Skip to content

Instantly share code, notes, and snippets.

@KimMyungSam
Created November 17, 2017 10:44
Show Gist options
  • Save KimMyungSam/5e5a9727968cbc6a7d06a6e180ed5f89 to your computer and use it in GitHub Desktop.
Save KimMyungSam/5e5a9727968cbc6a7d06a6e180ed5f89 to your computer and use it in GitHub Desktop.
ARIMA , adding prediction number
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"from pandas import read_csv\n",
"from pandas import datetime\n",
"import numpy as np\n",
"from matplotlib import pyplot\n",
"from statsmodels.tsa.arima_model import ARIMA\n",
"from sklearn.metrics import mean_squared_error\n",
" \n",
"def parser(x):\n",
"\treturn datetime.strptime('190'+x, '%Y-%m')\n",
" \n",
"# series = read_csv('lo.csv', header=0, parse_dates=[0], index_col=0, squeeze=True, date_parser=parser)\n",
"series = read_csv('excel.csv',header=0, parse_dates=[0], index_col=0)\n",
"# series.plot()\n",
"# pyplot.show()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"X = series.values[::-1]\n",
"# print ('x',X)\n",
"# size = int(len(X) * 0.90)\n",
"size = int(len(X) * 0.99)\n",
"train, test = X[0:size], X[size:len(X)]\n",
"test = np.append(test, 0) # predict를 위한 추가 임의값"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"predicted=128.214760, expected=126.000000, diff=2.214760\n",
"predicted=128.761586, expected=149.000000, diff=-20.238414\n",
"predicted=125.187545, expected=165.000000, diff=-39.812455\n",
"predicted=131.997542, expected=124.000000, diff=7.997542\n",
"predicted=123.921089, expected=127.000000, diff=-3.078911\n",
"predicted=127.303875, expected=176.000000, diff=-48.696125\n",
"predicted=145.735721, expected=136.000000, diff=9.735721\n",
"predicted=146.868254, expected=144.000000, diff=2.868254\n",
"predicted=146.561826, expected=0.000000, diff=146.561826\n",
"Test MSE: 2891.963\n",
"Prediction nums is [ 146.56182625]\n"
]
}
],
"source": [
"history = [float(x) for x in train]\n",
"predictions = list()\n",
"for t in range(len(test)):\n",
"\tmodel = ARIMA(history, order=(5,1,0))\n",
" # model = ARIMA(history, order=(5,1,0))\n",
"\tmodel_fit = model.fit(disp=0)\n",
"\toutput = model_fit.forecast()\n",
"\tyhat = output[0]\n",
"\tpredictions.append(yhat)\n",
"\tobs = test[t]\n",
"\thistory.append(obs)\n",
"\tdiff = yhat - obs\n",
"\tprint('predicted=%f, expected=%f, diff=%f' % (yhat, obs, yhat-obs))\n",
"error = mean_squared_error(test, predictions)\n",
"print('Test MSE: %.3f' % error)\n",
"print('Prediction nums is %s' % predictions[-1])"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAABIgAAANSCAYAAAAOLvUEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0xd611be0>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# plot\n",
"pyplot.figure(figsize=(20,15))\n",
"pyplot.plot(test, 'o-')\n",
"pyplot.plot(predictions, 'ro-')\n",
"pyplot.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Band2"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Band3"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Band4"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Band5"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment