From 1a2a34c8ec552e5923178de508144ddb46884ead Mon Sep 17 00:00:00 2001
From: MridulGupta75 <66024896+MridulGupta75@users.noreply.github.com>
Date: Thu, 6 Oct 2022 11:46:34 +0530
Subject: [PATCH] Added Music Recommandation System

---
 .../Music Recommandation system.ipynb         | 570 ++++++++++++++++++
 1 file changed, 570 insertions(+)
 create mode 100644 Python Codes/Music Recommandation system.ipynb

diff --git a/Python Codes/Music Recommandation system.ipynb b/Python Codes/Music Recommandation system.ipynb
new file mode 100644
index 0000000..0ee187f
--- /dev/null
+++ b/Python Codes/Music Recommandation system.ipynb	
@@ -0,0 +1,570 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 163,
+   "id": "bbec132a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 164,
+   "id": "2e799e1a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.metrics.pairwise import cosine_similarity"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 165,
+   "id": "0a59f28b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "songs=pd.read_csv(\"songdata.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 166,
+   "id": "d07d684a",
+   "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>artist</th>\n",
+       "      <th>song</th>\n",
+       "      <th>link</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>ABBA</td>\n",
+       "      <td>Ahe's My Kind Of Girl</td>\n",
+       "      <td>/a/abba/ahes+my+kind+of+girl_20598417.html</td>\n",
+       "      <td>Look at her face, it's a wonderful face  \\r\\nA...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ABBA</td>\n",
+       "      <td>Andante, Andante</td>\n",
+       "      <td>/a/abba/andante+andante_20002708.html</td>\n",
+       "      <td>Take it easy with me, please  \\r\\nTouch me gen...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ABBA</td>\n",
+       "      <td>As Good As New</td>\n",
+       "      <td>/a/abba/as+good+as+new_20003033.html</td>\n",
+       "      <td>I'll never know why I had to go  \\r\\nWhy I had...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ABBA</td>\n",
+       "      <td>Bang</td>\n",
+       "      <td>/a/abba/bang_20598415.html</td>\n",
+       "      <td>Making somebody happy is a question of give an...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ABBA</td>\n",
+       "      <td>Bang-A-Boomerang</td>\n",
+       "      <td>/a/abba/bang+a+boomerang_20002668.html</td>\n",
+       "      <td>Making somebody happy is a question of give an...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  artist                   song                                        link  \\\n",
+       "0   ABBA  Ahe's My Kind Of Girl  /a/abba/ahes+my+kind+of+girl_20598417.html   \n",
+       "1   ABBA       Andante, Andante       /a/abba/andante+andante_20002708.html   \n",
+       "2   ABBA         As Good As New        /a/abba/as+good+as+new_20003033.html   \n",
+       "3   ABBA                   Bang                  /a/abba/bang_20598415.html   \n",
+       "4   ABBA       Bang-A-Boomerang      /a/abba/bang+a+boomerang_20002668.html   \n",
+       "\n",
+       "                                                text  \n",
+       "0  Look at her face, it's a wonderful face  \\r\\nA...  \n",
+       "1  Take it easy with me, please  \\r\\nTouch me gen...  \n",
+       "2  I'll never know why I had to go  \\r\\nWhy I had...  \n",
+       "3  Making somebody happy is a question of give an...  \n",
+       "4  Making somebody happy is a question of give an...  "
+      ]
+     },
+     "execution_count": 166,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "songs.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 167,
+   "id": "f5585fc6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(57650, 4)"
+      ]
+     },
+     "execution_count": 167,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "songs.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 168,
+   "id": "aff4b924",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "songs = songs.sample(n=5000).drop('link', axis=1).reset_index(drop=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 169,
+   "id": "277ee09b",
+   "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>artist</th>\n",
+       "      <th>song</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>R. Kelly</td>\n",
+       "      <td>Break Up (Thats All We Do)</td>\n",
+       "      <td>Make up, and break up  \\r\\nThat's all we do  \\...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Zeromancer</td>\n",
+       "      <td>Mosquito Coil</td>\n",
+       "      <td>It's looking out  \\r\\nFrom inside  \\r\\nA Chris...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Great Big Sea</td>\n",
+       "      <td>Wave Over Wave</td>\n",
+       "      <td>Only name Table Rogers a share man am I  \\r\\nO...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Dan Fogelberg</td>\n",
+       "      <td>Faces Of America</td>\n",
+       "      <td>There was a time, a simpler time  \\r\\nWhen a m...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Elvis Costello</td>\n",
+       "      <td>Joe Porterhouse</td>\n",
+       "      <td>The children sit upon the stairs  \\r\\nHigh abo...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           artist                        song  \\\n",
+       "0        R. Kelly  Break Up (Thats All We Do)   \n",
+       "1      Zeromancer               Mosquito Coil   \n",
+       "2   Great Big Sea              Wave Over Wave   \n",
+       "3   Dan Fogelberg            Faces Of America   \n",
+       "4  Elvis Costello             Joe Porterhouse   \n",
+       "\n",
+       "                                                text  \n",
+       "0  Make up, and break up  \\r\\nThat's all we do  \\...  \n",
+       "1  It's looking out  \\r\\nFrom inside  \\r\\nA Chris...  \n",
+       "2  Only name Table Rogers a share man am I  \\r\\nO...  \n",
+       "3  There was a time, a simpler time  \\r\\nWhen a m...  \n",
+       "4  The children sit upon the stairs  \\r\\nHigh abo...  "
+      ]
+     },
+     "execution_count": 169,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "songs.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 170,
+   "id": "e11f1dbf",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5000, 3)"
+      ]
+     },
+     "execution_count": 170,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "songs.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 171,
+   "id": "f2058edb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "songs['text'] = songs['text'].str.replace('\\r', '')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 172,
+   "id": "187736e3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "songs['text'] = songs['text'].str.replace('\\n', '')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 173,
+   "id": "6244e6a4",
+   "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>artist</th>\n",
+       "      <th>song</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>R. Kelly</td>\n",
+       "      <td>Break Up (Thats All We Do)</td>\n",
+       "      <td>Make up, and break up  That's all we do  Then ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Zeromancer</td>\n",
+       "      <td>Mosquito Coil</td>\n",
+       "      <td>It's looking out  From inside  A Christmas bon...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Great Big Sea</td>\n",
+       "      <td>Wave Over Wave</td>\n",
+       "      <td>Only name Table Rogers a share man am I  On a ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Dan Fogelberg</td>\n",
+       "      <td>Faces Of America</td>\n",
+       "      <td>There was a time, a simpler time  When a man c...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Elvis Costello</td>\n",
+       "      <td>Joe Porterhouse</td>\n",
+       "      <td>The children sit upon the stairs  High above a...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "           artist                        song  \\\n",
+       "0        R. Kelly  Break Up (Thats All We Do)   \n",
+       "1      Zeromancer               Mosquito Coil   \n",
+       "2   Great Big Sea              Wave Over Wave   \n",
+       "3   Dan Fogelberg            Faces Of America   \n",
+       "4  Elvis Costello             Joe Porterhouse   \n",
+       "\n",
+       "                                                text  \n",
+       "0  Make up, and break up  That's all we do  Then ...  \n",
+       "1  It's looking out  From inside  A Christmas bon...  \n",
+       "2  Only name Table Rogers a share man am I  On a ...  \n",
+       "3  There was a time, a simpler time  When a man c...  \n",
+       "4  The children sit upon the stairs  High above a...  "
+      ]
+     },
+     "execution_count": 173,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "songs.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 174,
+   "id": "84d02c33",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tfidf = TfidfVectorizer(analyzer='word', stop_words='english')\n",
+    "lyrics_matrix = tfidf.fit_transform(songs['text'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 175,
+   "id": "c326c8ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cosine_similarities = cosine_similarity(lyrics_matrix) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 176,
+   "id": "dbada089",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "similarities = {}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 177,
+   "id": "1efe66f0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in range(len(cosine_similarities)):\n",
+    "    similar_indices = cosine_similarities[i].argsort()[:-50:-1] \n",
+    "    similarities[songs['song'].iloc[i]] = [(cosine_similarities[i][x], songs['song'][x], songs['artist'][x]) for x in similar_indices][1:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 178,
+   "id": "01209ca8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class ContentBasedRecommender:\n",
+    "    def __init__(self, matrix):\n",
+    "        self.matrix_similar = matrix\n",
+    "\n",
+    "    def _print_message(self, song, recom_song):\n",
+    "        rec_items = len(recom_song)\n",
+    "        print(f'The recommended songs for {song} are:')\n",
+    "        for i in range(rec_items):\n",
+    "            print(f\"{recom_song[i][1]} by {recom_song[i][2]}\") \n",
+    "            \n",
+    "    def recommend(self, recommendation):\n",
+    "        song = recommendation['song']\n",
+    "        number_songs = recommendation['number_songs']\n",
+    "        recom_song = self.matrix_similar[song][:number_songs]\n",
+    "        self._print_message(song=song, recom_song=recom_song)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 179,
+   "id": "56c182c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "recommedations = ContentBasedRecommender(similarities)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 180,
+   "id": "8c90bd31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "recommendation = {\n",
+    "    \"song\": songs['song'].iloc[10],\n",
+    "    \"number_songs\": 4 \n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 181,
+   "id": "53ea6163",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The recommended songs for Running For Cover are:\n",
+      "Keep On Running by Stevie Wonder\n",
+      "Running Man by Hanson\n",
+      "Save Me A Place by Fleetwood Mac\n",
+      "Watercolours In The Rain by Roxette\n"
+     ]
+    }
+   ],
+   "source": [
+    "recommedations.recommend(recommendation)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 182,
+   "id": "38ecc2b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "recommendation2 = {\n",
+    "    \"song\": songs['song'].iloc[120],\n",
+    "    \"number_songs\": 4 \n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 161,
+   "id": "122b988f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The recommended songs for No Way are:\n",
+      "Replacement Girl by Drake\n",
+      "Guadalajara by Elvis Presley\n",
+      "Soul Deep by Roxette\n",
+      "I Put A Spell On You by Bette Midler\n"
+     ]
+    }
+   ],
+   "source": [
+    "recommedations.recommend(recommendation2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 162,
+   "id": "cc0867a4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle\n",
+    "pickle.dump(similarities,open(\"sim.pkl\",\"wb\"))\n",
+    "pickle.dump(songs.to_dict(),open('songs.pkl','wb'))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}