#!/usr/bin/env python
# coding: utf-8

# ## Importing Libraries and Loading Data 

# In[1]:


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt


# In[2]:


# Reading movies file
movies = pd.read_csv('movies.csv', sep=',', encoding='latin-1', usecols=['title', 'genres'])


# In[3]:


movies.head()


# In[4]:


# Break up the big genre string into a string array
movies['genres'] = movies['genres'].str.split('|')
# Convert genres to string value
movies['genres'] = movies['genres'].fillna("").astype('str')


# # Recommendation based on Genre

# In[5]:


from sklearn.feature_extraction.text import TfidfVectorizer
tf = TfidfVectorizer(analyzer='word',ngram_range=(1, 2),min_df=0, stop_words='english')
tfidf_matrix = tf.fit_transform(movies['genres'])
tfidf_matrix.shape


# In[6]:


from sklearn.metrics.pairwise import cosine_similarity
cosine_sim = cosine_similarity(tfidf_matrix, tfidf_matrix)
cosine_sim[:4, :4]


# In[7]:


# Build a 1-dimensional array with movie titles
titles = movies['title']
indices = pd.Series(movies.index, index=movies['title'])

# Function that get movie recommendations based on the cosine similarity score of movie genres
def genre_recommendations(title):
    idx = indices[title]
    sim_scores = list(enumerate(cosine_sim[idx]))
    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
    sim_scores = sim_scores[1:21]
    movie_indices = [i[0] for i in sim_scores]
    return titles.iloc[movie_indices]


# In[8]:


genre_recommendations('Dark Knight ').head(20)


# # Recommendation based on Title

# In[9]:


from sklearn.feature_extraction.text import TfidfVectorizer
tf = TfidfVectorizer(analyzer='word',ngram_range=(1, 2),min_df=0, stop_words='english')
tfidf_matrix = tf.fit_transform(movies['title'])
tfidf_matrix.shape


# In[10]:


from sklearn.metrics.pairwise import cosine_similarity
cosine_sim = cosine_similarity(tfidf_matrix, tfidf_matrix)
cosine_sim[:4, :4]


# In[11]:


# Build a 1-dimensional array with movie titles
titles = movies['title']
indices = pd.Series(movies.index, index=movies['title'])

# Function that get movie recommendations based on the cosine similarity score of movie genres
def title_recommendations(title):
    idx = indices[title]
    sim_scores = list(enumerate(cosine_sim[idx]))
    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
    sim_scores = sim_scores[1:21]
    movie_indices = [i[0] for i in sim_scores]
    return titles.iloc[movie_indices]


# In[12]:


title_recommendations('Dark Knight ').head(20)