{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "SKRYfHwWyVaG"
},
"outputs": [],
"source": [
"# Importing Libraries\n",
"import numpy as np\n",
"import pandas as pd\n",
"import sklearn\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"import warnings\n",
"warnings.simplefilter(action='ignore', category=FutureWarning)"
]
},
{
"cell_type": "code",
"source": [
"#loading rating dataset\n",
"ratings = pd.read_csv(\"https://s3-us-west-2.amazonaws.com/recommender-tutorial/ratings.csv\")\n",
"print(ratings.head())"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "v_ZFn93Wy1ho",
"outputId": "97f98476-d909-4050-bc37-68369391d756"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" userId movieId rating timestamp\n",
"0 1 1 4.0 964982703\n",
"1 1 3 4.0 964981247\n",
"2 1 6 4.0 964982224\n",
"3 1 47 5.0 964983815\n",
"4 1 50 5.0 964982931\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# loading movie dataset\n",
"movies = pd.read_csv(\"https://s3-us-west-2.amazonaws.com/recommender-tutorial/movies.csv\")\n",
"print(movies.head())"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "_RCPOQWfy269",
"outputId": "4c3c68a1-dbbb-4795-d96a-4f9c11d3731b"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" movieId title \\\n",
"0 1 Toy Story (1995) \n",
"1 2 Jumanji (1995) \n",
"2 3 Grumpier Old Men (1995) \n",
"3 4 Waiting to Exhale (1995) \n",
"4 5 Father of the Bride Part II (1995) \n",
"\n",
" genres \n",
"0 Adventure|Animation|Children|Comedy|Fantasy \n",
"1 Adventure|Children|Fantasy \n",
"2 Comedy|Romance \n",
"3 Comedy|Drama|Romance \n",
"4 Comedy \n"
]
}
]
},
{
"cell_type": "code",
"source": [
"n_ratings = len(ratings)\n",
"n_movies = len(ratings['movieId'].unique())\n",
"n_users = len(ratings['userId'].unique())\n",
"\n",
"print(f\"Number of ratings: {n_ratings}\")\n",
"print(f\"Number of unique movieId's: {n_movies}\")\n",
"print(f\"Number of unique users: {n_users}\")\n",
"print(f\"Average ratings per user: {round(n_ratings/n_users, 2)}\")\n",
"print(f\"Average ratings per movie: {round(n_ratings/n_movies, 2)}\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ypivRYgqy4kb",
"outputId": "360eef9e-9186-4ed6-ed50-fe8e6a3fabf0"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Number of ratings: 100836\n",
"Number of unique movieId's: 9724\n",
"Number of unique users: 610\n",
"Average ratings per user: 165.3\n",
"Average ratings per movie: 10.37\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"user_freq = ratings[['userId', 'movieId']].groupby(\n",
" 'userId').count().reset_index()\n",
"user_freq.columns = ['userId', 'n_ratings']\n",
"print(user_freq.head())"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "PYZsye4-zAfi",
"outputId": "fb38061d-d9bc-4552-de9b-de418780ec32"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" userId n_ratings\n",
"0 1 232\n",
"1 2 29\n",
"2 3 39\n",
"3 4 216\n",
"4 5 44\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Find Lowest and Highest rated movies:\n",
"mean_rating = ratings.groupby('movieId')[['rating']].mean()\n",
"# Lowest rated movies\n",
"lowest_rated = mean_rating['rating'].idxmin()\n",
"movies.loc[movies['movieId'] == lowest_rated]\n",
"# Highest rated movies\n",
"highest_rated = mean_rating['rating'].idxmax()\n",
"movies.loc[movies['movieId'] == highest_rated]\n",
"# show number of people who rated movies rated movie highest\n",
"ratings[ratings['movieId']==highest_rated]\n",
"# show number of people who rated movies rated movie lowest\n",
"ratings[ratings['movieId']==lowest_rated]\n",
"\n",
"## the above movies has very low dataset. We will use bayesian average\n",
"movie_stats = ratings.groupby('movieId')[['rating']].agg(['count', 'mean'])\n",
"movie_stats.columns = movie_stats.columns.droplevel()"
],
"metadata": {
"id": "H1s9d6QIzBzv"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Now, we create user-item matrix using scipy csr matrix\n",
"from scipy.sparse import csr_matrix\n",
"\n",
"def create_matrix(df):\n",
"\n",
" N = len(df['userId'].unique())\n",
" M = len(df['movieId'].unique())\n",
"\n",
" # Map Ids to indices\n",
" user_mapper = dict(zip(np.unique(df[\"userId\"]), list(range(N))))\n",
" movie_mapper = dict(zip(np.unique(df[\"movieId\"]), list(range(M))))\n",
"\n",
" # Map indices to IDs\n",
" user_inv_mapper = dict(zip(list(range(N)), np.unique(df[\"userId\"])))\n",
" movie_inv_mapper = dict(zip(list(range(M)), np.unique(df[\"movieId\"])))\n",
"\n",
" user_index = [user_mapper[i] for i in df['userId']]\n",
" movie_index = [movie_mapper[i] for i in df['movieId']]\n",
"\n",
" X = csr_matrix((df[\"rating\"], (movie_index, user_index)), shape=(M, N))\n",
"\n",
" return X, user_mapper, movie_mapper, user_inv_mapper, movie_inv_mapper\n",
"\n",
"X, user_mapper, movie_mapper, user_inv_mapper, movie_inv_mapper = create_matrix(ratings)"
],
"metadata": {
"id": "2tG23gzjzDLg"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"\"\"\"\n",
"Find similar movies using KNN\n",
"\"\"\"\n",
"from sklearn.neighbors import NearestNeighbors\n",
"def find_similar_movies(movie_id, X, k, metric='cosine', show_distance=False):\n",
"\n",
" neighbour_ids = []\n",
"\n",
" movie_ind = movie_mapper[movie_id]\n",
" movie_vec = X[movie_ind]\n",
" k+=1\n",
" kNN = NearestNeighbors(n_neighbors=k, algorithm=\"brute\", metric=metric)\n",
" kNN.fit(X)\n",
" movie_vec = movie_vec.reshape(1,-1)\n",
" neighbour = kNN.kneighbors(movie_vec, return_distance=show_distance)\n",
" for i in range(0,k):\n",
" n = neighbour.item(i)\n",
" neighbour_ids.append(movie_inv_mapper[n])\n",
" neighbour_ids.pop(0)\n",
" return neighbour_ids\n",
"\n",
"\n",
"movie_titles = dict(zip(movies['movieId'], movies['title']))\n",
"\n",
"movie_id = 3\n",
"\n",
"similar_ids = find_similar_movies(movie_id, X, k=10)\n",
"movie_title = movie_titles[movie_id]\n",
"\n",
"print(f\"Since you watched {movie_title}\")\n",
"for i in similar_ids:\n",
" print(movie_titles[i])"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "onBGmGk5zGAZ",
"outputId": "c5a409ff-c16d-413f-9339-a2ff977eef69"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Since you watched Grumpier Old Men (1995)\n",
"Grumpy Old Men (1993)\n",
"Striptease (1996)\n",
"Nutty Professor, The (1996)\n",
"Twister (1996)\n",
"Father of the Bride Part II (1995)\n",
"Broken Arrow (1996)\n",
"Bio-Dome (1996)\n",
"Truth About Cats & Dogs, The (1996)\n",
"Sabrina (1995)\n",
"Birdcage, The (1996)\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"def recommend_movies_for_user(user_id, X, user_mapper, movie_mapper, movie_inv_mapper, k=10):\n",
" df1 = ratings[ratings['userId'] == user_id]\n",
"\n",
" if df1.empty:\n",
" print(f\"User with ID {user_id} does not exist.\")\n",
" return\n",
"\n",
" movie_id = df1[df1['rating'] == max(df1['rating'])]['movieId'].iloc[0]\n",
"\n",
" movie_titles = dict(zip(movies['movieId'], movies['title']))\n",
"\n",
" similar_ids = find_similar_movies(movie_id, X, k)\n",
" movie_title = movie_titles.get(movie_id, \"Movie not found\")\n",
"\n",
" if movie_title == \"Movie not found\":\n",
" print(f\"Movie with ID {movie_id} not found.\")\n",
" return\n",
"\n",
" print(f\"Since you watched {movie_title}, you might also like:\")\n",
" for i in similar_ids:\n",
" print(movie_titles.get(i, \"Movie not found\"))"
],
"metadata": {
"id": "PrN_SjhMzHxy"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"user_id = 150 # Replace with the desired user ID\n",
"recommend_movies_for_user(user_id, X, user_mapper, movie_mapper, movie_inv_mapper, k=10)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "L13wNuTOzJry",
"outputId": "5316c18d-8323-4fc8-8ed0-a503edf93f29"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Since you watched Twelve Monkeys (a.k.a. 12 Monkeys) (1995), you might also like:\n",
"Pulp Fiction (1994)\n",
"Terminator 2: Judgment Day (1991)\n",
"Independence Day (a.k.a. ID4) (1996)\n",
"Seven (a.k.a. Se7en) (1995)\n",
"Fargo (1996)\n",
"Fugitive, The (1993)\n",
"Usual Suspects, The (1995)\n",
"Jurassic Park (1993)\n",
"Star Wars: Episode IV - A New Hope (1977)\n",
"Heat (1995)\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"user_id = 415 # Replace with the desired user ID\n",
"recommend_movies_for_user(user_id, X, user_mapper, movie_mapper, movie_inv_mapper, k=10)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "pEZ5ISP8zLB1",
"outputId": "e61b8c3f-db5d-4c49-b876-5bc19a490ce4"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Since you watched Pulp Fiction (1994), you might also like:\n",
"Silence of the Lambs, The (1991)\n",
"Shawshank Redemption, The (1994)\n",
"Seven (a.k.a. Se7en) (1995)\n",
"Forrest Gump (1994)\n",
"Usual Suspects, The (1995)\n",
"Braveheart (1995)\n",
"Fight Club (1999)\n",
"Fargo (1996)\n",
"Terminator 2: Judgment Day (1991)\n",
"Reservoir Dogs (1992)\n"
]
}
]
}
]
}