From 9119557482868a32ffc278f8a9d8de86b5d07a7f Mon Sep 17 00:00:00 2001
From: chelseanguyenn <67062596+chelseanguyenn@users.noreply.github.com>
Date: Tue, 12 Aug 2025 10:59:04 -0700
Subject: [PATCH 1/2] Add files via upload

Uploaded oil spill detection colab
---
 OilSpillDetection_Fixed.ipynb | 404 ++++++++++++++++++++++++++++++++++
 1 file changed, 404 insertions(+)
 create mode 100644 OilSpillDetection_Fixed.ipynb

diff --git a/OilSpillDetection_Fixed.ipynb b/OilSpillDetection_Fixed.ipynb
new file mode 100644
index 00000000..a0b85265
--- /dev/null
+++ b/OilSpillDetection_Fixed.ipynb
@@ -0,0 +1,404 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "yDGmDi0cMcyD"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install -q kaggle\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from google.colab import files\n",
+        "files.upload()  # Upload kaggle.json\n",
+        "{\"username\":\"cheloceannguyen\",\"key\":\"0f1c72736e018e74a01d3cdd9e47ad04\"}"
+      ],
+      "metadata": {
+        "id": "Gk8B2Ny3OBhq",
+        "outputId": "b88b5703-6a79-4b71-f498-75b09c31da96",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 56
+        }
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "\n",
+              "     <input type=\"file\" id=\"files-13ece842-942e-484d-8348-1149de9b3588\" name=\"files[]\" multiple disabled\n",
+              "        style=\"border:none\" />\n",
+              "     <output id=\"result-13ece842-942e-484d-8348-1149de9b3588\">\n",
+              "      Upload widget is only available when the cell has been executed in the\n",
+              "      current browser session. Please rerun this cell to enable.\n",
+              "      </output>\n",
+              "      <script>// Copyright 2017 Google LLC\n",
+              "//\n",
+              "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+              "// you may not use this file except in compliance with the License.\n",
+              "// You may obtain a copy of the License at\n",
+              "//\n",
+              "//      http://www.apache.org/licenses/LICENSE-2.0\n",
+              "//\n",
+              "// Unless required by applicable law or agreed to in writing, software\n",
+              "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+              "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+              "// See the License for the specific language governing permissions and\n",
+              "// limitations under the License.\n",
+              "\n",
+              "/**\n",
+              " * @fileoverview Helpers for google.colab Python module.\n",
+              " */\n",
+              "(function(scope) {\n",
+              "function span(text, styleAttributes = {}) {\n",
+              "  const element = document.createElement('span');\n",
+              "  element.textContent = text;\n",
+              "  for (const key of Object.keys(styleAttributes)) {\n",
+              "    element.style[key] = styleAttributes[key];\n",
+              "  }\n",
+              "  return element;\n",
+              "}\n",
+              "\n",
+              "// Max number of bytes which will be uploaded at a time.\n",
+              "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
+              "\n",
+              "function _uploadFiles(inputId, outputId) {\n",
+              "  const steps = uploadFilesStep(inputId, outputId);\n",
+              "  const outputElement = document.getElementById(outputId);\n",
+              "  // Cache steps on the outputElement to make it available for the next call\n",
+              "  // to uploadFilesContinue from Python.\n",
+              "  outputElement.steps = steps;\n",
+              "\n",
+              "  return _uploadFilesContinue(outputId);\n",
+              "}\n",
+              "\n",
+              "// This is roughly an async generator (not supported in the browser yet),\n",
+              "// where there are multiple asynchronous steps and the Python side is going\n",
+              "// to poll for completion of each step.\n",
+              "// This uses a Promise to block the python side on completion of each step,\n",
+              "// then passes the result of the previous step as the input to the next step.\n",
+              "function _uploadFilesContinue(outputId) {\n",
+              "  const outputElement = document.getElementById(outputId);\n",
+              "  const steps = outputElement.steps;\n",
+              "\n",
+              "  const next = steps.next(outputElement.lastPromiseValue);\n",
+              "  return Promise.resolve(next.value.promise).then((value) => {\n",
+              "    // Cache the last promise value to make it available to the next\n",
+              "    // step of the generator.\n",
+              "    outputElement.lastPromiseValue = value;\n",
+              "    return next.value.response;\n",
+              "  });\n",
+              "}\n",
+              "\n",
+              "/**\n",
+              " * Generator function which is called between each async step of the upload\n",
+              " * process.\n",
+              " * @param {string} inputId Element ID of the input file picker element.\n",
+              " * @param {string} outputId Element ID of the output display.\n",
+              " * @return {!Iterable<!Object>} Iterable of next steps.\n",
+              " */\n",
+              "function* uploadFilesStep(inputId, outputId) {\n",
+              "  const inputElement = document.getElementById(inputId);\n",
+              "  inputElement.disabled = false;\n",
+              "\n",
+              "  const outputElement = document.getElementById(outputId);\n",
+              "  outputElement.innerHTML = '';\n",
+              "\n",
+              "  const pickedPromise = new Promise((resolve) => {\n",
+              "    inputElement.addEventListener('change', (e) => {\n",
+              "      resolve(e.target.files);\n",
+              "    });\n",
+              "  });\n",
+              "\n",
+              "  const cancel = document.createElement('button');\n",
+              "  inputElement.parentElement.appendChild(cancel);\n",
+              "  cancel.textContent = 'Cancel upload';\n",
+              "  const cancelPromise = new Promise((resolve) => {\n",
+              "    cancel.onclick = () => {\n",
+              "      resolve(null);\n",
+              "    };\n",
+              "  });\n",
+              "\n",
+              "  // Wait for the user to pick the files.\n",
+              "  const files = yield {\n",
+              "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
+              "    response: {\n",
+              "      action: 'starting',\n",
+              "    }\n",
+              "  };\n",
+              "\n",
+              "  cancel.remove();\n",
+              "\n",
+              "  // Disable the input element since further picks are not allowed.\n",
+              "  inputElement.disabled = true;\n",
+              "\n",
+              "  if (!files) {\n",
+              "    return {\n",
+              "      response: {\n",
+              "        action: 'complete',\n",
+              "      }\n",
+              "    };\n",
+              "  }\n",
+              "\n",
+              "  for (const file of files) {\n",
+              "    const li = document.createElement('li');\n",
+              "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
+              "    li.append(span(\n",
+              "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
+              "        `last modified: ${\n",
+              "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
+              "                                    'n/a'} - `));\n",
+              "    const percent = span('0% done');\n",
+              "    li.appendChild(percent);\n",
+              "\n",
+              "    outputElement.appendChild(li);\n",
+              "\n",
+              "    const fileDataPromise = new Promise((resolve) => {\n",
+              "      const reader = new FileReader();\n",
+              "      reader.onload = (e) => {\n",
+              "        resolve(e.target.result);\n",
+              "      };\n",
+              "      reader.readAsArrayBuffer(file);\n",
+              "    });\n",
+              "    // Wait for the data to be ready.\n",
+              "    let fileData = yield {\n",
+              "      promise: fileDataPromise,\n",
+              "      response: {\n",
+              "        action: 'continue',\n",
+              "      }\n",
+              "    };\n",
+              "\n",
+              "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
+              "    let position = 0;\n",
+              "    do {\n",
+              "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
+              "      const chunk = new Uint8Array(fileData, position, length);\n",
+              "      position += length;\n",
+              "\n",
+              "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
+              "      yield {\n",
+              "        response: {\n",
+              "          action: 'append',\n",
+              "          file: file.name,\n",
+              "          data: base64,\n",
+              "        },\n",
+              "      };\n",
+              "\n",
+              "      let percentDone = fileData.byteLength === 0 ?\n",
+              "          100 :\n",
+              "          Math.round((position / fileData.byteLength) * 100);\n",
+              "      percent.textContent = `${percentDone}% done`;\n",
+              "\n",
+              "    } while (position < fileData.byteLength);\n",
+              "  }\n",
+              "\n",
+              "  // All done.\n",
+              "  yield {\n",
+              "    response: {\n",
+              "      action: 'complete',\n",
+              "    }\n",
+              "  };\n",
+              "}\n",
+              "\n",
+              "scope.google = scope.google || {};\n",
+              "scope.google.colab = scope.google.colab || {};\n",
+              "scope.google.colab._files = {\n",
+              "  _uploadFiles,\n",
+              "  _uploadFilesContinue,\n",
+              "};\n",
+              "})(self);\n",
+              "</script> "
+            ],
+            "text/plain": [
+              "<IPython.core.display.HTML object>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!mkdir -p ~/.kaggle\n",
+        "!cp kaggle.json ~/.kaggle/\n",
+        "!chmod 600 ~/.kaggle/kaggle.json\n"
+      ],
+      "metadata": {
+        "id": "BgHq4xbEOKGQ",
+        "outputId": "6271de97-85e9-4e7e-970f-34e84cde1f2f",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        }
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "cp: cannot stat 'kaggle.json': No such file or directory\n",
+            "chmod: cannot access '/root/.kaggle/kaggle.json': No such file or directory\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!kaggle datasets download -d kabeer2004/water-pollution-images -p /content/data\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "eTV4H2W-OM_b",
+        "outputId": "677be07f-5746-4956-9b91-9862b4a6b8a1"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Traceback (most recent call last):\n",
+            "  File \"/usr/local/bin/kaggle\", line 10, in <module>\n",
+            "    sys.exit(main())\n",
+            "             ^^^^^^\n",
+            "  File \"/usr/local/lib/python3.11/dist-packages/kaggle/cli.py\", line 68, in main\n",
+            "    out = args.func(**command_args)\n",
+            "          ^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+            "  File \"/usr/local/lib/python3.11/dist-packages/kaggle/api/kaggle_api_extended.py\", line 1741, in dataset_download_cli\n",
+            "    with self.build_kaggle_client() as kaggle:\n",
+            "         ^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+            "  File \"/usr/local/lib/python3.11/dist-packages/kaggle/api/kaggle_api_extended.py\", line 688, in build_kaggle_client\n",
+            "    username=self.config_values['username'],\n",
+            "             ~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^\n",
+            "KeyError: 'username'\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import zipfile\n",
+        "import os\n",
+        "\n",
+        "zip_path = \"/content/data/water-pollution-images.zip\"\n",
+        "extract_path = \"/content/data/water_pollution\"\n",
+        "\n",
+        "with zipfile.ZipFile(zip_path, 'r') as zip_ref:\n",
+        "    zip_ref.extractall(extract_path)\n",
+        "\n",
+        "# Optional: remove the zip file to save space\n",
+        "os.remove(zip_path)\n"
+      ],
+      "metadata": {
+        "id": "iI9S9Pj9OQzx"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import os\n",
+        "from PIL import Image\n",
+        "from pathlib import Path\n",
+        "\n",
+        "def is_image_valid(img_path):\n",
+        "    try:\n",
+        "        with Image.open(img_path) as img:\n",
+        "            img.verify()\n",
+        "        return True\n",
+        "    except:\n",
+        "        return False\n",
+        "\n",
+        "def clean_dataset(folder):\n",
+        "    folder = Path(folder)\n",
+        "    deleted = 0\n",
+        "    for img_path in folder.rglob(\"*.*\"):\n",
+        "        if not is_image_valid(img_path):\n",
+        "            img_path.unlink()\n",
+        "            deleted += 1\n",
+        "    print(f\"Deleted {deleted} invalid images.\")\n",
+        "\n",
+        "clean_dataset(\"/content/data/water_pollution\")\n"
+      ],
+      "metadata": {
+        "id": "-Elo_gP0OT3V",
+        "outputId": "5f71eaa8-3cdd-4b2a-ff55-be94be13102d",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        }
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Deleted 1 invalid images.\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from collections import defaultdict\n",
+        "\n",
+        "summary = defaultdict(int)\n",
+        "for root, _, files in os.walk(\"/content/data/water_pollution\"):\n",
+        "    for file in files:\n",
+        "        if file.endswith(('.png', '.jpg', '.jpeg')):\n",
+        "            label = os.path.basename(root)\n",
+        "            summary[label] += 1\n",
+        "\n",
+        "print(\"Image count per label/class:\")\n",
+        "for label, count in summary.items():\n",
+        "    print(f\"{label}: {count}\")\n"
+      ],
+      "metadata": {
+        "id": "5d7-PywzOYxV",
+        "outputId": "487337fa-3f4c-4769-8124-0d04c8f5c4d6",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        }
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Image count per label/class:\n",
+            "waterpollution: 289\n"
+          ]
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file

From 3adc9978c7637785efa3420769ec2d48ef7c34e9 Mon Sep 17 00:00:00 2001
From: chelseanguyenn <67062596+chelseanguyenn@users.noreply.github.com>
Date: Tue, 12 Aug 2025 11:01:43 -0700
Subject: [PATCH 2/2] Delete OilSpillDetection_Fixed.ipynb

Wrong file of model
---
 OilSpillDetection_Fixed.ipynb | 404 ----------------------------------
 1 file changed, 404 deletions(-)
 delete mode 100644 OilSpillDetection_Fixed.ipynb

diff --git a/OilSpillDetection_Fixed.ipynb b/OilSpillDetection_Fixed.ipynb
deleted file mode 100644
index a0b85265..00000000
--- a/OilSpillDetection_Fixed.ipynb
+++ /dev/null
@@ -1,404 +0,0 @@
-{
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "yDGmDi0cMcyD"
-      },
-      "outputs": [],
-      "source": [
-        "!pip install -q kaggle\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "from google.colab import files\n",
-        "files.upload()  # Upload kaggle.json\n",
-        "{\"username\":\"cheloceannguyen\",\"key\":\"0f1c72736e018e74a01d3cdd9e47ad04\"}"
-      ],
-      "metadata": {
-        "id": "Gk8B2Ny3OBhq",
-        "outputId": "b88b5703-6a79-4b71-f498-75b09c31da96",
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 56
-        }
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "data": {
-            "text/html": [
-              "\n",
-              "     <input type=\"file\" id=\"files-13ece842-942e-484d-8348-1149de9b3588\" name=\"files[]\" multiple disabled\n",
-              "        style=\"border:none\" />\n",
-              "     <output id=\"result-13ece842-942e-484d-8348-1149de9b3588\">\n",
-              "      Upload widget is only available when the cell has been executed in the\n",
-              "      current browser session. Please rerun this cell to enable.\n",
-              "      </output>\n",
-              "      <script>// Copyright 2017 Google LLC\n",
-              "//\n",
-              "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
-              "// you may not use this file except in compliance with the License.\n",
-              "// You may obtain a copy of the License at\n",
-              "//\n",
-              "//      http://www.apache.org/licenses/LICENSE-2.0\n",
-              "//\n",
-              "// Unless required by applicable law or agreed to in writing, software\n",
-              "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
-              "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
-              "// See the License for the specific language governing permissions and\n",
-              "// limitations under the License.\n",
-              "\n",
-              "/**\n",
-              " * @fileoverview Helpers for google.colab Python module.\n",
-              " */\n",
-              "(function(scope) {\n",
-              "function span(text, styleAttributes = {}) {\n",
-              "  const element = document.createElement('span');\n",
-              "  element.textContent = text;\n",
-              "  for (const key of Object.keys(styleAttributes)) {\n",
-              "    element.style[key] = styleAttributes[key];\n",
-              "  }\n",
-              "  return element;\n",
-              "}\n",
-              "\n",
-              "// Max number of bytes which will be uploaded at a time.\n",
-              "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
-              "\n",
-              "function _uploadFiles(inputId, outputId) {\n",
-              "  const steps = uploadFilesStep(inputId, outputId);\n",
-              "  const outputElement = document.getElementById(outputId);\n",
-              "  // Cache steps on the outputElement to make it available for the next call\n",
-              "  // to uploadFilesContinue from Python.\n",
-              "  outputElement.steps = steps;\n",
-              "\n",
-              "  return _uploadFilesContinue(outputId);\n",
-              "}\n",
-              "\n",
-              "// This is roughly an async generator (not supported in the browser yet),\n",
-              "// where there are multiple asynchronous steps and the Python side is going\n",
-              "// to poll for completion of each step.\n",
-              "// This uses a Promise to block the python side on completion of each step,\n",
-              "// then passes the result of the previous step as the input to the next step.\n",
-              "function _uploadFilesContinue(outputId) {\n",
-              "  const outputElement = document.getElementById(outputId);\n",
-              "  const steps = outputElement.steps;\n",
-              "\n",
-              "  const next = steps.next(outputElement.lastPromiseValue);\n",
-              "  return Promise.resolve(next.value.promise).then((value) => {\n",
-              "    // Cache the last promise value to make it available to the next\n",
-              "    // step of the generator.\n",
-              "    outputElement.lastPromiseValue = value;\n",
-              "    return next.value.response;\n",
-              "  });\n",
-              "}\n",
-              "\n",
-              "/**\n",
-              " * Generator function which is called between each async step of the upload\n",
-              " * process.\n",
-              " * @param {string} inputId Element ID of the input file picker element.\n",
-              " * @param {string} outputId Element ID of the output display.\n",
-              " * @return {!Iterable<!Object>} Iterable of next steps.\n",
-              " */\n",
-              "function* uploadFilesStep(inputId, outputId) {\n",
-              "  const inputElement = document.getElementById(inputId);\n",
-              "  inputElement.disabled = false;\n",
-              "\n",
-              "  const outputElement = document.getElementById(outputId);\n",
-              "  outputElement.innerHTML = '';\n",
-              "\n",
-              "  const pickedPromise = new Promise((resolve) => {\n",
-              "    inputElement.addEventListener('change', (e) => {\n",
-              "      resolve(e.target.files);\n",
-              "    });\n",
-              "  });\n",
-              "\n",
-              "  const cancel = document.createElement('button');\n",
-              "  inputElement.parentElement.appendChild(cancel);\n",
-              "  cancel.textContent = 'Cancel upload';\n",
-              "  const cancelPromise = new Promise((resolve) => {\n",
-              "    cancel.onclick = () => {\n",
-              "      resolve(null);\n",
-              "    };\n",
-              "  });\n",
-              "\n",
-              "  // Wait for the user to pick the files.\n",
-              "  const files = yield {\n",
-              "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
-              "    response: {\n",
-              "      action: 'starting',\n",
-              "    }\n",
-              "  };\n",
-              "\n",
-              "  cancel.remove();\n",
-              "\n",
-              "  // Disable the input element since further picks are not allowed.\n",
-              "  inputElement.disabled = true;\n",
-              "\n",
-              "  if (!files) {\n",
-              "    return {\n",
-              "      response: {\n",
-              "        action: 'complete',\n",
-              "      }\n",
-              "    };\n",
-              "  }\n",
-              "\n",
-              "  for (const file of files) {\n",
-              "    const li = document.createElement('li');\n",
-              "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
-              "    li.append(span(\n",
-              "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
-              "        `last modified: ${\n",
-              "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
-              "                                    'n/a'} - `));\n",
-              "    const percent = span('0% done');\n",
-              "    li.appendChild(percent);\n",
-              "\n",
-              "    outputElement.appendChild(li);\n",
-              "\n",
-              "    const fileDataPromise = new Promise((resolve) => {\n",
-              "      const reader = new FileReader();\n",
-              "      reader.onload = (e) => {\n",
-              "        resolve(e.target.result);\n",
-              "      };\n",
-              "      reader.readAsArrayBuffer(file);\n",
-              "    });\n",
-              "    // Wait for the data to be ready.\n",
-              "    let fileData = yield {\n",
-              "      promise: fileDataPromise,\n",
-              "      response: {\n",
-              "        action: 'continue',\n",
-              "      }\n",
-              "    };\n",
-              "\n",
-              "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
-              "    let position = 0;\n",
-              "    do {\n",
-              "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
-              "      const chunk = new Uint8Array(fileData, position, length);\n",
-              "      position += length;\n",
-              "\n",
-              "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
-              "      yield {\n",
-              "        response: {\n",
-              "          action: 'append',\n",
-              "          file: file.name,\n",
-              "          data: base64,\n",
-              "        },\n",
-              "      };\n",
-              "\n",
-              "      let percentDone = fileData.byteLength === 0 ?\n",
-              "          100 :\n",
-              "          Math.round((position / fileData.byteLength) * 100);\n",
-              "      percent.textContent = `${percentDone}% done`;\n",
-              "\n",
-              "    } while (position < fileData.byteLength);\n",
-              "  }\n",
-              "\n",
-              "  // All done.\n",
-              "  yield {\n",
-              "    response: {\n",
-              "      action: 'complete',\n",
-              "    }\n",
-              "  };\n",
-              "}\n",
-              "\n",
-              "scope.google = scope.google || {};\n",
-              "scope.google.colab = scope.google.colab || {};\n",
-              "scope.google.colab._files = {\n",
-              "  _uploadFiles,\n",
-              "  _uploadFilesContinue,\n",
-              "};\n",
-              "})(self);\n",
-              "</script> "
-            ],
-            "text/plain": [
-              "<IPython.core.display.HTML object>"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "!mkdir -p ~/.kaggle\n",
-        "!cp kaggle.json ~/.kaggle/\n",
-        "!chmod 600 ~/.kaggle/kaggle.json\n"
-      ],
-      "metadata": {
-        "id": "BgHq4xbEOKGQ",
-        "outputId": "6271de97-85e9-4e7e-970f-34e84cde1f2f",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        }
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "cp: cannot stat 'kaggle.json': No such file or directory\n",
-            "chmod: cannot access '/root/.kaggle/kaggle.json': No such file or directory\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "!kaggle datasets download -d kabeer2004/water-pollution-images -p /content/data\n"
-      ],
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "eTV4H2W-OM_b",
-        "outputId": "677be07f-5746-4956-9b91-9862b4a6b8a1"
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Traceback (most recent call last):\n",
-            "  File \"/usr/local/bin/kaggle\", line 10, in <module>\n",
-            "    sys.exit(main())\n",
-            "             ^^^^^^\n",
-            "  File \"/usr/local/lib/python3.11/dist-packages/kaggle/cli.py\", line 68, in main\n",
-            "    out = args.func(**command_args)\n",
-            "          ^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-            "  File \"/usr/local/lib/python3.11/dist-packages/kaggle/api/kaggle_api_extended.py\", line 1741, in dataset_download_cli\n",
-            "    with self.build_kaggle_client() as kaggle:\n",
-            "         ^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
-            "  File \"/usr/local/lib/python3.11/dist-packages/kaggle/api/kaggle_api_extended.py\", line 688, in build_kaggle_client\n",
-            "    username=self.config_values['username'],\n",
-            "             ~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^\n",
-            "KeyError: 'username'\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "import zipfile\n",
-        "import os\n",
-        "\n",
-        "zip_path = \"/content/data/water-pollution-images.zip\"\n",
-        "extract_path = \"/content/data/water_pollution\"\n",
-        "\n",
-        "with zipfile.ZipFile(zip_path, 'r') as zip_ref:\n",
-        "    zip_ref.extractall(extract_path)\n",
-        "\n",
-        "# Optional: remove the zip file to save space\n",
-        "os.remove(zip_path)\n"
-      ],
-      "metadata": {
-        "id": "iI9S9Pj9OQzx"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "import os\n",
-        "from PIL import Image\n",
-        "from pathlib import Path\n",
-        "\n",
-        "def is_image_valid(img_path):\n",
-        "    try:\n",
-        "        with Image.open(img_path) as img:\n",
-        "            img.verify()\n",
-        "        return True\n",
-        "    except:\n",
-        "        return False\n",
-        "\n",
-        "def clean_dataset(folder):\n",
-        "    folder = Path(folder)\n",
-        "    deleted = 0\n",
-        "    for img_path in folder.rglob(\"*.*\"):\n",
-        "        if not is_image_valid(img_path):\n",
-        "            img_path.unlink()\n",
-        "            deleted += 1\n",
-        "    print(f\"Deleted {deleted} invalid images.\")\n",
-        "\n",
-        "clean_dataset(\"/content/data/water_pollution\")\n"
-      ],
-      "metadata": {
-        "id": "-Elo_gP0OT3V",
-        "outputId": "5f71eaa8-3cdd-4b2a-ff55-be94be13102d",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        }
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Deleted 1 invalid images.\n"
-          ]
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "from collections import defaultdict\n",
-        "\n",
-        "summary = defaultdict(int)\n",
-        "for root, _, files in os.walk(\"/content/data/water_pollution\"):\n",
-        "    for file in files:\n",
-        "        if file.endswith(('.png', '.jpg', '.jpeg')):\n",
-        "            label = os.path.basename(root)\n",
-        "            summary[label] += 1\n",
-        "\n",
-        "print(\"Image count per label/class:\")\n",
-        "for label, count in summary.items():\n",
-        "    print(f\"{label}: {count}\")\n"
-      ],
-      "metadata": {
-        "id": "5d7-PywzOYxV",
-        "outputId": "487337fa-3f4c-4769-8124-0d04c8f5c4d6",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        }
-      },
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": [
-            "Image count per label/class:\n",
-            "waterpollution: 289\n"
-          ]
-        }
-      ]
-    }
-  ]
-}
\ No newline at end of file