import gradio as gr import os import numpy as np import datetime as dt import hopsworks import pandas as pd import utils import random from PIL import Image from io import BytesIO import requests import pickle MAX_MOVIES = 3 def fetch_new_predictions(): project = hopsworks.login() fs = project.get_feature_store(name='igijul63_featurestore') fg = fs.get_feature_group('movie_predictions', version=1) query = fg.select_all() new_predictions_df = query.read() hopsworks.logout() ids = new_predictions_df['id'].tolist() print(f"Predicted movies are {ids}") details = [] titles = [] for i, movie_id in enumerate(ids): movie_details = utils.get_movie_details(movie_id) if movie_details['budget'] > 0 : # movie_details['predicted_revenue'] = new_predictions[new_predictions['id'] == movie_id]['revenue'].values[0] movie_details['predicted_revenue'] = new_predictions_df.iloc[i,:]['revenue'] # movie_details['release_date'] = dt.datetime.strptime(movie_details['release_date'], '%Y-%m-%d').date() details.append(movie_details) details = pd.DataFrame(details) details.sort_values(by = 'release_date', ascending = False, inplace = True) # details = details[:MAX_MOVIES] idxs = random.sample(range(len(details)), 3) details = details.iloc[idxs, :] new_titles = [f"### {title}" for title in details['title']] new_revenues = [f"#### Predicted revenue is {int(revenue)}\$" for revenue in details['predicted_revenue']] get_img = lambda poster_path : Image.open(BytesIO(requests.get(f"https://image.tmdb.org/t/p/w500{poster_path}", stream=True).content)) new_images = [get_img(poster_path) for poster_path in details['poster_path']] return new_titles[0], new_titles[1], new_titles[2], new_revenues[0], new_revenues[1], new_revenues[2], new_images[0], new_images[1], new_images[2] def fetch_prediction_for_title(title): movie_id = utils.get_movie_by_title(title)['results'][0]['id'] project = hopsworks.login() fs = project.get_feature_store(name='igijul63_featurestore') fg = fs.get_feature_group('movie_predictions', version=1) query = fg.select_all() new_predictions_df = query.read() print(f"Got predictions df") movie_details = utils.get_movie_details(movie_id) if movie_id not in new_predictions_df['id'].tolist(): features = utils.extract_features(movie_id, latest=False) print(features) features_df = pd.DataFrame([features]) features_df = features_df[['top_cast_popularity', 'budget', 'crew_popularity', 'similar_revenues']] features_df[['budget','similar_revenues']] /= 1000000 model = utils.load_model() output = model.predict(features_df) new_revenue = output * 1000000 # new_revenue = random.randint(200 * 1e6, 1000 * 1e6) else: movie_prediction = new_predictions_df[new_predictions_df['id'] == movie_id] new_revenue = movie_prediction['revenue'] movie_details['predicted_revenue'] = new_revenue # movie_prediction['revenue'] new_title = f"### {movie_details['title']}" new_revenue = f"#### Predicted revenue is {int(movie_details['predicted_revenue'])}\$" get_img = lambda poster_path : Image.open(BytesIO(requests.get(f"https://image.tmdb.org/t/p/w500{poster_path}", stream=True).content)) new_image = get_img(movie_details['poster_path']) budget = f"#### Movie with budget of {movie_details['budget']} \$" overview = movie_details['overview'] hopsworks.logout() return new_revenue, new_image, budget, overview new_data = fetch_new_predictions() search_data = fetch_prediction_for_title(new_data[0][4:]) with gr.Blocks("soft") as demo: live = True gr.Markdown("## Movie revenue prediction") with gr.Tabs(): with gr.TabItem("New movies"): gr.Markdown("# Prediction for recently released movies") gr.Markdown("Press the button to see other new predictions!") reload_button = gr.Button(value="Refresh") with gr.Row(): title_0 = gr.Markdown(new_data[0]) title_1 = gr.Markdown(new_data[1]) title_2 = gr.Markdown(new_data[2]) with gr.Row(): image_0 = gr.Image(new_data[6]) image_1 = gr.Image(new_data[7]) image_2 = gr.Image(new_data[8]) with gr.Row(): prediction_0 = gr.Markdown(new_data[3]) prediction_1 = gr.Markdown(new_data[4]) prediction_2 = gr.Markdown(new_data[5]) with gr.TabItem("Search a movie"): gr.Markdown("## Predict a revenue for a selected movie! You can type the title you want to search for and we'll see if we can predict how much it will earn.") with gr.Row(): with gr.Column(scale = 3): input_title = gr.Textbox(value = new_data[0][4:]) with gr.Column(scale = 1): search_button = gr.Button(value="Search") with gr.Row(): with gr.Column(scale=3): with gr.Row(): prediction_s = gr.Markdown(search_data[0]) with gr.Row(): budget = gr.Markdown(search_data[2]) with gr.Row(): overview = gr.Markdown(search_data[3]) with gr.Column(scale=1): image_search = gr.Image(search_data[1]) search_button.click(fn = fetch_prediction_for_title, inputs = [input_title], outputs = [prediction_s, image_search, budget, overview]) reload_button.click(fn = fetch_new_predictions, inputs=[], outputs=[title_0, title_1, title_2, prediction_0, prediction_1, prediction_2, image_0, image_1, image_2]) demo.launch() # iface.launch()