movie recommendation syste,

Movie-recommendation-system/README.md

@@ -0,0 +1,2 @@
+# Movie-recommendation-system
+Movie Recommendation System , My first ML project

Movie-recommendation-system/app.py

@@ -0,0 +1,54 @@
+#pseudo code
+
+import streamlit as st
+import pickle
+import requests
+
+movies = pickle.load(open("movies_list.pkl", 'rb'))
+similarity = pickle.load(open("similarity.pkl",'rb'))
+movies_list = movies['title'].values
+st.header("Movie Recommender System")
+selectvalue=st.selectbox("Selcet movie from dropdown", movies_list)
+
+def fetch_poster(movie_id):
+    try:
+        url = "https://api.themoviedb.org/3/movie/{}?api_key=8cfe8dff1a6fff88fe27b573ee65c035&language=en-US".format(movie_id)
+        data = requests.get(url)
+        data = data.json()
+        poster_path = data['poster_path']
+        full_path = "https://image.tmdb.org/t/p/w500/" + poster_path
+        return full_path
+    except requests.exceptions.SSLError:
+        # Handle the error gracefully
+        st.error("Unable to fetch poster due to SSL verification error")
+        return "placeholder_image_url"  # Return a default image URL
+
+def recommend(movie):
+    index=movies[movies['title']==movie].index[0]
+    distance = sorted(list(enumerate(similarity[index])), reverse=True, key=lambda vector:vector[1])
+    recommend_movie=[]
+    recommend_poster=[]
+    for i in distance[1:6]:
+        movies_id=movies.iloc[i[0]].id
+        recommend_movie.append(movies.iloc[i[0]].title)
+        recommend_poster.append(fetch_poster(movies_id))
+    return recommend_movie, recommend_poster
+
+if st.button("Show Recommend"):
+    movie_name, movie_poster = recommend(selectvalue)
+    col1 , col2, col3, col4, col5 = st.columns(5)
+    with col1:
+        st.text(movie_name[0])
+        st.image(movie_poster[0])
+    with col2:
+        st.text(movie_name[1])
+        st.image(movie_poster[1])
+    with col3:
+        st.text(movie_name[2])
+        st.image(movie_poster[2])
+    with col4:
+        st.text(movie_name[3])
+        st.image(movie_poster[3])
+    with col5:
+        st.text(movie_name[4])
+        st.image(movie_poster[4])

Movie-recommendation-system/app_2.py

@@ -0,0 +1,51 @@
+# main code
+
+import streamlit as st
+import pickle
+import requests
+
+movies = pickle.load(open("movies_list.pkl", 'rb'))
+similarity = pickle.load(open("similarity.pkl",'rb'))
+movies_list = movies['title'].values
+st.header("Movie Recommender System")
+selectvalue = st.selectbox("Select movie from dropdown", movies_list)
+
+def fetch_poster(movie_id):
+    try:
+        url = "https://api.themoviedb.org/3/movie/{}?api_key=8cfe8dff1a6fff88fe27b573ee65c035&language=en-US".format(movie_id)
+        # Disablinb SSL verification for development
+        data = requests.get(url, verify=False)
+        data = data.json()
+        poster_path = data['poster_path']
+        if poster_path:
+            full_path = "https://image.tmdb.org/t/p/w500/" + poster_path
+            return full_path
+        else:
+            st.warning(f"No poster found for movie ID {movie_id}")
+            return None
+    except Exception as e:
+        st.error(f"Error fetching poster: {str(e)}")
+        return None
+
+def recommend(movie):
+    index = movies[movies['title']==movie].index[0]
+    distance = sorted(list(enumerate(similarity[index])), reverse=True, key=lambda vector:vector[1])
+    recommend_movie = []
+    recommend_poster = []
+    for i in distance[1:6]:
+        movies_id = movies.iloc[i[0]].id
+        recommend_movie.append(movies.iloc[i[0]].title)
+        poster = fetch_poster(movies_id)
+        recommend_poster.append(poster)
+    return recommend_movie, recommend_poster
+
+if st.button("Show Recommend"):
+    movie_name, movie_poster = recommend(selectvalue)
+    cols = st.columns(5)
+    for idx, (col, name, poster) in enumerate(zip(cols, movie_name, movie_poster)):
+        with col:
+            st.text(name)
+            if poster:  # showing image if url exists
+                st.image(poster)
+            else:
+                st.write("No poster available")

Movie-recommendation-system/main.ipynb

@@ -0,0 +1,1393 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "movies = pd.read_csv('top10K-TMDB-movies.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "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>id</th>\n",
+       "      <th>title</th>\n",
+       "      <th>genre</th>\n",
+       "      <th>original_language</th>\n",
+       "      <th>overview</th>\n",
+       "      <th>popularity</th>\n",
+       "      <th>release_date</th>\n",
+       "      <th>vote_average</th>\n",
+       "      <th>vote_count</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>278</td>\n",
+       "      <td>The Shawshank Redemption</td>\n",
+       "      <td>Drama,Crime</td>\n",
+       "      <td>en</td>\n",
+       "      <td>Framed in the 1940s for the double murder of h...</td>\n",
+       "      <td>94.075</td>\n",
+       "      <td>1994-09-23</td>\n",
+       "      <td>8.7</td>\n",
+       "      <td>21862</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>19404</td>\n",
+       "      <td>Dilwale Dulhania Le Jayenge</td>\n",
+       "      <td>Comedy,Drama,Romance</td>\n",
+       "      <td>hi</td>\n",
+       "      <td>Raj is a rich, carefree, happy-go-lucky second...</td>\n",
+       "      <td>25.408</td>\n",
+       "      <td>1995-10-19</td>\n",
+       "      <td>8.7</td>\n",
+       "      <td>3731</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>238</td>\n",
+       "      <td>The Godfather</td>\n",
+       "      <td>Drama,Crime</td>\n",
+       "      <td>en</td>\n",
+       "      <td>Spanning the years 1945 to 1955, a chronicle o...</td>\n",
+       "      <td>90.585</td>\n",
+       "      <td>1972-03-14</td>\n",
+       "      <td>8.7</td>\n",
+       "      <td>16280</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>424</td>\n",
+       "      <td>Schindler's List</td>\n",
+       "      <td>Drama,History,War</td>\n",
+       "      <td>en</td>\n",
+       "      <td>The true story of how businessman Oskar Schind...</td>\n",
+       "      <td>44.761</td>\n",
+       "      <td>1993-12-15</td>\n",
+       "      <td>8.6</td>\n",
+       "      <td>12959</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>240</td>\n",
+       "      <td>The Godfather: Part II</td>\n",
+       "      <td>Drama,Crime</td>\n",
+       "      <td>en</td>\n",
+       "      <td>In the continuing saga of the Corleone crime f...</td>\n",
+       "      <td>57.749</td>\n",
+       "      <td>1974-12-20</td>\n",
+       "      <td>8.6</td>\n",
+       "      <td>9811</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>667257</td>\n",
+       "      <td>Impossible Things</td>\n",
+       "      <td>Family,Drama</td>\n",
+       "      <td>es</td>\n",
+       "      <td>Matilde is a woman who, after the death of her...</td>\n",
+       "      <td>14.358</td>\n",
+       "      <td>2021-06-17</td>\n",
+       "      <td>8.6</td>\n",
+       "      <td>255</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>129</td>\n",
+       "      <td>Spirited Away</td>\n",
+       "      <td>Animation,Family,Fantasy</td>\n",
+       "      <td>ja</td>\n",
+       "      <td>A young girl, Chihiro, becomes trapped in a st...</td>\n",
+       "      <td>92.056</td>\n",
+       "      <td>2001-07-20</td>\n",
+       "      <td>8.5</td>\n",
+       "      <td>13093</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>730154</td>\n",
+       "      <td>Your Eyes Tell</td>\n",
+       "      <td>Romance,Drama</td>\n",
+       "      <td>ja</td>\n",
+       "      <td>A tragic accident lead to Kaori's blindness, b...</td>\n",
+       "      <td>51.345</td>\n",
+       "      <td>2020-10-23</td>\n",
+       "      <td>8.5</td>\n",
+       "      <td>339</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>372754</td>\n",
+       "      <td>Dou kyu sei – Classmates</td>\n",
+       "      <td>Romance,Animation</td>\n",
+       "      <td>ja</td>\n",
+       "      <td>Rihito Sajo, an honor student with a perfect s...</td>\n",
+       "      <td>14.285</td>\n",
+       "      <td>2016-02-20</td>\n",
+       "      <td>8.5</td>\n",
+       "      <td>239</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>372058</td>\n",
+       "      <td>Your Name.</td>\n",
+       "      <td>Romance,Animation,Drama</td>\n",
+       "      <td>ja</td>\n",
+       "      <td>High schoolers Mitsuha and Taki are complete s...</td>\n",
+       "      <td>158.270</td>\n",
+       "      <td>2016-08-26</td>\n",
+       "      <td>8.5</td>\n",
+       "      <td>8895</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       id                        title                     genre  \\\n",
+       "0     278     The Shawshank Redemption               Drama,Crime   \n",
+       "1   19404  Dilwale Dulhania Le Jayenge      Comedy,Drama,Romance   \n",
+       "2     238                The Godfather               Drama,Crime   \n",
+       "3     424             Schindler's List         Drama,History,War   \n",
+       "4     240       The Godfather: Part II               Drama,Crime   \n",
+       "5  667257            Impossible Things              Family,Drama   \n",
+       "6     129                Spirited Away  Animation,Family,Fantasy   \n",
+       "7  730154               Your Eyes Tell             Romance,Drama   \n",
+       "8  372754     Dou kyu sei – Classmates         Romance,Animation   \n",
+       "9  372058                   Your Name.   Romance,Animation,Drama   \n",
+       "\n",
+       "  original_language                                           overview  \\\n",
+       "0                en  Framed in the 1940s for the double murder of h...   \n",
+       "1                hi  Raj is a rich, carefree, happy-go-lucky second...   \n",
+       "2                en  Spanning the years 1945 to 1955, a chronicle o...   \n",
+       "3                en  The true story of how businessman Oskar Schind...   \n",
+       "4                en  In the continuing saga of the Corleone crime f...   \n",
+       "5                es  Matilde is a woman who, after the death of her...   \n",
+       "6                ja  A young girl, Chihiro, becomes trapped in a st...   \n",
+       "7                ja  A tragic accident lead to Kaori's blindness, b...   \n",
+       "8                ja  Rihito Sajo, an honor student with a perfect s...   \n",
+       "9                ja  High schoolers Mitsuha and Taki are complete s...   \n",
+       "\n",
+       "   popularity release_date  vote_average  vote_count  \n",
+       "0      94.075   1994-09-23           8.7       21862  \n",
+       "1      25.408   1995-10-19           8.7        3731  \n",
+       "2      90.585   1972-03-14           8.7       16280  \n",
+       "3      44.761   1993-12-15           8.6       12959  \n",
+       "4      57.749   1974-12-20           8.6        9811  \n",
+       "5      14.358   2021-06-17           8.6         255  \n",
+       "6      92.056   2001-07-20           8.5       13093  \n",
+       "7      51.345   2020-10-23           8.5         339  \n",
+       "8      14.285   2016-02-20           8.5         239  \n",
+       "9     158.270   2016-08-26           8.5        8895  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies.head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "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>id</th>\n",
+       "      <th>popularity</th>\n",
+       "      <th>vote_average</th>\n",
+       "      <th>vote_count</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>10000.000000</td>\n",
+       "      <td>10000.000000</td>\n",
+       "      <td>10000.000000</td>\n",
+       "      <td>10000.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>161243.505000</td>\n",
+       "      <td>34.697267</td>\n",
+       "      <td>6.621150</td>\n",
+       "      <td>1547.309400</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>211422.046043</td>\n",
+       "      <td>211.684175</td>\n",
+       "      <td>0.766231</td>\n",
+       "      <td>2648.295789</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>5.000000</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>4.600000</td>\n",
+       "      <td>200.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>10127.750000</td>\n",
+       "      <td>9.154750</td>\n",
+       "      <td>6.100000</td>\n",
+       "      <td>315.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>30002.500000</td>\n",
+       "      <td>13.637500</td>\n",
+       "      <td>6.600000</td>\n",
+       "      <td>583.500000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>310133.500000</td>\n",
+       "      <td>25.651250</td>\n",
+       "      <td>7.200000</td>\n",
+       "      <td>1460.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>934761.000000</td>\n",
+       "      <td>10436.917000</td>\n",
+       "      <td>8.700000</td>\n",
+       "      <td>31917.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  id    popularity  vote_average    vote_count\n",
+       "count   10000.000000  10000.000000  10000.000000  10000.000000\n",
+       "mean   161243.505000     34.697267      6.621150   1547.309400\n",
+       "std    211422.046043    211.684175      0.766231   2648.295789\n",
+       "min         5.000000      0.600000      4.600000    200.000000\n",
+       "25%     10127.750000      9.154750      6.100000    315.000000\n",
+       "50%     30002.500000     13.637500      6.600000    583.500000\n",
+       "75%    310133.500000     25.651250      7.200000   1460.000000\n",
+       "max    934761.000000  10436.917000      8.700000  31917.000000"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 10000 entries, 0 to 9999\n",
+      "Data columns (total 9 columns):\n",
+      " #   Column             Non-Null Count  Dtype  \n",
+      "---  ------             --------------  -----  \n",
+      " 0   id                 10000 non-null  int64  \n",
+      " 1   title              10000 non-null  object \n",
+      " 2   genre              9997 non-null   object \n",
+      " 3   original_language  10000 non-null  object \n",
+      " 4   overview           9987 non-null   object \n",
+      " 5   popularity         10000 non-null  float64\n",
+      " 6   release_date       10000 non-null  object \n",
+      " 7   vote_average       10000 non-null  float64\n",
+      " 8   vote_count         10000 non-null  int64  \n",
+      "dtypes: float64(2), int64(2), object(5)\n",
+      "memory usage: 703.2+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "movies.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['id', 'title', 'genre', 'original_language', 'overview', 'popularity',\n",
+       "       'release_date', 'vote_average', 'vote_count'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "movies.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "movies=movies[['id','title','overview','genre']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "movies['tags']=movies['overview']+movies['genre']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_movies = movies.drop(columns=['overview','genre'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "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>id</th>\n",
+       "      <th>title</th>\n",
+       "      <th>tags</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>278</td>\n",
+       "      <td>The Shawshank Redemption</td>\n",
+       "      <td>Framed in the 1940s for the double murder of h...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>19404</td>\n",
+       "      <td>Dilwale Dulhania Le Jayenge</td>\n",
+       "      <td>Raj is a rich, carefree, happy-go-lucky second...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>238</td>\n",
+       "      <td>The Godfather</td>\n",
+       "      <td>Spanning the years 1945 to 1955, a chronicle o...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>424</td>\n",
+       "      <td>Schindler's List</td>\n",
+       "      <td>The true story of how businessman Oskar Schind...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>240</td>\n",
+       "      <td>The Godfather: Part II</td>\n",
+       "      <td>In the continuing saga of the Corleone crime f...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9995</th>\n",
+       "      <td>10196</td>\n",
+       "      <td>The Last Airbender</td>\n",
+       "      <td>The story follows the adventures of Aang, a yo...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9996</th>\n",
+       "      <td>331446</td>\n",
+       "      <td>Sharknado 3: Oh Hell No!</td>\n",
+       "      <td>The sharks take bite out of the East Coast whe...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9997</th>\n",
+       "      <td>13995</td>\n",
+       "      <td>Captain America</td>\n",
+       "      <td>During World War II, a brave, patriotic Americ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9998</th>\n",
+       "      <td>2312</td>\n",
+       "      <td>In the Name of the King: A Dungeon Siege Tale</td>\n",
+       "      <td>A man named Farmer sets out to rescue his kidn...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9999</th>\n",
+       "      <td>455957</td>\n",
+       "      <td>Domino</td>\n",
+       "      <td>Seeking justice for his partner’s murder by an...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>10000 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          id                                          title  \\\n",
+       "0        278                       The Shawshank Redemption   \n",
+       "1      19404                    Dilwale Dulhania Le Jayenge   \n",
+       "2        238                                  The Godfather   \n",
+       "3        424                               Schindler's List   \n",
+       "4        240                         The Godfather: Part II   \n",
+       "...      ...                                            ...   \n",
+       "9995   10196                             The Last Airbender   \n",
+       "9996  331446                       Sharknado 3: Oh Hell No!   \n",
+       "9997   13995                                Captain America   \n",
+       "9998    2312  In the Name of the King: A Dungeon Siege Tale   \n",
+       "9999  455957                                         Domino   \n",
+       "\n",
+       "                                                   tags  \n",
+       "0     Framed in the 1940s for the double murder of h...  \n",
+       "1     Raj is a rich, carefree, happy-go-lucky second...  \n",
+       "2     Spanning the years 1945 to 1955, a chronicle o...  \n",
+       "3     The true story of how businessman Oskar Schind...  \n",
+       "4     In the continuing saga of the Corleone crime f...  \n",
+       "...                                                 ...  \n",
+       "9995  The story follows the adventures of Aang, a yo...  \n",
+       "9996  The sharks take bite out of the East Coast whe...  \n",
+       "9997  During World War II, a brave, patriotic Americ...  \n",
+       "9998  A man named Farmer sets out to rescue his kidn...  \n",
+       "9999  Seeking justice for his partner’s murder by an...  \n",
+       "\n",
+       "[10000 rows x 3 columns]"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "new_movies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: scikit-learn in c:\\users\\shiva\\.conda\\envs\\aienv\\lib\\site-packages (1.6.0)\n",
+      "Requirement already satisfied: numpy>=1.19.5 in c:\\users\\shiva\\.conda\\envs\\aienv\\lib\\site-packages (from scikit-learn) (2.2.1)\n",
+      "Requirement already satisfied: scipy>=1.6.0 in c:\\users\\shiva\\.conda\\envs\\aienv\\lib\\site-packages (from scikit-learn) (1.14.1)\n",
+      "Requirement already satisfied: joblib>=1.2.0 in c:\\users\\shiva\\.conda\\envs\\aienv\\lib\\site-packages (from scikit-learn) (1.4.2)\n",
+      "Requirement already satisfied: threadpoolctl>=3.1.0 in c:\\users\\shiva\\.conda\\envs\\aienv\\lib\\site-packages (from scikit-learn) (3.5.0)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Install scikit-learn package\n",
+    "%pip install scikit-learn\n",
+    "\n",
+    "from sklearn.feature_extraction.text import CountVectorizer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cv=CountVectorizer(max_features=10000 , stop_words='english')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-2 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: #000;\n",
+       "  --sklearn-color-text-muted: #666;\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: flex;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "  align-items: start;\n",
+       "  justify-content: space-between;\n",
+       "  gap: 0.5em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label .caption {\n",
+       "  font-size: 0.6rem;\n",
+       "  font-weight: lighter;\n",
+       "  color: var(--sklearn-color-text-muted);\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: 0.5em;\n",
+       "  text-align: center;\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>CountVectorizer(max_features=10000, stop_words=&#x27;english&#x27;)</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\"><div class=\"sk-estimator  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label  sk-toggleable__label-arrow\"><div><div>CountVectorizer</div></div><div><a class=\"sk-estimator-doc-link \" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.6/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html\">?<span>Documentation for CountVectorizer</span></a><span class=\"sk-estimator-doc-link \">i<span>Not fitted</span></span></div></label><div class=\"sk-toggleable__content \"><pre>CountVectorizer(max_features=10000, stop_words=&#x27;english&#x27;)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "CountVectorizer(max_features=10000, stop_words='english')"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vector = cv.fit_transform(new_movies['tags'].values.astype('U')).toarray()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(10000, 10000)"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vector.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics.pairwise import cosine_similarity"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "similarity = cosine_similarity(vector)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1.        , 0.05634362, 0.13041013, ..., 0.07559289, 0.11065667,\n",
+       "        0.06900656],\n",
+       "       [0.05634362, 1.        , 0.07715167, ..., 0.        , 0.03636965,\n",
+       "        0.        ],\n",
+       "       [0.13041013, 0.07715167, 1.        , ..., 0.02300219, 0.0673435 ,\n",
+       "        0.09449112],\n",
+       "       ...,\n",
+       "       [0.07559289, 0.        , 0.02300219, ..., 1.        , 0.03253   ,\n",
+       "        0.03042903],\n",
+       "       [0.11065667, 0.03636965, 0.0673435 , ..., 0.03253   , 1.        ,\n",
+       "        0.04454354],\n",
+       "       [0.06900656, 0.        , 0.09449112, ..., 0.03042903, 0.04454354,\n",
+       "        1.        ]], shape=(10000, 10000))"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "similarity"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "np.int64(2)"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "new_movies[new_movies['title']==\"The Godfather\"].index[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The Godfather\n",
+      "The Godfather: Part II\n",
+      "Blood Ties\n",
+      "Joker\n",
+      "Bomb City\n"
+     ]
+    }
+   ],
+   "source": [
+    "distance = sorted(list(enumerate(similarity[2])) , reverse=True, key=lambda vector:vector[1])\n",
+    "for i in distance[0:5]:\n",
+    "    print(new_movies.iloc[i[0]].title)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def recommend(movies):\n",
+    "    index=new_movies[new_movies['title']==movies].index[0]\n",
+    "    distance = sorted(list(enumerate(similarity[index])), reverse=True, key=lambda vector:vector[1])\n",
+    "    for i in distance[0:5]:\n",
+    "        print(new_movies.iloc[i[0]].title)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Iron Man\n",
+      "Iron Man 3\n",
+      "Guardians of the Galaxy Vol. 2\n",
+      "Avengers: Age of Ultron\n",
+      "Star Wars: Episode III - Revenge of the Sith\n"
+     ]
+    }
+   ],
+   "source": [
+    "recommend(\"Iron Man\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pickle.dump(new_movies , open('movies_list.pkl' , 'wb'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pickle.dump(similarity,open('similarity.pkl','wb'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "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>id</th>\n",
+       "      <th>title</th>\n",
+       "      <th>tags</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>278</td>\n",
+       "      <td>The Shawshank Redemption</td>\n",
+       "      <td>Framed in the 1940s for the double murder of h...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>19404</td>\n",
+       "      <td>Dilwale Dulhania Le Jayenge</td>\n",
+       "      <td>Raj is a rich, carefree, happy-go-lucky second...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>238</td>\n",
+       "      <td>The Godfather</td>\n",
+       "      <td>Spanning the years 1945 to 1955, a chronicle o...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>424</td>\n",
+       "      <td>Schindler's List</td>\n",
+       "      <td>The true story of how businessman Oskar Schind...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>240</td>\n",
+       "      <td>The Godfather: Part II</td>\n",
+       "      <td>In the continuing saga of the Corleone crime f...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9995</th>\n",
+       "      <td>10196</td>\n",
+       "      <td>The Last Airbender</td>\n",
+       "      <td>The story follows the adventures of Aang, a yo...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9996</th>\n",
+       "      <td>331446</td>\n",
+       "      <td>Sharknado 3: Oh Hell No!</td>\n",
+       "      <td>The sharks take bite out of the East Coast whe...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9997</th>\n",
+       "      <td>13995</td>\n",
+       "      <td>Captain America</td>\n",
+       "      <td>During World War II, a brave, patriotic Americ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9998</th>\n",
+       "      <td>2312</td>\n",
+       "      <td>In the Name of the King: A Dungeon Siege Tale</td>\n",
+       "      <td>A man named Farmer sets out to rescue his kidn...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9999</th>\n",
+       "      <td>455957</td>\n",
+       "      <td>Domino</td>\n",
+       "      <td>Seeking justice for his partner’s murder by an...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>10000 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          id                                          title  \\\n",
+       "0        278                       The Shawshank Redemption   \n",
+       "1      19404                    Dilwale Dulhania Le Jayenge   \n",
+       "2        238                                  The Godfather   \n",
+       "3        424                               Schindler's List   \n",
+       "4        240                         The Godfather: Part II   \n",
+       "...      ...                                            ...   \n",
+       "9995   10196                             The Last Airbender   \n",
+       "9996  331446                       Sharknado 3: Oh Hell No!   \n",
+       "9997   13995                                Captain America   \n",
+       "9998    2312  In the Name of the King: A Dungeon Siege Tale   \n",
+       "9999  455957                                         Domino   \n",
+       "\n",
+       "                                                   tags  \n",
+       "0     Framed in the 1940s for the double murder of h...  \n",
+       "1     Raj is a rich, carefree, happy-go-lucky second...  \n",
+       "2     Spanning the years 1945 to 1955, a chronicle o...  \n",
+       "3     The true story of how businessman Oskar Schind...  \n",
+       "4     In the continuing saga of the Corleone crime f...  \n",
+       "...                                                 ...  \n",
+       "9995  The story follows the adventures of Aang, a yo...  \n",
+       "9996  The sharks take bite out of the East Coast whe...  \n",
+       "9997  During World War II, a brave, patriotic Americ...  \n",
+       "9998  A man named Farmer sets out to rescue his kidn...  \n",
+       "9999  Seeking justice for his partner’s murder by an...  \n",
+       "\n",
+       "[10000 rows x 3 columns]"
+      ]
+     },
+     "execution_count": 55,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pickle.load(open('movies_list.pkl','rb'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "aienv",
+   "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": "3.10.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Movie-recommendation-system/requirements.txt

@@ -0,0 +1,5 @@
+pandas
+numpy
+seaborn
+matplotlib
+scikit-learn

Movie-recommendation-system/ssh.py

@@ -0,0 +1,15 @@
+import requests
+from requests.packages.urllib3.exceptions import InsecureRequestWarning
+requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
+
+def fetch_url():
+    url = "https://huggingface.co/spaces/Shiva7706/ML_Movie_recommendation_system"
+    try:
+        response = requests.get(url, verify=False)
+        print(f"Status Code: {response.status_code}")
+        print("Connection successful!")
+    except Exception as e:
+        print(f"Error: {e}")
+
+if __name__ == "__main__":
+    fetch_url()