Upload 22 files

.cache

@@ -0,0 +1 @@
+{"access_token": "BQD363D2V0DfTblE6WIENGJmMsHEwAK6fQ2iitJsDHaE6q-likgolb74XQUSq1EH4YC_1MsegenNN3ysZdjQT2SSXbXPbrlxWMvUiQWg-PxmX66T6NM", "token_type": "Bearer", "expires_in": 3600, "expires_at": 1719793255}

.cache22

@@ -0,0 +1 @@
+{"access_token": "BQCCSbvf9rV9on-exkGuwqveHa6SLR-wuLUwXJfApJQXQ9AKN7TYOPaaotvikq3nFJJ1aI_IPiSm3-Mi-vpd9W_NcwNJbj09ALJEpIEo8oW_5LZXNVI", "token_type": "Bearer", "expires_in": 3600, "expires_at": 1719792377}

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/data_clean.csv filter=lfs diff=lfs merge=lfs -text
+data/data_model.csv filter=lfs diff=lfs merge=lfs -text
+data/data.csv filter=lfs diff=lfs merge=lfs -text

ModellingPSD.ipynb

@@ -0,0 +1,1182 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "K6Ek26jtEbzM"
+      },
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "import ast\n",
+        "\n",
+        "from sklearn.compose import ColumnTransformer\n",
+        "from sklearn.pipeline import Pipeline\n",
+        "from sklearn.preprocessing import StandardScaler\n",
+        "from sklearn.cluster import KMeans\n",
+        "from sklearn.feature_extraction import FeatureHasher\n",
+        "\n",
+        "from scipy.spatial.distance import cdist\n",
+        "import numpy as np"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "jSok_FhgFQPa"
+      },
+      "outputs": [],
+      "source": [
+        "df = pd.read_csv('data/data_clean.csv')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "id": "fjlzGblwZiyl"
+      },
+      "outputs": [],
+      "source": [
+        "df['artists'] = df['artists'].apply(ast.literal_eval)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "JHmNLOXKFqEE",
+        "outputId": "6536ca09-4f23-4563-f4b3-99385f4272ec"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "Index(['valence', 'year', 'acousticness', 'artists', 'danceability',\n",
+              "       'duration_ms', 'energy', 'id', 'instrumentalness', 'key', 'liveness',\n",
+              "       'loudness', 'mode', 'name', 'popularity', 'speechiness', 'tempo'],\n",
+              "      dtype='object')"
+            ]
+          },
+          "execution_count": 4,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df.columns"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {
+        "id": "27JWURjxZiyl"
+      },
+      "outputs": [],
+      "source": [
+        "DF_COLUMNS = ['valence', 'year', 'acousticness', 'artists', 'danceability',\n",
+        "       'duration_ms', 'energy', 'id', 'instrumentalness', 'key',\n",
+        "       'liveness', 'loudness', 'mode', 'name', 'popularity', 'release_date',\n",
+        "       'speechiness', 'tempo']\n",
+        "DF_COLUMNS_MODEL = ['valence', 'year', 'acousticness','artists', 'danceability',\n",
+        "         'duration_ms', 'energy', 'instrumentalness', 'key',\n",
+        "         'liveness', 'loudness', 'mode', 'popularity', 'speechiness', 'tempo']"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "metadata": {
+        "id": "PasM5_-tZiyl"
+      },
+      "outputs": [],
+      "source": [
+        "\n",
+        "# Kolom yang akan di-hash\n",
+        "hash_columns = 'artists'\n",
+        "\n",
+        "# Inisialisasi FeatureHasher untuk kolom tertentu\n",
+        "hasher = FeatureHasher(n_features=10, input_type=\"string\")\n",
+        "\n",
+        "# Inisialisasi StandardScaler\n",
+        "scaler = StandardScaler()\n",
+        "\n",
+        "# Inisialisasi KMeans\n",
+        "kmeans = KMeans(n_clusters=10)\n",
+        "\n",
+        "# Definisikan transformer untuk hashing kolom tertentu\n",
+        "hash_transformer = ('hasher', hasher, hash_columns)\n",
+        "\n",
+        "# Definisikan transformer untuk kolom yang tidak di-hash\n",
+        "remainder_transformer = ('passthrough', 'remainder', slice(0, 0))\n",
+        "\n",
+        "# Gabungkan transformer untuk semua kolom\n",
+        "preprocessor = ColumnTransformer(\n",
+        "    transformers=[hash_transformer],\n",
+        "    remainder='passthrough')\n",
+        "\n",
+        "# Gabungkan preprocessor dengan algoritma clustering (KMeans)\n",
+        "pipeline = Pipeline([\n",
+        "    ('preprocessor', preprocessor),\n",
+        "    ('scaler', scaler),\n",
+        "    ('kmeans', kmeans)\n",
+        "])"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 26,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 283
+        },
+        "id": "8GPu5AWiZiym",
+        "outputId": "2d8d35c1-a5ba-4504-87f8-98cae876fe90"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<style>#sk-container-id-2 {\n",
+              "  /* Definition of color scheme common for light and dark mode */\n",
+              "  --sklearn-color-text: black;\n",
+              "  --sklearn-color-line: gray;\n",
+              "  /* Definition of color scheme for unfitted estimators */\n",
+              "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+              "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+              "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+              "  --sklearn-color-unfitted-level-3: chocolate;\n",
+              "  /* Definition of color scheme for fitted estimators */\n",
+              "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+              "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+              "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+              "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+              "\n",
+              "  /* Specific color for light theme */\n",
+              "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+              "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+              "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+              "  --sklearn-color-icon: #696969;\n",
+              "\n",
+              "  @media (prefers-color-scheme: dark) {\n",
+              "    /* Redefinition of color scheme for dark theme */\n",
+              "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+              "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+              "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+              "    --sklearn-color-icon: #878787;\n",
+              "  }\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 pre {\n",
+              "  padding: 0;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 input.sk-hidden--visually {\n",
+              "  border: 0;\n",
+              "  clip: rect(1px 1px 1px 1px);\n",
+              "  clip: rect(1px, 1px, 1px, 1px);\n",
+              "  height: 1px;\n",
+              "  margin: -1px;\n",
+              "  overflow: hidden;\n",
+              "  padding: 0;\n",
+              "  position: absolute;\n",
+              "  width: 1px;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-dashed-wrapped {\n",
+              "  border: 1px dashed var(--sklearn-color-line);\n",
+              "  margin: 0 0.4em 0.5em 0.4em;\n",
+              "  box-sizing: border-box;\n",
+              "  padding-bottom: 0.4em;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-container {\n",
+              "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+              "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+              "     so we also need the `!important` here to be able to override the\n",
+              "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+              "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+              "  display: inline-block !important;\n",
+              "  position: relative;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-text-repr-fallback {\n",
+              "  display: none;\n",
+              "}\n",
+              "\n",
+              "div.sk-parallel-item,\n",
+              "div.sk-serial,\n",
+              "div.sk-item {\n",
+              "  /* draw centered vertical line to link estimators */\n",
+              "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+              "  background-size: 2px 100%;\n",
+              "  background-repeat: no-repeat;\n",
+              "  background-position: center center;\n",
+              "}\n",
+              "\n",
+              "/* Parallel-specific style estimator block */\n",
+              "\n",
+              "#sk-container-id-2 div.sk-parallel-item::after {\n",
+              "  content: \"\";\n",
+              "  width: 100%;\n",
+              "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+              "  flex-grow: 1;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-parallel {\n",
+              "  display: flex;\n",
+              "  align-items: stretch;\n",
+              "  justify-content: center;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "  position: relative;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-parallel-item {\n",
+              "  display: flex;\n",
+              "  flex-direction: column;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
+              "  align-self: flex-end;\n",
+              "  width: 50%;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
+              "  align-self: flex-start;\n",
+              "  width: 50%;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
+              "  width: 0;\n",
+              "}\n",
+              "\n",
+              "/* Serial-specific style estimator block */\n",
+              "\n",
+              "#sk-container-id-2 div.sk-serial {\n",
+              "  display: flex;\n",
+              "  flex-direction: column;\n",
+              "  align-items: center;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "  padding-right: 1em;\n",
+              "  padding-left: 1em;\n",
+              "}\n",
+              "\n",
+              "\n",
+              "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+              "clickable and can be expanded/collapsed.\n",
+              "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+              "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+              "*/\n",
+              "\n",
+              "/* Pipeline and ColumnTransformer style (default) */\n",
+              "\n",
+              "#sk-container-id-2 div.sk-toggleable {\n",
+              "  /* Default theme specific background. It is overwritten whether we have a\n",
+              "  specific estimator or a Pipeline/ColumnTransformer */\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "}\n",
+              "\n",
+              "/* Toggleable label */\n",
+              "#sk-container-id-2 label.sk-toggleable__label {\n",
+              "  cursor: pointer;\n",
+              "  display: block;\n",
+              "  width: 100%;\n",
+              "  margin-bottom: 0;\n",
+              "  padding: 0.5em;\n",
+              "  box-sizing: border-box;\n",
+              "  text-align: center;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
+              "  /* Arrow on the left of the label */\n",
+              "  content: \"▸\";\n",
+              "  float: left;\n",
+              "  margin-right: 0.25em;\n",
+              "  color: var(--sklearn-color-icon);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "}\n",
+              "\n",
+              "/* Toggleable content - dropdown */\n",
+              "\n",
+              "#sk-container-id-2 div.sk-toggleable__content {\n",
+              "  max-height: 0;\n",
+              "  max-width: 0;\n",
+              "  overflow: hidden;\n",
+              "  text-align: left;\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-toggleable__content pre {\n",
+              "  margin: 0.2em;\n",
+              "  border-radius: 0.25em;\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+              "  /* Expand drop-down */\n",
+              "  max-height: 200px;\n",
+              "  max-width: 100%;\n",
+              "  overflow: auto;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+              "  content: \"▾\";\n",
+              "}\n",
+              "\n",
+              "/* Pipeline/ColumnTransformer-specific style */\n",
+              "\n",
+              "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+              "  background-color: var(--sklearn-color-fitted-level-2);\n",
+              "}\n",
+              "\n",
+              "/* Estimator-specific style */\n",
+              "\n",
+              "/* Colorize estimator box */\n",
+              "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-2);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
+              "#sk-container-id-2 div.sk-label label {\n",
+              "  /* The background is the default theme color */\n",
+              "  color: var(--sklearn-color-text-on-default-background);\n",
+              "}\n",
+              "\n",
+              "/* On hover, darken the color of the background */\n",
+              "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+              "}\n",
+              "\n",
+              "/* Label box, darken color on hover, fitted */\n",
+              "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  background-color: var(--sklearn-color-fitted-level-2);\n",
+              "}\n",
+              "\n",
+              "/* Estimator label */\n",
+              "\n",
+              "#sk-container-id-2 div.sk-label label {\n",
+              "  font-family: monospace;\n",
+              "  font-weight: bold;\n",
+              "  display: inline-block;\n",
+              "  line-height: 1.2em;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-label-container {\n",
+              "  text-align: center;\n",
+              "}\n",
+              "\n",
+              "/* Estimator-specific */\n",
+              "#sk-container-id-2 div.sk-estimator {\n",
+              "  font-family: monospace;\n",
+              "  border: 1px dotted var(--sklearn-color-border-box);\n",
+              "  border-radius: 0.25em;\n",
+              "  box-sizing: border-box;\n",
+              "  margin-bottom: 0.5em;\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-estimator.fitted {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-0);\n",
+              "}\n",
+              "\n",
+              "/* on hover */\n",
+              "#sk-container-id-2 div.sk-estimator:hover {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-2);\n",
+              "}\n",
+              "\n",
+              "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+              "\n",
+              "/* Common style for \"i\" and \"?\" */\n",
+              "\n",
+              ".sk-estimator-doc-link,\n",
+              "a:link.sk-estimator-doc-link,\n",
+              "a:visited.sk-estimator-doc-link {\n",
+              "  float: right;\n",
+              "  font-size: smaller;\n",
+              "  line-height: 1em;\n",
+              "  font-family: monospace;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "  border-radius: 1em;\n",
+              "  height: 1em;\n",
+              "  width: 1em;\n",
+              "  text-decoration: none !important;\n",
+              "  margin-left: 1ex;\n",
+              "  /* unfitted */\n",
+              "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+              "  color: var(--sklearn-color-unfitted-level-1);\n",
+              "}\n",
+              "\n",
+              ".sk-estimator-doc-link.fitted,\n",
+              "a:link.sk-estimator-doc-link.fitted,\n",
+              "a:visited.sk-estimator-doc-link.fitted {\n",
+              "  /* fitted */\n",
+              "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+              "  color: var(--sklearn-color-fitted-level-1);\n",
+              "}\n",
+              "\n",
+              "/* On hover */\n",
+              "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+              ".sk-estimator-doc-link:hover,\n",
+              "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+              ".sk-estimator-doc-link:hover {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+              "  color: var(--sklearn-color-background);\n",
+              "  text-decoration: none;\n",
+              "}\n",
+              "\n",
+              "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+              ".sk-estimator-doc-link.fitted:hover,\n",
+              "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+              ".sk-estimator-doc-link.fitted:hover {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-3);\n",
+              "  color: var(--sklearn-color-background);\n",
+              "  text-decoration: none;\n",
+              "}\n",
+              "\n",
+              "/* Span, style for the box shown on hovering the info icon */\n",
+              ".sk-estimator-doc-link span {\n",
+              "  display: none;\n",
+              "  z-index: 9999;\n",
+              "  position: relative;\n",
+              "  font-weight: normal;\n",
+              "  right: .2ex;\n",
+              "  padding: .5ex;\n",
+              "  margin: .5ex;\n",
+              "  width: min-content;\n",
+              "  min-width: 20ex;\n",
+              "  max-width: 50ex;\n",
+              "  color: var(--sklearn-color-text);\n",
+              "  box-shadow: 2pt 2pt 4pt #999;\n",
+              "  /* unfitted */\n",
+              "  background: var(--sklearn-color-unfitted-level-0);\n",
+              "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+              "}\n",
+              "\n",
+              ".sk-estimator-doc-link.fitted span {\n",
+              "  /* fitted */\n",
+              "  background: var(--sklearn-color-fitted-level-0);\n",
+              "  border: var(--sklearn-color-fitted-level-3);\n",
+              "}\n",
+              "\n",
+              ".sk-estimator-doc-link:hover span {\n",
+              "  display: block;\n",
+              "}\n",
+              "\n",
+              "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+              "\n",
+              "#sk-container-id-2 a.estimator_doc_link {\n",
+              "  float: right;\n",
+              "  font-size: 1rem;\n",
+              "  line-height: 1em;\n",
+              "  font-family: monospace;\n",
+              "  background-color: var(--sklearn-color-background);\n",
+              "  border-radius: 1rem;\n",
+              "  height: 1rem;\n",
+              "  width: 1rem;\n",
+              "  text-decoration: none;\n",
+              "  /* unfitted */\n",
+              "  color: var(--sklearn-color-unfitted-level-1);\n",
+              "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
+              "  /* fitted */\n",
+              "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+              "  color: var(--sklearn-color-fitted-level-1);\n",
+              "}\n",
+              "\n",
+              "/* On hover */\n",
+              "#sk-container-id-2 a.estimator_doc_link:hover {\n",
+              "  /* unfitted */\n",
+              "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+              "  color: var(--sklearn-color-background);\n",
+              "  text-decoration: none;\n",
+              "}\n",
+              "\n",
+              "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
+              "  /* fitted */\n",
+              "  background-color: var(--sklearn-color-fitted-level-3);\n",
+              "}\n",
+              "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;preprocessor&#x27;,\n",
+              "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
+              "                                   transformers=[(&#x27;hasher&#x27;,\n",
+              "                                                  FeatureHasher(input_type=&#x27;string&#x27;,\n",
+              "                                                                n_features=10),\n",
+              "                                                  &#x27;artists&#x27;)])),\n",
+              "                (&#x27;scaler&#x27;, StandardScaler()),\n",
+              "                (&#x27;kmeans&#x27;, KMeans(n_clusters=10))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;Pipeline<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.pipeline.Pipeline.html\">?<span>Documentation for Pipeline</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>Pipeline(steps=[(&#x27;preprocessor&#x27;,\n",
+              "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
+              "                                   transformers=[(&#x27;hasher&#x27;,\n",
+              "                                                  FeatureHasher(input_type=&#x27;string&#x27;,\n",
+              "                                                                n_features=10),\n",
+              "                                                  &#x27;artists&#x27;)])),\n",
+              "                (&#x27;scaler&#x27;, StandardScaler()),\n",
+              "                (&#x27;kmeans&#x27;, KMeans(n_clusters=10))])</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;preprocessor: ColumnTransformer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.compose.ColumnTransformer.html\">?<span>Documentation for preprocessor: ColumnTransformer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
+              "                  transformers=[(&#x27;hasher&#x27;,\n",
+              "                                 FeatureHasher(input_type=&#x27;string&#x27;,\n",
+              "                                               n_features=10),\n",
+              "                                 &#x27;artists&#x27;)])</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" ><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">hasher</label><div class=\"sk-toggleable__content fitted\"><pre>artists</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" ><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;FeatureHasher<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.feature_extraction.FeatureHasher.html\">?<span>Documentation for FeatureHasher</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>FeatureHasher(input_type=&#x27;string&#x27;, n_features=10)</pre></div> </div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-13\" type=\"checkbox\" ><label for=\"sk-estimator-id-13\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">remainder</label><div class=\"sk-toggleable__content fitted\"><pre>[&#x27;valence&#x27;, &#x27;year&#x27;, &#x27;acousticness&#x27;, &#x27;danceability&#x27;, &#x27;duration_ms&#x27;, &#x27;energy&#x27;, &#x27;instrumentalness&#x27;, &#x27;key&#x27;, &#x27;liveness&#x27;, &#x27;loudness&#x27;, &#x27;mode&#x27;, &#x27;popularity&#x27;, &#x27;speechiness&#x27;, &#x27;tempo&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-14\" type=\"checkbox\" ><label for=\"sk-estimator-id-14\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">passthrough</label><div class=\"sk-toggleable__content fitted\"><pre>passthrough</pre></div> </div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-15\" type=\"checkbox\" ><label for=\"sk-estimator-id-15\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;StandardScaler<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.preprocessing.StandardScaler.html\">?<span>Documentation for StandardScaler</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>StandardScaler()</pre></div> </div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-16\" type=\"checkbox\" ><label for=\"sk-estimator-id-16\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;KMeans<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.cluster.KMeans.html\">?<span>Documentation for KMeans</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>KMeans(n_clusters=10)</pre></div> </div></div></div></div></div></div>"
+            ],
+            "text/plain": [
+              "Pipeline(steps=[('preprocessor',\n",
+              "                 ColumnTransformer(remainder='passthrough',\n",
+              "                                   transformers=[('hasher',\n",
+              "                                                  FeatureHasher(input_type='string',\n",
+              "                                                                n_features=10),\n",
+              "                                                  'artists')])),\n",
+              "                ('scaler', StandardScaler()),\n",
+              "                ('kmeans', KMeans(n_clusters=10))])"
+            ]
+          },
+          "execution_count": 26,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "pipeline.fit(df[DF_COLUMNS_MODEL])"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 27,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "['model/pipeline.pkl']"
+            ]
+          },
+          "execution_count": 27,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "# export pipeline\n",
+        "import joblib\n",
+        "joblib.dump(pipeline, 'model/pipeline.pkl')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 28,
+      "metadata": {
+        "id": "vjExO0EvpCsT"
+      },
+      "outputs": [],
+      "source": [
+        "import yaml\n",
+        "import spotipy\n",
+        "from spotipy.oauth2 import SpotifyOAuth,SpotifyClientCredentials\n",
+        "\n",
+        "stream= open(\"streamlit/spotify/spotify.yaml\")\n",
+        "spotify_details = yaml.safe_load(stream)\n",
+        "auth_manager = SpotifyClientCredentials(client_id=spotify_details['Client_id'],\n",
+        "                                        client_secret=spotify_details['client_secret'])\n",
+        "\n",
+        "sp = spotipy.client.Spotify(auth_manager=auth_manager)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 29,
+      "metadata": {
+        "id": "ZTyFQkq0y7-J"
+      },
+      "outputs": [],
+      "source": [
+        "def get_song_spotify(song_name, data):\n",
+        "    log = open('log.txt','w')\n",
+        "    try:\n",
+        "        result = sp.search(q=song_name, limit=1)\n",
+        "    except:\n",
+        "        log.write('Error: Failed to search song')\n",
+        "        return None\n",
+        "\n",
+        "    if result['tracks']['items'] == []:\n",
+        "        return None\n",
+        "\n",
+        "    song = result['tracks']['items'][0]\n",
+        "\n",
+        "    id = song['id']\n",
+        "\n",
+        "    try:\n",
+        "        song_data = data[(data['id'] == id)].iloc[0]\n",
+        "        return song_data\n",
+        "    except:\n",
+        "        try:\n",
+        "            audio_features = sp.audio_features(id)\n",
+        "            song_data = {\n",
+        "                'valence': audio_features[0]['valence'],\n",
+        "                \"year\" : result['tracks']['items'][0]['album']['release_date'][:4],\n",
+        "                'acousticness': audio_features[0]['acousticness'],\n",
+        "                'artists': list(map(lambda x: x['name'], result['tracks']['items'][0]['artists'])),\n",
+        "                'danceability': audio_features[0]['danceability'],\n",
+        "                'duration_ms': audio_features[0]['duration_ms'],\n",
+        "                'energy': audio_features[0]['energy'],\n",
+        "                'id': id,\n",
+        "                'instrumentalness': audio_features[0]['instrumentalness'],\n",
+        "                'key': audio_features[0]['key'],\n",
+        "                'liveness': audio_features[0]['liveness'],\n",
+        "                'loudness': audio_features[0]['loudness'],\n",
+        "                'mode': audio_features[0]['mode'],\n",
+        "                'name': result['tracks']['items'][0]['name'],\n",
+        "                'popularity': result['tracks']['items'][0]['popularity'],\n",
+        "                'speechiness': audio_features[0]['speechiness'],\n",
+        "                'tempo': audio_features[0]['tempo']\n",
+        "            }\n",
+        "        except:\n",
+        "            log.write('Error: Failed to get audio features from Spotify')\n",
+        "            return None\n",
+        "\n",
+        "        return pd.DataFrame([song_data], columns=DF_COLUMNS).iloc[0]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 30,
+      "metadata": {
+        "id": "j2u3jFFly-aI"
+      },
+      "outputs": [],
+      "source": [
+        "def get_song_data(song_name, data):\n",
+        "    try:\n",
+        "        song_data = data[(data['name'] == song_name)].iloc[0]\n",
+        "        return song_data\n",
+        "    except:\n",
+        "        return get_song_spotify(song_name,data)\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 31,
+      "metadata": {
+        "id": "C0rZKlkq2pyH"
+      },
+      "outputs": [],
+      "source": [
+        "def df_song_data(list_song_name,data):\n",
+        "    rows_song_data = list()\n",
+        "    for song_name in list_song_name:\n",
+        "        rows_song_data.append(get_song_data(song_name,data))\n",
+        "\n",
+        "    return pd.DataFrame(rows_song_data,columns=DF_COLUMNS)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 32,
+      "metadata": {
+        "id": "aJ2LCdi-SvMv"
+      },
+      "outputs": [],
+      "source": [
+        "\n",
+        "def songs_recommendation(list_song_name,data,num_rec=10):\n",
+        "\n",
+        "    song_data_input = df_song_data(list_song_name,df)\n",
+        "\n",
+        "    vector = pipeline.named_steps[\"preprocessor\"].transform(df_song_data(list_song_name,data))\n",
+        "    vector = pipeline.named_steps[\"scaler\"].transform(vector)\n",
+        "\n",
+        "    vector = vector.mean(axis=0)\n",
+        "\n",
+        "    predicted_cluster = pipeline.named_steps[\"kmeans\"].predict([vector])\n",
+        "\n",
+        "    cluster_data = df[pipeline.named_steps[\"kmeans\"].labels_ == predicted_cluster[0]]\n",
+        "\n",
+        "    vector_cluster = pipeline.named_steps[\"preprocessor\"].transform(cluster_data)\n",
+        "    vector_cluster = pipeline.named_steps[\"scaler\"].transform(vector_cluster)\n",
+        "\n",
+        "    distance = cdist([vector],vector_cluster)\n",
+        "    index = list(np.argsort(distance)[:, :num_rec][0])\n",
+        "\n",
+        "    recsongs = cluster_data.iloc[index]\n",
+        "    recsongs = recsongs[~recsongs['name'].isin(list_song_name)]\n",
+        "    return song_data_input,recsongs\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 33,
+      "metadata": {
+        "id": "RtmQZUDBK6uw"
+      },
+      "outputs": [],
+      "source": [
+        "input,output = songs_recommendation(['505'],df)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 34,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 118
+        },
+        "id": "W8ZxWwofXA35",
+        "outputId": "cbd93a6a-ea55-42bf-91b8-5cbd6f8b8015"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<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>valence</th>\n",
+              "      <th>year</th>\n",
+              "      <th>acousticness</th>\n",
+              "      <th>artists</th>\n",
+              "      <th>danceability</th>\n",
+              "      <th>duration_ms</th>\n",
+              "      <th>energy</th>\n",
+              "      <th>id</th>\n",
+              "      <th>instrumentalness</th>\n",
+              "      <th>key</th>\n",
+              "      <th>liveness</th>\n",
+              "      <th>loudness</th>\n",
+              "      <th>mode</th>\n",
+              "      <th>name</th>\n",
+              "      <th>popularity</th>\n",
+              "      <th>release_date</th>\n",
+              "      <th>speechiness</th>\n",
+              "      <th>tempo</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>17006</th>\n",
+              "      <td>0.234</td>\n",
+              "      <td>2007</td>\n",
+              "      <td>0.00237</td>\n",
+              "      <td>[Arctic Monkeys]</td>\n",
+              "      <td>0.52</td>\n",
+              "      <td>253587</td>\n",
+              "      <td>0.852</td>\n",
+              "      <td>58ge6dfP91o9oXMzq3XkIS</td>\n",
+              "      <td>0.000058</td>\n",
+              "      <td>0</td>\n",
+              "      <td>0.0733</td>\n",
+              "      <td>-5.866</td>\n",
+              "      <td>1</td>\n",
+              "      <td>505</td>\n",
+              "      <td>76</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>0.0543</td>\n",
+              "      <td>140.267</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "       valence  year  acousticness           artists  danceability  \\\n",
+              "17006    0.234  2007       0.00237  [Arctic Monkeys]          0.52   \n",
+              "\n",
+              "       duration_ms  energy                      id  instrumentalness  key  \\\n",
+              "17006       253587   0.852  58ge6dfP91o9oXMzq3XkIS          0.000058    0   \n",
+              "\n",
+              "       liveness  loudness  mode name  popularity  release_date  speechiness  \\\n",
+              "17006    0.0733    -5.866     1  505          76           NaN       0.0543   \n",
+              "\n",
+              "         tempo  \n",
+              "17006  140.267  "
+            ]
+          },
+          "execution_count": 34,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "input"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 35,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 543
+        },
+        "id": "2z40QSBSXDEW",
+        "outputId": "3b3c4c68-009c-4094-c812-0f4fdfbc5ad1"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<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>valence</th>\n",
+              "      <th>year</th>\n",
+              "      <th>acousticness</th>\n",
+              "      <th>artists</th>\n",
+              "      <th>danceability</th>\n",
+              "      <th>duration_ms</th>\n",
+              "      <th>energy</th>\n",
+              "      <th>id</th>\n",
+              "      <th>instrumentalness</th>\n",
+              "      <th>key</th>\n",
+              "      <th>liveness</th>\n",
+              "      <th>loudness</th>\n",
+              "      <th>mode</th>\n",
+              "      <th>name</th>\n",
+              "      <th>popularity</th>\n",
+              "      <th>speechiness</th>\n",
+              "      <th>tempo</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>18509</th>\n",
+              "      <td>0.293</td>\n",
+              "      <td>2014</td>\n",
+              "      <td>0.000501</td>\n",
+              "      <td>[Young the Giant]</td>\n",
+              "      <td>0.466</td>\n",
+              "      <td>244693</td>\n",
+              "      <td>0.763</td>\n",
+              "      <td>5Az8KU81g2aLBbJN67F2CI</td>\n",
+              "      <td>0.00000</td>\n",
+              "      <td>0</td>\n",
+              "      <td>0.0973</td>\n",
+              "      <td>-4.448</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Mind Over Matter</td>\n",
+              "      <td>69</td>\n",
+              "      <td>0.0318</td>\n",
+              "      <td>154.914</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>18039</th>\n",
+              "      <td>0.370</td>\n",
+              "      <td>2012</td>\n",
+              "      <td>0.126000</td>\n",
+              "      <td>[One Direction]</td>\n",
+              "      <td>0.514</td>\n",
+              "      <td>200400</td>\n",
+              "      <td>0.727</td>\n",
+              "      <td>6M31fPFCYB8Job3MCjjrDV</td>\n",
+              "      <td>0.00000</td>\n",
+              "      <td>0</td>\n",
+              "      <td>0.0978</td>\n",
+              "      <td>-6.131</td>\n",
+              "      <td>1</td>\n",
+              "      <td>They Don't Know About Us</td>\n",
+              "      <td>79</td>\n",
+              "      <td>0.0492</td>\n",
+              "      <td>147.917</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>108337</th>\n",
+              "      <td>0.285</td>\n",
+              "      <td>2018</td>\n",
+              "      <td>0.103000</td>\n",
+              "      <td>[BTS]</td>\n",
+              "      <td>0.541</td>\n",
+              "      <td>275696</td>\n",
+              "      <td>0.661</td>\n",
+              "      <td>2tMBCYj22KxtmkAACIvvk4</td>\n",
+              "      <td>0.00000</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0.0779</td>\n",
+              "      <td>-5.838</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Magic Shop</td>\n",
+              "      <td>72</td>\n",
+              "      <td>0.0889</td>\n",
+              "      <td>149.926</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>17405</th>\n",
+              "      <td>0.205</td>\n",
+              "      <td>2008</td>\n",
+              "      <td>0.000354</td>\n",
+              "      <td>[Nickelback]</td>\n",
+              "      <td>0.536</td>\n",
+              "      <td>252653</td>\n",
+              "      <td>0.890</td>\n",
+              "      <td>06T10fEzN8ZCcqzQZYA184</td>\n",
+              "      <td>0.00165</td>\n",
+              "      <td>0</td>\n",
+              "      <td>0.1330</td>\n",
+              "      <td>-5.222</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Gotta Be Somebody</td>\n",
+              "      <td>63</td>\n",
+              "      <td>0.0601</td>\n",
+              "      <td>115.998</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>140275</th>\n",
+              "      <td>0.285</td>\n",
+              "      <td>2018</td>\n",
+              "      <td>0.103000</td>\n",
+              "      <td>[BTS]</td>\n",
+              "      <td>0.541</td>\n",
+              "      <td>275696</td>\n",
+              "      <td>0.661</td>\n",
+              "      <td>22ryCgQttpV7oCrn7llGRu</td>\n",
+              "      <td>0.00000</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0.0779</td>\n",
+              "      <td>-5.838</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Magic Shop</td>\n",
+              "      <td>68</td>\n",
+              "      <td>0.0889</td>\n",
+              "      <td>149.926</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>17373</th>\n",
+              "      <td>0.261</td>\n",
+              "      <td>2008</td>\n",
+              "      <td>0.004010</td>\n",
+              "      <td>[Theory of a Deadman]</td>\n",
+              "      <td>0.415</td>\n",
+              "      <td>215400</td>\n",
+              "      <td>0.781</td>\n",
+              "      <td>5xyACR2lzIyzFepF4qlAas</td>\n",
+              "      <td>0.00000</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0.1260</td>\n",
+              "      <td>-6.947</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Not Meant to Be</td>\n",
+              "      <td>58</td>\n",
+              "      <td>0.0357</td>\n",
+              "      <td>142.966</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>37677</th>\n",
+              "      <td>0.361</td>\n",
+              "      <td>2015</td>\n",
+              "      <td>0.092800</td>\n",
+              "      <td>[One Direction]</td>\n",
+              "      <td>0.546</td>\n",
+              "      <td>196933</td>\n",
+              "      <td>0.657</td>\n",
+              "      <td>1ZWLWVqeEMWMKTlteS0yLH</td>\n",
+              "      <td>0.00000</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0.1190</td>\n",
+              "      <td>-4.787</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Love You Goodbye</td>\n",
+              "      <td>70</td>\n",
+              "      <td>0.0332</td>\n",
+              "      <td>133.188</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>17340</th>\n",
+              "      <td>0.306</td>\n",
+              "      <td>2008</td>\n",
+              "      <td>0.131000</td>\n",
+              "      <td>[Taylor Swift]</td>\n",
+              "      <td>0.617</td>\n",
+              "      <td>236267</td>\n",
+              "      <td>0.741</td>\n",
+              "      <td>1D4PL9B8gOg78jiHg3FvBb</td>\n",
+              "      <td>0.00000</td>\n",
+              "      <td>2</td>\n",
+              "      <td>0.0772</td>\n",
+              "      <td>-3.970</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Love Story</td>\n",
+              "      <td>79</td>\n",
+              "      <td>0.0311</td>\n",
+              "      <td>118.984</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>36264</th>\n",
+              "      <td>0.385</td>\n",
+              "      <td>2008</td>\n",
+              "      <td>0.033000</td>\n",
+              "      <td>[Nickelback]</td>\n",
+              "      <td>0.489</td>\n",
+              "      <td>262627</td>\n",
+              "      <td>0.748</td>\n",
+              "      <td>1xQZtbipNLyP0e0hihE5F5</td>\n",
+              "      <td>0.00000</td>\n",
+              "      <td>2</td>\n",
+              "      <td>0.1440</td>\n",
+              "      <td>-5.488</td>\n",
+              "      <td>1</td>\n",
+              "      <td>I'd Come for You</td>\n",
+              "      <td>59</td>\n",
+              "      <td>0.0311</td>\n",
+              "      <td>147.998</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "        valence  year  acousticness                artists  danceability  \\\n",
+              "18509     0.293  2014      0.000501      [Young the Giant]         0.466   \n",
+              "18039     0.370  2012      0.126000        [One Direction]         0.514   \n",
+              "108337    0.285  2018      0.103000                  [BTS]         0.541   \n",
+              "17405     0.205  2008      0.000354           [Nickelback]         0.536   \n",
+              "140275    0.285  2018      0.103000                  [BTS]         0.541   \n",
+              "17373     0.261  2008      0.004010  [Theory of a Deadman]         0.415   \n",
+              "37677     0.361  2015      0.092800        [One Direction]         0.546   \n",
+              "17340     0.306  2008      0.131000         [Taylor Swift]         0.617   \n",
+              "36264     0.385  2008      0.033000           [Nickelback]         0.489   \n",
+              "\n",
+              "        duration_ms  energy                      id  instrumentalness  key  \\\n",
+              "18509        244693   0.763  5Az8KU81g2aLBbJN67F2CI           0.00000    0   \n",
+              "18039        200400   0.727  6M31fPFCYB8Job3MCjjrDV           0.00000    0   \n",
+              "108337       275696   0.661  2tMBCYj22KxtmkAACIvvk4           0.00000    1   \n",
+              "17405        252653   0.890  06T10fEzN8ZCcqzQZYA184           0.00165    0   \n",
+              "140275       275696   0.661  22ryCgQttpV7oCrn7llGRu           0.00000    1   \n",
+              "17373        215400   0.781  5xyACR2lzIyzFepF4qlAas           0.00000    1   \n",
+              "37677        196933   0.657  1ZWLWVqeEMWMKTlteS0yLH           0.00000    1   \n",
+              "17340        236267   0.741  1D4PL9B8gOg78jiHg3FvBb           0.00000    2   \n",
+              "36264        262627   0.748  1xQZtbipNLyP0e0hihE5F5           0.00000    2   \n",
+              "\n",
+              "        liveness  loudness  mode                      name  popularity  \\\n",
+              "18509     0.0973    -4.448     1          Mind Over Matter          69   \n",
+              "18039     0.0978    -6.131     1  They Don't Know About Us          79   \n",
+              "108337    0.0779    -5.838     1                Magic Shop          72   \n",
+              "17405     0.1330    -5.222     1         Gotta Be Somebody          63   \n",
+              "140275    0.0779    -5.838     1                Magic Shop          68   \n",
+              "17373     0.1260    -6.947     1           Not Meant to Be          58   \n",
+              "37677     0.1190    -4.787     1          Love You Goodbye          70   \n",
+              "17340     0.0772    -3.970     1                Love Story          79   \n",
+              "36264     0.1440    -5.488     1          I'd Come for You          59   \n",
+              "\n",
+              "        speechiness    tempo  \n",
+              "18509        0.0318  154.914  \n",
+              "18039        0.0492  147.917  \n",
+              "108337       0.0889  149.926  \n",
+              "17405        0.0601  115.998  \n",
+              "140275       0.0889  149.926  \n",
+              "17373        0.0357  142.966  \n",
+              "37677        0.0332  133.188  \n",
+              "17340        0.0311  118.984  \n",
+              "36264        0.0311  147.998  "
+            ]
+          },
+          "execution_count": 35,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "output"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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": "3.12.3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

controller.py

@@ -0,0 +1,15 @@
+
+def get_song_from_id(id):
+    
+    
+    return 
+
+
+def get_song_from_title(title):
+    
+    
+    return
+
+def get_recomendation(songs,n_rec):
+    
+    return 

data/data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97c42349c2e97339ff908ab01163ec5a3264f02ec65e78cb961c85077ded7f8
+size 29654587

data/data_by_year.csv

@@ -0,0 +1,101 @@
+mode,year,acousticness,danceability,duration_ms,energy,instrumentalness,liveness,loudness,speechiness,tempo,valence,popularity,key
+1,1921,0.8868960000000005,0.4185973333333336,260537.16666666663,0.23181513333333334,0.34487805886666656,0.20571,-17.04866666666665,0.073662,101.53149333333329,0.37932666666666665,0.6533333333333333,2
+1,1922,0.9385915492957748,0.4820422535211267,165469.74647887325,0.23781535211267596,0.4341948697183099,0.2407197183098592,-19.275281690140844,0.1166549295774648,100.88452112676056,0.5355492957746479,0.14084507042253522,10
+1,1923,0.9572467913513516,0.5773405405405401,177942.36216216214,0.2624064864864865,0.37173272502702703,0.2274621621621621,-14.129210810810811,0.0939486486486487,114.0107297297297,0.6254924324324328,5.389189189189189,0
+1,1924,0.940199860169493,0.5498940677966102,191046.70762711862,0.3443466101694912,0.5817009136440677,0.2352190677966101,-14.231343220338989,0.09208940677966099,120.68957203389822,0.6637254237288139,0.6610169491525424,10
+1,1925,0.9626070503597138,0.5738633093525181,184986.92446043165,0.2785935251798561,0.4182973612230215,0.2376679856115108,-14.14641366906474,0.11191798561151084,115.5219208633093,0.6219287769784171,2.6043165467625897,5
+1,1926,0.660817216981134,0.5998802612481859,156881.65747460088,0.2114670907111756,0.3330931111175616,0.2323695936139332,-18.492538461538466,0.4837036284470243,109.64803265602328,0.4369104571843251,1.4223512336719883,9
+1,1927,0.9361794552845558,0.6482682926829262,184993.59837398372,0.2643213008130081,0.3913284986504065,0.16845024390243893,-14.422373983739831,0.11360959349593502,114.84652357723554,0.6597004878048782,0.8016260162601626,7
+1,1928,0.9386165035685952,0.5342878667724027,214827.90642347344,0.20794779540047573,0.4948354801348136,0.17528937351308488,-17.191982553528927,0.15991149881046796,106.77226169706593,0.4957126883425853,1.5257731958762886,1
+1,1929,0.6014265861344558,0.6476698529411761,168999.41281512607,0.2418007352941172,0.21520403106092464,0.2360002100840333,-16.530376050420152,0.4900007352941176,110.94835714285715,0.6365298319327733,0.3403361344537815,7
+1,1930,0.936714937370057,0.5181758835758836,195150.28534303536,0.3335239189189189,0.35220592816528057,0.22131086278586296,-12.869221413721428,0.11990966735966745,109.87119438669428,0.6162376299376306,0.9267151767151768,2
+1,1931,0.8330399585921336,0.5952217391304357,171553.42546583852,0.2344967732919257,0.22141964161490724,0.22742795031055896,-16.51609420289853,0.4536189440993791,109.02528157349907,0.5131170807453418,0.17080745341614906,0
+1,1932,0.9357705179282878,0.5577976095617526,195749.37250996014,0.3020677290836656,0.22635657916334675,0.23249621513944224,-13.364055776892426,0.1390073705179282,115.11980079681273,0.5881599601593626,2.151394422310757,7
+1,1933,0.899897909117222,0.57029030390738,196219.25759768448,0.2798994211287988,0.1839489396816208,0.2090719247467437,-13.06900868306802,0.09112315484804634,112.522,0.5994099855282197,6.898697539797395,7
+1,1934,0.8911487501730107,0.528705882352941,189356.1262975779,0.2621313148788928,0.276382266643599,0.21345259515570927,-14.756875432525954,0.10245692041522483,115.39084602076124,0.5588046712802772,1.2577854671280275,0
+1,1935,0.7783855599472987,0.5558691699604746,220124.24703557312,0.2463669762845848,0.2258732980895915,0.2292998682476943,-15.41474967061924,0.3539123847167326,110.66795652173931,0.5455777997364957,1.5013175230566536,7
+1,1936,0.7723120800000008,0.5580055454545453,220809.1863636364,0.3083886092727274,0.2571099957181816,0.2214382727272726,-14.612999090909069,0.27902936363636377,109.88875454545445,0.5640635454545455,5.080909090909091,10
+1,1937,0.8654357853881286,0.5421572298325723,223216.5585996956,0.31104829528158273,0.3270876216438359,0.2259677321156773,-13.11514307458143,0.08567884322678843,115.2632222222222,0.5857894977168944,3.328767123287671,7
+1,1938,0.9192803908646014,0.47997797716150103,249177.09951060358,0.2809812398042416,0.3784246349265906,0.237111092985318,-14.290582381729198,0.095957259380098,111.6253278955954,0.5149111092985317,2.0962479608482867,0
+1,1939,0.9087381000000004,0.5126828,221602.065,0.2826715000000002,0.2776824694100001,0.2391015999999999,-13.900570000000005,0.1284626999999999,113.174592,0.5599248999999992,4.36,0
+1,1940,0.8476440499999951,0.52189235,182227.9445,0.3108928949999999,0.31684869986499986,0.26433510000000043,-13.684048000000017,0.2429576500000001,108.44933449999992,0.6167094700000009,0.93,7
+1,1941,0.8957376562500025,0.4804813541666676,201904.575,0.2656431979166666,0.4449516393124999,0.20183989583333312,-15.755536458333326,0.09136520833333356,107.91512291666668,0.4794560416666661,1.3572916666666666,7
+1,1942,0.8529343703923857,0.4646338882282997,222361.16825208085,0.2560794708680144,0.39288204787158104,0.2128784185493456,-15.02903210463735,0.08367835909631392,106.00839774078482,0.4774088585017848,1.1266349583828774,7
+1,1943,0.9027523185915528,0.4551456338028168,240119.9098591549,0.27999004225352114,0.4098969234647892,0.23921070422535246,-13.60212535211268,0.10571957746478874,106.19679154929581,0.4954545070422531,1.1816901408450704,5
+1,1944,0.9076531914893636,0.5001744680851068,245555.58643617018,0.2534414494680852,0.4492919654122334,0.2387719414893616,-14.58205585106382,0.17328324468085093,105.96392952127657,0.5406954787234041,3.1928191489361697,10
+1,1945,0.7096568630000005,0.5191431500000011,196161.557,0.2260444155,0.2758942570149996,0.2030099500000001,-16.9814715,0.3050972999999997,108.32407049999986,0.4913613500000002,2.1265,0
+1,1946,0.9199445823665852,0.4144450116009276,267677.82308584685,0.22217230858468667,0.4861264096461711,0.2108183294663576,-16.921774361948952,0.08800591647331797,103.1645551044084,0.3982538283062647,1.65661252900232,7
+1,1947,0.9139650224242392,0.4713208484848491,233137.38424242425,0.2635512000000002,0.3475934179090908,0.22382939393939366,-14.377607878787892,0.10056381818181824,108.991026060606,0.5082125454545455,1.6157575757575755,7
+1,1948,0.9221549999999956,0.4633694736842109,199194.87421052632,0.242464841052632,0.3554848223842104,0.21969357894736785,-15.505407368421027,0.1643593157894739,108.05836105263157,0.4621423684210526,1.5273684210526317,0
+1,1949,0.9075328949999956,0.4421993999999996,223199.3275,0.24611461499999965,0.2977615361899994,0.2088585500000004,-15.525844999999983,0.10299210000000003,108.87313549999992,0.4304195000000001,3.9389999999999996,0
+1,1950,0.8539413005999965,0.5042531000000008,215073.1255,0.3140711950000003,0.245000820015,0.2169584000000004,-13.863834499999962,0.1534527499999999,111.74972499999987,0.5516497000000001,3.2065,7
+1,1951,0.9022971956499974,0.4624800999999999,213154.641,0.25466565500000005,0.3084378555850002,0.21777739999999995,-15.812066000000033,0.10850664999999993,109.62587199999994,0.44134755,3.1495,0
+1,1952,0.8743009244999965,0.4570322000000001,229434.72699999998,0.25362601000000023,0.2884126469300002,0.2329722999999998,-15.95886600000001,0.1373617999999998,108.23228049999986,0.44313496204999947,3.338,0
+1,1953,0.8909223502564074,0.4374260512820513,217455.5682051282,0.2661968307692306,0.3183223943230766,0.22173405128205104,-15.499134871794872,0.09008825641025647,110.02556666666672,0.42914205128205135,3.5046153846153847,0
+1,1954,0.8650197272999992,0.4656388999999994,224029.36800000002,0.264347385,0.2974400082799999,0.2178411499999996,-15.408004500000024,0.10481329999999993,108.71309249999992,0.4523410500000002,7.987,0
+1,1955,0.8405510069999986,0.4881312,222137.44600000003,0.2950963400000001,0.21660442169000027,0.2214353500000001,-13.842262000000035,0.0895582,111.02127950000023,0.4724154999999997,10.1445,5
+1,1956,0.8230569899999975,0.4878145000000007,211846.9215,0.30476112000000016,0.23876341778000015,0.18225715000000026,-14.175195500000006,0.062312349999999926,112.20603900000013,0.5084230500000003,15.785,0
+1,1957,0.7928023589743608,0.5034812307692305,241604.8241025641,0.2952791333333324,0.1945206161692309,0.1827485641025636,-14.124848717948735,0.06435312820512826,112.75229487179486,0.5110101538461542,20.08205128205128,5
+1,1958,0.7796118650000005,0.4800213999999995,214146.9005,0.3087957550000006,0.18124111005999985,0.2058408500000003,-14.165171000000019,0.05699929999999995,113.32612349999994,0.4976614999999994,19.2575,0
+1,1959,0.7793927897435907,0.4821143076923083,216292.8369230769,0.3109944051282049,0.18814819406153835,0.1918429230769232,-14.460136923076945,0.06787430769230775,112.11770153846165,0.4784156410256422,20.773333333333333,0
+1,1960,0.7671814843243259,0.4860292432432435,210209.68378378375,0.3411423783783781,0.1765021594216216,0.20786372972972986,-13.814102702702725,0.0657835135135136,112.56167891891873,0.5239316756756759,19.783783783783786,0
+1,1961,0.7519038684210535,0.4891655789473678,232186.61421052628,0.3395318673684203,0.26462325314210544,0.20891257894736812,-14.171330526315785,0.0594759473684209,111.80895789473686,0.5128512105263155,19.59842105263158,0
+1,1962,0.720607806842106,0.4931643684210523,209294.41315789477,0.3710257,0.17147155094210545,0.20189573684210546,-13.177364210526294,0.057739842105263124,114.84100473684195,0.5477920526315792,22.127368421052637,0
+1,1963,0.7227048300000004,0.48162135,200510.5485,0.3653538849999999,0.18543231468,0.20374530000000027,-13.670647000000017,0.05203614999999992,114.32458749999985,0.5415274500000008,25.5355,0
+1,1964,0.6941005307692291,0.5041769743589742,195536.4117948718,0.394438825641026,0.1595978017794872,0.2172323589743596,-13.048075897435869,0.06659446153846146,115.0814892307692,0.55726042051282,26.32102564102564,0
+1,1965,0.6099113295384619,0.5034505641025638,196342.08615384615,0.4490272461538461,0.1183659460923078,0.21383912820512846,-11.888213333333338,0.05755646153846147,116.83544666666687,0.5809506666666668,27.52,0
+1,1966,0.5248094599699997,0.5070204999999981,216095.113,0.482208465,0.11512595556499995,0.21809309999999996,-11.356919500000007,0.055964050000000085,116.33542399999996,0.5801445499999996,28.2815,2
+1,1967,0.5296103243521767,0.4926885942971483,198987.5182591296,0.44682383191595854,0.1189468546723362,0.19091765882941508,-11.708829414707358,0.04909839919959968,116.6800225112558,0.5507916958479243,31.190595297648827,0
+1,1968,0.4937702403500001,0.5010080999999997,214980.984,0.4569696500000004,0.11277694928500002,0.2173509500000005,-12.043861999999995,0.0589884999999999,115.83259149999995,0.5659936500000002,31.2595,0
+1,1969,0.4488463039999994,0.4880977999999999,242545.9405,0.4876251299999994,0.15945270816500012,0.20696589999999992,-12.062166000000007,0.05497499999999995,117.02432850000014,0.5547452849999999,32.844,2
+1,1970,0.4600571139500007,0.5063075000000004,242852.1515,0.495633050000001,0.12756700308499988,0.21226880000000026,-11.772557999999995,0.051681499999999936,117.1116105,0.5720753999999992,34.3945,2
+1,1971,0.4583362981000009,0.5042738499999999,260511.7935,0.4963612550000003,0.12501788923,0.21491455000000012,-12.079936000000007,0.05942240000000008,118.27224749999992,0.5749132500000002,34.4475,2
+1,1972,0.4600428051999994,0.5209994499999997,245914.2285,0.5045261799999999,0.11488033375999974,0.20695495000000014,-11.773563499999995,0.05487124999999998,119.412852,0.5956881500000009,34.485,2
+1,1973,0.4165241889999992,0.5154494500000005,257002.7905,0.5361382499999989,0.09968022322999996,0.20137474999999974,-11.260197000000012,0.057825750000000085,120.14631649999998,0.5921162000000004,36.428000000000004,0
+1,1974,0.4472074226000001,0.51533975,252555.79100000003,0.5147236550000011,0.11636098351000007,0.20934634999999968,-11.816489000000018,0.0573193499999999,119.41645299999985,0.5812744000000009,32.2465,2
+1,1975,0.4337738871950005,0.5209980000000007,254969.3715,0.5232085050000003,0.11132203374499992,0.21544135000000025,-11.48593899999998,0.06109845,118.68401550000021,0.5694151500000002,34.812,2
+1,1976,0.36147063210999936,0.5297624999999999,267676.967,0.5538432500000001,0.12162904398000007,0.24903219999999995,-11.114236999999996,0.06274994999999996,120.52205800000002,0.5807332499999998,35.835,2
+1,1977,0.3393025333750004,0.5333237000000017,257121.848,0.560287959000001,0.12772103194499998,0.2232140500000004,-11.077354499999998,0.060854549999999966,122.18543050000022,0.58524655,35.8465,9
+1,1978,0.32896857344999936,0.5407746000000005,249051.887,0.5614288650000007,0.10038121450999994,0.21807094999999949,-10.891867999999995,0.06275740000000009,120.37794350000006,0.5895352500000014,35.891,2
+1,1979,0.29593224063,0.5620453000000001,252860.2265,0.5910127149999996,0.11575137201500015,0.21344310000000027,-10.977513500000004,0.06905859999999991,122.45681650000013,0.6099818000000005,36.172,0
+1,1980,0.28495539763589706,0.5561523589743594,252835.53333333327,0.5977773948717964,0.1287510612717948,0.20375410256410267,-10.700942051282043,0.05924861538461545,122.98500102564111,0.5980580512820513,36.206666666666656,0
+1,1981,0.3012042267400006,0.5421846999999999,250904.205,0.5993827249999998,0.14683794661999985,0.2250998999999999,-10.924404499999977,0.057915999999999926,123.16939500000014,0.5829518500000006,35.7525,9
+1,1982,0.2895800382050001,0.5642594000000005,248357.306,0.5909193894999996,0.10001638300000004,0.20100675,-10.9331225,0.06585305000000008,120.91860749999992,0.5864384500000001,36.247,2
+1,1983,0.2947778916300001,0.5456292999999998,251123.6985,0.6014252350000012,0.14541052329000045,0.1989224500000002,-11.200171000000024,0.06688600000000006,121.070629,0.5721198999999989,36.268,9
+1,1984,0.2877095803450008,0.5303089499999987,251845.2565,0.5910916750000013,0.14517303973500045,0.19770620000000003,-11.523238499999987,0.059264800000000166,121.37666200000015,0.5516387100000003,37.7745,9
+1,1985,0.2965709032099995,0.5556424000000012,252276.258,0.6015154800000013,0.11373855807499987,0.19920644999999984,-11.360688499999991,0.05846480000000006,121.9793035000001,0.5655964500000001,37.013000000000005,9
+1,1986,0.28508065642499997,0.5409334000000001,254708.4055,0.6149545999999998,0.10994085436499992,0.21187945000000014,-11.103995000000019,0.06481609999999999,120.49930200000016,0.5509485500000019,37.5775,9
+1,1987,0.3116640663948722,0.5410193333333342,247543.3230769231,0.5798395538461533,0.10197451746666662,0.20201810256410305,-11.623467179487175,0.05778964102564103,120.84570717948708,0.5414511794871785,39.685128205128215,7
+1,1988,0.32200994651282105,0.5404594358974372,257442.5897435897,0.5856792461538458,0.11719038022051302,0.20770753846153808,-11.519821025641036,0.06609989743589745,120.02442564102579,0.5464853897435901,39.60051282051282,7
+1,1989,0.3133512518150009,0.5472274499999988,254203.5935,0.584046375000001,0.11318254461499995,0.19908020000000007,-11.38413000000001,0.06393924999999995,120.5790015000003,0.5483329000000007,39.1825,7
+1,1990,0.3328699505850001,0.5352986500000001,256451.4035,0.5715913950000007,0.12582626809499972,0.19096090000000004,-11.327479499999981,0.06434529999999995,120.06273350000023,0.5265268499999999,40.7855,7
+1,1991,0.33276529163076995,0.5558243589743591,245912.00615384613,0.5594023641025635,0.11509233979999993,0.18862892307692355,-10.955768717948725,0.07110158974358982,119.36257435897407,0.5486552307692295,41.65589743589744,7
+1,1992,0.3208087638250009,0.5550648499999989,246506.46,0.5828642050000001,0.1006900830649998,0.20024550000000071,-10.575404499999976,0.07306230000000008,122.58621850000021,0.5590983000000014,42.994,7
+1,1993,0.3090685537400004,0.5698781500000001,251667.9675,0.5625599100000002,0.11529396538000007,0.1949322500000003,-10.882701000000026,0.07635054999999992,120.36493599999993,0.5555684500000001,42.9975,7
+1,1994,0.3062343630899999,0.5528299500000016,250992.254,0.578772685000001,0.11188575994999997,0.1921651000000001,-10.282273000000004,0.07604935000000011,118.44516999999986,0.5266491500000006,45.0615,7
+1,1995,0.30251180612000045,0.5590457500000001,246624.0915,0.5785795100000009,0.12326879606999998,0.2013737000000004,-10.119450000000008,0.08375444999999987,119.28197799999987,0.5302466999999994,44.801,0
+1,1996,0.30102687980000065,0.5878306000000001,248180.983,0.5860684750000011,0.09505281203500013,0.1986863000000002,-9.44381849999999,0.08607765000000005,117.70835699999998,0.5608732500000001,44.903999999999996,7
+1,1997,0.3067156934549995,0.5768138499999994,245749.2815,0.5986987151000001,0.10469017861999998,0.1984788000000003,-9.200875500000018,0.08850605000000017,118.18231600000021,0.5485525000000002,45.582,7
+1,1998,0.29148946157000016,0.5862116499999998,248542.6075,0.6051975050000015,0.1113257503499999,0.1937308999999996,-8.971167999999997,0.09173105000000006,118.54010800000003,0.5377209,45.8945,7
+1,1999,0.2715901110661201,0.5821579190158892,245177.7452588416,0.6375226022552535,0.09406814106611992,0.20630804715530507,-8.266409533572531,0.09440717580727807,119.50949051768335,0.5564528446950284,47.25832906201947,0
+1,2000,0.28932270051635994,0.590918047034764,242724.6426380368,0.6254128323108387,0.10116776879345596,0.1976860429447853,-8.247765848670758,0.08920541922290394,118.9993231083843,0.5594754601226991,46.6840490797546,7
+1,2001,0.2868424748428934,0.5833178553615969,240307.79600997505,0.6269855221945144,0.10721401899251867,0.18702563591022486,-8.305095261845384,0.08918229426433916,117.76539900249378,0.541479107231919,48.75012468827929,7
+1,2002,0.28262428988500105,0.5761602999999997,239503.283,0.6412697960000012,0.08804835031499995,0.1939111999999998,-7.686639500000013,0.08430759999999995,119.23973849999993,0.5423971500000008,48.6555,7
+1,2003,0.25647051817297833,0.5757633060388944,244670.5752302968,0.6601652610030712,0.08304927466734914,0.19697630501535301,-7.485545035823955,0.09392574206755384,120.9146218014328,0.5305042476970324,48.62640736949847,7
+1,2004,0.2805589466225845,0.5676803662258397,237378.70803662261,0.6488679450661226,0.07793403490844357,0.2021994404883014,-7.601655137334684,0.09423880976602242,121.29034587995956,0.5244885554425227,49.27314343845372,7
+1,2005,0.2557635068666665,0.5722805641025652,237229.5882051282,0.653208511282051,0.09019436118461543,0.19008162564102585,-7.46615897435897,0.09333369230769203,121.61796666666649,0.5325309230769236,50.95333333333333,0
+1,2006,0.2799863520256408,0.5682301538461539,234042.91435897435,0.6503262820512825,0.07770147187692314,0.1882892820512821,-7.265500512820514,0.08584676923076921,121.79861538461536,0.5200283076923078,51.31384615384616,7
+1,2007,0.2540809575538463,0.5634143589743592,241049.96256410255,0.6683047743589737,0.07295726805128197,0.19612656410256424,-7.044535897435892,0.08434733333333336,124.0875164102562,0.5167938461538473,51.07589743589744,7
+1,2008,0.2491917627212275,0.5791928388746803,240107.31560102306,0.6714608207672623,0.0636620903171356,0.19843140664961625,-6.8438040920716166,0.07735636828644507,123.50993350383641,0.5275418925831203,50.63017902813299,0
+1,2009,0.26192861909693904,0.5641903571428577,238140.0132653061,0.6707487551020408,0.07587207368367352,0.2052522959183674,-7.0460147959183645,0.08545780612244899,123.4638076530612,0.5071696617346935,51.440816326530616,0
+1,2010,0.2426866435515872,0.5724883432539687,242811.8045634921,0.6817778026289684,0.08298056821924611,0.19970064484126995,-6.9099042658730125,0.08103149801587313,123.5702152777779,0.5208951587301589,52.73015873015873,0
+1,2011,0.27318266251859197,0.5528669806643526,236998.787307883,0.6483008934060499,0.10377233216658402,0.20330882498760566,-7.574986117997006,0.08747927615270201,121.48399702528488,0.4724536787307882,53.30738720872582,2
+1,2012,0.24995304438046245,0.5708818508997433,245807.45758354763,0.6565714601542408,0.08520552067866319,0.1897330077120824,-7.260549614395888,0.08174246786632405,121.78173624678669,0.4627090128534706,52.65501285347044,7
+1,2013,0.2574880859564779,0.5711480263157896,242267.66143724695,0.6455968914473688,0.09836505391700387,0.19963081983805714,-7.472039473684207,0.09384888663967614,120.80682945344118,0.4547411943319834,54.047064777327925,1
+1,2014,0.24931264588029906,0.5899476807980057,233728.31471321694,0.6487954437905223,0.07656955483790515,0.1918215960099752,-7.06743990024938,0.08406054862842896,122.30526284289296,0.4630487780548628,55.543142144638395,0
+1,2015,0.2539522577102332,0.5937740628166152,230029.0466058764,0.6270642715298895,0.1067868780547114,0.18885643363728474,-7.625639311043569,0.09677922998986847,120.11541134751768,0.4320983687943254,56.70060790273557,7
+1,2016,0.28417102995548144,0.6002023928770179,221396.51029493602,0.5928552316082347,0.09398438711741793,0.18116989426822505,-8.061056204785759,0.10431329994435183,118.65262993878693,0.4315320589872012,59.6471897607123,0
+1,2017,0.2860990665261043,0.6122170180722886,211115.6967871486,0.5904210208835337,0.09709060906626496,0.1917126004016064,-8.31262951807228,0.1105364959839356,117.20273995983936,0.4164763112449793,63.26355421686747,1
+1,2018,0.2676329907750836,0.6635004755111744,206001.0071326676,0.6024346220161672,0.05421712166904419,0.17632553495007114,-7.168785068949124,0.12717555872563022,121.9223076557296,0.4479212743699474,63.29624346172135,1
+1,2019,0.2782985863365824,0.6448141097998967,201024.78809645973,0.5932240360184717,0.07764024697280643,0.17261641867624464,-7.722191893278596,0.12104335556695732,120.23564443304272,0.4588176295536167,65.25654181631606,1
+1,2020,0.2199308880935964,0.6929043349753701,193728.39753694585,0.6312316354679793,0.016375524305418724,0.1785354187192117,-6.595066995073878,0.14138369458128058,124.28312857142865,0.5010478078817729,64.30197044334976,1

data/data_clean.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c810e41a438408daa46ce1e5b84465306bda6c85baf48bd34879c44922ec5e
+size 27385463

data/data_model.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3a793966668338184f9dfd0eddb71fe73a8c1e8328da26a24da8e46d94d72c
+size 37670908

data_cleaning.ipynb

@@ -0,0 +1,309 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "K6Ek26jtEbzM"
+      },
+      "outputs": [],
+      "source": [
+        "import pandas as pd"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "jSok_FhgFQPa"
+      },
+      "outputs": [],
+      "source": [
+        "df = pd.read_csv('data/data.csv')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "Index(['valence', 'year', 'acousticness', 'artists', 'danceability',\n",
+              "       'duration_ms', 'energy', 'explicit', 'id', 'instrumentalness', 'key',\n",
+              "       'liveness', 'loudness', 'mode', 'name', 'popularity', 'release_date',\n",
+              "       'speechiness', 'tempo'],\n",
+              "      dtype='object')"
+            ]
+          },
+          "execution_count": 3,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df.columns"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "selected_columns = ['valence', 'year', 'acousticness', 'artists', 'danceability',\n",
+        "       'duration_ms', 'energy','id', 'instrumentalness', 'key',\n",
+        "       'liveness', 'loudness', 'mode', 'name', 'popularity',\n",
+        "       'speechiness', 'tempo']\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "df.to_csv('data/data_clean.csv', columns=selected_columns, index=False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<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>valence</th>\n",
+              "      <th>year</th>\n",
+              "      <th>acousticness</th>\n",
+              "      <th>artists</th>\n",
+              "      <th>danceability</th>\n",
+              "      <th>duration_ms</th>\n",
+              "      <th>energy</th>\n",
+              "      <th>explicit</th>\n",
+              "      <th>id</th>\n",
+              "      <th>instrumentalness</th>\n",
+              "      <th>key</th>\n",
+              "      <th>liveness</th>\n",
+              "      <th>loudness</th>\n",
+              "      <th>mode</th>\n",
+              "      <th>name</th>\n",
+              "      <th>popularity</th>\n",
+              "      <th>release_date</th>\n",
+              "      <th>speechiness</th>\n",
+              "      <th>tempo</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>0.0594</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.982</td>\n",
+              "      <td>['Sergei Rachmaninoff', 'James Levine', 'Berli...</td>\n",
+              "      <td>0.279</td>\n",
+              "      <td>831667</td>\n",
+              "      <td>0.211</td>\n",
+              "      <td>0</td>\n",
+              "      <td>4BJqT0PrAfrxzMOxytFOIz</td>\n",
+              "      <td>0.878000</td>\n",
+              "      <td>10</td>\n",
+              "      <td>0.665</td>\n",
+              "      <td>-20.096</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Piano Concerto No. 3 in D Minor, Op. 30: III. ...</td>\n",
+              "      <td>4</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.0366</td>\n",
+              "      <td>80.954</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>0.9630</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.732</td>\n",
+              "      <td>['Dennis Day']</td>\n",
+              "      <td>0.819</td>\n",
+              "      <td>180533</td>\n",
+              "      <td>0.341</td>\n",
+              "      <td>0</td>\n",
+              "      <td>7xPhfUan2yNtyFG0cUWkt8</td>\n",
+              "      <td>0.000000</td>\n",
+              "      <td>7</td>\n",
+              "      <td>0.160</td>\n",
+              "      <td>-12.441</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Clancy Lowered the Boom</td>\n",
+              "      <td>5</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.4150</td>\n",
+              "      <td>60.936</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>0.0394</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.961</td>\n",
+              "      <td>['KHP Kridhamardawa Karaton Ngayogyakarta Hadi...</td>\n",
+              "      <td>0.328</td>\n",
+              "      <td>500062</td>\n",
+              "      <td>0.166</td>\n",
+              "      <td>0</td>\n",
+              "      <td>1o6I8BglA6ylDMrIELygv1</td>\n",
+              "      <td>0.913000</td>\n",
+              "      <td>3</td>\n",
+              "      <td>0.101</td>\n",
+              "      <td>-14.850</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Gati Bali</td>\n",
+              "      <td>5</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.0339</td>\n",
+              "      <td>110.339</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>0.1650</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.967</td>\n",
+              "      <td>['Frank Parker']</td>\n",
+              "      <td>0.275</td>\n",
+              "      <td>210000</td>\n",
+              "      <td>0.309</td>\n",
+              "      <td>0</td>\n",
+              "      <td>3ftBPsC5vPBKxYSee08FDH</td>\n",
+              "      <td>0.000028</td>\n",
+              "      <td>5</td>\n",
+              "      <td>0.381</td>\n",
+              "      <td>-9.316</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Danny Boy</td>\n",
+              "      <td>3</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.0354</td>\n",
+              "      <td>100.109</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>0.2530</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.957</td>\n",
+              "      <td>['Phil Regan']</td>\n",
+              "      <td>0.418</td>\n",
+              "      <td>166693</td>\n",
+              "      <td>0.193</td>\n",
+              "      <td>0</td>\n",
+              "      <td>4d6HGyGT8e121BsdKmw9v6</td>\n",
+              "      <td>0.000002</td>\n",
+              "      <td>3</td>\n",
+              "      <td>0.229</td>\n",
+              "      <td>-10.096</td>\n",
+              "      <td>1</td>\n",
+              "      <td>When Irish Eyes Are Smiling</td>\n",
+              "      <td>2</td>\n",
+              "      <td>1921</td>\n",
+              "      <td>0.0380</td>\n",
+              "      <td>101.665</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "   valence  year  acousticness  \\\n",
+              "0   0.0594  1921         0.982   \n",
+              "1   0.9630  1921         0.732   \n",
+              "2   0.0394  1921         0.961   \n",
+              "3   0.1650  1921         0.967   \n",
+              "4   0.2530  1921         0.957   \n",
+              "\n",
+              "                                             artists  danceability  \\\n",
+              "0  ['Sergei Rachmaninoff', 'James Levine', 'Berli...         0.279   \n",
+              "1                                     ['Dennis Day']         0.819   \n",
+              "2  ['KHP Kridhamardawa Karaton Ngayogyakarta Hadi...         0.328   \n",
+              "3                                   ['Frank Parker']         0.275   \n",
+              "4                                     ['Phil Regan']         0.418   \n",
+              "\n",
+              "   duration_ms  energy  explicit                      id  instrumentalness  \\\n",
+              "0       831667   0.211         0  4BJqT0PrAfrxzMOxytFOIz          0.878000   \n",
+              "1       180533   0.341         0  7xPhfUan2yNtyFG0cUWkt8          0.000000   \n",
+              "2       500062   0.166         0  1o6I8BglA6ylDMrIELygv1          0.913000   \n",
+              "3       210000   0.309         0  3ftBPsC5vPBKxYSee08FDH          0.000028   \n",
+              "4       166693   0.193         0  4d6HGyGT8e121BsdKmw9v6          0.000002   \n",
+              "\n",
+              "   key  liveness  loudness  mode  \\\n",
+              "0   10     0.665   -20.096     1   \n",
+              "1    7     0.160   -12.441     1   \n",
+              "2    3     0.101   -14.850     1   \n",
+              "3    5     0.381    -9.316     1   \n",
+              "4    3     0.229   -10.096     1   \n",
+              "\n",
+              "                                                name  popularity release_date  \\\n",
+              "0  Piano Concerto No. 3 in D Minor, Op. 30: III. ...           4         1921   \n",
+              "1                            Clancy Lowered the Boom           5         1921   \n",
+              "2                                          Gati Bali           5         1921   \n",
+              "3                                          Danny Boy           3         1921   \n",
+              "4                        When Irish Eyes Are Smiling           2         1921   \n",
+              "\n",
+              "   speechiness    tempo  \n",
+              "0       0.0366   80.954  \n",
+              "1       0.4150   60.936  \n",
+              "2       0.0339  110.339  \n",
+              "3       0.0354  100.109  \n",
+              "4       0.0380  101.665  "
+            ]
+          },
+          "execution_count": 5,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df.head()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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": "3.12.4"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

main.py

@@ -0,0 +1,31 @@
+import time
+import streamlit as st
+
+# PAGE TITLE
+st.set_page_config(page_title='Music Recommender App', page_icon='🎵')
+
+# TITLE 
+st.title('Music Recommender App')
+
+with st.sidebar:
+    st.header('Welcome to the Music Recommender System!')
+    st.write('This is a simple music recommender system that uses the Spotify API to recommend songs based on the song you input. The system uses the Spotify API to get the audio features of the song you input and then recommends songs that are similar to it.')
+    # sparation
+    st.write('---')
+    
+    with st.expander('⚙️ Setting'):
+        num_rec = st.slider('Number of Recommendations', min_value=1, max_value=20, value=5)
+
+
+with st.form(key='my_form'):
+    # INPUT
+    song_title = st.text_input("Song title", "")
+    generate_button = st.form_submit_button("Generate")
+    
+
+if generate_button:
+    with st.spinner('Generating Recommendations...'):
+        time.sleep(2)    
+    st.write("Recommendations for", song_title)
+    
+    

model.py

@@ -0,0 +1,124 @@
+import joblib
+import pandas as pd
+import numpy as np
+import ast
+from scipy.spatial.distance import cdist
+
+
+
+import yaml
+import spotipy
+from spotipy.oauth2 import SpotifyOAuth,SpotifyClientCredentials
+
+DF_COLUMNS = ['valence', 'year', 'acousticness', 'artists', 'danceability',
+       'duration_ms', 'energy', 'id', 'instrumentalness', 'key',
+       'liveness', 'loudness', 'mode', 'name', 'popularity', 'release_date',
+       'speechiness', 'tempo']
+DF_COLUMNS_MODEL = ['valence', 'year', 'acousticness','artists', 'danceability',
+         'duration_ms', 'energy', 'instrumentalness', 'key',
+         'liveness', 'loudness', 'mode', 'popularity', 'speechiness', 'tempo']
+
+pipeline = joblib.load('model/pipeline.pkl')
+
+
+stream= open("spotify/spotify.yaml")
+spotify_details = yaml.safe_load(stream)
+auth_manager = SpotifyClientCredentials(client_id=spotify_details['Client_id'],
+                                        client_secret=spotify_details['client_secret'])
+
+sp = spotipy.client.Spotify(auth_manager=auth_manager)
+
+def get_song_spotify(song_name, data):
+    log = open('log.txt','w')
+    try:
+        result = sp.search(q=song_name, limit=1)
+    except:
+        log.write('Error: Failed to search song')
+        return None
+
+    if result['tracks']['items'] == []:
+        return None
+
+    song = result['tracks']['items'][0]
+
+    id = song['id']
+
+    try:
+        song_data = data[(data['id'] == id)].iloc[0]
+        return song_data
+    except:
+        try:
+            audio_features = sp.audio_features(id)
+            song_data = {
+                'valence': audio_features[0]['valence'],
+                "year" : result['tracks']['items'][0]['album']['release_date'][:4],
+                'acousticness': audio_features[0]['acousticness'],
+                'artists': list(map(lambda x: x['name'], result['tracks']['items'][0]['artists'])),
+                'danceability': audio_features[0]['danceability'],
+                'duration_ms': audio_features[0]['duration_ms'],
+                'energy': audio_features[0]['energy'],
+                'id': id,
+                'instrumentalness': audio_features[0]['instrumentalness'],
+                'key': audio_features[0]['key'],
+                'liveness': audio_features[0]['liveness'],
+                'loudness': audio_features[0]['loudness'],
+                'mode': audio_features[0]['mode'],
+                'name': result['tracks']['items'][0]['name'],
+                'popularity': result['tracks']['items'][0]['popularity'],
+                'speechiness': audio_features[0]['speechiness'],
+                'tempo': audio_features[0]['tempo']
+            }
+        except:
+            log.write('Error: Failed to get audio features from Spotify')
+            return None
+
+        return pd.DataFrame([song_data], columns=DF_COLUMNS).iloc[0]
+
+def get_song_data(song_name, data):
+    try:
+        song_data = data[(data['name'] == song_name)].iloc[0]
+        return song_data
+    except:
+        return get_song_spotify(song_name,data)
+
+def df_song_data(list_song_name,data):
+    rows_song_data = list()
+    for song_name in list_song_name:
+        rows_song_data.append(get_song_data(song_name,data))
+
+    return pd.DataFrame(rows_song_data,columns=DF_COLUMNS)
+
+def songs_recommendation(list_song_name,data,num_rec=10):
+
+    song_data_input = df_song_data(list_song_name,data).to_dict(orient='records')
+
+    vector = pipeline.named_steps["preprocessor"].transform(df_song_data(list_song_name,data))
+    vector = pipeline.named_steps["scaler"].transform(vector)
+
+    vector = vector.mean(axis=0)
+
+    predicted_cluster = pipeline.named_steps["kmeans"].predict([vector])
+
+    cluster_data = data[pipeline.named_steps["kmeans"].labels_ == predicted_cluster[0]]
+
+    vector_cluster = pipeline.named_steps["preprocessor"].transform(cluster_data)
+    vector_cluster = pipeline.named_steps["scaler"].transform(vector_cluster)
+
+    distance = cdist([vector],vector_cluster)
+    index = list(np.argsort(distance)[:, :num_rec][0])
+
+    recsongs = cluster_data.iloc[index]
+    recsongs = recsongs[~recsongs['name'].isin(list_song_name)].to_dict(orient='records')
+    return song_data_input,recsongs
+
+def get_url(id_track):
+    try:
+        result = sp.track(id_track)
+        return {"image": result['album']['images'][0]['url'],"sample": result['preview_url']}
+    except:
+        return 'https://i.scdn.co/image/ab67616d00004851f221ae4798e902bf102e1bd2'
+
+
+df = pd.read_csv('data/data_clean.csv')
+df['artists'] = df['artists'].apply(ast.literal_eval)
+

model/pipeline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe2e2477452c9e98e13ece48cb8ff1c512d85371f33a557ead66b20c5b4a4cc
+size 688202

recyclebin/ModellingPSD.ipynb

@@ -0,0 +1,332 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "metadata": {
+        "id": "K6Ek26jtEbzM"
+      },
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "import ast\n",
+        "\n",
+        "from sklearn.compose import ColumnTransformer\n",
+        "from sklearn.pipeline import Pipeline\n",
+        "from sklearn.preprocessing import StandardScaler\n",
+        "from sklearn.cluster import KMeans\n",
+        "from sklearn.feature_extraction import FeatureHasher"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 15,
+      "metadata": {
+        "id": "jSok_FhgFQPa"
+      },
+      "outputs": [],
+      "source": [
+        "df = pd.read_csv('data/data_clean.csv')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 16,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "df['artists'] = df['artists'].apply(ast.literal_eval)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 17,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "JHmNLOXKFqEE",
+        "outputId": "ab92c016-b009-4378-b320-995b268be64f"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "Index(['valence', 'year', 'acousticness', 'artists', 'danceability',\n",
+              "       'duration_ms', 'energy', 'explicit', 'id', 'instrumentalness', 'key',\n",
+              "       'liveness', 'loudness', 'mode', 'name', 'popularity', 'release_date',\n",
+              "       'speechiness', 'tempo'],\n",
+              "      dtype='object')"
+            ]
+          },
+          "execution_count": 17,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df.columns"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 18,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "DF_COLUMNS = ['valence', 'year', 'acousticness', 'artists', 'danceability',\n",
+        "       'duration_ms', 'energy', 'id', 'instrumentalness', 'key',\n",
+        "       'liveness', 'loudness', 'mode', 'name', 'popularity',\n",
+        "       'speechiness', 'tempo']\n",
+        "DF_COLUMNS_MODEL = ['valence', 'year', 'acousticness', 'danceability',\n",
+        "         'duration_ms', 'energy', 'instrumentalness', 'key',\n",
+        "         'liveness', 'loudness', 'mode', 'popularity', 'speechiness', 'tempo']"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "\n",
+        "\n",
+        "# Kolom yang akan di-hash\n",
+        "hash_columns = 'artists'\n",
+        "\n",
+        "# Inisialisasi FeatureHasher untuk kolom tertentu\n",
+        "hasher = FeatureHasher(n_features=10, input_type=\"string\")\n",
+        "\n",
+        "# Inisialisasi StandardScaler\n",
+        "scaler = StandardScaler()\n",
+        "\n",
+        "# Inisialisasi KMeans\n",
+        "kmeans = KMeans(n_clusters=10)\n",
+        "\n",
+        "# Definisikan transformer untuk hashing kolom tertentu\n",
+        "hash_transformer = ('hasher', hasher, hash_columns)\n",
+        "\n",
+        "# Definisikan transformer untuk kolom yang tidak di-hash\n",
+        "remainder_transformer = ('passthrough', 'remainder', slice(0, 0))\n",
+        "\n",
+        "# Gabungkan transformer untuk semua kolom\n",
+        "preprocessor = ColumnTransformer(\n",
+        "    transformers=[hash_transformer], \n",
+        "    remainder='passthrough')\n",
+        "\n",
+        "# Gabungkan preprocessor dengan algoritma clustering (KMeans)\n",
+        "pipeline = Pipeline([\n",
+        "    ('preprocessor', preprocessor),\n",
+        "    ('scaler', scaler),\n",
+        "    ('kmeans', kmeans)\n",
+        "])"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "pipeline.fit(df[DF_COLUMNS_MODEL])"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import yaml\n",
+        "import spotipy\n",
+        "from spotipy.oauth2 import SpotifyOAuth,SpotifyClientCredentials\n",
+        "\n",
+        "stream= open(\"streamlit/spotify/spotify.yaml\")\n",
+        "spotify_details = yaml.safe_load(stream)\n",
+        "auth_manager = SpotifyClientCredentials(client_id=spotify_details['Client_id'],\n",
+        "                                        client_secret=spotify_details['client_secret'])\n",
+        "sp = spotipy.client.Spotify(auth_manager=auth_manager)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def get_song_spotify(song_name,data):\n",
+        "    log = open('log.txt','w')\n",
+        "    try:\n",
+        "        result = sp.search(q=song_name, limit=1)\n",
+        "    except:\n",
+        "        log.write('Error: Failed to search song')\n",
+        "        return None\n",
+        "    \n",
+        "    if result['tracks']['items'] == []:\n",
+        "        return None\n",
+        "    \n",
+        "    song = result['tracks']['items'][0]\n",
+        "    \n",
+        "    id = song['id']\n",
+        "    \n",
+        "    try:\n",
+        "        song_data = data[(data['id'] == id)].iloc[0]\n",
+        "        return song_data\n",
+        "    except:\n",
+        "        try:\n",
+        "            audio_features = sp.audio_features(id)\n",
+        "            song_data = {\n",
+        "                'valence': audio_features[0]['valence'],\n",
+        "                \"year\" : result['tracks']['items'][0]['album']['release_date'][:4],\n",
+        "                'acousticness': audio_features[0]['acousticness'],\n",
+        "                'artists': list(map(lambda x: x['name'], result['tracks']['items'][0]['artists'])),\n",
+        "                'danceability': audio_features[0]['danceability'],\n",
+        "                'duration_ms': audio_features[0]['duration_ms'],\n",
+        "                'energy': audio_features[0]['energy'],\n",
+        "                'id': id,\n",
+        "                'instrumentalness': audio_features[0]['instrumentalness'],\n",
+        "                'key': audio_features[0]['key'],\n",
+        "                'liveness': audio_features[0]['liveness'],\n",
+        "                'loudness': audio_features[0]['loudness'],\n",
+        "                'mode': audio_features[0]['mode'],\n",
+        "                'name': result['tracks']['items'][0]['name'],\n",
+        "                'popularity': result['tracks']['items'][0]['popularity'],\n",
+        "                'speechiness': audio_features[0]['speechiness'],\n",
+        "                'tempo': audio_features[0]['tempo']\n",
+        "            }\n",
+        "        except:\n",
+        "            log.write('Error: Failed to get audio features from Spotify')\n",
+        "            return None\n",
+        "        \n",
+        "        return pd.DataFrame([song_data], columns=DF_COLUMNS)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def get_song_data(song_name,data):\n",
+        "    try:\n",
+        "        song_data = data[(data['song_name'] == song_name)].iloc[0].to_df()\n",
+        "        return song_data\n",
+        "    except:\n",
+        "        return get_song_spotify(song_name,data)\n",
+        "        "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "song_data = get_song_data('Shape of You',df)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def df_song_data(list_song_name,data):\n",
+        "    rows_song_data = pd.DataFrame(columns=DF_COLUMNS)\n",
+        "    for song_name in list_song_name:\n",
+        "        rows_song_data.(get_song_data(song_name,data))\n",
+        "        \n",
+        "    return pd.DataFrame(rows_song_data,columns=DF_COLUMNS)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "df_song_data(['Shape of You','Despacito'],df)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "vector = pipeline.named_steps[[\"preprocessor\",]].transform(df_song_data(['Shape of You','Despacito'],df))\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "mean_vector = vector.mean(axis=0)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "predicted_cluster = kmeans.predict([mean_vector])"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from scipy.spatial.distance import cdist\n",
+        "import numpy as np\n",
+        "\n",
+        "def songs_recommendation(list_song_name,data):\n",
+        "\n",
+        "    vector = pipeline.named_steps[\"preprocessor\"].transform(df_song_data(list_song_name,df))\n",
+        "    vector = pipeline.named_steps[\"scaler\"].transform(vector)\n",
+        "\n",
+        "    vector = vector.mean(axis=0)\n",
+        "\n",
+        "    predicted_cluster = kmeans.predict([vector])\n",
+        "    \n",
+        "    cluster_data = df[pipeline.named_steps[\"kmeans\"].labels_ == predicted_cluster[0]]\n",
+        "    \n",
+        "    vector_cluster = pipeline.named_steps[\"preprocessor\"].transform(cluster_data)\n",
+        "    vector_cluster = pipeline.named_steps[\"scaler\"].transform(vector_cluster)\n",
+        "    \n",
+        "    distance = cdist([vector],vector_cluster)\n",
+        "    index = list(np.argsort(distance)[:, :10][0])\n",
+        "    \n",
+        "    recsongs = cluster_data.iloc[index]\n",
+        "    return recsongs[~recsongs['name'].isin(list_song_name)]"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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": "3.12.3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

recyclebin/check.ipynb

@@ -0,0 +1,230 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import yaml\n",
+    "import spotipy\n",
+    "from spotipy.oauth2 import SpotifyOAuth,SpotifyClientCredentials\n",
+    "\n",
+    "stream= open(\"streamlit/spotify/spotify.yaml\")\n",
+    "spotify_details = yaml.safe_load(stream)\n",
+    "auth_manager = SpotifyClientCredentials(client_id=spotify_details['Client_id'],\n",
+    "                                        client_secret=spotify_details['client_secret'])\n",
+    "sp = spotipy.client.Spotify(auth_manager=auth_manager)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'danceability': 0.808,\n",
+       "  'energy': 0.626,\n",
+       "  'key': 7,\n",
+       "  'loudness': -12.733,\n",
+       "  'mode': 1,\n",
+       "  'speechiness': 0.168,\n",
+       "  'acousticness': 0.00187,\n",
+       "  'instrumentalness': 0.159,\n",
+       "  'liveness': 0.376,\n",
+       "  'valence': 0.37,\n",
+       "  'tempo': 123.99,\n",
+       "  'type': 'audio_features',\n",
+       "  'id': '4JpKVNYnVcJ8tuMKjAj50A',\n",
+       "  'uri': 'spotify:track:4JpKVNYnVcJ8tuMKjAj50A',\n",
+       "  'track_href': 'https://api.spotify.com/v1/tracks/4JpKVNYnVcJ8tuMKjAj50A',\n",
+       "  'analysis_url': 'https://api.spotify.com/v1/audio-analysis/4JpKVNYnVcJ8tuMKjAj50A',\n",
+       "  'duration_ms': 535223,\n",
+       "  'time_signature': 4}]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_song_spotipy(song_name,data):\n",
+    "    \n",
+    "    results = sp.search(q=song_name, limit=1)\n",
+    "    \n",
+    "    if results['tracks']['items'] == []:\n",
+    "        return None\n",
+    "    \n",
+    "    song_id = results['tracks']['items'][0]['id']\n",
+    "    \n",
+    "    try:\n",
+    "        song_data = data[(data['id'] == song_id)].iloc[0]\n",
+    "        return song_data\n",
+    "    \n",
+    "    except:   \n",
+    "        try:\n",
+    "            audio_features = sp.audio_features(song_id)\n",
+    "            song_data = {\n",
+    "                'name': results['tracks']['items'][0]['name'],\n",
+    "                'id': song_id,\n",
+    "                'artist_name': list(map(lambda x: x['name'], results['tracks']['items'][0]['artists'])),\n",
+    "                'danceability': audio_features[0]['danceability'],\n",
+    "                'energy': audio_features[0]['energy'],\n",
+    "                'key': audio_features[0]['key'],\n",
+    "                'loudness': audio_features[0]['loudness'],\n",
+    "                'mode': audio_features[0]['mode'],\n",
+    "                'speechiness': audio_features[0]['speechiness'],\n",
+    "                'acousticness': audio_features[0]['acousticness'],\n",
+    "                'instrumentalness': audio_features[0]['instrumentalness'],\n",
+    "                'liveness': audio_features[0]['liveness'],\n",
+    "                'valence': audio_features[0]['valence'],\n",
+    "                'tempo': audio_features[0]['tempo'],\n",
+    "                'duration_ms': audio_features[0]['duration_ms'],\n",
+    "                'time_signature': audio_features[0]['time_signature'],\n",
+    "                'popularity': results['tracks']['items'][0]['popularity'], \n",
+    "                \"year\" : results['tracks']['items'][0]['album']['release_date'][:4],\n",
+    "            }\n",
+    "            return song_data\n",
+    "\n",
+    "        except:\n",
+    "            return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'song_name': 'Cincin',\n",
+       " 'song_id': '7J0isBrUxhIYZVdrBOOlIh',\n",
+       " 'artist_name': ['Hindia'],\n",
+       " 'danceability': 0.531,\n",
+       " 'energy': 0.882,\n",
+       " 'key': 4,\n",
+       " 'loudness': -4.205,\n",
+       " 'mode': 0,\n",
+       " 'speechiness': 0.0559,\n",
+       " 'acousticness': 0.00445,\n",
+       " 'instrumentalness': 0,\n",
+       " 'liveness': 0.621,\n",
+       " 'valence': 0.476,\n",
+       " 'tempo': 155.024,\n",
+       " 'duration_ms': 266330,\n",
+       " 'time_signature': 4}"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def get_song_data(song_name, data):\n",
+    "    \n",
+    "    try:\n",
+    "        song_data = data[(data['song_name'] == song_name)].iloc[0]\n",
+    "        return song_data\n",
+    "    except:\n",
+    "        return get_song_spotipy(song_name, data)\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def artists_hash(song_data):\n",
+    "    artists = song_data['artists']\n",
+    "    hash_artists = h.transform(artists)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_mean_vector(song_list, data):\n",
+    "    song_vectors_list = []\n",
+    "    \n",
+    "    for song in song_list:\n",
+    "        song_data = get_song_data(song, data)\n",
+    "        if song_data is None:\n",
+    "            continue\n",
+    "        \n",
+    "        song_vector = "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dict_contoh = {\n",
+    "    'song_name': 'song_name',\n",
+    "    'artists': 'artists',\n",
+    "    'danceability': 'danceability',\n",
+    "    'energy': 'energy',\n",
+    "}\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "KeyError",
+     "evalue": "('song_name', 'artists')",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[5], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdict_contoh\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43msong_name\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43martists\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\n",
+      "\u001b[0;31mKeyError\u001b[0m: ('song_name', 'artists')"
+     ]
+    }
+   ],
+   "source": [
+    "dict_contoh['song_name', 'artists']"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".env",
+   "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": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,7 @@
+joblib==1.4.2
+numpy==2.0.0
+pandas==2.2.2
+PyYAML==6.0.1
+PyYAML==6.0.1
+scipy==1.14.0
+spotipy==2.24.0

spotify/spotify.yaml

@@ -0,0 +1,2 @@
+Client_id : 598aa182877149449da2c07b959e006d
+client_secret : 6553d92e14a140f69ec9bd816efa3719