{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "name": "Can_changing_point.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "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": "3.6.10"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "kqXl71t9suiG"
      },
      "source": [
        "# Estimating the Date of COVID-19 Changes\n",
        "\n",
        "https://nbviewer.jupyter.org/github/jramkiss/jramkiss.github.io/blob/master/_posts/notebooks/covid19-changes.ipynb "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gFnvD8OysuiI",
        "outputId": "74b6f2c4-00a6-4c91-fed0-a66c8d5d3d94"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "\n",
        "import seaborn as sns; sns.set()\n",
        "import matplotlib.pyplot as plt\n",
        "import matplotlib.dates as mdates\n",
        "\n",
        "\n",
        "from sklearn.linear_model import LinearRegression\n",
        "\n",
        "from scipy import stats\n",
        "import statsmodels.api as sm\n",
        "import pylab\n",
        "\n",
        "# from google.colab import files\n",
        "# from io import StringIO\n",
        "# uploaded = files.upload()\n",
        "\n",
        "url = 'https://raw.githubusercontent.com/assemzh/ProbProg-COVID-19/master/full_grouped.csv'\n",
        "data = pd.read_csv(url)\n",
        "\n",
        "data.Date = pd.to_datetime(data.Date)\n",
        "\n",
        "# for fancy python printing\n",
        "from IPython.display import Markdown, display\n",
        "def printmd(string):\n",
        "    display(Markdown(string))\n",
        "    \n",
        "import warnings\n",
        "warnings.filterwarnings('ignore')\n",
        "\n",
        "import matplotlib as mpl\n",
        "mpl.rcParams['figure.dpi'] = 250"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/statsmodels/tools/_testing.py:19: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.\n",
            "  import pandas.util.testing as tm\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hzvPpvVvphTD"
      },
      "source": [
        "## Create country\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "koX5yGHrsuib"
      },
      "source": [
        "# function to make the time series of confirmed and daily confirmed cases for a specific country\n",
        "def create_country (country, end_date, state = False) : \n",
        "    if state :\n",
        "        df = data.loc[data[\"Province/State\"] == country, [\"Province/State\", \"Date\", \"Confirmed\", \"Deaths\", \"Recovered\"]]\n",
        "    else : \n",
        "        df = data.loc[data[\"Country/Region\"] == country, [\"Country/Region\", \"Date\", \"Confirmed\", \"Deaths\", \"Recovered\"]]\n",
        "    df.columns = [\"country\", \"date\", \"confirmed\", \"deaths\", \"recovered\"]\n",
        "\n",
        "     # group by country and date, sum(confirmed, deaths, recovered). do this because countries have multiple cities \n",
        "    df = df[df.date >= '2020-03-01']\n",
        "    df = df.groupby(['country','date'])['confirmed', 'deaths', 'recovered'].sum().reset_index()\n",
        "\n",
        "    # convert date string to datetime\n",
        "    std_dateparser = lambda x: str(x)[5:10]\n",
        "    df.date = pd.to_datetime(df.date)\n",
        "    df['date_only'] = df.date.apply(std_dateparser)\n",
        "    df = df.sort_values(by = \"date\")\n",
        "    df = df[df.date <= end_date]\n",
        "\n",
        "\n",
        "    # make new confirmed cases every day:\n",
        "    cases_shifted = np.array([0] + list(df.confirmed[:-1]))\n",
        "    daily_confirmed = np.array(df.confirmed) - cases_shifted\n",
        "    df[\"daily_confirmed\"] = daily_confirmed \n",
        "\n",
        "    fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(7, 6))\n",
        "    ax = [ax]\n",
        "    sns.lineplot(x = df.date, \n",
        "                 y = df.daily_confirmed, \n",
        "                 ax = ax[0])\n",
        "\n",
        "    ax[0].set(ylabel='Daily Confirmed Cases')\n",
        "\n",
        "    ax[0].xaxis.get_label().set_fontsize(16)\n",
        "    ax[0].yaxis.get_label().set_fontsize(16)\n",
        "    ax[0].title.set_fontsize(20)\n",
        "    ax[0].tick_params(labelsize=16)\n",
        "    myFmt = mdates.DateFormatter('%b %-d')\n",
        "    ax[0].xaxis.set_major_formatter(myFmt)\n",
        "\n",
        "    ax[0].set(ylabel='Daily Confirmed Cases', xlabel='');\n",
        "    ax[0].legend(loc = \"bottom right\", fontsize=12.8)\n",
        "    sns.set_style(\"ticks\")\n",
        "    ax[0].xaxis.set_major_locator(mdates.MonthLocator(interval=1))   #to get a tick every month\n",
        "    plt.tight_layout()\n",
        "    sns.despine()\n",
        "    plt.savefig('/content/sample_data/can_daily.pdf')\n",
        "    print(df.tail())\n",
        "    return df\n",
        "\n",
        "\n",
        "def summary(samples):\n",
        "    site_stats = {}\n",
        "    for k, v in samples.items():\n",
        "        site_stats[k] = {\n",
        "            \"mean\": torch.mean(v, 0),\n",
        "            \"std\": torch.std(v, 0),\n",
        "            \"5%\": v.kthvalue(int(len(v) * 0.05), dim=0)[0],\n",
        "            \"95%\": v.kthvalue(int(len(v) * 0.95), dim=0)[0],\n",
        "        }\n",
        "    return site_stats"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 560
        },
        "id": "w_A0fd4Zsuiw",
        "outputId": "057e9433-0a28-4696-fa87-00f3a8d0f547"
      },
      "source": [
        "cad = create_country(\"Canada\", end_date = \"2020-05-31\")"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "No handles with labels found to put in legend.\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "   country       date  confirmed  deaths  recovered date_only  daily_confirmed\n",
            "87  Canada 2020-05-27      88975    6875          0     05-27              899\n",
            "88  Canada 2020-05-28      89962    6981          0     05-28              987\n",
            "89  Canada 2020-05-29      90895    7062          0     05-29              933\n",
            "90  Canada 2020-05-30      91667    7158          0     05-30              772\n",
            "91  Canada 2020-05-31      92465    7373          0     05-31              798\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 504x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UR0BM7TysujG"
      },
      "source": [
        "cad_start = \"2020-04-01\" # 13 confirmed cases\n",
        "cad = cad[cad.date >= cad_start].reset_index(drop = True)\n",
        "cad[\"days_since_start\"] = np.arange(cad.shape[0]) + 1"
      ],
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OaTHo6I2sujp",
        "outputId": "831e792a-7114-43d0-900b-80210ef7d551"
      },
      "source": [
        "cad.shape\n",
        "cad_tmp = cad[cad.date < \"2020-05-31\"]\n",
        "cad_tmp.shape"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(60, 8)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "loi3CtjSsuoz"
      },
      "source": [
        "## Data for Regression"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Os_M7r4Tsuo4"
      },
      "source": [
        "# variable for data to easily swap it out:\n",
        "country_ = \"Canada\"\n",
        "reg_data = cad_tmp.copy()"
      ],
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "3RjDFEbA91X-",
        "outputId": "b9d5593b-0a33-48d0-b986-eb9c378f6c5d"
      },
      "source": [
        "reg_data.head()"
      ],
      "execution_count": 8,
      "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>country</th>\n",
              "      <th>date</th>\n",
              "      <th>confirmed</th>\n",
              "      <th>deaths</th>\n",
              "      <th>recovered</th>\n",
              "      <th>date_only</th>\n",
              "      <th>daily_confirmed</th>\n",
              "      <th>days_since_start</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Canada</td>\n",
              "      <td>2020-04-01</td>\n",
              "      <td>9547</td>\n",
              "      <td>108</td>\n",
              "      <td>0</td>\n",
              "      <td>04-01</td>\n",
              "      <td>1033</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Canada</td>\n",
              "      <td>2020-04-02</td>\n",
              "      <td>11271</td>\n",
              "      <td>138</td>\n",
              "      <td>0</td>\n",
              "      <td>04-02</td>\n",
              "      <td>1724</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Canada</td>\n",
              "      <td>2020-04-03</td>\n",
              "      <td>12424</td>\n",
              "      <td>178</td>\n",
              "      <td>0</td>\n",
              "      <td>04-03</td>\n",
              "      <td>1153</td>\n",
              "      <td>3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Canada</td>\n",
              "      <td>2020-04-04</td>\n",
              "      <td>12965</td>\n",
              "      <td>217</td>\n",
              "      <td>0</td>\n",
              "      <td>04-04</td>\n",
              "      <td>541</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Canada</td>\n",
              "      <td>2020-04-05</td>\n",
              "      <td>15743</td>\n",
              "      <td>258</td>\n",
              "      <td>0</td>\n",
              "      <td>04-05</td>\n",
              "      <td>2778</td>\n",
              "      <td>5</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "  country       date  confirmed  ...  date_only  daily_confirmed days_since_start\n",
              "0  Canada 2020-04-01       9547  ...      04-01             1033                1\n",
              "1  Canada 2020-04-02      11271  ...      04-02             1724                2\n",
              "2  Canada 2020-04-03      12424  ...      04-03             1153                3\n",
              "3  Canada 2020-04-04      12965  ...      04-04              541                4\n",
              "4  Canada 2020-04-05      15743  ...      04-05             2778                5\n",
              "\n",
              "[5 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JkO0Z8M0supC"
      },
      "source": [
        "## Change Point Estimation in Pyro"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aIUed4Ny3-oq"
      },
      "source": [
        "!pip install pyro-ppl\n",
        "!pip install numpyro"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3ZS9fTPxsupD"
      },
      "source": [
        "import torch\n",
        "\n",
        "import pyro\n",
        "import pyro.distributions as dist\n",
        "from torch import nn\n",
        "from pyro.nn import PyroModule, PyroSample\n",
        "\n",
        "from pyro.infer import MCMC, NUTS, HMC\n",
        "from pyro.infer.autoguide import AutoGuide, AutoDiagonalNormal\n",
        "\n",
        "from pyro.infer import SVI, Trace_ELBO\n",
        "from pyro.infer import Predictive"
      ],
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9gPrEaEJsupP"
      },
      "source": [
        "# we should be able to have an empirical estimate for the mean of the prior for the 2nd regression bias term\n",
        "# this will be something like b = log(max(daily_confirmed))\n",
        "\n",
        "# might be able to have 1 regression model but change the data so that we have new terms for (tau < t) \n",
        "# like an interaction term\n",
        "\n",
        "class COVID_change(PyroModule):\n",
        "    def __init__(self, in_features, out_features, b1_mu, b2_mu):\n",
        "        super().__init__()\n",
        "        self.linear1 = PyroModule[nn.Linear](in_features, out_features, bias = False)\n",
        "        self.linear1.weight = PyroSample(dist.Normal(0.5, 0.25).expand([1, 1]).to_event(1))\n",
        "        self.linear1.bias = PyroSample(dist.Normal(b1_mu, 1.))\n",
        "        \n",
        "        # could possibly have stronger priors for the 2nd regression line, because we wont have as much data\n",
        "        self.linear2 = PyroModule[nn.Linear](in_features, out_features, bias = False)\n",
        "        self.linear2.weight = PyroSample(dist.Normal(0., 0.25).expand([1, 1])) #.to_event(1))\n",
        "        self.linear2.bias = PyroSample(dist.Normal(b2_mu, b2_mu/4))\n",
        "\n",
        "    def forward(self, x, y=None):\n",
        "        tau = pyro.sample(\"tau\", dist.Beta(4, 3))\n",
        "        sigma = pyro.sample(\"sigma\", dist.Uniform(0., 3.))\n",
        "        # fit lm's to data based on tau\n",
        "        sep = int(np.ceil(tau.detach().numpy() * len(x)))\n",
        "        mean1 = self.linear1(x[:sep]).squeeze(-1)\n",
        "        mean2 = self.linear2(x[sep:]).squeeze(-1)\n",
        "        mean = torch.cat((mean1, mean2))\n",
        "        obs = pyro.sample(\"obs\", dist.StudentT(2, mean, sigma), obs=y)\n",
        "        return mean"
      ],
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "if0toOMysupU",
        "outputId": "5abea1ce-9b6f-47e5-d0fb-5e992fdff6b8"
      },
      "source": [
        "tensor_data = torch.tensor(reg_data[[\"confirmed\", \"days_since_start\", \"daily_confirmed\"]].values, dtype=torch.float)\n",
        "x_data = tensor_data[:, 1].unsqueeze_(1)\n",
        "y_data = np.log(tensor_data[:, 0])\n",
        "y_data_daily = np.log(tensor_data[:, 2])\n",
        "# prior hyper params\n",
        "# take log of the average of the 1st quartile to get the prior mean for the bias of the 2nd regression line\n",
        "q1 = np.quantile(y_data, q = 0.25)\n",
        "bias_1_mean = np.mean(y_data.numpy()[y_data <= q1])\n",
        "print(\"Prior mean for Bias 1: \", bias_1_mean)\n",
        "\n",
        "# take log of the average of the 4th quartile to get the prior mean for the bias of the 2nd regression line\n",
        "q4 = np.quantile(y_data, q = 0.75)\n",
        "bias_2_mean = np.mean(y_data.numpy()[y_data >= q4])\n",
        "print(\"Prior mean for Bias 2: \", bias_2_mean)"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Prior mean for Bias 1:  9.807537\n",
            "Prior mean for Bias 2:  11.346226\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nrm8RrFasupc"
      },
      "source": [
        "## Approximate Inference with Stochastic Variational Inference"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "x0nDLSPisupm"
      },
      "source": [
        "# HMC with NUTS"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "X1rSXXtKsupm",
        "outputId": "20b6692c-8c0e-4960-dbe8-70b4900ef24f"
      },
      "source": [
        "model = COVID_change(1, 1, \n",
        "                     b1_mu = bias_1_mean,\n",
        "                     b2_mu = bias_2_mean)\n",
        "# need more than 400 samples/chain if we want to use a flat prior on b_2 and w_2\n",
        "num_samples = 400 \n",
        "# mcmc \n",
        "nuts_kernel = NUTS(model)\n",
        "mcmc = MCMC(nuts_kernel, \n",
        "            num_samples=num_samples,\n",
        "            warmup_steps = 200, \n",
        "            num_chains = 1)\n",
        "mcmc.run(x_data, y_data)\n",
        "samples = mcmc.get_samples()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Warmup:  14%|█▎        | 81/600 [03:04,  2.77s/it, step size=4.74e-04, acc. prob=0.768]"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "J301TyxW1KCs"
      },
      "source": [
        "# Save the model:\n",
        "import dill\n",
        "# with open('canada.pkl', 'wb') as f:\n",
        "# \tdill.dump(mcmc, f)\n",
        "with open('canada.pkl', 'rb') as f:\n",
        "\tmcmc = dill.load(f)\n",
        " \n",
        "samples = mcmc.get_samples()"
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7Z968a5xsupv",
        "outputId": "28f7c2c1-c274-40ff-f1fe-6a014a18e242"
      },
      "source": [
        "# extract individual posteriors\n",
        "weight_1_post = samples[\"linear1.weight\"].detach().numpy()\n",
        "weight_2_post = samples[\"linear2.weight\"].detach().numpy()\n",
        "bias_1_post = samples[\"linear1.bias\"].detach().numpy()\n",
        "bias_2_post = samples[\"linear2.bias\"].detach().numpy()\n",
        "tau_post = samples[\"tau\"].detach().numpy()\n",
        "sigma_post = samples[\"sigma\"].detach().numpy()\n",
        "\n",
        "# build likelihood distribution:\n",
        "tau_days = list(map(int, np.ceil(tau_post * len(x_data))))\n",
        "mean_ = torch.zeros(len(tau_days), len(x_data))\n",
        "obs_ = torch.zeros(len(tau_days), len(x_data))\n",
        "for i in range(len(tau_days)) : \n",
        "    mean_[i, :] = torch.cat((x_data[:tau_days[i]] * weight_1_post[i] + bias_1_post[i],\n",
        "                          x_data[tau_days[i]:] * weight_2_post[i] + bias_2_post[i])).reshape(len(x_data))\n",
        "    obs_[i, :] = dist.Normal(mean_[i, :], sigma_post[i]).sample()\n",
        "samples[\"_RETURN\"] = mean_\n",
        "samples[\"obs\"] = obs_\n",
        "pred_summary = summary(samples)\n",
        "mu = pred_summary[\"_RETURN\"] # mean\n",
        "y = pred_summary[\"obs\"] # samples from likelihood: mu + sigma\n",
        "y_shift = np.exp(y[\"mean\"]) - np.exp(torch.cat((y[\"mean\"][0:1], y[\"mean\"][:-1])))\n",
        "print(y_shift)\n",
        "predictions = pd.DataFrame({\n",
        "    \"days_since_start\": x_data[:, 0],\n",
        "    \"mu_mean\": mu[\"mean\"],    # mean of likelihood\n",
        "    \"mu_perc_5\": mu[\"5%\"],\n",
        "    \"mu_perc_95\": mu[\"95%\"],\n",
        "    \"y_mean\": y[\"mean\"],      # mean of likelihood + noise\n",
        "    \"y_perc_5\": y[\"5%\"],\n",
        "    \"y_perc_95\": y[\"95%\"],\n",
        "    \"true_confirmed\": y_data,\n",
        "    \"true_daily_confirmed\": y_data_daily,\n",
        "    \"y_daily_mean\": y_shift\n",
        "})\n",
        "\n",
        "w1_ = pred_summary[\"linear1.weight\"]\n",
        "w2_ = pred_summary[\"linear2.weight\"]\n",
        "\n",
        "b1_ = pred_summary[\"linear1.bias\"]\n",
        "b2_ = pred_summary[\"linear2.bias\"]\n",
        "\n",
        "tau_ = pred_summary[\"tau\"]\n",
        "sigma_ = pred_summary[\"sigma\"]\n",
        "\n",
        "ind = int(np.ceil(tau_[\"mean\"] * len(x_data)))"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "tensor([   0.0000,  727.1113,  776.8818,  859.6709,  832.1074,  945.3135,\n",
            "        1014.7129,  996.6602, 1131.5000, 1086.5820, 1244.2402, 1195.3945,\n",
            "        1430.0781, 1417.9062, 1539.4922, 1552.6270, 1763.2773, 1789.0117,\n",
            "        1848.0234, 1886.7617, 2246.4258, 2244.3242, 2354.2656, 2558.8750,\n",
            "        2518.5430, 2823.3281, 2865.2891, 1941.1133,  885.2461,  911.7383,\n",
            "         964.2578, 1015.9414, 1019.3633,  851.6523,  960.4297, 1332.5898,\n",
            "         818.9727, 1011.7500, 1237.0469, 1173.5938, 1120.4219, 1043.4375,\n",
            "        1428.8125,  939.1172, 1239.2109, 1244.3438, 1315.2188, 1143.2344,\n",
            "        1224.4062, 1627.6016, 1157.5469, 1258.6172, 1339.1484, 1467.2500,\n",
            "        1332.7891, 1694.3828, 1578.7344, 1356.3359, 1407.2188, 1640.9141])\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "KegzMbLOsuqC"
      },
      "source": [
        "## Model Diagnostics\n",
        "\n",
        "- Residual plots: Should these be samples from the likelihood compared with the actual data? Or just the mean of the likelihood?\n",
        "- $\\hat{R}$: The factor that the scale of the current distribution will be reduced by if we were to run the simulations forever. As n tends to $\\inf$, $\\hat{R}$ tends to 1. So we want values close to 1.\n",
        "- Mixing and Stationarity: I sampled 4 chains. Do I then take these chains, split them in half and plot them. If they converge to the same stationary distribution, does that mean the MCMC converged? What do I do with more sampled chains?"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QUh6fBjtsuqV",
        "outputId": "9c2553d5-50d3-4bc9-caee-5ecc1d26b8c9"
      },
      "source": [
        "mcmc.summary()\n",
        "diag = mcmc.diagnostics()"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "                         mean       std    median      5.0%     95.0%     n_eff     r_hat\n",
            "                tau      0.44      0.02      0.44      0.40      0.47     92.91      1.02\n",
            "              sigma      0.03      0.00      0.03      0.02      0.03     22.72      1.00\n",
            "linear1.weight[0,0]      0.06      0.00      0.06      0.05      0.06     32.69      1.00\n",
            "       linear1.bias      9.42      0.02      9.42      9.38      9.46     33.20      1.00\n",
            "linear2.weight[0,0]      0.02      0.00      0.02      0.02      0.02    199.67      1.01\n",
            "       linear2.bias     10.49      0.04     10.49     10.42     10.55    193.03      1.00\n",
            "\n",
            "Number of divergences: 0\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LJ2a6Epnsuqf"
      },
      "source": [
        "## Posterior Plots"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 331
        },
        "id": "bPpET7b6suqg",
        "outputId": "0e13a02c-c562-4974-cc43-e2ed8e2d5f19"
      },
      "source": [
        "print(ind)\n",
        "print(reg_data.date[ind])\n",
        "\n",
        "sns.distplot(weight_1_post, \n",
        "             kde_kws = {\"label\": \"Weight posterior before CP\"}, \n",
        "             color = \"red\",\n",
        "             norm_hist = True,\n",
        "             kde = True)\n",
        "plt.axvline(x = w1_[\"mean\"], linestyle = '--',label = \"Mean weight before CP\" ,\n",
        "              color = \"red\")\n",
        "\n",
        "sns.distplot(weight_2_post, \n",
        "             kde_kws = {\"label\": \"Weight posterior after CP\"}, \n",
        "             color = \"teal\",\n",
        "             norm_hist = True,\n",
        "             kde = True)\n",
        "plt.axvline(x = w2_[\"mean\"], linestyle = '--',label = \"Mean weight after CP\" ,\n",
        "              color = \"teal\")\n",
        "\n",
        "legend = plt.legend(loc='upper right')\n",
        "legend.get_frame().set_alpha(1)\n",
        "sns.set_style(\"ticks\")\n",
        "plt.tight_layout()\n",
        "sns.despine()\n",
        "plt.savefig('/content/sample_data/canada_weights.pdf')\n"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "27\n",
            "2020-04-28 00:00:00\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MRsFkRGT2HmN",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "25c833e4-c9d0-4006-c9b9-d659be0568a6"
      },
      "source": [
        "print(w1_[\"mean\"])\n",
        "print(w2_[\"mean\"])"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "tensor([[0.0551]])\n",
            "tensor([[0.0163]])\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1vMeIvtLYIND",
        "outputId": "b44a656d-5993-4017-c7ec-03bb3b68cb6c"
      },
      "source": [
        "1 - w2_[\"mean\"]/w1_[\"mean\"]"
      ],
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[0.7040]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 395
        },
        "id": "oksH-_TWWF4l",
        "outputId": "8364aef6-dfdc-4685-cbfc-10a92b542e3a"
      },
      "source": [
        "start_date_ = str(reg_data.date[0]).split(' ')[0]\n",
        "change_date_ = str(reg_data.date[ind]).split(' ')[0]\n",
        "print(\"Date of change for {}: {}\".format(country_, change_date_))\n",
        "import seaborn as sns\n",
        "\n",
        "# plot data:\n",
        "fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(7, 5))\n",
        "ax = [ax]\n",
        "# log regression model\n",
        "ax[0].scatter(y = np.exp(y_data[:ind]), x = x_data[:ind], s = 15);\n",
        "ax[0].scatter(y = np.exp(y_data[ind:]), x = x_data[ind:], s = 15, color = \"red\");\n",
        "\n",
        "ax[0].plot(predictions[\"days_since_start\"],\n",
        "           np.exp(predictions[\"y_mean\"]), \n",
        "           color = \"green\",\n",
        "           label = \"Fitted line by MCMC-NUTS model\") \n",
        "\n",
        "ax[0].axvline(ind, \n",
        "              linestyle = '--', linewidth = 1.5,\n",
        "              label = \"Date of Change: Apr 28, 2020\",\n",
        "              color = \"black\")\n",
        "\n",
        "ax[0].fill_between(predictions[\"days_since_start\"], \n",
        "                   np.exp(predictions[\"y_perc_5\"]), \n",
        "                   np.exp(predictions[\"y_perc_95\"]), \n",
        "                   alpha = 0.25,\n",
        "                   label = \"90% CI of predictions\",\n",
        "                   color = \"teal\");\n",
        "ax[0].fill_betweenx([0, 1], \n",
        "                    tau_[\"5%\"] * len(x_data), \n",
        "                    tau_[\"95%\"] * len(x_data), \n",
        "                    alpha = 0.25,\n",
        "                    label = \"90% CI of changing point\",\n",
        "                    color = \"lightcoral\",\n",
        "                    transform=ax[0].get_xaxis_transform());\n",
        "ax[0].set(ylabel = \"Total Cases\",)\n",
        "\n",
        "ax[0].legend(loc = \"lower right\", fontsize=12.8)\n",
        "ax[0].set_ylim([1500,150000])\n",
        "ax[0].xaxis.get_label().set_fontsize(16)\n",
        "ax[0].yaxis.get_label().set_fontsize(16)\n",
        "ax[0].title.set_fontsize(20)\n",
        "ax[0].tick_params(labelsize=16)\n",
        "\n",
        "plt.xticks(ticks=[0,14,27,39,54], labels=[\"Apr 1\", \"Apr 15\",\n",
        "                                             \"Apr 28\",\n",
        "                                             \"May 10\",\n",
        "                                             \"May 25\"], fontsize=15)\n",
        "ax[0].set_yscale('log')\n",
        "plt.setp(ax[0].get_xticklabels(), rotation=0, horizontalalignment='center')\n",
        "print(reg_data.columns)\n",
        "myFmt = mdates.DateFormatter('%m-%d')\n",
        "sns.set_style(\"ticks\")\n",
        "sns.despine()\n",
        "plt.savefig('/content/sample_data/canada_cp.pdf')\n"
      ],
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Date of change for Canada: 2020-04-28\n",
            "Index(['country', 'date', 'confirmed', 'deaths', 'recovered', 'date_only',\n",
            "       'daily_confirmed', 'days_since_start'],\n",
            "      dtype='object')\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 504x360 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 470
        },
        "id": "HrWADTLYsurS",
        "outputId": "36e7cafb-b42a-4c1b-d60a-28136eb43b1d"
      },
      "source": [
        "fig, ax = plt.subplots(1,3, figsize=(15, 6))\n",
        "\n",
        "#plt.figure(figsize=(11, 5))\n",
        "sns.lineplot(x=\"date\", \n",
        "             y=\"confirmed\", \n",
        "             data= reg_data,\n",
        "             ax = ax[0]\n",
        "            ).set_title(\"Confirmed COVID-19 Cases in %s\" % country_)\n",
        "ax[0].axvline(reg_data.date[ind], color=\"red\", linestyle=\"--\")\n",
        "ax[1].scatter(y = reg_data.confirmed[:ind], x = x_data[:ind], s = 15);\n",
        "ax[1].scatter(y = reg_data.confirmed[ind:], x = x_data[ind:], s = 15, color = \"red\");\n",
        "\n",
        "ax[1].plot(predictions[\"days_since_start\"],\n",
        "           np.exp(predictions[\"y_mean\"]), \n",
        "           color = \"green\",\n",
        "           label = \"Mean\") \n",
        "ax[1].axvline(ind, linestyle = '--', \n",
        "              linewidth = 1,\n",
        "              label = \"Day of Change\")\n",
        "ax[1].legend(loc = \"upper left\")\n",
        "ax[1].set(ylabel = \"Confirmed Cases\", \n",
        "          xlabel = \"Days since %s\" % start_date_,\n",
        "          title = \"Confirmed Cases: %s\" % country_);\n",
        "\n",
        "\n",
        "ax[2].scatter(y = reg_data.daily_confirmed[:ind], x = x_data[:ind], s = 15);\n",
        "ax[2].scatter(y = reg_data.daily_confirmed[ind:], x = x_data[ind:], s = 15, color = \"red\");\n",
        "\n",
        "ax[2].plot(predictions[\"days_since_start\"],\n",
        "           predictions[\"y_daily_mean\"], \n",
        "           color = \"green\",\n",
        "           label = \"Mean\") \n",
        "\n",
        "ax[2].axvline(ind, linestyle = '--', \n",
        "              linewidth = 1,\n",
        "              label = \"Day of Change\")\n",
        "ax[2].legend(loc = \"upper left\")\n",
        "ax[2].set(ylabel = \"Daily Confirmed Cases\", \n",
        "          xlabel = \"Days since %s\" % start_date_,\n",
        "          title = \"Daily Confirmed Cases: %s\" % country_);\n",
        "printmd(\"**Date of change for {}: {}**\".format(country_, change_date_));\n",
        "\n",
        "import matplotlib.dates as mdates\n",
        "myFmt = mdates.DateFormatter('%m-%d')\n",
        "ax[0].xaxis.set_major_formatter(myFmt)\n",
        "\n",
        "# ax[0].set_xticklabels(reg_data.date, rotation = 45,  fontsize=\"10\", va=\"center\")\n",
        "plt.setp(ax[0].get_xticklabels(), rotation=30, horizontalalignment='right')\n",
        "ax[0].set(ylabel='Confirmed Cases', xlabel='Date');\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.savefig('/content/sample_data/can_mean.pdf')"
      ],
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/markdown": "**Date of change for Canada: 2020-04-28**",
            "text/plain": [
              "<IPython.core.display.Markdown object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1080x432 with 3 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "P-RF4xjKoz9k"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}