{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyNi+Ewkxp2IZ8viyYUSIC21",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"gpuClass": "standard"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
]
},
{
"cell_type": "code",
"source": [
"from google.colab import drive\n",
"drive.mount('/content/drive')\n",
"project_path = '/content/drive/MyDrive/projects/Stock_Predicter'\n",
"%cd $project_path"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Xr3Qozgfktoc",
"outputId": "78396a70-6eaa-462b-f7ca-75e282dab940"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Mounted at /content/drive\n",
"/content/drive/MyDrive/projects/Stock_Predicter\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# install dotenv\n",
"!pip install python-dotenv"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "E0itUkoVeKYn",
"outputId": "a876789d-096c-4301-e316-023f87e2e5de"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting python-dotenv\n",
" Downloading python_dotenv-1.0.0-py3-none-any.whl (19 kB)\n",
"Installing collected packages: python-dotenv\n",
"Successfully installed python-dotenv-1.0.0\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# install polygon client\n",
"!pip install polygon-api-client"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2bylenpXc1oB",
"outputId": "c47ad32c-3c50-41d9-a6ce-c051fb6639b5"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting polygon-api-client\n",
" Downloading polygon_api_client-1.8.5-py3-none-any.whl (38 kB)\n",
"Requirement already satisfied: urllib3<2.0.0,>=1.26.9 in /usr/local/lib/python3.9/dist-packages (from polygon-api-client) (1.26.15)\n",
"Collecting websockets<11.0,>=10.3\n",
" Downloading websockets-10.4-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (106 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m106.5/106.5 KB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: certifi<2023.0.0,>=2022.5.18 in /usr/local/lib/python3.9/dist-packages (from polygon-api-client) (2022.12.7)\n",
"Installing collected packages: websockets, polygon-api-client\n",
"Successfully installed polygon-api-client-1.8.5 websockets-10.4\n"
]
}
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "e8SQqogMQYLh"
},
"outputs": [],
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import pandas as pd\n",
"import pandas_datareader as web\n",
"import datetime as dt\n",
"import yfinance as yfin\n",
"\n",
"from sklearn.preprocessing import MinMaxScaler\n",
"from tensorflow.keras.models import Sequential\n",
"from tensorflow.keras.layers import Dense, Dropout, LSTM\n",
"from dotenv import dotenv_values\n",
"from polygon import RESTClient\n"
]
},
{
"cell_type": "code",
"source": [
"config = dotenv_values(\"env_stock_predictor\")\n",
"POLIGON_API_KEY = config['POLIGON_API_KEY']"
],
"metadata": {
"id": "MwIQIS6GeSJr"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Select a company for now\n",
"ticker = 'AAPL'\n",
"\n",
"start = dt.datetime(2013,1,1)\n",
"end = dt.date.today()\n",
"# end = dt.datetime(2023,3,15)\n",
"\n",
"# data = web.DataReader(ticker, 'yahoo', start, end) # This trows \"TypeError: string indices must be integers\"\n",
"\n",
"yfin.pdr_override()\n",
"data = web.data.get_data_yahoo(ticker, start, end)\n",
"print(data.tail())"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "O6dtJpJwS5Eg",
"outputId": "8782cb37-06ce-47c0-b352-f1f82a6db7de"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\r[*********************100%***********************] 1 of 1 completed\n",
" Open High Low Close Adj Close \\\n",
"Date \n",
"2023-03-29 159.369995 161.050003 159.350006 160.770004 160.770004 \n",
"2023-03-30 161.529999 162.470001 161.270004 162.360001 162.360001 \n",
"2023-03-31 162.440002 165.000000 161.910004 164.899994 164.899994 \n",
"2023-04-03 164.270004 166.289993 164.220001 166.169998 166.169998 \n",
"2023-04-04 166.600006 166.839996 165.110001 165.630005 165.630005 \n",
"\n",
" Volume \n",
"Date \n",
"2023-03-29 51305700 \n",
"2023-03-30 49501700 \n",
"2023-03-31 68694700 \n",
"2023-04-03 56976200 \n",
"2023-04-04 46237900 \n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# using the poligon API\n",
"poligon_client = RESTClient(api_key=POLIGON_API_KEY)"
],
"metadata": {
"id": "LEfjQ4cZi0tn"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# bars = poligon_client.get_aggs(ticker=ticker, multiplier=1, timespan=\"day\", from_=\"2023-01-09\", to=\"2023-01-15\")\n",
"bars = poligon_client.get_aggs(ticker=ticker, multiplier=1, timespan=\"day\", from_=start, to=end)\n"
],
"metadata": {
"id": "edWz4rdxdwqh"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"for bar in bars[-5:]:\n",
" print(type(bar))\n",
" print(bar)\n",
" print(bar.timestamp)\n",
" print(dt.date.fromtimestamp(bar.timestamp/1000))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "IX_o3NTggblq",
"outputId": "7a974d77-952e-425b-c702-e9a60fbb89be"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
"Agg(open=152.81, high=153.47, low=151.83, close=152.87, volume=47204791.0, vwap=152.6973, timestamp=1678251600000, transactions=405203, otc=None)\n",
"1678251600000\n",
"2023-03-08\n",
"\n",
"Agg(open=153.559, high=154.535, low=150.225, close=150.59, volume=53833122.0, vwap=152.4689, timestamp=1678338000000, transactions=480909, otc=None)\n",
"1678338000000\n",
"2023-03-09\n",
"\n",
"Agg(open=150.21, high=150.94, low=147.6096, close=148.5, volume=68559600.0, vwap=149.0716, timestamp=1678424400000, transactions=611457, otc=None)\n",
"1678424400000\n",
"2023-03-10\n",
"\n",
"Agg(open=147.805, high=153.14, low=147.7, close=150.47, volume=84457122.0, vwap=151.1835, timestamp=1678680000000, transactions=760660, otc=None)\n",
"1678680000000\n",
"2023-03-13\n",
"\n",
"Agg(open=151.28, high=153.4, low=150.1, close=152.59, volume=72045893.0, vwap=152.1061, timestamp=1678766400000, transactions=565196, otc=None)\n",
"1678766400000\n",
"2023-03-14\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"print(type(spy))\n",
"print(spy.head())"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "EMoXLT5vd8Ex",
"outputId": "d3c00e06-bf0a-4384-a21d-643d72a6848c"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Open High Low Close Adj Close \\\n",
"Date \n",
"2022-10-24 375.890015 380.059998 373.109985 378.869995 375.704315 \n",
"2022-10-25 378.790009 385.250000 378.670013 384.920013 381.703735 \n",
"2022-10-26 381.619995 387.579987 381.350006 382.019989 378.827972 \n",
"2022-10-27 383.070007 385.000000 379.329987 379.980011 376.805023 \n",
"2022-10-28 379.869995 389.519989 379.679993 389.019989 385.769470 \n",
"\n",
" Volume \n",
"Date \n",
"2022-10-24 85436900 \n",
"2022-10-25 78846300 \n",
"2022-10-26 104087300 \n",
"2022-10-27 81971800 \n",
"2022-10-28 100302000 \n"
]
}
]
},
{
"cell_type": "code",
"source": [
"df = web.DataReader('GE', 'yahoo', start='2019-09-10', end='2019-10-09')\n",
"print(start)\n",
"print(end)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 353
},
"id": "THGxnQbSUgvw",
"outputId": "82234614-328b-40b7-9024-fa32e20b2858"
},
"execution_count": null,
"outputs": [
{
"output_type": "error",
"ename": "TypeError",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mweb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataReader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'GE'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'yahoo'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstart\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'2019-09-10'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mend\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'2019-10-09'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstart\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mend\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.9/dist-packages/pandas/util/_decorators.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 205\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 206\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mnew_arg_name\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnew_arg_value\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 207\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 208\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 209\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mcast\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mF\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.9/dist-packages/pandas_datareader/data.py\u001b[0m in \u001b[0;36mDataReader\u001b[0;34m(name, data_source, start, end, retry_count, pause, session, api_key)\u001b[0m\n\u001b[1;32m 368\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 369\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mdata_source\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m\"yahoo\"\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 370\u001b[0;31m return YahooDailyReader(\n\u001b[0m\u001b[1;32m 371\u001b[0m \u001b[0msymbols\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 372\u001b[0m \u001b[0mstart\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstart\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.9/dist-packages/pandas_datareader/base.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 251\u001b[0m \u001b[0;31m# If a single symbol, (e.g., 'GOOG')\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 252\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msymbols\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mstring_types\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 253\u001b[0;31m \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_read_one_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_params\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msymbols\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 254\u001b[0m \u001b[0;31m# Or multiple symbols, (e.g., ['GOOG', 'AAPL', 'MSFT'])\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 255\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msymbols\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mDataFrame\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.9/dist-packages/pandas_datareader/yahoo/daily.py\u001b[0m in \u001b[0;36m_read_one_data\u001b[0;34m(self, url, params)\u001b[0m\n\u001b[1;32m 151\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 152\u001b[0m \u001b[0mj\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mre\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msearch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mptrn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mresp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtext\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mre\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDOTALL\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgroup\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 153\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mj\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"context\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"dispatcher\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"stores\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"HistoricalPriceStore\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 154\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 155\u001b[0m \u001b[0mmsg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"No data fetched for symbol {} using {}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mTypeError\u001b[0m: string indices must be integers"
]
}
]
},
{
"cell_type": "code",
"source": [
"scaler = MinMaxScaler(feature_range=(0,1))\n",
"scaled_data = scaler.fit_transform(data['Close'].values.reshape(-1,1))\n",
"prediction_days = 60\n",
"\n",
"x_train = []\n",
"y_train = []\n",
"\n",
"for x in range()"
],
"metadata": {
"id": "ccV59ukvXaNF"
},
"execution_count": null,
"outputs": []
}
]
} |