{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from statsmodels.tsa.statespace.varmax import VARMAX\n", "import pandas as pd\n", "import numpy as np\n", "\n", "%matplotlib inline\n", "\n", "import matplotlib\n", "import matplotlib.pyplot as plt\n", "\n", "from random import random" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 100 entries, 0 to 99\n", "Data columns (total 2 columns):\n", "v1 100 non-null float64\n", "v2 100 non-null float64\n", "dtypes: float64(2)\n", "memory usage: 1.6 KB\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
v1v2
970.0236460.941460
980.3530590.483105
990.4182061.151123
\n", "
" ], "text/plain": [ " v1 v2\n", "97 0.023646 0.941460\n", "98 0.353059 0.483105\n", "99 0.418206 1.151123" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cols = ['v1', 'v2']\n", "lst = []\n", "for i in range(100):\n", " v1 = random()\n", " v2 = v1 + random()\n", " row = [v1,v2]\n", " lst.append(row)\n", " \n", "df = pd.DataFrame(lst, columns=cols)\n", "df.info()\n", "df.tail(3)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/anaconda3/lib/python3.6/site-packages/statsmodels/tsa/statespace/varmax.py:152: EstimationWarning: Estimation of VARMA(p,q) models is not generically robust, due especially to identification issues.\n", " EstimationWarning)\n", "/anaconda3/lib/python3.6/site-packages/statsmodels/base/model.py:508: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n", " \"Check mle_retvals\", ConvergenceWarning)\n", "/anaconda3/lib/python3.6/site-packages/statsmodels/tsa/statespace/varmax.py:152: EstimationWarning: Estimation of VARMA(p,q) models is not generically robust, due especially to identification issues.\n", " EstimationWarning)\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
v1v2
0NaNNaN
1000.5187110.961162
990.4182061.151123
\n", "
" ], "text/plain": [ " v1 v2\n", "0 NaN NaN\n", "100 0.518711 0.961162\n", "99 0.418206 1.151123" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model = VARMAX(df.values.tolist(), order=(1,1))\n", "model_fit = model.fit(disp=False)\n", "\n", "y = pd.DataFrame(model_fit.forecast(), columns=cols)\n", "y.loc[100] = y.loc[0]\n", "y.loc[99] = df.loc[99]\n", "y.loc[0] = [np.nan, np.nan]\n", "y.tail(3)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.plot(df['v1'], 'b')\n", "plt.plot(df['v2'], 'g')\n", "\n", "plt.plot(y.tail(2), 'r')\n", "\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Statespace Model Results
Dep. Variable: ['y1', 'y2'] No. Observations: 100
Model: VARMA(1,1) Log Likelihood -32.332
+ intercept AIC 90.664
Date: Sat, 01 Sep 2018 BIC 124.531
Time: 21:25:31 HQIC 104.370
Sample: 0
- 100
Covariance Type: opg
\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Ljung-Box (Q): 33.31, 37.15 Jarque-Bera (JB): 3.53, 6.67
Prob(Q): 0.76, 0.60 Prob(JB): 0.17, 0.04
Heteroskedasticity (H): 1.15, 1.03 Skew: 0.00, -0.05
Prob(H) (two-sided): 0.70, 0.94 Kurtosis: 2.08, 1.74
\n", "\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Results for equation y1
coef std err z P>|z| [0.025 0.975]
const 0.2345 0.662 0.354 0.723 -1.064 1.533
L1.y1 -0.6849 1.119 -0.612 0.540 -2.878 1.508
L1.y2 0.5941 0.800 0.743 0.458 -0.974 2.162
L1.e(y1) 0.6219 1.127 0.552 0.581 -1.586 2.830
L1.e(y2) -0.6160 0.808 -0.762 0.446 -2.200 0.968
\n", "\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Results for equation y2
coef std err z P>|z| [0.025 0.975]
const 1.1360 0.826 1.376 0.169 -0.483 2.755
L1.y1 -0.3137 1.411 -0.222 0.824 -3.079 2.452
L1.y2 -0.0052 1.023 -0.005 0.996 -2.010 2.000
L1.e(y1) 0.3306 1.417 0.233 0.816 -2.446 3.107
L1.e(y2) -0.1307 1.005 -0.130 0.897 -2.099 1.838
\n", "\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Error covariance matrix
coef std err z P>|z| [0.025 0.975]
sqrt.var.y1 0.2661 0.028 9.669 0.000 0.212 0.320
sqrt.cov.y1.y2 0.2827 0.049 5.755 0.000 0.186 0.379
sqrt.var.y2 0.3037 0.039 7.855 0.000 0.228 0.380


Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step)." ], "text/plain": [ "\n", "\"\"\"\n", " Statespace Model Results \n", "==============================================================================\n", "Dep. Variable: ['y1', 'y2'] No. Observations: 100\n", "Model: VARMA(1,1) Log Likelihood -32.332\n", " + intercept AIC 90.664\n", "Date: Sat, 01 Sep 2018 BIC 124.531\n", "Time: 21:25:31 HQIC 104.370\n", "Sample: 0 \n", " - 100 \n", "Covariance Type: opg \n", "===================================================================================\n", "Ljung-Box (Q): 33.31, 37.15 Jarque-Bera (JB): 3.53, 6.67\n", "Prob(Q): 0.76, 0.60 Prob(JB): 0.17, 0.04\n", "Heteroskedasticity (H): 1.15, 1.03 Skew: 0.00, -0.05\n", "Prob(H) (two-sided): 0.70, 0.94 Kurtosis: 2.08, 1.74\n", " Results for equation y1 \n", "==============================================================================\n", " coef std err z P>|z| [0.025 0.975]\n", "------------------------------------------------------------------------------\n", "const 0.2345 0.662 0.354 0.723 -1.064 1.533\n", "L1.y1 -0.6849 1.119 -0.612 0.540 -2.878 1.508\n", "L1.y2 0.5941 0.800 0.743 0.458 -0.974 2.162\n", "L1.e(y1) 0.6219 1.127 0.552 0.581 -1.586 2.830\n", "L1.e(y2) -0.6160 0.808 -0.762 0.446 -2.200 0.968\n", " Results for equation y2 \n", "==============================================================================\n", " coef std err z P>|z| [0.025 0.975]\n", "------------------------------------------------------------------------------\n", "const 1.1360 0.826 1.376 0.169 -0.483 2.755\n", "L1.y1 -0.3137 1.411 -0.222 0.824 -3.079 2.452\n", "L1.y2 -0.0052 1.023 -0.005 0.996 -2.010 2.000\n", "L1.e(y1) 0.3306 1.417 0.233 0.816 -2.446 3.107\n", "L1.e(y2) -0.1307 1.005 -0.130 0.897 -2.099 1.838\n", " Error covariance matrix \n", "==================================================================================\n", " coef std err z P>|z| [0.025 0.975]\n", "----------------------------------------------------------------------------------\n", "sqrt.var.y1 0.2661 0.028 9.669 0.000 0.212 0.320\n", "sqrt.cov.y1.y2 0.2827 0.049 5.755 0.000 0.186 0.379\n", "sqrt.var.y2 0.3037 0.039 7.855 0.000 0.228 0.380\n", "==================================================================================\n", "\n", "Warnings:\n", "[1] Covariance matrix calculated using the outer product of gradients (complex-step).\n", "\"\"\"" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model_fit.summary()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 2 }