO CREATE 1D DATA INTO TIME SERIES DATASET\n","def new_dataset(dataset, step_size):\n","\tdata_X, data_Y = [], []\n","\tfor i in range(len(dataset)-step_size-1):\n","\t\ta = dataset[i:(i+step_size), 0]\n","\t\tdata_X.append(a)\n","\t\tdata_Y.append(dataset[i + step_size, 0])\n","\treturn np.array(data_X), np.array(data_Y)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"5ovu8nAJxFRb","colab_type":"code","colab":{}},"source":["# IMPORTING IMPORTANT LIBRARIES\n","import pandas as pd\n","import matplotlib.pyplot as plt\n","import numpy as np \n","import math\n","from sklearn.preprocessing import MinMaxScaler\n","from sklearn.metrics import mean_squared_error\n","from keras.models import Sequential\n","from keras.layers import Dense, Activation\n","from keras.layers import LSTM\n"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"MR5ZH2cUxKpv","colab_type":"code","colab":{}},"source":["# FOR REPRODUCIBILITY\n","np.random.seed(7)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"HEBGkQJQxNrF","colab_type":"code","colab":{}},"source":["# IMPORTING DATASET \n","dataset = dataset.reindex(index = dataset.index[::-1])"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"qjQJZJx-xQOY","colab_type":"code","colab":{}},"source":["# CREATING OWN INDEX FOR FLEXIBILITY\n","obs = np.arange(1, len(dataset) + 1, 1)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"LFjIZMzJxUFR","colab_type":"code","colab":{}},"source":["# TAKING DIFFERENT INDICATORS FOR PREDICTION\n","OHLC_avg = dataset.mean(axis = 1)\n","HLC_avg = dataset[['High', 'Low', 'Close']].mean(axis = 1)\n","close_val = dataset[['Close']]"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"MduBu78PxXYX","colab_type":"code","outputId":"775c954d-6d5b-490c-b07d-d04cde4f8cf1","executionInfo":{"status":"ok","timestamp":1565977315547,"user_tz":240,"elapsed":1436,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":283}},"source":["# PLOTTING All INDICATORS IN PLOT\n","plt.plot(OHLC_avg, 'yellow', label = 'OHLC avg')\n","plt.plot(close_val, 'blue', label = 'Closing price')\n","plt.xlabel('Days')\n","plt.ylabel('OHLC average')\n","plt.show()\n"],"execution_count":75,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAY8AAAEKCAYAAADq59mMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n","text/plain":["<Figure size 432x288 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"code","metadata":{"id":"dvM1ej2vxfHQ","colab_type":"code","outputId":"848b5066-70bc-4894-d459-389bb90b6390","executionInfo":{"status":"ok","timestamp":1565977317476,"user_tz":240,"elapsed":1108,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":283}},"source":["plt.plot(HLC_avg, 'red', label = 'HLC avg')\n","plt.xlabel('Days')\n","plt.ylabel('HLC average')\n","plt.show()\n"],"execution_count":76,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAY8AAAEKCAYAAADq59mMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nB+9V5Ztid8QAAAAASUVORK5CYII=\n","text/plain":["<Figure size 432x288 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"code","metadata":{"id":"yRwx0FA8ycRW","colab_type":"code","outputId":"25d80acc-f214-4607-fdf7-e261aa4cfb1d","executionInfo":{"status":"ok","timestamp":1565977318119,"user_tz":240,"elapsed":652,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":283}},"source":["plt.plot(close_val, 'blue', label = 'Closing price')\n","plt.xlabel('Days')\n","plt.ylabel('Closing Values')\n","plt.show()"],"execution_count":77,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAY8AAAEKCAYAAADq59mMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nBx4GVJAU4k0uAAAAAElFTkSuQmCC\n","text/plain":["<Figure size 432x288 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"code","metadata":{"id":"z8Dx3owPynMb","colab_type":"code","colab":{}},"source":["# PREPARATION OF TIME SERIES DATASE\n","OHLC_avg = np.reshape(OHLC_avg.values, (len(OHLC_avg),1)) \n","scaler = MinMaxScaler(feature_range=(0, 1))\n","OHLC_avg = scaler.fit_transform(OHLC_avg)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"9HAD1oZozwym","colab_type":"code","colab":{}},"source":["# TRAIN-TEST SPLIT\n","train_OHLC = int(len(OHLC_avg) * 0.75)\n","test_OHLC = len(OHLC_avg) - train_OHLC\n","train_OHLC, test_OHLC = OHLC_avg[0:train_OHLC,:], OHLC_avg[train_OHLC:len(OHLC_avg),:]"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"Yet5xNOoz0x-","colab_type":"code","colab":{}},"source":["# TIME-SERIES DATASET (FOR TIME T, VALUES FOR TIME T+1)\n","trainX, trainY = new_dataset(train_OHLC, 1)\n","testX, testY = new_dataset(test_OHLC, 1)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"FHbI5KDKz4W7","colab_type":"code","colab":{}},"source":["# RESHAPING TRAIN AND TEST DATA\n","trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))\n","testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))\n","step_size = 1\n"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"ycBSKqy9z78c","colab_type":"code","colab":{}},"source":["# LSTM MODEL\n","model = Sequential()\n","model.add(LSTM(32, input_shape=(1, step_size), return_sequences = True))\n","model.add(LSTM(16))\n","model.add(Dense(1))\n","model.add(Activation('linear'))"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"eW5inyg0z_b1","colab_type":"code","outputId":"788810cb-6ecb-4202-b77d-f017603f0db5","executionInfo":{"status":"ok","timestamp":1565978117682,"user_tz":240,"elapsed":794197,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":1000}},"source":["# MODEL COMPILING AND TRAINING\n","model.compile(loss='mean_squared_error', optimizer='adagrad',metrics = ['mae']) # Try mae, adam, adagrad and compare!!!\n","model.fit(trainX, trainY, epochs=50, batch_size=1, verbose=2)"],"execution_count":83,"outputs":[{"output_type":"stream","text":["Epoch 1/50\n"," - 17s - loss: 0.0069 - mean_absolute_error: 0.0469\n","Epoch 2/50\n"," - 16s - loss: 3.2351e-04 - mean_absolute_error: 0.0151\n","Epoch 3/50\n"," - 16s - loss: 2.5536e-04 - mean_absolute_error: 0.0134\n","Epoch 4/50\n"," - 16s - loss: 2.0761e-04 - mean_absolute_error: 0.0119\n","Epoch 5/50\n"," - 16s - loss: 1.7103e-04 - mean_absolute_error: 0.0106\n","Epoch 6/50\n"," - 16s - loss: 1.4206e-04 - mean_absolute_error: 0.0095\n","Epoch 7/50\n"," - 16s - loss: 1.2193e-04 - mean_absolute_error: 0.0086\n","Epoch 8/50\n"," - 16s - loss: 1.0676e-04 - mean_absolute_error: 0.0079\n","Epoch 9/50\n"," - 16s - loss: 9.4709e-05 - mean_absolute_error: 0.0073\n","Epoch 10/50\n"," - 16s - loss: 8.5842e-05 - mean_absolute_error: 0.0068\n","Epoch 11/50\n"," - 16s - loss: 7.8493e-05 - mean_absolute_error: 0.0063\n","Epoch 12/50\n"," - 16s - loss: 7.2784e-05 - mean_absolute_error: 0.0059\n","Epoch 13/50\n"," - 16s - loss: 6.9067e-05 - mean_absolute_error: 0.0057\n","Epoch 14/50\n"," - 16s - loss: 6.5934e-05 - mean_absolute_error: 0.0054\n","Epoch 15/50\n"," - 16s - loss: 6.3742e-05 - mean_absolute_error: 0.0052\n","Epoch 16/50\n"," - 16s - loss: 6.1641e-05 - mean_absolute_error: 0.0050\n","Epoch 17/50\n"," - 16s - loss: 6.0256e-05 - mean_absolute_error: 0.0048\n","Epoch 18/50\n"," - 16s - loss: 5.8790e-05 - mean_absolute_error: 0.0047\n","Epoch 19/50\n"," - 16s - loss: 5.8635e-05 - mean_absolute_error: 0.0046\n","Epoch 20/50\n"," - 16s - loss: 5.7532e-05 - mean_absolute_error: 0.0046\n","Epoch 21/50\n"," - 16s - loss: 5.7646e-05 - mean_absolute_error: 0.0045\n","Epoch 22/50\n"," - 16s - loss: 5.6888e-05 - mean_absolute_error: 0.0045\n","Epoch 23/50\n"," - 16s - loss: 5.6290e-05 - mean_absolute_error: 0.0044\n","Epoch 24/50\n"," - 16s - loss: 5.6468e-05 - mean_absolute_error: 0.0044\n","Epoch 25/50\n"," - 16s - loss: 5.6016e-05 - mean_absolute_error: 0.0044\n","Epoch 26/50\n"," - 16s - loss: 5.6304e-05 - mean_absolute_error: 0.0043\n","Epoch 27/50\n"," - 16s - loss: 5.6393e-05 - mean_absolute_error: 0.0043\n","Epoch 28/50\n"," - 16s - loss: 5.6047e-05 - mean_absolute_error: 0.0043\n","Epoch 29/50\n"," - 16s - loss: 5.5954e-05 - mean_absolute_error: 0.0043\n","Epoch 30/50\n"," - 16s - loss: 5.5951e-05 - mean_absolute_error: 0.0043\n","Epoch 31/50\n"," - 16s - loss: 5.5833e-05 - mean_absolute_error: 0.0043\n","Epoch 32/50\n"," - 16s - loss: 5.5562e-05 - mean_absolute_error: 0.0043\n","Epoch 33/50\n"," - 16s - loss: 5.5405e-05 - mean_absolute_error: 0.0042\n","Epoch 34/50\n"," - 16s - loss: 5.5316e-05 - mean_absolute_error: 0.0042\n","Epoch 35/50\n"," - 16s - loss: 5.5298e-05 - mean_absolute_error: 0.0042\n","Epoch 36/50\n"," - 16s - loss: 5.5540e-05 - mean_absolute_error: 0.0042\n","Epoch 37/50\n"," - 16s - loss: 5.5571e-05 - mean_absolute_error: 0.0042\n","Epoch 38/50\n"," - 16s - loss: 5.5888e-05 - mean_absolute_error: 0.0042\n","Epoch 39/50\n"," - 16s - loss: 5.4770e-05 - mean_absolute_error: 0.0042\n","Epoch 40/50\n"," - 16s - loss: 5.4992e-05 - mean_absolute_error: 0.0042\n","Epoch 41/50\n"," - 16s - loss: 5.5870e-05 - mean_absolute_error: 0.0042\n","Epoch 42/50\n"," - 16s - loss: 5.5852e-05 - mean_absolute_error: 0.0042\n","Epoch 43/50\n"," - 16s - loss: 5.5567e-05 - mean_absolute_error: 0.0042\n","Epoch 44/50\n"," - 16s - loss: 5.5679e-05 - mean_absolute_error: 0.0042\n","Epoch 45/50\n"," - 16s - loss: 5.5616e-05 - mean_absolute_error: 0.0042\n","Epoch 46/50\n"," - 16s - loss: 5.6006e-05 - mean_absolute_error: 0.0042\n","Epoch 47/50\n"," - 16s - loss: 5.5492e-05 - mean_absolute_error: 0.0042\n","Epoch 48/50\n"," - 16s - loss: 5.5145e-05 - mean_absolute_error: 0.0042\n","Epoch 49/50\n"," - 16s - loss: 5.5507e-05 - mean_absolute_error: 0.0042\n","Epoch 50/50\n"," - 16s - loss: 5.5681e-05 - mean_absolute_error: 0.0042\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/plain":["<keras.callbacks.History at 0x7f15880497b8>"]},"metadata":{"tags":[]},"execution_count":83}]},{"cell_type":"code","metadata":{"id":"1amjmgWGFICM","colab_type":"code","colab":{"base_uri":"https://localhost:8080/","height":50},"outputId":"793002e6-54b1-413c-dde6-efffe6faac8d","executionInfo":{"status":"ok","timestamp":1565978385230,"user_tz":240,"elapsed":898,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}}},"source":["mae = model.evaluate(testX, testY, batch_size=16)\n","print('Mean Absolute Error for Y:', mae)"],"execution_count":87,"outputs":[{"output_type":"stream","text":["565/565 [==============================] - 0s 250us/step\n","Mean Absolute Error for Y: [9.329830344243025e-06, 0.0026545574847378034]\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"yT3NCySy0y7g","colab_type":"text"},"source":["**The mean absolute error is lower than the past model with one feature. The errror is almost 0.0026. So the training model should be pretty close to testing model.**"]},{"cell_type":"code","metadata":{"id":"6uYIJzE_0DxZ","colab_type":"code","colab":{}},"source":["# PREDICTION\n","trainPredict = model.predict(trainX)\n","testPredict = model.predict(testX)"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"ROLKJGIl2J_e","colab_type":"code","colab":{}},"source":["# DE-NORMALIZING FOR PLOTTING\n","trainPredict = scaler.inverse_transform(trainPredict)\n","trainY = scaler.inverse_transform([trainY])\n","testPredict = scaler.inverse_transform(testPredict)\n","testY = scaler.inverse_transform([testY])"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"R-s7kUbd2KNc","colab_type":"code","outputId":"b0425c17-415a-41a9-a3c7-d3829358f8b9","executionInfo":{"status":"ok","timestamp":1565978407619,"user_tz":240,"elapsed":1425,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":34}},"source":["# TRAINING rmse\n","trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))\n","print('Train : %.2f' % (trainScore))"],"execution_count":90,"outputs":[{"output_type":"stream","text":["Train : 14.47\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"PwM4dL-n2Sfr","colab_type":"code","outputId":"8ff47f43-5a38-497a-8c43-3dd5a1a3d251","executionInfo":{"status":"ok","timestamp":1565978409272,"user_tz":240,"elapsed":484,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":34}},"source":["# TEST RMSE\n","testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))\n","print('Test RMSE: %.2f' % (testScore))"],"execution_count":91,"outputs":[{"output_type":"stream","text":["Test RMSE: 5.88\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"DwSzCAOg2Sui","colab_type":"code","colab":{}},"source":["# CREATING SIMILAR DATASET TO PLOT TRAINING PREDICTIONS\n","trainPredictPlot = np.empty_like(OHLC_avg)\n","trainPredictPlot[:, :] = np.nan\n","trainPredictPlot[step_size:len(trainPredict)+step_size, :] = trainPredict"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"JNZkZbvS2S8A","colab_type":"code","colab":{}},"source":["# CREATING SIMILAR DATASSET TO PLOT TEST PREDICTIONS\n","testPredictPlot = np.empty_like(OHLC_avg)\n","testPredictPlot[:, :] = np.nan\n","testPredictPlot[len(trainPredict)+(step_size*2)+1:len(OHLC_avg)-1, :] = testPredict"],"execution_count":0,"outputs":[]},{"cell_type":"code","metadata":{"id":"uMlLzjbO2KVv","colab_type":"code","outputId":"73e936bf-4275-49e1-8a8c-6255c930cfb8","executionInfo":{"status":"ok","timestamp":1565978414993,"user_tz":240,"elapsed":1462,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":283}},"source":["# PLOT OF MAIN OHLC VALUES, TRAIN PREDICTIONS AND TEST PREDICTIONS\n","plt.plot(trainPredictPlot, 'r', label = 'training set')\n","plt.plot(testPredictPlot, 'b', label = 'predicted stock price/test set')\n","plt.legend(loc = 'upper right')\n","plt.xlabel('Time in Days')\n","plt.ylabel('Trend of training and prediction data')\n","plt.show()\n"],"execution_count":94,"outputs":[{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAY8AAAEKCAYAAADq59mMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n","text/plain":["<Figure size 432x288 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"cell_type":"markdown","metadata":{"id":"zHx-W08B2wps","colab_type":"text"},"source":["**We trained our data for the first 1700 or so days and then tested for the rest. The prediction plot has kept up with the pattern how ever not to my satisfaction.**"]},{"cell_type":"code","metadata":{"id":"C5SQ_pi82KS5","colab_type":"code","outputId":"053cd7ec-42f0-452d-cc86-768e0a88531c","executionInfo":{"status":"ok","timestamp":1565978422972,"user_tz":240,"elapsed":1560,"user":{"displayName":"Nupur Deshpande","photoUrl":"","userId":"13787757531456301957"}},"colab":{"base_uri":"https://localhost:8080/","height":50}},"source":["# PREDICT FUTURE VALUES\n","last_val = testPredict[-1]\n","last_val_scaled = last_val/last_val\n","next_val = model.predict(np.reshape(last_val_scaled, (1,1,1)))\n","print(\"Last Day Value:\", np.asscalar(last_val))\n","print(\"Next Day Value:\", np.asscalar(last_val*next_val))\n","# print np.append(last_val, next_val)\n"],"execution_count":95,"outputs":[{"output_type":"stream","text":["Last Day Value: 139.6865234375\n","Next Day Value: 138.06378173828125\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"IXmqKOhv5k_4","colab_type":"text"},"source":["**The value  was found  relying on OHLC values. As the days increase the value is decreasing or rather stabilizing. However this is a wrong way of going about since amazon prices are still booming not decreasing.**\n","\n","**Next notebook I'll focus on NOT overfitting the model and trying to get more data. Also I'll perform hyperparameter tuning and then try to PREDICT the STOCK PRICE MOVEMENT instead of the prices** "]},{"cell_type":"markdown","metadata":{"id":"j4UZTgxim3s7","colab_type":"text"},"source":["  Code Ref for LSTM:\n","  \n","  https://github.com/LiamConnell/deep-algotrading\n","  \n","  https://keras.io/getting-started/sequential-model-guide/"]},{"cell_type":"markdown","metadata":{"id":"bWkl-qKK8p4s","colab_type":"text"},"source":["**IN THE NEXT NOTEBOOK I AM GOING TO FOCUS MORE ON NORMALIZATION WITH HYPERPARAMTER TUNING AND LESS ON FEATURE EXTRACTION. THE REASON FOR THIS IS IT LOOKS LIKE A LSTM ESPECIALLY ON KERAS DOESN'T DO A GREAT JOB AT PREDICTING DAY TO DAY VALUES.**"]},{"cell_type":"markdown","metadata":{"id":"uYzRzdkT1xbz","colab_type":"text"},"source":["**CONCLUSION FOR THIS NOTEBOOK:**\n","\n","**1. FEATURES**:\n","\n","**Focused on feature engineering and made a total of 19 features. Most of them were based on momentum and moving avaerage and EMA. Even Bollinger Bands were calculated**\n","\n","**2. ARIMA MODEL**\n","\n","**Got a great ARIMA model with less differemce AIC and BIC and P values close to the coefficient**\n","\n","**3. FOURIER TRANSFORM MODEL**\n","\n","**We got great predictions with Fourier Transform very close to the actual values**\n","\n","**4. FEATURE ENGINEERING WITH XGBOOST**\n","\n","**Refer to feature extraction graph where features are highest by their closeness to their Closing values. As predicted EMA is pretty high in this feature.** \n","\n","**5. LSTM MODEL WITH ONE FEATURE** \n","\n","**LSTM model with one feature did NOT give us the predictions we wanted.**\n","\n","**6. LSTM MODEL WITH MULTIPLE FEATURES**\n","\n","**LSTM model with multiple features again did not give us predictions we wanted.**\n","\n","**I have come to the conclusion that LSTMs are not great at predicting Stock Prices when you just input stock price directly but rather better at predicting stock price movement over a long period of time.With the help of these movements we can calclate the price.**\n","\n","**For this reason  I will use a larger dataset in the next notebook that can be observed for longer time and then predict stock price movement**\n"," \n"]}]}