Skip to content

Instantly share code, notes, and snippets.

@dartdog
Created November 22, 2013 17:49
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save dartdog/7604008 to your computer and use it in GitHub Desktop.
Save dartdog/7604008 to your computer and use it in GitHub Desktop.
{
"metadata": {
"name": "gistfile1.txt"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": "import numpy as np\nimport pandas as pd\nimport statsmodels.api as sm\nimport matplotlib.pyplot as plt\nfrom StringIO import StringIO \nimport requests\n\nprint 'Numpy:', np.__version__\nprint 'Pandas:', pd.__version__\nimport statsmodels\nprint 'Statsmodels:', statsmodels.__version__\n\nnp.set_printoptions(precision=2)",
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": "Numpy: 1.8.0\nPandas: 0.12.0-1047-g2d2e8b5\nStatsmodels: 0.6.0.dev-Unknown\n"
}
],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": "act = requests.get('https://docs.google.com/spreadsheet/ccc?key=0Ak_wF7ZGeMmHdFZtQjI1a1hhUWR2UExCa2E4MFhiWWc&output=csv&gid=1')\ndata = pd.read_csv(StringIO(act.content),index_col=0,parse_dates=['date'], thousands=',').sort_index() #converts to numbers",
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": "# In your example, you weren't able to predict because your dataframe was not sorted correctly;\n# If you look at the model summary table, you'll see that the sample runs from\n# 08-01-2013 to 05-01-2000\ndata['Unit Sales'].plot()",
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 3,
"text": "<matplotlib.axes.AxesSubplot at 0x5623250>"
},
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAXkAAAEPCAYAAACneLThAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nJwAAAABJRU5ErkJggg==\n",
"text": "<matplotlib.figure.Figure at 0x3a82590>"
}
],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": "# Augmented Dicky-Fuller test for unit roots\n# Null Hypothesis: Unit Root\n# Alternative Hypothesis: AR(p), where here p is selected as the lag <= 12 that minimizes AIC\nprint 'Augmented Dicky-Fuller Test (p <= 12)'\nprint sm.tsa.adfuller(data['Unit Sales'], 12)[1], '=> we cannot reject unit root in data'\nprint sm.tsa.adfuller(data['Unit Sales'].diff()[1:], 11)[1], '=> we can reject unit root in differenced data at 1%'",
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": "Augmented Dicky-Fuller Test (p <= 12)\n0.453907629823 => we cannot reject unit root in data\n0.00470416125858 => we can reject unit root in differenced data at 1%\n"
}
],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": "# So it looks like an appropriate model might be ARIMA(12,1,0)\np=12\nd=1\nq=0\nmod = sm.tsa.ARIMA(data['Unit Sales'], order=[p,d,q], freq='M') # mod is an object of class ARIMA\nres = mod.fit(); # res is an object of class ARIMAResults",
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 5
},
{
"cell_type": "code",
"collapsed": false,
"input": "print res.summary() # sometimes the Display() command isn't as nice as print\n\n# The roots table gives you information about the stationarity of the estimated ARIMA\n# model (i.e. did you choose a high enough `d`). All the roots are greater than 1 in\n# modulus, so our model is stationary. We could guess this would happen based on the\n# ADF test of the differenced data, which told us that we had one unit root.",
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": " ARIMA Model Results \n==============================================================================\nDep. Variable: D.Unit Sales No. Observations: 160\nModel: ARIMA(12, 1, 0) Log Likelihood -1150.617\nMethod: css-mle S.D. of innovations 314.595\nDate: Wed, 20 Nov 2013 AIC 2329.233\nTime: 07:29:34 BIC 2372.285\nSample: 06-01-2000 HQIC 2346.715\n - 09-01-2013 \n=======================================================================================\n coef std err z P>|z| [95.0% Conf. Int.]\n---------------------------------------------------------------------------------------\nconst 7.6884 12.774 0.602 0.548 -17.348 32.725\nar.L1.D.Unit Sales -0.2200 0.068 -3.228 0.002 -0.354 -0.086\nar.L2.D.Unit Sales -0.1089 0.070 -1.550 0.123 -0.247 0.029\nar.L3.D.Unit Sales -0.0310 0.070 -0.440 0.660 -0.169 0.107\nar.L4.D.Unit Sales -0.1597 0.070 -2.270 0.025 -0.298 -0.022\nar.L5.D.Unit Sales -0.1137 0.070 -1.635 0.104 -0.250 0.023\nar.L6.D.Unit Sales -0.2565 0.066 -3.861 0.000 -0.387 -0.126\nar.L7.D.Unit Sales -0.2117 0.068 -3.114 0.002 -0.345 -0.078\nar.L8.D.Unit Sales -0.2040 0.069 -2.942 0.004 -0.340 -0.068\nar.L9.D.Unit Sales -0.0047 0.070 -0.067 0.947 -0.143 0.133\nar.L10.D.Unit Sales -0.0956 0.071 -1.355 0.177 -0.234 0.043\nar.L11.D.Unit Sales -0.0327 0.070 -0.465 0.642 -0.170 0.105\nar.L12.D.Unit Sales 0.4781 0.068 7.082 0.000 0.346 0.610\n Roots \n==============================================================================\n Real Imaginary Modulus Frequency\n------------------------------------------------------------------------------\nAR.1 -1.1018 -0.0000j 1.1018 -0.5000\nAR.2 -0.9003 -0.5025j 1.0311 -0.4190\nAR.3 -0.9003 +0.5025j 1.0311 0.4190\nAR.4 -0.5342 -0.8814j 1.0307 -0.3367\nAR.5 -0.5342 +0.8814j 1.0307 0.3367\nAR.6 0.0008 -1.0515j 1.0515 -0.2499\nAR.7 0.0008 +1.0515j 1.0515 0.2499\nAR.8 0.5202 -0.9593j 1.0913 -0.1709\nAR.9 0.5202 +0.9593j 1.0913 0.1709\nAR.10 0.8766 -0.5080j 1.0131 -0.0836\nAR.11 0.8766 +0.5080j 1.0131 0.0836\nAR.12 1.2439 -0.0000j 1.2439 -0.0000\n------------------------------------------------------------------------------\n"
}
],
"prompt_number": 6
},
{
"cell_type": "code",
"collapsed": false,
"input": "predict = res.predict('2012-1-01','2015-01-01', dynamic=True)\n\nfig = plt.figure(figsize=(10,3))\nax = fig.add_subplot(111)\n#ax.plot(data.index, data['Unit Sales'])\nax.plot(data.index, data['Unit Sales']-data['Unit Sales'].mean())\nax.plot(predict.index, predict, 'r-');",
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "display_data",
"png": "iVBORw0KGgoAAAANSUhEUgAAAmAAAADICAYAAABPu116AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text": "<matplotlib.figure.Figure at 0x5bcd910>"
}
],
"prompt_number": 7
},
{
"cell_type": "code",
"collapsed": false,
"input": "",
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 7
}
],
"metadata": {}
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment