Add mlforecast

book/machinelearning/timeseries.ipynb

@@ -154,6 +154,55 @@
     "for train, test in cv.split(range(10)):\n",
     "    print(\"train:\", train, \"test:\", test)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Time Series Forecasting with Machine Learning with `mlforecast`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Do you want to perform powerful time series forecasting?\n",
+    "\n",
+    "Try `mlforecast` by Nixtla.\n",
+    "\n",
+    "`mlforecast` lets you run Machine Learning models for time series forecasting, even on remote clusters like Ray or Spark.\n",
+    "\n",
+    "Feature Engineering, support for exogenous variables, and probabilistic forecasting are also included."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install mlforecast"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lightgbm as lgb\n",
+    "\n",
+    "from mlforecast import MLForecast\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "\n",
+    "mlf = MLForecast(\n",
+    "    models = [LinearRegression(), lgb.LGBMRegressor()],\n",
+    "    lags=[1, 12],\n",
+    "    freq = 'M'\n",
+    ")\n",
+    "mlf.fit(df)\n",
+    "mlf.predict(12)"
+   ]
   }
  ],
  "metadata": {