Subhradeep Rang srang992

## import.py
import pandas as pd
import numpy as np
import re
import nltk
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
nltk.download('stopwords')
nltk.download('punkt')
from nltk import word_tokenize
from nltk.corpus import stopwords

## netflix_data.csv
show_id,type,title,director,cast,country,date_added,release_year,rating,duration,listed_in,description
s1,Movie,Dick Johnson Is Dead,Kirsten Johnson,,United States,"September 25, 2021",2020,PG-13,90 min,Documentaries,"As her father nears the end of his life, filmmaker Kirsten Johnson stages his death in inventive and comical ways to help them both face the inevitable."
s2,TV Show,Blood & Water,,"Ama Qamata, Khosi Ngema, Gail Mabalane, Thabang Molaba, Dillon Windvogel, Natasha Thahane, Arno Greeff, Xolile Tshabalala, Getmore Sithole, Cindy Mahlangu, Ryle De Morny, Greteli Fincham, Sello Maake Ka-Ncube, Odwa Gwanya, Mekaila Mathys, Sandi Schultz, Duane Williams, Shamilla Miller, Patrick Mofokeng",South Africa,"September 24, 2021",2021,TV-MA,2 Seasons,"International TV Shows, TV Dramas, TV Mysteries","After crossing paths at a party, a Cape Town teen sets out to prove whether a private-school swimming star is her sister who was abducted at birth."
s3,TV Show,Ganglands,Julien Leclercq,"Sami Bouajila, Tracy Gotoas

## clean_desc.py
def clean_desc(s):
    s = str(s)
    s = s.lower()
    s = re.sub(r'[^a-zA-Z]', ' ', s)
    return s

# make a copy of the main data and do the preprocessing steps on that data
netflix_data_copy['clean_desc'] = netflix_data_copy['description'].apply(cleaning)

#tokenizing the words for lemmatization and removing stopwords

## tfidf.py

# making an object of TfidfVectorizer in which words contains only in 1 document and word repeated in 70% of documents are ignored.
tfidf = TfidfVectorizer(min_df = 2, max_df = 0.7)


# fitting the cleaned text in TfidfVectorizer
X = tfidf.fit_transform(netflix_data_copy['clean_desc'])


# making a suitable dataframe for calculating the cosine similarity and save it

## recommend.py
def recommend_table(list_of_movie_enjoyed, tfidf_data, movie_count=20):
    """
    function for recommending movies
    :param list_of_movie_enjoyed: list of movies
    :param tfidf_data: self-explanatory
    :param movie_count: no of movies to suggest
    :return: dataframe containing suggested movie
    """
    movie_enjoyed_df = tfidf_data.reindex(list_of_movie_enjoyed)
    user_prof = movie_enjoyed_df.mean()

## app.py
"""
main streamlit app
"""
import pickle
import pandas as pd
import streamlit as st
from streamlit import session_state as session
from src.recommend.recommend import recommend_table


## app_import.py
import pickle
import pandas as pd
import streamlit as st
from streamlit import session_state as session
from src.recommend.recommend import recommend_table

## load_file.py
@st.cache(persist=True, show_spinner=False, suppress_st_warning=True)
def load_data():
    """
    load and cache data
    :return: tfidf data
    """
    tfidf_data = pd.read_csv("data/tfidf_data.csv", index_col=0)
    return tfidf_data


## app.py
dataframe = None

st.title("""
Netflix Recommendation System
This is an Content Based Recommender System made on implicit ratings :smile:.
 """)

st.text("")
st.text("")
st.text("")

## test_web.html
<html>
  <body>
    <div>
      <p>Hello World!</p>
      <div>
        <p>Choose me!</p>
      </div>
    </div>
    <div>
      <p>Why are you not looking at me?</p>
	import pandas as pd
	import numpy as np
	import re
	import nltk
	from sklearn.feature_extraction.text import TfidfVectorizer
	from sklearn.metrics.pairwise import cosine_similarity
	nltk.download('stopwords')
	nltk.download('punkt')
	from nltk import word_tokenize
	from nltk.corpus import stopwords
	show_id,type,title,director,cast,country,date_added,release_year,rating,duration,listed_in,description
	s1,Movie,Dick Johnson Is Dead,Kirsten Johnson,,United States,"September 25, 2021",2020,PG-13,90 min,Documentaries,"As her father nears the end of his life, filmmaker Kirsten Johnson stages his death in inventive and comical ways to help them both face the inevitable."
	s2,TV Show,Blood & Water,,"Ama Qamata, Khosi Ngema, Gail Mabalane, Thabang Molaba, Dillon Windvogel, Natasha Thahane, Arno Greeff, Xolile Tshabalala, Getmore Sithole, Cindy Mahlangu, Ryle De Morny, Greteli Fincham, Sello Maake Ka-Ncube, Odwa Gwanya, Mekaila Mathys, Sandi Schultz, Duane Williams, Shamilla Miller, Patrick Mofokeng",South Africa,"September 24, 2021",2021,TV-MA,2 Seasons,"International TV Shows, TV Dramas, TV Mysteries","After crossing paths at a party, a Cape Town teen sets out to prove whether a private-school swimming star is her sister who was abducted at birth."
	s3,TV Show,Ganglands,Julien Leclercq,"Sami Bouajila, Tracy Gotoas
	def clean_desc(s):
	s = str(s)
	s = s.lower()
	s = re.sub(r'[^a-zA-Z]', ' ', s)
	return s

	# make a copy of the main data and do the preprocessing steps on that data
	netflix_data_copy['clean_desc'] = netflix_data_copy['description'].apply(cleaning)

	#tokenizing the words for lemmatization and removing stopwords

	# making an object of TfidfVectorizer in which words contains only in 1 document and word repeated in 70% of documents are ignored.
	tfidf = TfidfVectorizer(min_df = 2, max_df = 0.7)


	# fitting the cleaned text in TfidfVectorizer
	X = tfidf.fit_transform(netflix_data_copy['clean_desc'])


	# making a suitable dataframe for calculating the cosine similarity and save it
	def recommend_table(list_of_movie_enjoyed, tfidf_data, movie_count=20):
	"""
	function for recommending movies
	:param list_of_movie_enjoyed: list of movies
	:param tfidf_data: self-explanatory
	:param movie_count: no of movies to suggest
	:return: dataframe containing suggested movie
	"""
	movie_enjoyed_df = tfidf_data.reindex(list_of_movie_enjoyed)
	user_prof = movie_enjoyed_df.mean()
	"""
	main streamlit app
	"""
	import pickle
	import pandas as pd
	import streamlit as st
	from streamlit import session_state as session
	from src.recommend.recommend import recommend_table
	@st.cache(persist=True, show_spinner=False, suppress_st_warning=True)
	def load_data():
	"""
	load and cache data
	:return: tfidf data
	"""
	tfidf_data = pd.read_csv("data/tfidf_data.csv", index_col=0)
	return tfidf_data
	dataframe = None

	st.title("""
	Netflix Recommendation System
	This is an Content Based Recommender System made on implicit ratings :smile:.
	""")

	st.text("")
	st.text("")
	st.text("")
	<html>
	<body>
	<div>
	<p>Hello World!</p>
	<div>
	<p>Choose me!</p>
	</div>
	</div>
	<div>
	<p>Why are you not looking at me?</p>