{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2f04eee0-5928-4e74-a754-6dc2e528810c",
   "metadata": {},
   "source": [
    "# ZhangBLUP"
   ]
  },
  {
   "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": "2024-03-05T21:24:05.648919Z",
     "iopub.status.busy": "2024-03-05T21:24:05.648291Z",
     "iopub.status.idle": "2024-03-05T21:24:06.960359Z",
     "shell.execute_reply": "2024-03-05T21:24:06.960057Z"
    }
   },
   "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"
   ]
  },
  {
   "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": "2024-03-05T21:24:06.962342Z",
     "iopub.status.busy": "2024-03-05T21:24:06.962164Z",
     "iopub.status.idle": "2024-03-05T21:24:06.971585Z",
     "shell.execute_reply": "2024-03-05T21:24:06.971332Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "class ZhangBLUP(pyagingModel):\n",
      "    def __init__(self):\n",
      "        super().__init__()\n",
      "\n",
      "    def preprocess(self, x):\n",
      "        \"\"\"\n",
      "        Scales the input PyTorch tensor per row with mean 0 and std 1.\n",
      "        \"\"\"\n",
      "        row_means = torch.mean(x, dim=1, keepdim=True)\n",
      "        row_stds = torch.std(x, dim=1, keepdim=True)\n",
      "\n",
      "        # Avoid division by zero in case of a row with constant value\n",
      "        row_stds = torch.where(row_stds == 0, torch.ones_like(row_stds), row_stds)\n",
      "\n",
      "        x_scaled = (x - row_means) / row_stds\n",
      "        return x_scaled\n",
      "\n",
      "    def postprocess(self, x):\n",
      "        return x\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def print_entire_class(cls):\n",
    "    source = inspect.getsource(cls)\n",
    "    print(source)\n",
    "\n",
    "print_entire_class(pya.models.ZhangBLUP)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "78536494-f1d9-44de-8583-c89a310d2307",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:06.973159Z",
     "iopub.status.busy": "2024-03-05T21:24:06.973058Z",
     "iopub.status.idle": "2024-03-05T21:24:06.974566Z",
     "shell.execute_reply": "2024-03-05T21:24:06.974329Z"
    }
   },
   "outputs": [],
   "source": [
    "model = pya.models.ZhangBLUP()"
   ]
  },
  {
   "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": "2024-03-05T21:24:06.976007Z",
     "iopub.status.busy": "2024-03-05T21:24:06.975925Z",
     "iopub.status.idle": "2024-03-05T21:24:06.977763Z",
     "shell.execute_reply": "2024-03-05T21:24:06.977538Z"
    }
   },
   "outputs": [],
   "source": [
    "model.metadata[\"clock_name\"] = \"zhangblup\"\n",
    "model.metadata[\"data_type\"] = \"DNA methylation\"  # Paper: The predictors use DNA-methylation beta values.\n",
    "model.metadata[\"species\"] = \"Homo sapiens\"  # Paper: The training collection comprises human blood and saliva cohorts.\n",
    "model.metadata[\"year\"] = 2019\n",
    "model.metadata[\"approved_by_author\"] = \"⌛\"\n",
    "model.metadata[\"citation\"] = \"Zhang, Q., Vallerga, C.L., Walker, R.M. et al. Improved precision of epigenetic clock estimates across tissues and its implication for biological ageing. Genome Medicine 11, 54 (2019).\"\n",
    "model.metadata[\"doi\"] = \"https://doi.org/10.1186/s13073-019-0667-1\"\n",
    "model.metadata[\"notes\"] = \"High-dimensional chronological-age predictor using best linear unbiased prediction across the full quality-controlled set of 319,607 methylation probes.\"\n",
    "model.metadata[\"research_only\"] = None\n",
    "model.metadata[\"tissue\"] = [\"whole blood\", \"saliva\"]  # Paper: The assembled training collection contained 13,402 blood and 259 saliva samples.\n",
    "model.metadata[\"predicts\"] = [\"chronological age\"]  # Paper: Both released predictors estimate chronological age.\n",
    "model.metadata[\"training_target\"] = [\"chronological age\"]  # Paper: Chronological age was the regression outcome.\n",
    "model.metadata[\"unit\"] = [\"years\"]  # Paper: Predicted chronological age and prediction error are reported in years.\n",
    "model.metadata[\"model_type\"] = \"best linear unbiased prediction\"  # Paper: BLUP was one of the two age-prediction methods.\n",
    "model.metadata[\"platform\"] = [\"Illumina 450K\", \"Illumina EPIC\"]  # Paper: The 14 training cohorts were measured on HumanMethylation450 and EPIC arrays.\n",
    "model.metadata[\"population\"] = \"all ages\"  # Paper: The assembled 14-cohort collection spanned ages 2–104 years.\n",
    "model.metadata[\"journal\"] = \"Genome Medicine\"\n",
    "model.metadata[\"last_author\"] = \"Peter M. Visscher\"\n",
    "model.metadata[\"n_features\"] = 319607\n",
    "model.metadata[\"citations\"] = 519\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": "c2844c3a-8e78-48bd-95b5-9301c8b46012",
   "metadata": {},
   "source": [
    "#### Download GitHub repository"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "0ee560a3-8ab6-4202-b8b2-cebf75089bfb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:06.979299Z",
     "iopub.status.busy": "2024-03-05T21:24:06.979222Z",
     "iopub.status.idle": "2024-03-05T21:24:17.301214Z",
     "shell.execute_reply": "2024-03-05T21:24:17.300886Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "github_url = \"https://github.com/qzhang314/DNAm-based-age-predictor.git\"\n",
    "github_folder_name = github_url.split('/')[-1].split('.')[0]\n",
    "os.system(f\"git clone {github_url}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eb5774d0-e6ea-4d18-949e-6ba1f0534d2a",
   "metadata": {},
   "source": [
    "#### Download from R package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "3460ce9a-719e-494c-9a94-21fc97dd0be4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:17.302886Z",
     "iopub.status.busy": "2024-03-05T21:24:17.302775Z",
     "iopub.status.idle": "2024-03-05T21:24:17.305137Z",
     "shell.execute_reply": "2024-03-05T21:24:17.304884Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing download.r\n"
     ]
    }
   ],
   "source": [
    "%%writefile download.r\n",
    "\n",
    "data = readRDS(\"DNAm-based-age-predictor/data.rds\")\n",
    "\n",
    "write.csv(data, \"example_data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "11ba180b-0ca9-40e0-8a89-72bc4e085451",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:17.306563Z",
     "iopub.status.busy": "2024-03-05T21:24:17.306464Z",
     "iopub.status.idle": "2024-03-05T21:24:20.964109Z",
     "shell.execute_reply": "2024-03-05T21:24:20.963851Z"
    }
   },
   "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": "2024-03-05T21:24:20.965851Z",
     "iopub.status.busy": "2024-03-05T21:24:20.965755Z",
     "iopub.status.idle": "2024-03-05T21:24:21.066559Z",
     "shell.execute_reply": "2024-03-05T21:24:21.066264Z"
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_table('DNAm-based-age-predictor/blup.coef', sep=' ')\n",
    "df['feature'] = df['probe']\n",
    "df['coefficient'] = df['coef']\n",
    "\n",
    "model.features = df['feature'][1:].tolist()"
   ]
  },
  {
   "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": "2024-03-05T21:24:21.068372Z",
     "iopub.status.busy": "2024-03-05T21:24:21.068272Z",
     "iopub.status.idle": "2024-03-05T21:24:21.093386Z",
     "shell.execute_reply": "2024-03-05T21:24:21.093063Z"
    }
   },
   "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": "2024-03-05T21:24:21.095068Z",
     "iopub.status.busy": "2024-03-05T21:24:21.094975Z",
     "iopub.status.idle": "2024-03-05T21:24:21.097916Z",
     "shell.execute_reply": "2024-03-05T21:24:21.097694Z"
    }
   },
   "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": "markdown",
   "id": "f7fdae64-096a-4640-ade7-6a17b78a01d5",
   "metadata": {},
   "source": [
    "#### From CSV file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "86de757f-fb38-4bcb-b91e-fc3372d22aad",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:21.099379Z",
     "iopub.status.busy": "2024-03-05T21:24:21.099292Z",
     "iopub.status.idle": "2024-03-05T21:24:36.755051Z",
     "shell.execute_reply": "2024-03-05T21:24:36.754740Z"
    }
   },
   "outputs": [],
   "source": [
    "reference_feature_values_df = pd.read_csv('example_data.csv', index_col=0)\n",
    "reference_feature_values_df = reference_feature_values_df.loc[:, model.features]\n",
    "model.reference_values = reference_feature_values_df.mean().tolist()"
   ]
  },
  {
   "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": "2024-03-05T21:24:36.756917Z",
     "iopub.status.busy": "2024-03-05T21:24:36.756810Z",
     "iopub.status.idle": "2024-03-05T21:24:36.758463Z",
     "shell.execute_reply": "2024-03-05T21:24:36.758236Z"
    }
   },
   "outputs": [],
   "source": [
    "model.preprocess_name = 'scale_row'\n",
    "model.preprocess_dependencies = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ff4a21cb-cf41-44dc-9ed1-95cf8aa15772",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2024-03-05T21:24:36.759873Z",
     "iopub.status.busy": "2024-03-05T21:24:36.759794Z",
     "iopub.status.idle": "2024-03-05T21:24:36.761383Z",
     "shell.execute_reply": "2024-03-05T21:24:36.761159Z"
    }
   },
   "outputs": [],
   "source": [
    "model.postprocess_name = None\n",
    "model.postprocess_dependencies = None"
   ]
  },
  {
   "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": "2024-03-05T21:24:36.762791Z",
     "iopub.status.busy": "2024-03-05T21:24:36.762716Z",
     "iopub.status.idle": "2024-03-05T21:24:36.765304Z",
     "shell.execute_reply": "2024-03-05T21:24:36.765090Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Attributes:\n",
      "\n",
      "training: True\n",
      "metadata: {'approved_by_author': '⌛',\n",
      " 'citation': 'Zhang, Qian, et al. \"Improved precision of epigenetic clock '\n",
      "             'estimates across tissues and its implication for biological '\n",
      "             'ageing.\" Genome medicine 11 (2019): 1-11.',\n",
      " 'clock_name': 'zhangblup',\n",
      " 'data_type': 'methylation',\n",
      " 'doi': 'https://doi.org/10.1186/s13073-019-0667-1',\n",
      " 'notes': None,\n",
      " 'research_only': None,\n",
      " 'species': 'Homo sapiens',\n",
      " 'version': None,\n",
      " 'year': 2019}\n",
      "reference_values: [0.05946290980445651, 0.9016779859564634, 0.8511621554128406, 0.07497523935546724, 0.08079601941558237, 0.13789119095690058, 0.959990162673912, 0.054840405638908254, 0.11271586156940745, 0.06867464793155438, 0.04092332774669377, 0.03122014881875939, 0.12091171597794977, 0.8626077673429406, 0.02002095456899887, 0.037161243530447204, 0.5228131230887364, 0.025038065219011623, 0.03411737762225109, 0.023966201717807785, 0.13213191286915785, 0.03613520841142101, 0.11053625925027737, 0.09303164766153527, 0.07697707482010466, 0.040677518106921974, 0.016422537053260692, 0.01646509240082735, 0.9634930275356334, 0.8664078943468241]... [Total elements: 319607]\n",
      "preprocess_name: 'scale_row'\n",
      "preprocess_dependencies: None\n",
      "postprocess_name: None\n",
      "postprocess_dependencies: None\n",
      "features: ['cg18478105', 'cg14361672', 'cg01763666', 'cg02115394', 'cg13417420', 'cg12480843', 'cg26724186', 'cg24133276', 'cg19607165', 'cg11073926', 'cg08770523', 'cg24040570', 'cg15998406', 'cg11947782', 'cg11945228', 'cg14361409', 'cg00376553', 'cg12898275', 'cg21650422', 'cg24176744', 'cg08360726', 'cg07469408', 'cg08730728', 'cg22782271', 'cg26846647', 'cg24568647', 'cg01415275', 'cg00172270', 'cg27548741', 'cg09659208']... [Total elements: 319607]\n",
      "base_model_features: None\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Structure:\n",
      "\n",
      "base_model: LinearModel(\n",
      "  (linear): Linear(in_features=319607, out_features=1, bias=True)\n",
      ")\n",
      "\n",
      "%==================================== Model Details ====================================%\n",
      "Model Parameters and Weights:\n",
      "\n",
      "base_model.linear.weight: [-0.011127361096441746, 0.0005570068024098873, -0.01769556663930416, 0.009089098311960697, -0.016315005719661713, -0.012607994489371777, -0.006776333786547184, 0.005497894249856472, -0.031007202342152596, 0.007024446967989206, 0.0072049410082399845, 0.006631432566791773, -0.028644423931837082, -0.0067995828576385975, -0.003207291942089796, -0.010230086743831635, 0.002228884259238839, -0.0012665422400459647, 0.010415713302791119, -0.0016215209616348147, 0.015202521346509457, -0.0019047950627282262, -0.01444777101278305, 0.01679779589176178, -0.0016255266964435577, -0.0027738267090171576, -0.0028552687726914883, 0.0026693870313465595, 0.0018644158262759447, 0.004981260746717453]... [Tensor of shape torch.Size([1, 319607])]\n",
      "base_model.linear.bias: tensor([91.1540])\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": "2024-03-05T21:24:36.766917Z",
     "iopub.status.busy": "2024-03-05T21:24:36.766804Z",
     "iopub.status.idle": "2024-03-05T21:24:36.821344Z",
     "shell.execute_reply": "2024-03-05T21:24:36.820983Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[107.0536],\n",
       "        [ 90.5363],\n",
       "        [ 81.2531],\n",
       "        [ 97.2001],\n",
       "        [ 91.7565],\n",
       "        [ 95.9860],\n",
       "        [ 97.9471],\n",
       "        [ 97.2143],\n",
       "        [107.3615],\n",
       "        [ 90.4772]], dtype=torch.float64, grad_fn=<AddmmBackward0>)"
      ]
     },
     "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": "2024-03-05T21:24:36.823632Z",
     "iopub.status.busy": "2024-03-05T21:24:36.823512Z",
     "iopub.status.idle": "2024-03-05T21:24:36.964554Z",
     "shell.execute_reply": "2024-03-05T21:24:36.964090Z"
    }
   },
   "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": "2024-03-05T21:24:36.966595Z",
     "iopub.status.busy": "2024-03-05T21:24:36.966485Z",
     "iopub.status.idle": "2024-03-05T21:24:36.976316Z",
     "shell.execute_reply": "2024-03-05T21:24:36.975971Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted file: download.r\n",
      "Deleted folder: DNAm-based-age-predictor\n",
      "Deleted file: example_data.csv\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": "3.9.17"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}