main.py

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt
#Import TfIdfVectorizer from scikit-learn
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel
df1=pd.read_csv('/Users/sbm/Desktop/AI_projects/input-data/tmdb_5000_credits.csv')
df2=pd.read_csv('/Users/sbm/Desktop/AI_projects/input-data/tmdb_5000_movies.csv')
df1.columns = ['id','tittle','cast','crew']
df2= df2.merge(df1,on='id')
df2.head(5)
C= df2['vote_average'].mean()
m= df2['vote_count'].quantile(0.9)
q_movies = df2.copy().loc[df2['vote_count'] >= m]
q_movies.shape
def weighted_rating(x, m=m, C=C):
    v = x['vote_count']
    R = x['vote_average']
    # Calculation based on the IMDB formula
    return (v/(v+m) * R) + (m/(m+v) * C)
q_movies['score'] = q_movies.apply(weighted_rating, axis=1)
#Sort movies based on score calculated above
q_movies = q_movies.sort_values('score', ascending=False)

#Print the top 15 movies
# print(q_movies[['title', 'vote_count', 'vote_average', 'score']].head(10))

pop= df2.sort_values('popularity', ascending=False)
plt.figure(figsize=(12,4))

def plotGraph(pop):
    plt.barh(pop['title'].head(6),pop['popularity'].head(6), align='center',
        color='skyblue')
    plt.gca().invert_yaxis()
    plt.xlabel("Popularity")
    plt.title("Popular Movies")

plotGraph(pop)

#Define a TF-IDF Vectorizer Object. Remove all english stop words such as 'the', 'a'
tfidf = TfidfVectorizer(stop_words='english')

#Replace NaN with an empty string
df2['overview'] = df2['overview'].fillna('')

#Construct the required TF-IDF matrix by fitting and transforming the data
tfidf_matrix = tfidf.fit_transform(df2['overview'])

#Output the shape of tfidf_matrix
print(tfidf_matrix.shape)
def calculate_cosine_similarity(tfidf_matrix):
    # Compute the cosine similarity matrix
    cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)
    return cosine_sim

cosine_sim = calculate_cosine_similarity(tfidf_matrix)
# Compute the cosine similarity matrix
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)
#Construct a reverse map of indices and movie titles
indices = pd.Series(df2.index, index=df2['title']).drop_duplicates()
# Function that takes in movie title as input and outputs most similar movies
def get_recommendations(title, cosine_sim=cosine_sim):
    # Get the index of the movie that matches the title
    idx = indices[title]

    # Get the pairwise similarity scores of all movies with that movie
    sim_scores = list(enumerate(cosine_sim[idx]))

    # Sort the movies based on the similarity scores
    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)

    # Get the scores of the 10 most similar movies
    sim_scores = sim_scores[1:11]

    # Get the movie indices
    movie_indices = [i[0] for i in sim_scores]

    # Return the top 10 most similar movies
    return df2['title'].iloc[movie_indices]

# Ensure the function call is inside the main block
if __name__ == "__main__":
    print(get_recommendations('The Dark Knight Rises'))