gg230707_delays.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyP87ZwWA9DigxjKwtvftdwC",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/pachterlab/GVP_2023/blob/main/gg230707_delays.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "st5HNcGvRb9l"
      },
      "outputs": [],
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import scipy\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "tau=1 #residence time\n",
        "gamma = 2\n",
        "T = 3\n",
        "nT = 100\n",
        "t = np.linspace(0,T,nT)\n",
        "b = 3\n",
        "k = 0.6"
      ],
      "metadata": {
        "id": "BUDMZVObRhuK"
      },
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "nC = 5000\n",
        "X = np.zeros((nT,nC,2))\n",
        "for c_ in range(nC):\n",
        "    arrivals_x1_num = np.random.poisson(T*k)\n",
        "    arrival_times_x1 =  np.random.uniform(0,T,arrivals_x1_num)\n",
        "    arrival_time_storage_1 = []\n",
        "    exit_time_storage_1 = []\n",
        "    for arr in range(arrivals_x1_num):\n",
        "        bs = np.random.geometric(1/(1+b))-1\n",
        "        if bs>0:\n",
        "            arrival_time_storage_1 += [arrival_times_x1[arr]]*bs\n",
        "            exit_time_storage_1 += [arrival_times_x1[arr] + tau]*bs\n",
        "    arrival_time_storage_1 = np.asarray(arrival_time_storage_1)\n",
        "    exit_time_storage_1 = np.asarray(exit_time_storage_1)\n",
        "    arrival_time_storage_2 = np.copy(exit_time_storage_1)\n",
        "\n",
        "    mat_lifetimes = np.random.exponential(1/gamma,arrival_time_storage_2.shape)\n",
        "    exit_time_storage_2 = arrival_time_storage_2 + mat_lifetimes\n",
        "\n",
        "    for tind,t_ in enumerate(t):\n",
        "        extant_at_t_1 = (((exit_time_storage_1)>t_)&(arrival_time_storage_1<=t_)).sum()\n",
        "        extant_at_t_2 = (((exit_time_storage_2)>t_)&(arrival_time_storage_2<=t_)).sum()\n",
        "        X[tind,c_,0] = extant_at_t_1\n",
        "        X[tind,c_,1] = extant_at_t_2\n"
      ],
      "metadata": {
        "id": "E2TVdecuRmX4"
      },
      "execution_count": 32,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plt.plot(t,X.mean(1))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 465
        },
        "id": "Y7R-BfnmT15_",
        "outputId": "24d0f505-24a6-4b72-9d5d-44188af2340e"
      },
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7fed5e78cdf0>,\n",
              " <matplotlib.lines.Line2D at 0x7fed5e78ce50>]"
            ]
          },
          "metadata": {},
          "execution_count": 33
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jFbfIKY8T19W",
        "outputId": "45db7dbe-feec-42ac-aa7b-7858f495eba9"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(100, 5000, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 36
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_ = X[-1,:,:]"
      ],
      "metadata": {
        "id": "0eqTmrgVTfWL"
      },
      "execution_count": 37,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_.mean(0)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "i940485dR-cm",
        "outputId": "9ef883a2-f2b3-4f75-c439-5cedde0e3178"
      },
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1.8414, 0.8762])"
            ]
          },
          "metadata": {},
          "execution_count": 39
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_.var(0)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-565dWWlTibI",
        "outputId": "e19e063c-8dbd-4df3-c18a-aa6669f2ffcc"
      },
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([13.05664604,  3.65487356])"
            ]
          },
          "metadata": {},
          "execution_count": 41
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "np.corrcoef(X_.T)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8LYtWJC7UKKP",
        "outputId": "515b2a52-a20d-41d9-9f3d-e5cfede00519"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[ 1.        , -0.00232118],\n",
              "       [-0.00232118,  1.        ]])"
            ]
          },
          "metadata": {},
          "execution_count": 43
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "4CKRvPw9UNy7"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}