{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# Mammalian3"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a3f514a3-772c-4a14-afdf-5a8376851ff4",
   "metadata": {},
   "source": [
    "## Index\n",
    "1. [Instantiate model class](#Instantiate-model-class)\n",
    "2. [Define clock metadata](#Define-clock-metadata)\n",
    "3. [Download clock dependencies](#Download-clock-dependencies)\n",
    "5. [Load features](#Load-features)\n",
    "6. [Load weights into base model](#Load-weights-into-base-model)\n",
    "7. [Load reference values](#Load-reference-values)\n",
    "8. [Load preprocess and postprocess objects](#Load-preprocess-and-postprocess-objects)\n",
    "10. [Check all clock parameters](#Check-all-clock-parameters)\n",
    "10. [Basic test](#Basic-test)\n",
    "11. [Save torch model](#Save-torch-model)\n",
    "12. [Clear directory](#Clear-directory)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d95fafdc-643a-40ea-a689-200bd132e90c",
   "metadata": {},
   "source": [
    "Let's first import some packages:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4adfb4de-cd79-4913-a1af-9e23e9e236c9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:56:09.877750Z",
     "iopub.status.busy": "2025-04-07T17:56:09.877357Z",
     "iopub.status.idle": "2025-04-07T17:56:11.378033Z",
     "shell.execute_reply": "2025-04-07T17:56:11.377721Z"
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import inspect\n",
    "import shutil\n",
    "import json\n",
    "import torch\n",
    "import pandas as pd\n",
    "import pyaging as pya\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "145082e5-ced4-47ae-88c0-cb69773e3c5a",
   "metadata": {},
   "source": [
    "## Instantiate model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "8aa77372-7ed3-4da7-abc9-d30372106139",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:56:11.379766Z",
     "iopub.status.busy": "2025-04-07T17:56:11.379544Z",
     "iopub.status.idle": "2025-04-07T17:56:11.387918Z",
     "shell.execute_reply": "2025-04-07T17:56:11.387611Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class Mammalian3(pyagingModel):\n",
      "    def __init__(self):\n",
      "        super().__init__()\n",
      "\n",
      "    def forward(self, x):\n",
      "        x_cpg = x[:, :-1707]  # number of species in lookup table\n",
      "        x_species = x[:, -1707:]  # number of species in lookup table\n",
      "        x = self.base_model(x_cpg)\n",
      "        x = self.postprocess(x, x_species)\n",
      "        return x\n",
      "\n",
      "    def preprocess(self, x):\n",
      "        return x\n",
      "\n",
      "    def postprocess(self, x, x_species):\n",
      "        \"\"\"\n",
      "        Converts output of to units of years.\n",
      "        \"\"\"\n",
      "        indices = torch.argmax(x_species, dim=1)\n",
      "        anage_array = self.postprocess_dependencies[0]\n",
      "        anage_tensor = torch.tensor(anage_array, dtype=x.dtype, device=x.device)\n",
      "\n",
      "        gestation_time = anage_tensor[indices, 0].unsqueeze(1)\n",
      "        average_maturity_age = anage_tensor[indices, 1].unsqueeze(1)\n",
      "        m_hat = 5 * (gestation_time / average_maturity_age) ** (0.38)\n",
      "\n",
      "        # Create a mask for negative and non-negative values\n",
      "        mask_negative = x < 0\n",
      "        mask_non_negative = ~mask_negative\n",
      "\n",
      "        x_pos = x[mask_non_negative]\n",
      "        x_neg = x[mask_negative]\n",
      "\n",
      "        gestation_time_pos = gestation_time[mask_non_negative]\n",
      "        gestation_time_neg = gestation_time[mask_negative]\n",
      "\n",
      "        average_maturity_age_pos = average_maturity_age[mask_non_negative]\n",
      "        average_maturity_age_neg = average_maturity_age[mask_negative]\n",
      "\n",
      "        m_hat_pos = m_hat[mask_non_negative]\n",
      "        m_hat_neg = m_hat[mask_negative]\n",
      "\n",
      "        # Initialize the result tensor\n",
      "        age_tensor = torch.empty_like(x)\n",
      "\n",
      "        # Exponential transformation for negative values\n",
      "        age_tensor[mask_non_negative] = (\n",
      "            m_hat_pos * (average_maturity_age_pos + gestation_time_pos) * (x_pos + 1) - gestation_time_pos\n",
      "        )\n",
      "\n",
      "        # Linear transformation for non-negative values\n",
      "        age_tensor[mask_negative] = (\n",
      "            m_hat_neg * (average_maturity_age_neg + gestation_time_neg) * torch.exp(x_neg) - gestation_time_neg\n",
      "        )\n",
      "\n",
      "        return age_tensor\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.Mammalian3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:56:11.389147Z",
     "iopub.status.busy": "2025-04-07T17:56:11.389059Z",
     "iopub.status.idle": "2025-04-07T17:56:11.390801Z",
     "shell.execute_reply": "2025-04-07T17:56:11.390572Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.Mammalian3()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "51f8615e-01fa-4aa5-b196-3ee2b35d261c",
   "metadata": {},
   "source": [
    "## Define clock metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6601da9e-8adc-44ee-9308-75e3cd31b816",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:56:11.392144Z",
     "iopub.status.busy": "2025-04-07T17:56:11.392062Z",
     "iopub.status.idle": "2025-04-07T17:56:11.394011Z",
     "shell.execute_reply": "2025-04-07T17:56:11.393776Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"mammalian3\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: methylation\n",
    "model.metadata[\"species\"] = \"multiple species\"  # Paper: multi\n",
    "model.metadata[\"year\"] = 2023\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Lu, A. T., et al. \\\"Universal DNA methylation age across mammalian tissues.\\\" Nature Aging 3.9 (2023): 1144-1166.\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1038/s43587-023-00462-6\"\n",
    "model.metadata[\"notes\"] = \"Universal pan-mammalian clock 3 fits a log-linear age transformation based on gestation and sexual maturity and returns chronological age in years.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"multi-tissue\"]  # Paper: multi-tissue\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: The official inverse transformation returns DNAm chronological age in years.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: log-linear transformed chronological age\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: The official inverse transformation returns DNAm chronological age in years.\n",
    "model.metadata[\"model_type\"] = \"elastic net regression\"  # Paper: Elastic net\n",
    "model.metadata[\"platform\"] = [\"Horvath MammalMethylChip40\"]  # Paper: HorvathMammalMethylChip40\n",
    "model.metadata[\"population\"] = \"multiple mammalian species\"  # Paper: 11,754 samples from 185 mammalian species, prenatal to 139 years\n",
    "model.metadata[\"journal\"] = \"Nature Aging\"\n",
    "model.metadata[\"last_author\"] = \"Steve Horvath\"\n",
    "model.metadata[\"n_features\"] = 2467\n",
    "model.metadata[\"citations\"] = 390\n",
    "model.metadata[\"citations_date\"] = \"2026-07-05\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "74492239-5aae-4026-9d90-6bc9c574c110",
   "metadata": {},
   "source": [
    "## Download clock dependencies"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5881f33e-0486-45d1-bd87-9c995f47ca62",
   "metadata": {},
   "source": [
    "#### Download GitHub repository"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "e85525f7-6da4-4962-a7d5-0607e76eea33",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:56:11.395286Z",
     "iopub.status.busy": "2025-04-07T17:56:11.395204Z",
     "iopub.status.idle": "2025-04-07T17:58:06.790129Z",
     "shell.execute_reply": "2025-04-07T17:58:06.789812Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "github_url = \"https://github.com/shorvath/MammalianMethylationConsortium.git\"\n",
    "github_folder_name = github_url.split('/')[-1].split('.')[0]\n",
    "os.system(f\"git clone {github_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2c3e8ec5-a59b-48c5-ae7c-8d2a344ce11a",
   "metadata": {},
   "source": [
    "#### Download from R package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "3fbce39a-5eae-4bff-ac42-d5da0b357bc0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:06.791649Z",
     "iopub.status.busy": "2025-04-07T17:58:06.791547Z",
     "iopub.status.idle": "2025-04-07T17:58:06.794077Z",
     "shell.execute_reply": "2025-04-07T17:58:06.793788Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing download.r\n"
     ]
    }
   ],
   "source": [
    "%%writefile download.r\n",
    "\n",
    "options(repos = c(CRAN = \"https://cloud.r-project.org/\"))\n",
    "\n",
    "myinput.list=readRDS('MammalianMethylationConsortium/UniversalPanMammalianClock/ClockParameters/mydata_GitHub.Rds')\n",
    "anage=myinput.list[[3]]\n",
    "anage=subset(anage,select=c(SpeciesLatinName,GestationTimeInYears, averagedMaturity.yrs,maxAge))\n",
    "anage$HighmaxAge=1.3*anage$maxAge\n",
    "anage$HighmaxAge[anage$SpeciesLatinName=='Homo sapiens']=anage$maxAge[anage$SpeciesLatinName=='Homo sapiens']\n",
    "anage$HighmaxAge[anage$SpeciesLatinName=='Mus musculus']=anage$maxAge[anage$SpeciesLatinName=='Mus musculus']\n",
    "write.csv(anage, \"species_annotation.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3733db47-ba6b-4df7-9b8f-0341b6796586",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:06.795244Z",
     "iopub.status.busy": "2025-04-07T17:58:06.795145Z",
     "iopub.status.idle": "2025-04-07T17:58:07.872058Z",
     "shell.execute_reply": "2025-04-07T17:58:07.871588Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "os.system(\"Rscript download.r\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5035b180-3d1b-4432-8ebe-b9c92bd93a7f",
   "metadata": {},
   "source": [
    "## Load features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15f4af76-b93c-438c-b57f-f129d6e9ec99",
   "metadata": {},
   "source": [
    "#### From CSV file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "8a3d5de6-6303-487a-8b4d-e6345792f7be",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.873787Z",
     "iopub.status.busy": "2025-04-07T17:58:07.873649Z",
     "iopub.status.idle": "2025-04-07T17:58:07.888562Z",
     "shell.execute_reply": "2025-04-07T17:58:07.887675Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('MammalianMethylationConsortium/UniversalPanMammalianClock/ClockParameters/clock3.csv')\n",
    "df['feature'] = df['var']\n",
    "df['coefficient'] = df['beta_clock3']\n",
    "cpg_features = df['feature'][1:].tolist()\n",
    "\n",
    "anage_df = pd.read_csv('species_annotation.csv', index_col=0)\n",
    "anage_df = anage_df[~anage_df['averagedMaturity.yrs'].isna()]\n",
    "anage_df = anage_df[~anage_df['GestationTimeInYears'].isna()]\n",
    "anage_df = anage_df.reset_index().drop('index', axis=1)\n",
    "anage_df = anage_df.fillna(0)\n",
    "species_features = anage_df['SpeciesLatinName'].tolist()\n",
    "\n",
    "model.features = cpg_features + species_features"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ee6d8fa0-4767-4c45-9717-eb1c95e2ddc0",
   "metadata": {},
   "source": [
    "## Load weights into base model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e09b3463-4fd4-41b1-ac21-e63ddd223fe0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.892887Z",
     "iopub.status.busy": "2025-04-07T17:58:07.892506Z",
     "iopub.status.idle": "2025-04-07T17:58:07.897013Z",
     "shell.execute_reply": "2025-04-07T17:58:07.895709Z"
    }
   },
   "outputs": [],
   "source": [
    "weights = torch.tensor(df['coefficient'][1:].tolist()).unsqueeze(0)\n",
    "intercept = torch.tensor([df['coefficient'][0]])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ad261636-5b00-4979-bb1d-67a851f7aa19",
   "metadata": {},
   "source": [
    "#### Linear model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "d7f43b99-26f2-4622-9a76-316712058877",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.900988Z",
     "iopub.status.busy": "2025-04-07T17:58:07.900598Z",
     "iopub.status.idle": "2025-04-07T17:58:07.905009Z",
     "shell.execute_reply": "2025-04-07T17:58:07.903941Z"
    }
   },
   "outputs": [],
   "source": [
    "base_model = pya.models.LinearModel(input_dim=len(model.features))\n",
    "\n",
    "base_model.linear.weight.data = weights.float()\n",
    "base_model.linear.bias.data = intercept.float()\n",
    "\n",
    "model.base_model = base_model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ad8b4c1d-9d57-48b7-9a30-bcfea7b747b1",
   "metadata": {},
   "source": [
    "## Load reference values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ade0f4c9-2298-4fc3-bb72-d200907dd731",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.907478Z",
     "iopub.status.busy": "2025-04-07T17:58:07.907341Z",
     "iopub.status.idle": "2025-04-07T17:58:07.910311Z",
     "shell.execute_reply": "2025-04-07T17:58:07.909615Z"
    }
   },
   "outputs": [],
   "source": [
    "reference_list = np.array([0] * len(model.features))\n",
    "reference_list[len(cpg_features) + np.where(anage_df.SpeciesLatinName == 'Homo sapiens')[0][0]] = 0.5\n",
    "model.reference_values = reference_list"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af3bcf7b-74a8-4d21-9ccb-4de0c2b0516b",
   "metadata": {},
   "source": [
    "## Load preprocess and postprocess objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7a22fb20-c605-424d-8efb-7620c2c0755c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.913870Z",
     "iopub.status.busy": "2025-04-07T17:58:07.913664Z",
     "iopub.status.idle": "2025-04-07T17:58:07.916071Z",
     "shell.execute_reply": "2025-04-07T17:58:07.915485Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = None\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ff4a21cb-cf41-44dc-9ed1-95cf8aa15772",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.918350Z",
     "iopub.status.busy": "2025-04-07T17:58:07.918134Z",
     "iopub.status.idle": "2025-04-07T17:58:07.922074Z",
     "shell.execute_reply": "2025-04-07T17:58:07.921116Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = 'mammalian3'\n",
    "anage_df = anage_df.loc[:, ['GestationTimeInYears','averagedMaturity.yrs', 'maxAge',\t'HighmaxAge']]\n",
    "anage_array = np.array(anage_df)\n",
    "model.postprocess_dependencies = [anage_array]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "86e3d6b1-e67e-4f3d-bd39-0ebec5726c3c",
   "metadata": {},
   "source": [
    "## Check all clock parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "2168355c-47d9-475d-b816-49f65e74887c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.923748Z",
     "iopub.status.busy": "2025-04-07T17:58:07.923622Z",
     "iopub.status.idle": "2025-04-07T17:58:07.933683Z",
     "shell.execute_reply": "2025-04-07T17:58:07.932821Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Lu, A. T., et al. \"Universal DNA methylation age across '\n",
      "             'mammalian tissues.\" Nature aging 3.9 (2023): 1144-1166.',\n",
      " 'clock_name': 'mammalian3',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1038/s43587-023-00462-6',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'multi',\n",
      " 'version': None,\n",
      " 'year': 2023}\n",
      "reference_values: array([0, 0, 0, ..., 0, 0, 0])\n",
      "preprocess_name: None\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: 'mammalian3'\n",
      "postprocess_dependencies: [array([[2.19178082e-02, 2.49315068e+00, 3.60000000e+01, 4.68000000e+01],\n",
      "       [1.64383562e-02, 3.00000000e+00, 1.15000000e+01, 1.49500000e+01],\n",
      "       [3.01369863e-02, 4.50000000e+00, 1.50000000e+01, 1.95000000e+01],\n",
      "       ...,\n",
      "       [1.48575342e-01, 1.15317808e+00, 0.00000000e+00, 0.00000000e+00],\n",
      "       [6.95616438e-02, 1.16958904e-01, 0.00000000e+00, 0.00000000e+00],\n",
      "       [3.15068493e-01, 4.58334000e-01, 2.70000000e+01, 3.51000000e+01]])]\n",
      "features: ['cg00101675', 'cg06259996', 'cg08938156', 'cg15168457', 'cg20370622', 'cg27593991', 'cg20146241', 'cg03747401', 'cg15403305', 'cg02692845', 'cg03679521', 'cg20236179', 'cg11700079', 'cg01910711', 'cg14880272', 'cg10501210', 'cg26844246', 'cg04889095', 'cg13532184', 'cg24312350', 'cg26603143', 'cg06482098', 'cg19927064', 'cg08180952', 'cg10040836', 'cg11686722', 'cg14297772', 'cg11857072', 'cg12501063', 'cg14136214']... [Total elements: 2467]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=2467, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-0.10135350376367569, 0.04514911025762558, 0.6632716655731201, 0.7662340998649597, 0.5491911172866821, -0.3694111108779907, -0.002222728915512562, 0.0004926819819957018, -0.0002535470121074468, -0.49059367179870605, 0.2822667062282562, -0.1023203656077385, 0.358728289604187, 0.17924486100673676, -0.00814816728234291, -0.2773776352405548, 0.16013844311237335, 0.2220076322555542, 0.2895165681838989, 0.16183039546012878, -0.7255541682243347, -0.06926611810922623, 1.412476897239685, 0.2184896171092987, -0.0025988039560616016, 0.24800099432468414, -0.2124103307723999, -0.3366895020008087, -0.2291051298379898, -0.03193030506372452]... [Tensor of shape torch.Size([1, 760])]\n",
      "base_model.linear.bias: tensor([-6.3568])\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pya.utils.print_model_details(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "986d0262-e0c7-4036-b687-dee53ba392fb",
   "metadata": {},
   "source": [
    "## Basic test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "936b9877-d076-4ced-99aa-e8d4c58c5caf",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.936385Z",
     "iopub.status.busy": "2025-04-07T17:58:07.936252Z",
     "iopub.status.idle": "2025-04-07T17:58:07.943664Z",
     "shell.execute_reply": "2025-04-07T17:58:07.943416Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[ 9.0804],\n",
       "        [ 0.2373],\n",
       "        [-0.0573],\n",
       "        [-0.1587],\n",
       "        [25.9575],\n",
       "        [-0.4438],\n",
       "        [-0.0849],\n",
       "        [-0.2192],\n",
       "        [-0.0791],\n",
       "        [ 0.0677]], dtype=torch.float64, grad_fn=<IndexPutBackward0>)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "torch.manual_seed(42)\n",
    "input = torch.randn(10, len(model.features), dtype=float)\n",
    "model.eval()\n",
    "model.to(float)\n",
    "pred = model(input)\n",
    "pred"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fe8299d7-9285-4e22-82fd-b664434b4369",
   "metadata": {},
   "source": [
    "## Save torch model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "5ef2fa8d-c80b-4fdd-8555-79c0d541788e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.944942Z",
     "iopub.status.busy": "2025-04-07T17:58:07.944857Z",
     "iopub.status.idle": "2025-04-07T17:58:07.948243Z",
     "shell.execute_reply": "2025-04-07T17:58:07.947974Z"
    }
   },
   "outputs": [],
   "source": [
    "torch.save(model, f\"../weights/{model.metadata['clock_name']}.pt\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bac6257b-8d08-4a90-8d0b-7f745dc11ac1",
   "metadata": {},
   "source": [
    "## Clear directory\n",
    "<a id=\"10\"></a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "11aeaa70-44c0-42f9-86d7-740e3849a7a6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-04-07T17:58:07.949592Z",
     "iopub.status.busy": "2025-04-07T17:58:07.949503Z",
     "iopub.status.idle": "2025-04-07T17:58:08.087052Z",
     "shell.execute_reply": "2025-04-07T17:58:08.086718Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: species_annotation.csv\n",
      "Deleted folder: MammalianMethylationConsortium\n",
      "Deleted file: download.r\n"
     ]
    }
   ],
   "source": [
    "# Function to remove a folder and all its contents\n",
    "def remove_folder(path):\n",
    "    try:\n",
    "        shutil.rmtree(path)\n",
    "        print(f\"Deleted folder: {path}\")\n",
    "    except Exception as e:\n",
    "        print(f\"Error deleting folder {path}: {e}\")\n",
    "\n",
    "# Get a list of all files and folders in the current directory\n",
    "all_items = os.listdir('.')\n",
    "\n",
    "# Loop through the items\n",
    "for item in all_items:\n",
    "    # Check if it's a file and does not end with .ipynb\n",
    "    if os.path.isfile(item) and not item.endswith('.ipynb'):\n",
    "        os.remove(item)\n",
    "        print(f\"Deleted file: {item}\")\n",
    "    # Check if it's a folder\n",
    "    elif os.path.isdir(item):\n",
    "        remove_folder(item)"
   ]
  }
 ],
 "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}