Oguz
Get In Touch
Kadıköy, İstanbul
mail@oguzerdogan.com
Ph: +90 554 524 0164
Back
Uncategorized
49 min read

WordPress Enlighter Plugin – Theme Options

Merhaba bu yazımda WordPress üzerinde kodları görselleştirmek için kullanılan bir plugin olan Enlighter – Customizable Syntax Highlighter‘ın stil seçeneklerini gösteriyorum.

Blog’um içerisinde kod satırlarını göstermek için kendi stilimi oluşturduğum ve kullanacağım son temayı da en son kısımda görebilirsiniz.

Englighter

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Godzilla

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Beyond

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Classic

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

MowTwo

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Eclipse

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Droide

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Minimal

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Atomic

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Rowhammer

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Bootsrap4

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Dracula

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Monokai

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])

Custom

import pickle
import streamlit as st
import requests
import os
from PIL import Image
from dotenv import load_dotenv
import pandas as pd
logo = Image.open('images/logo.png')
frame = Image.open('images/frame.png')

load_dotenv()
API = os.getenv('MOVIE_API')

st.set_page_config(
   page_title="Film Tavsiye Sistemi",
   page_icon="🤖",
   layout="wide",
   initial_sidebar_state="expanded",
)


def get_movie_poster(movie_id):
    url = f"https://api.themoviedb.org/3/movie/{movie_id}?api_key={API}&language=en-US"
    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


def content_based_recommender(title, cosine_sim, dataframe):
    # index'leri olusturma
    indices = pd.Series(dataframe.index, index=dataframe['original_title'])
    indices = indices[~indices.index.duplicated(keep='last')]
    # title'ın index'ini yakalama
    movie_index = indices[title]
    # title'a gore benzerlik skorlarını hesapalama
    similarity_scores = pd.DataFrame(cosine_sim[movie_index], columns=["score"])
    # kendisi haric ilk 10 filmi getirme
    movie_indices = similarity_scores.sort_values("score", ascending=False)[1:6].index

    movie_names = []
    movie_posters = []

    for i in movie_indices[0:6]:
        # fetch the movie poster
        movie_id = dataframe.iloc[i].id
        movie_posters.append(get_movie_poster(movie_id))
        movie_names.append(movies.iloc[i]['original_title'])

    return movie_names, movie_posters


col1, col2, col3 = st.columns(3)
with col1:
    st.image(frame, width=125)

with col2:
    st.image(logo, caption='🧠 Miull, Skills of tomorrow!', width=350)

with col3:
    st.markdown("[![Foo](https://img.icons8.com/material-outlined/96/000000/github.png)](https://github.com/oguzerdo)")

st.header('Film Tavsiye Sistemi')

movies = pickle.load(open('model/movie_list.pkl', 'rb'))
cosine_sim = pickle.load(open('model/cosine_sim.pkl', 'rb'))

movie_list = movies['original_title'].values  # Tüm film isimlerini alma

selected_movie = st.selectbox("Açılır menüden film seçiniz.", movie_list) # Açılır menüde film isimlerini gösterme.

if st.button('Tavsiyeleri gör'):
    movie_names, movie_posters = content_based_recommender(selected_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])


if st.button('Şansımı denemek istiyorum'):
    random_movie = movies['original_title'].sample(1).values[0]
    st.subheader(random_movie)
    movie_names, movie_posters = content_based_recommender(random_movie, cosine_sim, movies)

    col1, col2, col3, col4, col5 = st.columns(5)
    with col1:
        st.text(movie_names[0])
        st.image(movie_posters[0])
    with col2:
        st.text(movie_names[1])
        st.image(movie_posters[1])

    with col3:
        st.text(movie_names[2])
        st.image(movie_posters[2])
    with col4:
        st.text(movie_names[3])
        st.image(movie_posters[3])
    with col5:
        st.text(movie_names[4])
        st.image(movie_posters[4])
Oğuz
Oğuz
http://www.oguzerdogan.com
Data Delivery Guy

Related Posts

  • Oğuz
  • Posted by Oğuz
Eylül 5, 2023
1 min read

Linux Anaconda ve Miniconda Kurulumu

Selam bu yazımda bir linux makinesi içerisinde hızlıca miniconda kurulumunun nasıl olacağını anlatacağım. Miniconda anaconda’nın daha...

101 Data Engineer Uncategorized
Read More
  • Oğuz
  • Posted by Oğuz
Aralık 25, 2022
4 min read

Google Cloud Üzerinde Storage Seçimi

Google Cloud Platform içerisinde çok fazla farklı depolama ve database seçeneği mevcut. Bir data engineer olarak,...

Uncategorized
Read More
  • Oğuz
  • Posted by Oğuz
Aralık 23, 2022
5 min read

SSH Key ile Birden Fazla GIT Servisini Organize Etme

Selamlar, özellikle birden fazla Github servisini ya da aynı Git servisinde birden fazla hesapla kullandığımızda authentication...

Uncategorized
Read More

Leave a Reply

E-posta adresiniz yayınlanmayacak. Gerekli alanlar * ile işaretlenmişlerdir

We use cookies to give you the best experience. Cookie Policy