Created
December 17, 2018 16:47
-
-
Save ianlcassidy/f985c0b83dee89424f5167892739df1a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from typing import Dict | |
import pandas as pd | |
from sklearn.metrics import euclidean_distances | |
def get_personalized_hotel_recommendations(df: pd.DataFrame, user_features: Dict) -> pd.DataFrame: | |
# features used to compute the similarity | |
features = ['distance', 'avg_rate', 'star_rating', 'user_rating'] | |
# create the features | |
df_features = df[features].copy() | |
df_features = normalize_features(df_features) | |
# artifically set the distance of the user anchor to be the min of the | |
# normalized distance | |
user_features['distance'] = df_features['distance'].min() | |
df_user = pd.DataFrame([user_features]) | |
df_features = pd.concat([df_user, df_features], sort=False) | |
# compute the distances | |
X = df_features.values | |
Y = df_features.values[0].reshape(1, -1) | |
distances = euclidean_distances(X, Y) | |
df_sorted = df.copy() | |
df_sorted['similarity_distance'] = distances[1:] | |
return df_sorted.sort_values('similarity_distance').reset_index(drop=True) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment