Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| import pandas as pd | |
| import json | |
| from huggingface_hub import hf_hub_url, cached_download, hf_hub_download | |
| from gensim.models import KeyedVectors | |
| # Setup model | |
| json_file = hf_hub_download(repo_id="map222/recipe-spice-model", filename="ingredient_count.json") | |
| with open(json_file, 'r') as json_stream: | |
| ingredient_count = json.load(json_stream ) | |
| w2v_file = hf_hub_download(repo_id="map222/recipe-spice-model", filename="recipe_w2v_16.gensim") | |
| recipe_w2v = KeyedVectors.load(w2v_file) | |
| print('Loaded w2v') | |
| recipe_tsv = hf_hub_download(repo_id="map222/recipe-spice-model", filename="recipe_NER.tsv") | |
| print('downloaded recipes') | |
| recipe_NER = pd.read_csv(recipe_tsv, sep='\t' ) | |
| def calc_cooccurrence(ingredient: str, | |
| candidates, | |
| recipes): | |
| ''' Calc how often the top ingredient co-occurs with the candidates | |
| - also removes candidates that are re-phrase of ingredient (e.g. "beef" and "ground beef") | |
| ingredient: str name of an ingredient ("apple") | |
| candidates: potential other ingredients ("orange") | |
| recipes: iterable of possible ingredients | |
| ''' | |
| co_count = {} | |
| for candidate in candidates: | |
| co_count[candidate] = sum([candidate in recipe and ingredient in recipe for recipe in recipes]) | |
| return co_count | |
| def get_fusion_ingredients(ingredient: str, | |
| recipe_model, #gensim model | |
| recipes, #iterable of recipes | |
| ingredient_count: dict, | |
| max_candidates = 20, | |
| min_occurence_factor = 100 # minimum number of recipes an ingredient has to be in | |
| ): | |
| print(recipes.head() ) | |
| print(recipes.info() ) | |
| print(recipes.apply(lambda row: ingredient in row).head() ) | |
| ingredient_recipes = recipes.loc[recipes.apply(lambda row: ingredient in row)] | |
| ingredient_candidates = recipe_model.wv.most_similar(ingredient, topn=50) # get top similar ingredients | |
| candidate_names = list(zip(*ingredient_candidates))[0] | |
| pruned_candidates = [candidate for candidate in candidate_names if ingredient not in candidate][:max_candidates] # clean up candidates to remove duplicates (e.g. "gala apple") | |
| cooccurrence_counts = calc_cooccurrence(ingredient, candidate_names, ingredient_recipes) # get counts for normalization | |
| # final score for sorting: similarity / how often co-occur / total occurences | |
| min_occurences = max(cooccurrence_counts.values()) / min_occurence_factor | |
| freq_norm_candidates = {candidate[0]: candidate[1] / (cooccurrence_counts[candidate[0]]+1) / ingredient_count[candidate[0]] for candidate in ingredient_candidates if candidate[0] in pruned_candidates and cooccurrence_counts[candidate[0]] > min_occurences} | |
| top_candidates = sorted([(k,v) for k,v in freq_norm_candidates.items()], key=lambda x: x[1])[-5:] | |
| return top_candidates, cooccurrence_counts, pruned_candidates # return multiple for debugging | |
| def helper_func(text): | |
| spicy_candidates, cooccurrence_counts, most_similar = get_fusion_ingredients(text, recipe_w2v, recipe_NER['NER'], ingredient_count ) | |
| print('ran similarity') | |
| spicy_df = pd.DataFrame(spicy_candidates, columns = ["Spicy ingredient", "spiciness"]).iloc[::-1] | |
| print('in between') | |
| top_df = pd.DataFrame(most_similar, columns = ["Top ingredient"]) | |
| print('made dataframes') | |
| return spicy_df, top_df | |
| app = gr.Blocks() | |
| with app: | |
| gr.Markdown("# Recipe Spice") | |
| gr.Markdown( | |
| """ | |
| This model uses Word2Vec trained on a 200k recipe corpus to generate ingredient similarities | |
| [see here for a notebook walking through the training](https://github.com/map222/Kibbeh/blob/deploy_space/ingredient_finder.ipynb). Then it finds the "spiciest" | |
| ingredient by finding other ingredients that are similar, but don't occur together often. Enter an ingredient below; | |
| for output, the left column shows the "spiciest" ingredients, and the right column shows the closest. | |
| """ | |
| ) | |
| with gr.Row(): | |
| text_in = gr.Textbox(lines=1, placeholder="Ingredient", label="Find something fun!") | |
| with gr.Row(): | |
| with gr.Column(): | |
| gr.Markdown("Spicy ingredients") | |
| spicy_df = gr.Dataframe(interactive=False) | |
| with gr.Column(): | |
| gr.Markdown("Top ingredients") | |
| top_df = gr.Dataframe(interactive=False) | |
| text_in.submit(helper_func, inputs=[text_in], outputs=[spicy_df, top_df]) | |
| app.launch() |