Spaces:

diivien
/

Music-Popularity-Prediction

Running

App Files Files Community

diivien commited on Jun 30, 2023

Commit

18ad38b

1 Parent(s): b208fb5

finalize

Browse files

Files changed (2) hide show

Exploratory Data Analysis.ipynb +0 -0
Model Building.ipynb +91 -7

Exploratory Data Analysis.ipynb CHANGED Viewed

The diff for this file is too large to render. See raw diff

Model Building.ipynb CHANGED Viewed

@@ -1068,7 +1068,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
    "id": "d66743ec",
    "metadata": {},
    "outputs": [
@@ -1333,7 +1333,7 @@
        "[64334 rows x 13 columns]"
       ]
      },
-     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1348,7 +1348,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
    "id": "4797c378",
    "metadata": {},
    "outputs": [],
@@ -1364,7 +1364,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
    "id": "6c8a6fd9",
    "metadata": {},
    "outputs": [],
@@ -1405,7 +1405,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
    "id": "077ca8bd",
    "metadata": {},
    "outputs": [
@@ -1506,7 +1506,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
    "id": "e4c87875",
    "metadata": {},
    "outputs": [
@@ -1627,7 +1627,7 @@
        "oversampling2              0.004290          0.004862  0.006231  "
       ]
      },
-     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1639,6 +1639,81 @@
     "df_pivot"
    ]
   },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -5437,6 +5512,15 @@
     "evaluate_study(pipe_LGBM,lgbm_best_params)\n"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,

   },
   {
    "cell_type": "code",
+   "execution_count": 9,
    "id": "d66743ec",
    "metadata": {},
    "outputs": [
        "[64334 rows x 13 columns]"
       ]
      },
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
   },
   {
    "cell_type": "code",
+   "execution_count": 10,
    "id": "4797c378",
    "metadata": {},
    "outputs": [],
   },
   {
    "cell_type": "code",
+   "execution_count": 11,
    "id": "6c8a6fd9",
    "metadata": {},
    "outputs": [],
   },
   {
    "cell_type": "code",
+   "execution_count": 12,
    "id": "077ca8bd",
    "metadata": {},
    "outputs": [
   },
   {
    "cell_type": "code",
+   "execution_count": 13,
    "id": "e4c87875",
    "metadata": {},
    "outputs": [
        "oversampling2              0.004290          0.004862  0.006231  "
       ]
      },
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
     "df_pivot"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "1317e9df",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" 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;num&#x27;,\n",
+       "                                                  Pipeline(steps=[(&#x27;scaler&#x27;,\n",
+       "                                                                   MinMaxScaler())]),\n",
+       "                                                  [&#x27;loudness&#x27;, &#x27;duration_ms&#x27;,\n",
+       "                                                   &#x27;tempo&#x27;]),\n",
+       "                                                 (&#x27;cat&#x27;,\n",
+       "                                                  Pipeline(steps=[(&#x27;encoder&#x27;,\n",
+       "                                                                   TargetEncoder())]),\n",
+       "                                                  [&#x27;track_genre&#x27;, &#x27;key&#x27;,\n",
+       "                                                   &#x27;time_signature&#x27;])])),\n",
+       "                (&#x27;over&#x27;,\n",
+       "                 SMOTENC(categorical_features=[3, 4, 5, 6, 9], n_jobs=4,\n",
+       "                         random_state=42)),\n",
+       "                (&#x27;classifier&#x27;, LinearSVC(dual=False))])</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 sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;preprocessor&#x27;,\n",
+       "                 ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
+       "                                   transformers=[(&#x27;num&#x27;,\n",
+       "                                                  Pipeline(steps=[(&#x27;scaler&#x27;,\n",
+       "                                                                   MinMaxScaler())]),\n",
+       "                                                  [&#x27;loudness&#x27;, &#x27;duration_ms&#x27;,\n",
+       "                                                   &#x27;tempo&#x27;]),\n",
+       "                                                 (&#x27;cat&#x27;,\n",
+       "                                                  Pipeline(steps=[(&#x27;encoder&#x27;,\n",
+       "                                                                   TargetEncoder())]),\n",
+       "                                                  [&#x27;track_genre&#x27;, &#x27;key&#x27;,\n",
+       "                                                   &#x27;time_signature&#x27;])])),\n",
+       "                (&#x27;over&#x27;,\n",
+       "                 SMOTENC(categorical_features=[3, 4, 5, 6, 9], n_jobs=4,\n",
+       "                         random_state=42)),\n",
+       "                (&#x27;classifier&#x27;, LinearSVC(dual=False))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">preprocessor: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(remainder=&#x27;passthrough&#x27;,\n",
+       "                  transformers=[(&#x27;num&#x27;,\n",
+       "                                 Pipeline(steps=[(&#x27;scaler&#x27;, MinMaxScaler())]),\n",
+       "                                 [&#x27;loudness&#x27;, &#x27;duration_ms&#x27;, &#x27;tempo&#x27;]),\n",
+       "                                (&#x27;cat&#x27;,\n",
+       "                                 Pipeline(steps=[(&#x27;encoder&#x27;, TargetEncoder())]),\n",
+       "                                 [&#x27;track_genre&#x27;, &#x27;key&#x27;, &#x27;time_signature&#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 sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">num</label><div class=\"sk-toggleable__content\"><pre>[&#x27;loudness&#x27;, &#x27;duration_ms&#x27;, &#x27;tempo&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MinMaxScaler</label><div class=\"sk-toggleable__content\"><pre>MinMaxScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>[&#x27;track_genre&#x27;, &#x27;key&#x27;, &#x27;time_signature&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">TargetEncoder</label><div class=\"sk-toggleable__content\"><pre>TargetEncoder()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">remainder</label><div class=\"sk-toggleable__content\"><pre>[&#x27;explicit&#x27;, &#x27;danceability&#x27;, &#x27;energy&#x27;, &#x27;mode&#x27;, &#x27;speechiness&#x27;, &#x27;acousticness&#x27;, &#x27;instrumentalness&#x27;, &#x27;liveness&#x27;, &#x27;valence&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">passthrough</label><div class=\"sk-toggleable__content\"><pre>passthrough</pre></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator 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 sk-toggleable__label-arrow\">SMOTENC</label><div class=\"sk-toggleable__content\"><pre>SMOTENC(categorical_features=[3, 4, 5, 6, 9], n_jobs=4, random_state=42)</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator 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 sk-toggleable__label-arrow\">LinearSVC</label><div class=\"sk-toggleable__content\"><pre>LinearSVC(dual=False)</pre></div></div></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "Pipeline(steps=[('preprocessor',\n",
+       "                 ColumnTransformer(remainder='passthrough',\n",
+       "                                   transformers=[('num',\n",
+       "                                                  Pipeline(steps=[('scaler',\n",
+       "                                                                   MinMaxScaler())]),\n",
+       "                                                  ['loudness', 'duration_ms',\n",
+       "                                                   'tempo']),\n",
+       "                                                 ('cat',\n",
+       "                                                  Pipeline(steps=[('encoder',\n",
+       "                                                                   TargetEncoder())]),\n",
+       "                                                  ['track_genre', 'key',\n",
+       "                                                   'time_signature'])])),\n",
+       "                ('over',\n",
+       "                 SMOTENC(categorical_features=[3, 4, 5, 6, 9], n_jobs=4,\n",
+       "                         random_state=42)),\n",
+       "                ('classifier', LinearSVC(dual=False))])"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "oversampling2_SVC"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
     "evaluate_study(pipe_LGBM,lgbm_best_params)\n"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "37bcee22",
+   "metadata": {},
+   "source": [
+    "#### CatBoost Classifier Model"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,