{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DDADPl-phDUC"
      },
      "source": [
        "# **Music recommender**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "E7Cu5Fmqct7J"
      },
      "source": [
        "# **Load Data**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 540
        },
        "id": "bI8bNavbajsv",
        "outputId": "7cba8b5d-4a63-433f-be3c-87ce794833ba"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-793c32c8-99a6-4873-9585-738e1d4b2ab1\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-793c32c8-99a6-4873-9585-738e1d4b2ab1\">\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"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Saving music_data.csv to music_data.csv\n",
            "                                          title  \\\n",
            "0  100 Club 1996 ''We Love You Beatles'' - Live   \n",
            "1                             Yo Quiero Contigo   \n",
            "4                                       Emerald   \n",
            "6                                         Karma   \n",
            "7                                   Money Blues   \n",
            "\n",
            "                           release          artist_name   duration  \\\n",
            "0     Sex Pistols - The Interviews          Sex Pistols   88.73751   \n",
            "1  Sentenciados - Platinum Edition  Baby Rasta & Gringo  167.36608   \n",
            "4                          Emerald              Bedrock  501.86404   \n",
            "6         The Diary Of Alicia Keys          Alicia Keys  255.99955   \n",
            "7                        Slidetime        Joanna Connor  243.66975   \n",
            "\n",
            "   artist_familiarity  artist_hotttnesss  year  listeners  playcount  \\\n",
            "0            0.731184           0.549204     0        172        210   \n",
            "1            0.610186           0.355320     0       9753      16911   \n",
            "4            0.654039           0.390625  2004        973       2247   \n",
            "6            0.933916           0.778674  2003     250304    1028356   \n",
            "7            0.479218           0.332857     0        429       1008   \n",
            "\n",
            "                                                tags  \n",
            "0              The Beatles, title is a full sentence  \n",
            "1  Reggaeton, alexis y fido, Eliana, mis videos, ...  \n",
            "4                                              dance  \n",
            "6    rnb, soul, Alicia Keys, female vocalists, Karma  \n",
            "7                                 guitar girl, blues  \n"
          ]
        }
      ],
      "source": [
        "import pandas as pd\n",
        "from google.colab import files\n",
        "\n",
        "# Upload the file\n",
        "uploaded = files.upload()\n",
        "\n",
        "# Assuming the file is named \"music_data.csv\"\n",
        "data_path = \"music_data.csv\"\n",
        "\n",
        "# Load the data\n",
        "df = pd.read_csv(data_path)\n",
        "df.dropna(inplace=True)\n",
        "\n",
        "# Display the first few rows of the dataset\n",
        "print(df.head())\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "9E3in0U3dK5I",
        "outputId": "c1d5362a-6a33-4543-ff4d-4e11cf8220ec"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 5063,\n  \"fields\": [\n    {\n      \"column\": \"title\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4854,\n        \"samples\": [\n          \"I Wish I Had A Girl\",\n          \"Jump [Jacques Lu Cont Edit]\",\n          \"Mulin' Around\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"release\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4187,\n        \"samples\": [\n          \"Le Bordel Magnifique\",\n          \"Charlotte's Web (OST)\",\n          \"X.O. Experience\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"artist_name\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2461,\n        \"samples\": [\n          \"Lee Ritenour\",\n          \"Pennywise\",\n          \"Anneli Drecker\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"duration\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 107.73289375974717,\n        \"min\": 1.04444,\n        \"max\": 1815.2224,\n        \"num_unique_values\": 3939,\n        \"samples\": [\n          294.24281,\n          240.79628,\n          115.53914\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"artist_familiarity\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.14886096792686204,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2474,\n        \"samples\": [\n          0.787098355481,\n          0.481771820142,\n          0.374024633035\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"artist_hotttnesss\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.1347303774485448,\n        \"min\": 0.0,\n        \"max\": 1.08250255673,\n        \"num_unique_values\": 2398,\n        \"samples\": [\n          0.376018761952,\n          0.355667956383,\n          0.289970666912\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"year\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 917,\n        \"min\": 0,\n        \"max\": 2010,\n        \"num_unique_values\": 69,\n        \"samples\": [\n          1979,\n          0,\n          1965\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"listeners\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 150513,\n        \"min\": 0,\n        \"max\": 2451482,\n        \"num_unique_values\": 3914,\n        \"samples\": [\n          781546,\n          6216,\n          396579\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"playcount\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1115103,\n        \"min\": 0,\n        \"max\": 23182516,\n        \"num_unique_values\": 4422,\n        \"samples\": [\n          62736,\n          1305,\n          17033\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tags\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4583,\n        \"samples\": [\n          \"dance, 90s, trance, House, jungle\",\n          \"country, favorite songs, classic country, linedance, Martina McBride\",\n          \"90s, heavy metal, thrash metal, metal, punk\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
              "type": "dataframe",
              "variable_name": "df"
            },
            "text/html": [
              "\n",
              "  <div id=\"df-b9e5c35d-1534-4ad7-8661-887b39a472e9\" class=\"colab-df-container\">\n",
              "    <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>title</th>\n",
              "      <th>release</th>\n",
              "      <th>artist_name</th>\n",
              "      <th>duration</th>\n",
              "      <th>artist_familiarity</th>\n",
              "      <th>artist_hotttnesss</th>\n",
              "      <th>year</th>\n",
              "      <th>listeners</th>\n",
              "      <th>playcount</th>\n",
              "      <th>tags</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>100 Club 1996 ''We Love You Beatles'' - Live</td>\n",
              "      <td>Sex Pistols - The Interviews</td>\n",
              "      <td>Sex Pistols</td>\n",
              "      <td>88.73751</td>\n",
              "      <td>0.731184</td>\n",
              "      <td>0.549204</td>\n",
              "      <td>0</td>\n",
              "      <td>172</td>\n",
              "      <td>210</td>\n",
              "      <td>The Beatles, title is a full sentence</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Yo Quiero Contigo</td>\n",
              "      <td>Sentenciados - Platinum Edition</td>\n",
              "      <td>Baby Rasta &amp; Gringo</td>\n",
              "      <td>167.36608</td>\n",
              "      <td>0.610186</td>\n",
              "      <td>0.355320</td>\n",
              "      <td>0</td>\n",
              "      <td>9753</td>\n",
              "      <td>16911</td>\n",
              "      <td>Reggaeton, alexis y fido, Eliana, mis videos, ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Emerald</td>\n",
              "      <td>Emerald</td>\n",
              "      <td>Bedrock</td>\n",
              "      <td>501.86404</td>\n",
              "      <td>0.654039</td>\n",
              "      <td>0.390625</td>\n",
              "      <td>2004</td>\n",
              "      <td>973</td>\n",
              "      <td>2247</td>\n",
              "      <td>dance</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>Karma</td>\n",
              "      <td>The Diary Of Alicia Keys</td>\n",
              "      <td>Alicia Keys</td>\n",
              "      <td>255.99955</td>\n",
              "      <td>0.933916</td>\n",
              "      <td>0.778674</td>\n",
              "      <td>2003</td>\n",
              "      <td>250304</td>\n",
              "      <td>1028356</td>\n",
              "      <td>rnb, soul, Alicia Keys, female vocalists, Karma</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>Money Blues</td>\n",
              "      <td>Slidetime</td>\n",
              "      <td>Joanna Connor</td>\n",
              "      <td>243.66975</td>\n",
              "      <td>0.479218</td>\n",
              "      <td>0.332857</td>\n",
              "      <td>0</td>\n",
              "      <td>429</td>\n",
              "      <td>1008</td>\n",
              "      <td>guitar girl, blues</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b9e5c35d-1534-4ad7-8661-887b39a472e9')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-b9e5c35d-1534-4ad7-8661-887b39a472e9 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-b9e5c35d-1534-4ad7-8661-887b39a472e9');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-3ffda883-e826-470a-8413-bc736b2d9130\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-3ffda883-e826-470a-8413-bc736b2d9130')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-3ffda883-e826-470a-8413-bc736b2d9130 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "                                          title  \\\n",
              "0  100 Club 1996 ''We Love You Beatles'' - Live   \n",
              "1                             Yo Quiero Contigo   \n",
              "4                                       Emerald   \n",
              "6                                         Karma   \n",
              "7                                   Money Blues   \n",
              "\n",
              "                           release          artist_name   duration  \\\n",
              "0     Sex Pistols - The Interviews          Sex Pistols   88.73751   \n",
              "1  Sentenciados - Platinum Edition  Baby Rasta & Gringo  167.36608   \n",
              "4                          Emerald              Bedrock  501.86404   \n",
              "6         The Diary Of Alicia Keys          Alicia Keys  255.99955   \n",
              "7                        Slidetime        Joanna Connor  243.66975   \n",
              "\n",
              "   artist_familiarity  artist_hotttnesss  year  listeners  playcount  \\\n",
              "0            0.731184           0.549204     0        172        210   \n",
              "1            0.610186           0.355320     0       9753      16911   \n",
              "4            0.654039           0.390625  2004        973       2247   \n",
              "6            0.933916           0.778674  2003     250304    1028356   \n",
              "7            0.479218           0.332857     0        429       1008   \n",
              "\n",
              "                                                tags  \n",
              "0              The Beatles, title is a full sentence  \n",
              "1  Reggaeton, alexis y fido, Eliana, mis videos, ...  \n",
              "4                                              dance  \n",
              "6    rnb, soul, Alicia Keys, female vocalists, Karma  \n",
              "7                                 guitar girl, blues  "
            ]
          },
          "execution_count": 2,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "b_sSacbdHcn6",
        "outputId": "f745b028-fd97-4b19-b9f0-9e041621e5d3"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "Index: 5063 entries, 0 to 9530\n",
            "Data columns (total 10 columns):\n",
            " #   Column              Non-Null Count  Dtype  \n",
            "---  ------              --------------  -----  \n",
            " 0   title               5063 non-null   object \n",
            " 1   release             5063 non-null   object \n",
            " 2   artist_name         5063 non-null   object \n",
            " 3   duration            5063 non-null   float64\n",
            " 4   artist_familiarity  5063 non-null   float64\n",
            " 5   artist_hotttnesss   5063 non-null   float64\n",
            " 6   year                5063 non-null   int64  \n",
            " 7   listeners           5063 non-null   int64  \n",
            " 8   playcount           5063 non-null   int64  \n",
            " 9   tags                5063 non-null   object \n",
            "dtypes: float64(3), int64(3), object(4)\n",
            "memory usage: 435.1+ KB\n",
            "None\n",
            "          duration  artist_familiarity  artist_hotttnesss         year  \\\n",
            "count  5063.000000         5063.000000        5063.000000  5063.000000   \n",
            "mean    243.156073            0.626861           0.439664  1392.483705   \n",
            "std     107.732894            0.148861           0.134730   917.360336   \n",
            "min       1.044440            0.000000           0.000000     0.000000   \n",
            "25%     183.535870            0.527033           0.363132     0.000000   \n",
            "50%     229.145670            0.619531           0.417819  1993.000000   \n",
            "75%     280.920365            0.731184           0.510325  2004.000000   \n",
            "max    1815.222400            1.000000           1.082503  2010.000000   \n",
            "\n",
            "          listeners     playcount  \n",
            "count  5.063000e+03  5.063000e+03  \n",
            "mean   4.526352e+04  2.622274e+05  \n",
            "std    1.505135e+05  1.115104e+06  \n",
            "min    0.000000e+00  0.000000e+00  \n",
            "25%    7.545000e+02  1.894500e+03  \n",
            "50%    3.387000e+03  9.439000e+03  \n",
            "75%    1.787350e+04  6.269500e+04  \n",
            "max    2.451482e+06  2.318252e+07  \n",
            "Unique values in 'title': 4854\n",
            "Unique values in 'artist_name': 2461\n",
            "Unique values in 'tags': 4583\n"
          ]
        }
      ],
      "source": [
        "# Display basic information about the dataset\n",
        "print(df.info())\n",
        "\n",
        "# Display summary statistics for numerical columns\n",
        "print(df.describe())\n",
        "\n",
        "# Display unique values for categorical columns\n",
        "print(\"Unique values in 'title':\", df['title'].nunique())\n",
        "print(\"Unique values in 'artist_name':\", df['artist_name'].nunique())\n",
        "print(\"Unique values in 'tags':\", df['tags'].nunique())"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wPVFDtk9g9ox"
      },
      "source": [
        "# **Preprocessing**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3fsU1IvylyZg",
        "outputId": "c2ba3adc-c077-454a-94de-ca9bb0ba4807"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Label encoders and scaler saved successfully.\n"
          ]
        }
      ],
      "source": [
        "import pandas as pd\n",
        "from sklearn.preprocessing import LabelEncoder, MinMaxScaler\n",
        "import joblib\n",
        "import re\n",
        "\n",
        "# Function to clean tags and artist names\n",
        "def clean_text(text):\n",
        "    # Convert to lowercase\n",
        "    text = text.lower()\n",
        "    # Remove special characters and digits\n",
        "    text = re.sub(r'[^a-zA-Z\\s]', '', text)\n",
        "    # Remove extra white spaces\n",
        "    text = re.sub(r'\\s+', ' ', text).strip()\n",
        "    return text\n",
        "\n",
        "# Clean 'tags' and 'artist_name' columns\n",
        "df['tags'] = df['tags'].apply(clean_text)\n",
        "df['artist_name'] = df['artist_name'].apply(clean_text)\n",
        "\n",
        "def label_encode_data(df):\n",
        "    df = df.copy(deep=True)\n",
        "    label_encoders = {}\n",
        "    unknown_label = 'unknown'  # Define an unknown label\n",
        "\n",
        "    for column in ['tags', 'title', 'artist_name']:\n",
        "        le = LabelEncoder()\n",
        "        unique_categories = df[column].unique().tolist()\n",
        "        unique_categories.append(unknown_label)\n",
        "        le.fit(unique_categories)\n",
        "        df[column] = le.transform(df[column].astype(str))\n",
        "        label_encoders[column] = le\n",
        "\n",
        "    return df, label_encoders\n",
        "\n",
        "# Normalize numerical features\n",
        "scaler = MinMaxScaler()\n",
        "df[['listeners', 'playcount']] = scaler.fit_transform(df[['listeners', 'playcount']])\n",
        "\n",
        "# Label encode categorical features\n",
        "df_scaled, label_encoders = label_encode_data(df)\n",
        "\n",
        "# Save the encoders and scaler\n",
        "joblib.dump(label_encoders, \"/content/new_label_encoders.joblib\")\n",
        "joblib.dump(scaler, \"/content/new_scaler.joblib\")\n",
        "\n",
        "print(\"Label encoders and scaler saved successfully.\")\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JBWZWp_8Jr82",
        "outputId": "73a312c1-3615-4a87-965b-c2fc41fc50e7"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Data split into training and testing sets.\n",
            "Maximum value in y_train: 4854\n",
            "Maximum value in y_test: 4850\n",
            "Number of unique titles: 4855\n",
            "Maximum value in y_train after clipping: 4854\n",
            "Maximum value in y_test after clipping: 4850\n"
          ]
        }
      ],
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "# Split data into features and target\n",
        "X = df_scaled[['tags', 'artist_name']]\n",
        "y = df_scaled['title']\n",
        "\n",
        "# Split the dataset into training and testing sets\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
        "print(\"Data split into training and testing sets.\")\n",
        "\n",
        "# Number of unique titles\n",
        "num_unique_titles = len(label_encoders['title'].classes_)\n",
        "\n",
        "# Check for out-of-bounds indices in y_train and y_test\n",
        "print(\"Maximum value in y_train:\", y_train.max())\n",
        "print(\"Maximum value in y_test:\", y_test.max())\n",
        "print(\"Number of unique titles:\", num_unique_titles)\n",
        "\n",
        "# If any out-of-bounds values are found, print them\n",
        "out_of_bounds_train = y_train[y_train >= num_unique_titles]\n",
        "out_of_bounds_test = y_test[y_test >= num_unique_titles]\n",
        "\n",
        "if not out_of_bounds_train.empty:\n",
        "    print(\"Out-of-bounds values in y_train:\", out_of_bounds_train)\n",
        "if not out_of_bounds_test.empty:\n",
        "    print(\"Out-of-bounds values in y_test:\", out_of_bounds_test)\n",
        "\n",
        "# Fix out-of-bounds values by setting them to a valid index\n",
        "y_train = y_train.clip(upper=num_unique_titles - 1)\n",
        "y_test = y_test.clip(upper=num_unique_titles - 1)\n",
        "\n",
        "# Print the maximum values after clipping\n",
        "print(\"Maximum value in y_train after clipping:\", y_train.max())\n",
        "print(\"Maximum value in y_test after clipping:\", y_test.max())\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "syYhdUbxgA-K"
      },
      "source": [
        "# **Training**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aaR1IGymKQq2",
        "outputId": "9e5115a5-1a75-4672-a0b3-4fdd314e1a79"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Epoch 1, Training Loss: 8.921830113728841, Validation Loss: 8.836441385979747\n",
            "Epoch 2, Training Loss: 8.331391870239635, Validation Loss: 9.148561271966672\n",
            "Epoch 3, Training Loss: 7.494005516429007, Validation Loss: 10.484928570541681\n",
            "Epoch 4, Training Loss: 6.704833826606657, Validation Loss: 11.745069999320835\n",
            "Early stopping triggered\n",
            "Improved model trained and saved successfully.\n"
          ]
        }
      ],
      "source": [
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "from torch.utils.data import DataLoader\n",
        "import numpy as np\n",
        "\n",
        "# Define the neural network model with Dropout and Batch Normalization\n",
        "class ImprovedSongRecommender(nn.Module):\n",
        "    def __init__(self, input_size, num_titles):\n",
        "        super(ImprovedSongRecommender, self).__init__()\n",
        "        self.fc1 = nn.Linear(input_size, 128)\n",
        "        self.bn1 = nn.BatchNorm1d(128)\n",
        "        self.fc2 = nn.Linear(128, 256)\n",
        "        self.bn2 = nn.BatchNorm1d(256)\n",
        "        self.fc3 = nn.Linear(256, 128)\n",
        "        self.bn3 = nn.BatchNorm1d(128)\n",
        "        self.output = nn.Linear(128, num_titles)\n",
        "        self.dropout = nn.Dropout(0.5)\n",
        "\n",
        "    def forward(self, x):\n",
        "        x = torch.relu(self.bn1(self.fc1(x)))\n",
        "        x = self.dropout(x)\n",
        "        x = torch.relu(self.bn2(self.fc2(x)))\n",
        "        x = self.dropout(x)\n",
        "        x = torch.relu(self.bn3(self.fc3(x)))\n",
        "        x = self.dropout(x)\n",
        "        x = self.output(x)\n",
        "        return x\n",
        "\n",
        "# Adjusting input size for the model\n",
        "input_size = X_train.shape[1]  # Number of features in the input\n",
        "num_unique_titles = len(label_encoders['title'].classes_)  # Number of unique titles including 'unknown'\n",
        "\n",
        "# Initialize the model with the correct input size and output size\n",
        "model = ImprovedSongRecommender(input_size, num_unique_titles)\n",
        "\n",
        "# Initialize the optimizer and loss function\n",
        "optimizer = optim.AdamW(model.parameters(), lr=0.001, weight_decay=0.01)\n",
        "criterion = nn.CrossEntropyLoss()\n",
        "\n",
        "# Use a learning rate scheduler\n",
        "scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=3, gamma=0.1)\n",
        "\n",
        "# Early stopping parameters\n",
        "patience = 3\n",
        "min_delta = 0.01\n",
        "best_val_loss = np.inf\n",
        "patience_counter = 0\n",
        "\n",
        "# Function to train the model\n",
        "def train_model(model, X_train, y_train, X_test, y_test):\n",
        "    global best_val_loss, patience_counter\n",
        "    train_loader = DataLoader(list(zip(X_train.values.astype(float), y_train)), batch_size=10, shuffle=True)\n",
        "    test_loader = DataLoader(list(zip(X_test.values.astype(float), y_test)), batch_size=10, shuffle=False)\n",
        "\n",
        "    model.train()\n",
        "    for epoch in range(20):  # Increase the number of epochs\n",
        "        train_loss = 0\n",
        "        for features, labels in train_loader:\n",
        "            optimizer.zero_grad()\n",
        "            outputs = model(features.float())\n",
        "            loss = criterion(outputs, labels.long())\n",
        "            loss.backward()\n",
        "            optimizer.step()\n",
        "            train_loss += loss.item()\n",
        "\n",
        "        # Step the scheduler\n",
        "        scheduler.step()\n",
        "\n",
        "        # Validation phase\n",
        "        model.eval()\n",
        "        validation_loss = 0\n",
        "        with torch.no_grad():\n",
        "            for features, labels in test_loader:\n",
        "                outputs = model(features.float())\n",
        "                loss = criterion(outputs, labels.long())\n",
        "                validation_loss += loss.item()\n",
        "\n",
        "        avg_val_loss = validation_loss / len(test_loader)\n",
        "        print(f'Epoch {epoch+1}, Training Loss: {train_loss / len(train_loader)}, Validation Loss: {avg_val_loss}')\n",
        "\n",
        "        # Early stopping\n",
        "        if avg_val_loss < best_val_loss - min_delta:\n",
        "            best_val_loss = avg_val_loss\n",
        "            patience_counter = 0\n",
        "        else:\n",
        "            patience_counter += 1\n",
        "            if patience_counter >= patience:\n",
        "                print(\"Early stopping triggered\")\n",
        "                break\n",
        "\n",
        "# Train the model\n",
        "train_model(model, X_train, y_train, X_test, y_test)\n",
        "\n",
        "# Save the trained model\n",
        "model_path = '/content/improved_model.pth'\n",
        "torch.save(model.state_dict(), model_path)\n",
        "\n",
        "print(\"Improved model trained and saved successfully.\")\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "g4hJVlNXf5Vu"
      },
      "source": [
        "# **Testing**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KwqV-HnCOvtz",
        "outputId": "d412ce92-3ab8-4f3d-df83-22ef9e857203"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Recommendations: ['Betrayal Is A Symptom', 'The Earth Will Shake', 'Saturday', 'Firehouse Rock', 'Breathe Easy']\n"
          ]
        }
      ],
      "source": [
        "import torch\n",
        "from joblib import load\n",
        "\n",
        "# Define the same neural network model\n",
        "class ImprovedSongRecommender(nn.Module):\n",
        "    def __init__(self, input_size, num_titles):\n",
        "        super(ImprovedSongRecommender, self).__init__()\n",
        "        self.fc1 = nn.Linear(input_size, 128)\n",
        "        self.bn1 = nn.BatchNorm1d(128)\n",
        "        self.fc2 = nn.Linear(128, 256)\n",
        "        self.bn2 = nn.BatchNorm1d(256)\n",
        "        self.fc3 = nn.Linear(256, 128)\n",
        "        self.bn3 = nn.BatchNorm1d(128)\n",
        "        self.output = nn.Linear(128, num_titles)\n",
        "        self.dropout = nn.Dropout(0.5)\n",
        "\n",
        "    def forward(self, x):\n",
        "        x = torch.relu(self.bn1(self.fc1(x)))\n",
        "        x = self.dropout(x)\n",
        "        x = torch.relu(self.bn2(self.fc2(x)))\n",
        "        x = self.dropout(x)\n",
        "        x = torch.relu(self.bn3(self.fc3(x)))\n",
        "        x = self.dropout(x)\n",
        "        x = self.output(x)\n",
        "        return x\n",
        "\n",
        "# Load the trained model\n",
        "model_path = '/content/improved_model.pth'\n",
        "num_unique_titles = 4855  # Update this to match your dataset\n",
        "\n",
        "model = ImprovedSongRecommender(input_size=2, num_titles=num_unique_titles)  # Adjust input size accordingly\n",
        "model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')))\n",
        "model.eval()\n",
        "\n",
        "# Load the label encoders and scaler\n",
        "label_encoders_path = '/content/new_label_encoders.joblib'\n",
        "scaler_path = '/content/new_scaler.joblib'\n",
        "\n",
        "label_encoders = load(label_encoders_path)\n",
        "scaler = load(scaler_path)\n",
        "\n",
        "# Create a mapping from encoded indices to actual song titles\n",
        "index_to_song_title = {index: title for index, title in enumerate(label_encoders['title'].classes_)}\n",
        "\n",
        "def encode_input(tags, artist_name):\n",
        "    tags = tags.strip().replace('\\n', '')\n",
        "    artist_name = artist_name.strip().replace('\\n', '')\n",
        "\n",
        "    try:\n",
        "        encoded_tags = label_encoders['tags'].transform([tags])[0]\n",
        "    except ValueError:\n",
        "        encoded_tags = label_encoders['tags'].transform(['unknown'])[0]\n",
        "\n",
        "    try:\n",
        "        encoded_artist = label_encoders['artist_name'].transform([artist_name])[0]\n",
        "    except ValueError:\n",
        "        encoded_artist = label_encoders['artist_name'].transform(['unknown'])[0]\n",
        "\n",
        "    return [encoded_tags, encoded_artist]\n",
        "\n",
        "def recommend_songs(tags, artist_name):\n",
        "    encoded_input = encode_input(tags, artist_name)\n",
        "    input_tensor = torch.tensor([encoded_input]).float()\n",
        "\n",
        "    with torch.no_grad():\n",
        "        output = model(input_tensor)\n",
        "\n",
        "    recommendations_indices = torch.topk(output, 5).indices.squeeze().tolist()\n",
        "    recommendations = [index_to_song_title.get(idx, \"Unknown song\") for idx in recommendations_indices]\n",
        "\n",
        "    return recommendations\n",
        "\n",
        "# Test the recommendation function\n",
        "tags = \"rock\"\n",
        "artist_name = \"The Beatles\"\n",
        "\n",
        "recommendations = recommend_songs(tags, artist_name)\n",
        "print(\"Recommendations:\", recommendations)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3HzLKv5mPxOv",
        "outputId": "62b37d04-4857-44fb-b5c4-8ead55db9b1a"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Recommendations: ['Betrayal Is A Symptom', 'Carnival (from \"Black Orpheus\")', 'Saturday', 'The Earth Will Shake', 'Start!']\n",
            "Recommendations: ['Old Friends', 'Betrayal Is A Symptom', 'Between Love & Hate', 'Carnival (from \"Black Orpheus\")', 'Satin Doll']\n"
          ]
        }
      ],
      "source": [
        "import torch\n",
        "from joblib import load\n",
        "\n",
        "# Define the same neural network model\n",
        "class ImprovedSongRecommender(nn.Module):\n",
        "    def __init__(self, input_size, num_titles):\n",
        "        super(ImprovedSongRecommender, self).__init__()\n",
        "        self.fc1 = nn.Linear(input_size, 128)\n",
        "        self.bn1 = nn.BatchNorm1d(128)\n",
        "        self.fc2 = nn.Linear(128, 256)\n",
        "        self.bn2 = nn.BatchNorm1d(256)\n",
        "        self.fc3 = nn.Linear(256, 128)\n",
        "        self.bn3 = nn.BatchNorm1d(128)\n",
        "        self.output = nn.Linear(128, num_titles)\n",
        "        self.dropout = nn.Dropout(0.5)\n",
        "\n",
        "    def forward(self, x):\n",
        "        x = torch.relu(self.bn1(self.fc1(x)))\n",
        "        x = self.dropout(x)\n",
        "        x = torch.relu(self.bn2(self.fc2(x)))\n",
        "        x = self.dropout(x)\n",
        "        x = torch.relu(self.bn3(self.fc3(x)))\n",
        "        x = self.dropout(x)\n",
        "        x = self.output(x)\n",
        "        return x\n",
        "\n",
        "# Load the trained model\n",
        "model_path = '/content/improved_model.pth'\n",
        "num_unique_titles = 4855  # Update this to match your dataset\n",
        "\n",
        "model = ImprovedSongRecommender(input_size=2, num_titles=num_unique_titles)  # Adjust input size accordingly\n",
        "model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')))\n",
        "model.eval()\n",
        "\n",
        "# Load the label encoders and scaler\n",
        "label_encoders_path = '/content/new_label_encoders.joblib'\n",
        "scaler_path = '/content/new_scaler.joblib'\n",
        "\n",
        "label_encoders = load(label_encoders_path)\n",
        "scaler = load(scaler_path)\n",
        "\n",
        "# Create a mapping from encoded indices to actual song titles\n",
        "index_to_song_title = {index: title for index, title in enumerate(label_encoders['title'].classes_)}\n",
        "\n",
        "def encode_input(tags, artist_name):\n",
        "    tags = tags.strip().replace('\\n', '')\n",
        "    artist_name = artist_name.strip().replace('\\n', '')\n",
        "\n",
        "    try:\n",
        "        encoded_tags = label_encoders['tags'].transform([tags])[0]\n",
        "    except ValueError:\n",
        "        encoded_tags = label_encoders['tags'].transform(['unknown'])[0]\n",
        "\n",
        "    try:\n",
        "        encoded_artist = label_encoders['artist_name'].transform([artist_name])[0]\n",
        "    except ValueError:\n",
        "        encoded_artist = label_encoders['artist_name'].transform(['unknown'])[0]\n",
        "\n",
        "    return [encoded_tags, encoded_artist]\n",
        "\n",
        "def recommend_songs(tags, artist_name):\n",
        "    encoded_input = encode_input(tags, artist_name)\n",
        "    input_tensor = torch.tensor([encoded_input]).float()\n",
        "\n",
        "    with torch.no_grad():\n",
        "        output = model(input_tensor)\n",
        "\n",
        "    recommendations_indices = torch.topk(output, 5).indices.squeeze().tolist()\n",
        "    recommendations = [index_to_song_title.get(idx, \"Unknown song\") for idx in recommendations_indices]\n",
        "\n",
        "    return recommendations\n",
        "\n",
        "# Test the recommendation function with new inputs\n",
        "tags = \"pop\"\n",
        "artist_name = \"Adele\"\n",
        "\n",
        "recommendations = recommend_songs(tags, artist_name)\n",
        "print(\"Recommendations:\", recommendations)\n",
        "\n",
        "# Test with another set of inputs\n",
        "tags = \"jazz\"\n",
        "artist_name = \"Miles Davis\"\n",
        "\n",
        "recommendations = recommend_songs(tags, artist_name)\n",
        "print(\"Recommendations:\", recommendations)\n"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.8.1"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}