Load the negative dataset to jupyter and rename the positive dataset

Author: LerkkaP

…ED_Spotify_artist_info_random_sample.csv artists_negative.csvCLEANED_Spotify_artist_info_random_sample.csv renamed to artists_negative.csv CLEANED_Spotify_artist_info_random_sample.csv renamed to artists_negative.csv

@@ -12,24 +12,52 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "31cf5f11-c2d1-4fb5-bfa2-d16d25e6b130",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
    "source": [
     "%pip install --quiet pandas==2.3.2 wordcloud==1.9.4"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 3,
    "id": "564a2258",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "                      ids           names  popularity  followers  \\\n",
+      "0  2P3aLwJ41aRYkyFFw2FRM7  sam concepcion          45     168497   \n",
+      "1  2FCVB3cfCC0e3O8G7Gs8t6    bleib modern          28      23349   \n",
+      "2  3ZaPFQ05J5qSM5I3Smbp44          tevvez          58     259154   \n",
+      "3  71WUmUmWWaqqGtVP8MlPJb   semi.official           4       1050   \n",
+      "4  0MVM5Khj39EkpVtLvU9Ujp        ovsicori           4        316   \n",
+      "\n",
+      "                                genres  first_release  last_release  \\\n",
+      "0                                  opm           2007          2023   \n",
+      "1          dark post-punk, modern goth           2014          2024   \n",
+      "2                        gym hardstyle           2018          2024   \n",
+      "3  abstract hip hop, minnesota hip hop           2003          2003   \n",
+      "4                             ambient            2017          2023   \n",
+      "\n",
+      "   num_releases  num_tracks  monthly_listeners  \n",
+      "0            20           1           583900.0  \n",
+      "1            14           3            40842.0  \n",
+      "2            20           1          1521671.0  \n",
+      "3             1          17              820.0  \n",
+      "4             8           5             1025.0  \n",
       "92\n",
       "[ 3  5  1  1 20  1  2  6  3  1  1  2  2  1  1  2  1  1  2  1  3  2  2  1\n",
       "  1 13  1  8 23  1  1  4  2  3  1  1  1  1  1  1  1  1  9  2  4  9  1  3\n",
@@ -44,7 +72,8 @@
     "import matplotlib.pyplot as plt\n",
     "from wordcloud import WordCloud\n",
     "\n",
-    "df_csv = pd.read_csv(\"artists.csv\")\n",
+    "df_positive = pd.read_csv(\"artists_positive.csv\")\n",
+    "df_negative = pd.read_csv(\"artists_negative.csv\")\n",
     "df_json = pd.read_json(\"spotify-artists.json\")\n",
     "df_json_normalized = pd.json_normalize(df_json[\"artists\"])\n",
     "\n",
@@ -62,12 +91,10 @@
     "        \"Image\": image}\n",
     "\n",
     "df_json_final = pd.DataFrame(data)\n",
-    "df = df_json_final.merge(df_csv, on='SpotifyId', how='inner')\n",
-    "df[\"Date\"] = pd.to_datetime(df[\"Date\"], format='%Y%m%d')\n",
-    "#print(df.head())\n",
+    "df = df_json_final.merge(df_positive, on=\"SpotifyId\", how=\"inner\")\n",
+    "df[\"Date\"] = pd.to_datetime(df[\"Date\"], format=\"%Y%m%d\")\n",
     "\n",
     "flat_genres = df.explode(\"Genres\")\n",
-    "#print(flat_genres)\n",
     "\n",
     "unique, counts = np.unique(flat_genres[\"Genres\"], return_counts=True)\n",
     "print(len(unique))\n",
@@ -202,9 +229,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Week1",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "week1"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -216,7 +243,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,