Spaces:
Runtime error
Runtime error
File size: 2,459 Bytes
2f9c8ed |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
import numpy as np
import re
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import NearestNeighbors
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import FunctionTransformer
def scaling(dataframe):
scaler=StandardScaler()
prep_data=scaler.fit_transform(dataframe.iloc[:,6:15].to_numpy())
return prep_data,scaler
def nn_predictor(prep_data):
neigh = NearestNeighbors(metric='cosine',algorithm='brute')
neigh.fit(prep_data)
return neigh
def build_pipeline(neigh,scaler,params):
transformer = FunctionTransformer(neigh.kneighbors,kw_args=params)
pipeline=Pipeline([('std_scaler',scaler),('NN',transformer)])
return pipeline
def extract_data(dataframe,ingredients):
extracted_data=dataframe.copy()
extracted_data=extract_ingredient_filtered_data(extracted_data,ingredients)
return extracted_data
def extract_ingredient_filtered_data(dataframe,ingredients):
extracted_data=dataframe.copy()
regex_string=''.join(map(lambda x:f'(?=.*{x})',ingredients))
extracted_data=extracted_data[extracted_data['RecipeIngredientParts'].str.contains(regex_string,regex=True,flags=re.IGNORECASE)]
return extracted_data
def apply_pipeline(pipeline,_input,extracted_data):
_input=np.array(_input).reshape(1,-1)
return extracted_data.iloc[pipeline.transform(_input)[0]]
import pandas as pd
def recommend(dataset,_input,ingredients=[],params={'n_neighbors':5,'return_distance':False})-> pd.DataFrame:
extracted_data=extract_data(dataset,ingredients)
if extracted_data.shape[0]>=params['n_neighbors']:
prep_data,scaler=scaling(extracted_data)
neigh=nn_predictor(prep_data)
pipeline=build_pipeline(neigh,scaler,params)
return apply_pipeline(pipeline,_input,extracted_data)
else:
raise Exception("an error occured")
def extract_quoted_strings(s):
# Find all the strings inside double quotes
strings = re.findall(r'"([^"]*)"', s)
# Join the strings with 'and'
return strings
def output_recommended_recipes(dataframe):
if dataframe is not None:
output=dataframe.copy()
output=output.to_dict("records")
for recipe in output:
recipe['RecipeIngredientParts']=extract_quoted_strings(recipe['RecipeIngredientParts'])
recipe['RecipeInstructions']=extract_quoted_strings(recipe['RecipeInstructions'])
else:
output=None
return output
|