{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "kernelspec": {
      "display_name": "Python [conda env:textbook]",
      "language": "python",
      "name": "conda-env-textbook-py"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.6.6"
    },
    "toc": {
      "nav_menu": {},
      "number_sections": true,
      "sideBar": true,
      "skip_h1_title": false,
      "toc_cell": false,
      "toc_position": {},
      "toc_section_display": "block",
      "toc_window_display": false
    },
    "varInspector": {
      "cols": {
        "lenName": 16,
        "lenType": 16,
        "lenVar": 40
      },
      "kernels_config": {
        "python": {
          "delete_cmd_postfix": "",
          "delete_cmd_prefix": "del ",
          "library": "var_list.py",
          "varRefreshCmd": "print(var_dic_list())"
        },
        "r": {
          "delete_cmd_postfix": ") ",
          "delete_cmd_prefix": "rm(",
          "library": "var_list.r",
          "varRefreshCmd": "cat(var_dic_list()) "
        }
      },
      "oldHeight": 122,
      "position": {
        "height": "879px",
        "left": "759.983px",
        "right": "20px",
        "top": "151.989px",
        "width": "400px"
      },
      "types_to_exclude": [
        "module",
        "function",
        "builtin_function_or_method",
        "instance",
        "_Feature"
      ],
      "varInspector_section_display": "block",
      "window_display": false
    },
    "colab": {
      "name": "example_fitting_time_series.ipynb",
      "provenance": []
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "e3rRgMIgdAvW",
        "colab_type": "text"
      },
      "source": [
        "# Fitting a time series with SVR"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qlYdw4FjdAva",
        "colab_type": "text"
      },
      "source": [
        "This notebook loads up some actual measurements of the sun over time, cleans the data, and then uses machine learning techniques to fit those data. \n",
        "\n",
        "Specifically for the data, the observations are from the Solar Dynamics Observatory (SDO) Extreme Ultraviolet Variability Experiment (EVE) that measures all the light coming from the sun between 5 nanometers (nm) and 105 nm. We'll be working just with the measurements taken at 17.1 nm; light that is emitted from the Iron (Fe) IX ion in the corona, which only exists at a temperature of about 600,000 K -- a fairly moderate temperature for the solar corona. \n",
        "\n",
        "Specifically for the machine learning, we'll be using Support Vector Regression (SVR) and validation curves. Support Vector Machines (SVM) are typically used in a type of **classification**, an important category of machine learning that focuses on identifying and labeling groups in the data. SVMs can be extended to regression. There's some discussion of the function we'll be using [here](http://scikit-learn.org/stable/modules/generated/sklearn.svm.SVR.html) and [here](http://scikit-learn.org/stable/modules/svm.html#svm-regression). Validation curves are a way of quantifying the question: _which fit is the best fit?_ Data scientists are probably used to seeing things like reduced $\\chi^2$. The purpose is the same, but these tools are built together in a python module we'll be using extensively, called [scikit-learn](http://scikit-learn.org/stable/). \n",
        "\n",
        "\n",
        "Next line download this <a href=\"https://raw.githubusercontent.com/jmason86/python_convenience_functions/master/jpm_time_conversions.py\">PY file</a>.\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VArZ4Dj7dSfS",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# For Google Colab\n",
        "! rm jpm_time_conversions.py -f\n",
        "! wget https://raw.githubusercontent.com/jmason86/python_convenience_functions/master/jpm_time_conversions.py -q | python"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "UaEoK-P-dAvb",
        "colab_type": "text"
      },
      "source": [
        "First we'll import all the stuff we're going to need, just to get that out of the way."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "sHAzr0zRdAvc",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Standard modules\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "%matplotlib inline\n",
        "import seaborn as sns\n",
        "plt.style.use('seaborn')\n",
        "from scipy.io.idl import readsav\n",
        "from sklearn.pipeline import make_pipeline\n",
        "from sklearn.model_selection import validation_curve, ShuffleSplit\n",
        "from sklearn.metrics import explained_variance_score, make_scorer\n",
        "from sklearn.svm import SVR\n",
        "\n",
        "# Custom modules\n",
        "from jpm_time_conversions import metatimes_to_seconds_since_start, datetimeindex_to_human"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "mMIxmLxSdAvg",
        "colab_type": "text"
      },
      "source": [
        "## Load and clean data"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xe4V1i5XdAvh",
        "colab_type": "text"
      },
      "source": [
        "Next we will load up the data. You can download that dataset from [here](https://www.dropbox.com/s/bt5oh244mt4jw72/Example%20Dimming%20Light%20Curve.sav?dl=0) and then just update the path below as necessary to point to it. We're using [pandas](https://pandas.pydata.org/) DataFrames largely because they are highly compatible with scikit-learn, as we'll see later. Finally, we'll use the ```head()``` function to take a quick look at the data. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1YiLOG_zfBl9",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "! rm uc?id=15sWqoZ6LvBA8mxZ07vDsVQtFNiDpfiEW -f\n",
        "! wget https://drive.google.com/uc?id=15sWqoZ6LvBA8mxZ07vDsVQtFNiDpfiEW -q"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gU-tBC6NdAvi",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 197
        },
        "outputId": "b25c288f-67fa-4876-c46e-d4659b6aad69"
      },
      "source": [
        "idl_generated_data = readsav('uc?id=15sWqoZ6LvBA8mxZ07vDsVQtFNiDpfiEW')\n",
        "light_curve_df = pd.DataFrame({'irradiance':idl_generated_data.irradiance.byteswap().newbyteorder(),  # [W/m^2]\n",
        "                               'uncertainty':idl_generated_data.uncertainty.byteswap().newbyteorder()})  # [%]\n",
        "light_curve_df.index = pd.DatetimeIndex(idl_generated_data.datetime.astype(str))\n",
        "light_curve_df.head()"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>irradiance</th>\n",
              "      <th>uncertainty</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2012-04-16 17:43:20</th>\n",
              "      <td>0.246831</td>\n",
              "      <td>0.052733</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-04-16 17:44:19</th>\n",
              "      <td>0.399922</td>\n",
              "      <td>0.085439</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-04-16 17:45:18</th>\n",
              "      <td>0.275836</td>\n",
              "      <td>0.058930</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-04-16 17:46:17</th>\n",
              "      <td>0.319487</td>\n",
              "      <td>0.068255</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2012-04-16 17:47:16</th>\n",
              "      <td>0.920058</td>\n",
              "      <td>0.196561</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                     irradiance  uncertainty\n",
              "2012-04-16 17:43:20    0.246831     0.052733\n",
              "2012-04-16 17:44:19    0.399922     0.085439\n",
              "2012-04-16 17:45:18    0.275836     0.058930\n",
              "2012-04-16 17:46:17    0.319487     0.068255\n",
              "2012-04-16 17:47:16    0.920058     0.196561"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cjM6wpeDdAvm",
        "colab_type": "text"
      },
      "source": [
        "Next we'll plot the data so we can get a quick idea of what we're working with. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6Gu7MrLYdAvn",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 504
        },
        "outputId": "218ac645-a14b-4d30-959b-df50d49a1940"
      },
      "source": [
        "plt.errorbar(x=light_curve_df.index, y=light_curve_df['irradiance'], yerr=light_curve_df['uncertainty'], fmt='o')\n",
        "plt.title(\"t$_0$ = \" + datetimeindex_to_human(light_curve_df.index)[0])\n",
        "plt.xlabel('time')\n",
        "plt.ylabel('irradiance [%]');"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/pandas/plotting/_matplotlib/converter.py:103: FutureWarning: Using an implicitly registered datetime converter for a matplotlib plotting method. The converter was registered by pandas on import. Future versions of pandas will require you to explicitly register matplotlib converters.\n",
            "\n",
            "To register the converters:\n",
            "\t>>> from pandas.plotting import register_matplotlib_converters\n",
            "\t>>> register_matplotlib_converters()\n",
            "  warnings.warn(msg, FutureWarning)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe8AAAFpCAYAAAC1YKAIAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTURE5DIM3kRERC7D4E1EROQy/z9wW+gkKVBE3gAAAABJRU5ErkJggg==\n",
            "text/plain": [
              "<Figure size 576x396 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cZPjLRgFdAvq",
        "colab_type": "text"
      },
      "source": [
        "So sure, these are some measurements of ultraviolet light from the sun. But looking at it, it could be almost anything. It's just a time series. Your eye can naturally trace some basic shapes in the data; you can pretty easily see through the noise. But what we'd like is to have just that smooth curve. The original motivation that lead to the example was to be able to parameterize the depth and slope of that dip about a quarter of the way through; that's a coronal dimming and it contains information about a violent coronal mass ejection that resulted in some bad space weather. If interested, you can read the papers about this coronal dimming work [here](https://ui.adsabs.harvard.edu/#abs/2016SPD....4740402M/abstract) and [here](https://ui.adsabs.harvard.edu/#abs/2014ApJ...789...61M/abstract)."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2bpZACpIdAvr",
        "colab_type": "text"
      },
      "source": [
        "So we want to pull out the smooth curve underlying that data. There are plenty of traditional approaches to do this. We could smooth. We could fit polynomials. We could fit a spline. We chose this as a first example to help bridge the gap between the familiar and the probably less familiar machine learning method. Lets start with a little bit of code."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XdJGzSUedAvs",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Pull data out of the DataFrame for compatibility formatting\n",
        "X = metatimes_to_seconds_since_start(light_curve_df.index)\n",
        "y = light_curve_df['irradiance'].values"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FIuCowfldAvv",
        "colab_type": "text"
      },
      "source": [
        "This X, y format is the standard when using nearly anything in scikit-learn. They've built a very nice, uniform application programming interface (API). In this particular case, it's pretty obvious that the X is time and y is the intensity. They are each 1 dimensional. But in general, this same syntax is used even when we have highly dimensional data. Each of the y dimensions is known as a **feature**, in machine learning parlance. We convert the times to seconds since start to avoid issues interpreting timestamps later."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Vq8EA_XLdAvw",
        "colab_type": "text"
      },
      "source": [
        "Next we'll do a bit of cleaning. Most machine learning methods cannot accept missing data. You have to \"impute\", i.e., decide how you want to fill in those missing data. scikit-learn has a whole [Imputer](http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.Imputer.html) tool for dealing with this. In our case, we'll just get rid of those missing data, marked by a NaN, since we still maintain the proper timing with our X axis. We'll also do a bit of shaping for compatibility with scikit-learn functions."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cX6D66v5dAvx",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "finite_irradiance_indices = np.isfinite(y)\n",
        "X = X[finite_irradiance_indices]\n",
        "X = X.reshape(len(X), 1)\n",
        "uncertainty = light_curve_df['uncertainty'].values[np.isfinite(y)]\n",
        "y = y[finite_irradiance_indices]"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IAbkcak2dAvz",
        "colab_type": "text"
      },
      "source": [
        "## Best fit determination"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RT9WaEcldAv0",
        "colab_type": "text"
      },
      "source": [
        "Here, we're just defining a quick helper function that we'll be using in the next section. We'll come back and explain this momentarily."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "s5L2CvYLdAv1",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Helper function for compatibility with validation_curve\n",
        "def jpm_svr(gamma=5e-8, **kwargs):\n",
        "    return make_pipeline(SVR(kernel='rbf', C=1e3, gamma=gamma, **kwargs))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5me_So-5dAv4",
        "colab_type": "text"
      },
      "source": [
        "Now to figure out which fit is going to be the best one, we still need to decide on what range we're going to test across. If this were a polynomial fit, we'd be talking about which polynomial orders we'd like to try fitting. In the case of SVR, that free parameter is called $\\gamma$. Having some a priori knowledge of what range is sensible for this data, we'll generate an array of $\\gamma$s to test. Another note of nomenclature, in machine learning, these are known as **hyper parameters*"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CuBb_t4wdAv4",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "gamma = np.logspace(-10, -5, num=20, base=10)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JzKP4cKjdAv7",
        "colab_type": "text"
      },
      "source": [
        "Another thing we'll need in order to determine which fit is best is a metric to do that scoring. scikit-learn has many options available. The default is R^2 but we'll overwrite that default with explained variance."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pLtVkcqvdAv8",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "evs = make_scorer(explained_variance_score)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "r8Ut85u6dAv-",
        "colab_type": "text"
      },
      "source": [
        "The last bit of prep before we can figure out which fit is best is to decide which data will be used to train the data and which will be used to score the fit. This concept is probably new to those who haven't dealt with machine learning before. It comes from one of the fundamental purposes of the discipline: prediction. If I'd like to validate my model without waiting for new data to come in (if new data are even still being generated), then I can simply allocate some of my existing data for training and treat the other chunk like new incoming data to validate and quantify how good the predictions are. Relatedly, a common problem is that if you fit _all_ of the data, your model will do a really good job of fitting that data, but do terrible with any new data. It's sort of like overfitting. We'll come back to that next, but first, lets just split the data 50/50. A shuffle split picks a uniformly random selection of data points. This way we can be sure our data still span the whole time series, instead of just picking e.g., the first quarter of data to train on. With the ```n_splits``` optional input, we can decide how many different sets we want to make. In other words, choose some random points to train on. Now choose another random set of points to train on. Repeat, repeat, repeat for as many times as you define with ```n_splits```. This helps make our results more robust. You can play around with how many splits you need to get final results (later) that don't vary much. We've already done that and found that 20 works pretty well. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Jap9pIZOdAv_",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "shuffle_split = ShuffleSplit(n_splits=20, train_size=0.5, test_size=0.5, random_state=None)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "saJRhQgldAwD",
        "colab_type": "text"
      },
      "source": [
        "Now we can get to the validation curve. First we'll discuss the input, then run it, plot it, and discuss it. \n",
        "\n",
        "The first input makes use of our earlier helper function, ```jpm_svr()```. All this function does is make a pipeline around the SVR function. Pipelines in scikit-learn are pretty nifty. They result in an object that has the same API as any other model type, but allow you to wrap up a whole bunch of different methods together. For example, you could wrap up a bunch of pre-processing like Impute in here. In this case, our helper function is just allowing us to input a variety of $\\gamma$s in a single call to validation curve. \n",
        "\n",
        "The next inputs are just the X and y arrays. Pretty straight forward. Next we define the name of the parameter that is going to be varied: $\\gamma$ in this case. Models other than SVR would have other hyperparameters and may even have more than one. Then we pass in that array of different $\\gamma$s to vary. \n",
        "\n",
        "Next we've got a few optional inputs. ```cv``` is the cross-validation strategy. This is where we can input our ```shuffle_split``` object just defined. ```n_jobs``` is a really nice and quick way to parallelize this work. Literally just pass in the number of parallel threads you want. Be careful using this out in the wild though. If you're building this into a bigger suite of code that is itself already running in parallel, you can end up actually slowing things down and get confusing results when each higher-level parallel thread try to spin off new threads for the validation curve. Then finally, we have ```scoring```, where we can input the explained variance object we defined earlier."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "G92NDHRYdAwD",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train_score, val_score = validation_curve(jpm_svr(), X, y,\n",
        "                                          'svr__gamma',\n",
        "                                          gamma, cv=shuffle_split, n_jobs=3, scoring=evs)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "10PhXaRVdAwH",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 380
        },
        "outputId": "010a82ad-5075-4ea9-e17a-fb6c6a4d4522"
      },
      "source": [
        "p1 = plt.semilogx(gamma, np.median(train_score, 1), label='training score')\n",
        "p2 = plt.semilogx(gamma, np.median(val_score, 1), label='validation score')\n",
        "plt.title('Validation Curve')\n",
        "plt.xlabel('gamma')\n",
        "plt.ylabel('score')\n",
        "plt.ylim(0, 1)\n",
        "plt.legend(loc='best');"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe8AAAFrCAYAAAD4qAEDAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<Figure size 576x396 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6-HIWxRAdAwJ",
        "colab_type": "text"
      },
      "source": [
        "This is a pretty iconic looking validation curve. The major common features are all there. The training score starts low for low values of the hyperparameter ($\\gamma$ in this case for SVR). It then monotonically increases across the whole range. In other words, ever more complicated models do a better job of fitting the training data. Where things get interesting is when you look at the validation score. It too starts out low for low values of $\\gamma$, but it is also low at very high $\\gamma$. In the middle somewhere we find a peak. This tells us that a complicated model can do an excellent job with data it is trained on, but does terrible when that learned model is applied to new data. In more traditional terms, you can think of the gap between the training and validation score at high $\\gamma$ as overfitting and the terrible scores at low $\\gamma$ as underfitting. That peak in the middle is our best fit. So lets now programmatically grab that peak value of $\\gamma$. Note that for each of the ```n_splits``` in our ```shuffle_split```, we have a different set of scores. That's why in the plot and below, we're taking a median across axis 1. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4fQLj4iudAwK",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 123
        },
        "outputId": "5aa10754-f162-4e9c-bbaf-0c1260a1e8fe"
      },
      "source": [
        "scores = np.median(val_score, axis=1)\n",
        "best_fit_score = np.max(scores)\n",
        "best_fit_gamma = gamma[np.argmax(scores)]\n",
        "print('Scores: {}'.format(str(scores)))\n",
        "print('Best score: {}'.format(str(best_fit_score)))\n",
        "print('Best fit gamma: {}'.format(str(best_fit_gamma)))"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Scores: [ 0.02917288  0.02105645  0.02169628  0.0852256   0.23053576  0.33218942\n",
            "  0.34236068  0.36317277  0.37585797  0.39744256  0.46183734  0.45968287\n",
            "  0.44282197  0.42727723  0.44990313  0.47643549  0.43441923  0.26152219\n",
            "  0.01226673 -0.93569731]\n",
            "Best score: 0.47643549274929575\n",
            "Best fit gamma: 8.858667904100833e-07\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "P6xF8bHAdAwM",
        "colab_type": "text"
      },
      "source": [
        "## Fitting the data"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "s_jBwcZvdAwN",
        "colab_type": "text"
      },
      "source": [
        "Now that we've identified which gamma results in the best fit, we can actually run that fit on the data and include uncertainties as well. Unfortunately, validation curve doesn't let us pass uncertainties in yet, but there is [an active issue on the GitHub repository to do so](https://github.com/scikit-learn/scikit-learn/issues/10252). The API expects us to provide sample weight instead of uncertainty, so we just do an inverse. Then we run the SVR fit with our best gamma. Finally, we _predict_. This is the common parlance in machine learning but in this context what we're really getting back is the y values of the fit. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "j2YMgObLdAwO",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "sample_weight = 1 / uncertainty\n",
        "model = SVR(kernel='rbf', C=1e3, gamma=best_fit_gamma).fit(X, y, sample_weight)\n",
        "y_fit = model.predict(X)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "iv4v1hSbdAwQ",
        "colab_type": "text"
      },
      "source": [
        "Finally we can produce a nice plot showing our new machine-learning-identified best fit over the original data."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AoeE-rE5dAwR",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "outputId": "8102048d-3682-4954-b153-0ecf501ca749"
      },
      "source": [
        "plt.errorbar(X.ravel(), y, yerr=uncertainty, color='black', fmt='o', label='Input light curve')\n",
        "plt.plot(X.ravel(), y_fit, linewidth=6, label='Fit')\n",
        "plt.title(\"t$_0$ = \" + datetimeindex_to_human(light_curve_df.index)[0])\n",
        "plt.xlabel('time [seconds since start]')\n",
        "plt.ylabel('irradiance [%]')\n",
        "plt.legend(loc='best');"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe8AAAFpCAYAAAC1YKAIAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<Figure size 576x396 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "QTSLj8htdAwU",
        "colab_type": "text"
      },
      "source": [
        "## Recap\n",
        "In this example, we've used a familiar goal -- fitting a time series -- as a way to introduce some common machine learning concepts. In particular, we introduced data cleaning (e.g., ```Impute```), training vs validation/prediction data sets (e.g., ```shuffle_split```), and validation (e.g., ```validation_curve```). "
      ]
    }
  ]
}