{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "BTCBeer.ipynb",
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"metadata": {
"id": "k_nPyHLfhNcr"
},
"source": [
"# Credits to everythingcomputerscience.com for code snippets",
"# First import the libraries that we need to use\n",
"import pandas as pd\n",
"import numpy as np\n",
"import requests\n",
"import json\n",
"\n",
"# Fetch Bitcoin price data from coinbase",
"def fetch_daily_data(symbol):\n",
" pair_split = symbol.split('/') # symbol must be in format XXX/XXX ie. BTC/EUR\n",
" symbol = pair_split[0] + '-' + pair_split[1]\n",
" url = f'https://api.pro.coinbase.com/products/{symbol}/candles?granularity=86400'\n",
" response = requests.get(url)\n",
" if response.status_code == 200: # check to make sure the response from server is good\n",
" data = pd.DataFrame(json.loads(response.text), columns=['unix', 'low', 'high', 'open', 'close', 'volume'])\n",
" data['date'] = pd.to_datetime(data['unix'], unit='s') # convert to a readable date\n",
" data['vol_fiat'] = data['volume'] * data['close'] # multiply the BTC volume by closing price to approximate fiat volume\n",
"\n",
"# if we failed to get any data, print an error...otherwise write the file\n",
" if data is None:\n",
" print(\"Did not return any data from Coinbase for this symbol\")\n",
" else:\n",
" data.to_csv(f'Coinbase_{pair_split[0] + pair_split[1]}_dailydata.csv', index=False)\n",
" \n",
" else:\n",
" print(\"Did not receieve OK response from Coinbase API\")\n",
"\n",
"\n",
"if __name__ == \"__main__\":\n",
" # we set which pair we want to retrieve data for\n",
" pair = \"BTC/USD\"\n",
" fetch_daily_data(symbol=pair)\n"
],
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"resources": {
"http://localhost:8080/nbextensions/google.colab/files.js": {
"data": "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",
"ok": true,
"headers": [
[
"content-type",
"application/javascript"
]
],
"status": 200,
"status_text": ""
}
},
"base_uri": "https://localhost:8080/",
"height": 73
},
"id": "zEh7SQSjheeF",
"outputId": "a011a9b8-c0b9-49ab-f2be-ae94e8581909"
},
"source": [
"#load data\n",
"from google.colab import files\n",
"uploaded = files.upload()"
],
"execution_count": 3,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"\n",
" \n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"Saving Coinbase_BTCUSD_dailydata.csv to Coinbase_BTCUSD_dailydata (1).csv\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "sG7p82QyhihU"
},
"source": [
"#store date into variable\n",
"df = pd.read_csv('Coinbase_BTCUSD_dailydata.csv')"
],
"execution_count": 4,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "bhsdKIgDhmhS"
},
"source": [
"#remove unnecessary columns\n",
"df.drop(['unix','low','high','open','volume','date', 'vol_fiat'],1,inplace=True)"
],
"execution_count": 5,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "7ofUWzYHhsxt"
},
"source": [
"# A variable for predicting 'n' days into the future\n",
"prediction_days = 15 #number can be adjusted\n",
"\n",
"#create another column shifted 'n' units up\n",
"df['Prediction'] = df[['close']].shift(-prediction_days)"
],
"execution_count": 6,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "4cSj13-Gh5dC"
},
"source": [
"#create the independent data set\n",
"\n",
"#convert the dataframe to a numpy array and drop the prediction column\n",
"X = np.array(df.drop(['Prediction'],1))\n",
"\n",
"#remove last 'n' rows where 'n' is the prediction days\n",
"X = X[:len(df)-prediction_days]\n"
],
"execution_count": 7,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "iNxiSxIuh-pO"
},
"source": [
"#create the dependent data set\n",
"\n",
"#convert the dataframe to a numpy array\n",
"y = np.array(df['Prediction'])\n",
"\n",
"#get all of the values except the last 'n' rows\n",
"y = y[:-prediction_days]"
],
"execution_count": 8,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "owErtZ-niA4Z"
},
"source": [
"#split the data into 80% training and 20% testing\n",
"from sklearn.model_selection import train_test_split\n",
"x_train, x_test, y_train, y_test = train_test_split(X,y, test_size = 0.2)"
],
"execution_count": 9,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "BqkLo2_5iFuR"
},
"source": [
"#set the prediction_days_array equal to the last n rows from the original data set\n",
"prediction_days_array = np.array(df.drop(['Prediction'],1))[-prediction_days:]"
],
"execution_count": 10,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ziT5lcKniJDx",
"outputId": "cd8225dc-e7b1-4dba-e267-04c68b4a81c4"
},
"source": [
"#support vector machine regression\n",
"from sklearn.svm import SVR\n",
"\n",
"#create and train the Support Vector Machine (Regression) using radial basis function\n",
"svr_rbf = SVR(kernel='rbf', C=1e3, gamma=0.00001)\n",
"svr_rbf.fit(x_train, y_train)"
],
"execution_count": 11,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"SVR(C=1000.0, cache_size=200, coef0=0.0, degree=3, epsilon=0.1, gamma=1e-05,\n",
" kernel='rbf', max_iter=-1, shrinking=True, tol=0.001, verbose=False)"
]
},
"metadata": {
"tags": []
},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "S-anymDqiLVb",
"outputId": "e946a7be-659e-4658-cdb7-bcab463bca3d"
},
"source": [
"#test the model\n",
"svr_rbf_confidence = svr_rbf.score(x_test, y_test)\n",
"print(\"svr_rbf accuracy: \", svr_rbf_confidence)"
],
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"text": [
"svr_rbf accuracy: 0.30612217029950317\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "M5Y4osmriesQ",
"outputId": "6340fe09-eaf1-4b92-b56b-86f54fe73b33"
},
"source": [
"#print the predicted values\n",
"svm_prediction = svr_rbf.predict(x_test)\n",
"print(svm_prediction)\n",
"\n",
"print()\n",
"\n",
"#print the actual values\n",
"print(y_test)\n"
],
"execution_count": 13,
"outputs": [
{
"output_type": "stream",
"text": [
"[11624.8463675 19561.15748274 11681.18157266 19121.78204198\n",
" 16061.81401548 22163.60095396 17745.50995948 11800.45317139\n",
" 18290.40244972 20583.08910285 11844.86470776 22432.22132921\n",
" 11783.70866612 19981.22645502 18085.98942874 19418.95255572\n",
" 10666.73388238 11709.29029636 12155.07037139 18267.92240289\n",
" 19495.15704152 17812.16739327 11728.74857029 11795.09951855\n",
" 9196.61240191 11109.55685766 19492.34155869 20536.24958849\n",
" 9722.3092784 20091.82906305 20548.77042097 11068.83481441\n",
" 24732.3585646 12413.93268737 11814.94730182 11113.05815133\n",
" 20336.69644925 21492.67917572 21125.6939205 16058.57674341\n",
" 19646.12549442 17803.02531122 22347.27882738 23517.25303109\n",
" 11623.21898228 18621.25252478 15690.84162411 11311.25777113\n",
" 18105.13610436 19697.56868592 20868.77367555 15676.90683752\n",
" 19748.24047653 16793.8125835 20834.66965799 10970.62002356\n",
" 11480.53137431]\n",
"\n",
"[ 9130.11 19272.37 10730. 18821.28 11328.95 46448.1 13460. 10779.63\n",
" 15482.9 54916.38 11672.93 51601.73 10840.73 47232.45 18675.25 18316.22\n",
" 9355.74 11351.62 9941. 19713.94 15705.79 11760.45 11950. 10551.65\n",
" 9138.51 9175.85 16310.81 32112.01 9301.91 55923.52 23228.35 10172.52\n",
" 48511.6 11810.07 11388.53 10500.05 35512.67 33080.66 32288.56 10933.09\n",
" 19225.63 17170. 34030.64 48368.52 11330.06 11068.54 10670.47 10375.\n",
" 15342.25 19375.6 33488.99 12808. 18782.97 16339.56 32261.87 10679.95\n",
" 10690.53]\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "SOE9dr9Cig5y",
"outputId": "7c05452c-1c02-4d16-902f-02091ae5fa2d"
},
"source": [
"#print the model predictions for the next 'n' = 30 days\n",
"svm_prediction = svr_rbf.predict(prediction_days_array)\n",
"print (\"prediction values next days\", svm_prediction)\n"
],
"execution_count": 24,
"outputs": [
{
"output_type": "stream",
"text": [
"prediction values next days [12171.9073289 9548.26687829 9152.66150705 9235.89962889\n",
" 12734.39574266 13486.79951074 9236.76043918 9662.11120577\n",
" 9305.2884286 9837.94183414 10689.04578924 11520.98120533\n",
" 10407.3707233 9436.95894675 10894.10643987]\n"
],
"name": "stdout"
}
]
}
]
}