From 3500e6cfc9a75e3672078858aa8c865f45751938 Mon Sep 17 00:00:00 2001
From: Adrien <adrien.payen@student.uclouvain.be>
Date: Fri, 24 May 2024 17:31:09 +0200
Subject: [PATCH] update files
---
Home.py | 6 +-
.../content_based.ipynb | 0
evaluator.ipynb => backend/evaluator.ipynb | 0
evaluator.py => backend/evaluator.py | 0
website.py => backend/website.py | 0
content_based.py | 412 ------------------
6 files changed, 3 insertions(+), 415 deletions(-)
rename content_based.ipynb => backend/content_based.ipynb (100%)
rename evaluator.ipynb => backend/evaluator.ipynb (100%)
rename evaluator.py => backend/evaluator.py (100%)
rename website.py => backend/website.py (100%)
delete mode 100644 content_based.py
diff --git a/Home.py b/Home.py
index ded0143d..c70b755e 100644
--- a/Home.py
+++ b/Home.py
@@ -26,7 +26,7 @@ def display_user_movies(df, title, column_name):
# Sélectionner le nombre de films à afficher en fonction de la colonne
if column_name == 'top_10':
- filtered_df = filtered_df.sort_values(by=column_name, ascending=False).head(10)
+ filtered_df = filtered_df.sort_values(by=column_name, ascending=False).head(15)
else:
filtered_df = filtered_df.sort_values(by=column_name, ascending=False)
@@ -84,7 +84,7 @@ def display_recommendations_ub(user_name, user_id):
testset = trainset.build_anti_testset()
# Créer une instance de l'algorithme de filtrage collaboratif basé sur les utilisateurs
- recommender = UserBased(k=340, min_k=340)
+ recommender = UserBased(k=60, min_k=60)
recommender.fit(trainset)
top_10_predictions = recommender.get_top_n_pred_ub(testset, user_id)
@@ -178,7 +178,7 @@ def display_recommendations_latent_factor(user_name, user_id):
-def display_content_based_recommendations(user_name, user_id=-1, n=10):
+def display_content_based_recommendations(user_name, user_id=-1, n=15):
cols_html = ""
# Call the test_contentbased_class function to get top N recommendations
diff --git a/content_based.ipynb b/backend/content_based.ipynb
similarity index 100%
rename from content_based.ipynb
rename to backend/content_based.ipynb
diff --git a/evaluator.ipynb b/backend/evaluator.ipynb
similarity index 100%
rename from evaluator.ipynb
rename to backend/evaluator.ipynb
diff --git a/evaluator.py b/backend/evaluator.py
similarity index 100%
rename from evaluator.py
rename to backend/evaluator.py
diff --git a/website.py b/backend/website.py
similarity index 100%
rename from website.py
rename to backend/website.py
diff --git a/content_based.py b/content_based.py
deleted file mode 100644
index 18822949..00000000
--- a/content_based.py
+++ /dev/null
@@ -1,412 +0,0 @@
-
-import numpy as np
-import pandas as pd
-import random as rd
-from surprise import AlgoBase
-from surprise.prediction_algorithms.predictions import PredictionImpossible
-
-from loaders import load_ratings
-from loaders import load_items
-from constants import Constant as C
-
-from sklearn.linear_model import LinearRegression
-from sklearn.ensemble import GradientBoostingRegressor, RandomForestRegressor
-from sklearn.svm import SVR
-from sklearn.feature_extraction.text import TfidfVectorizer
-
-
-# All the dataframes
-df_items = load_items()
-df_ratings = load_ratings()
-df_tag = pd.read_csv(C.CONTENT_PATH/C.TAGS_FILENAME)
-
-df_features = df_tag[C.TAG]
-
-class ContentBased(AlgoBase):
- def __init__(self, features_method, regressor_method):
- AlgoBase.__init__(self)
- self.regressor_method = regressor_method
- self.content_features = self.create_content_features(features_method)
- self.user_profile_explain = {}
-
- def create_content_features(self, features_method):
- """Content Analyzer"""
- df_items = load_items()
- df_ratings = load_ratings()
- df_tag = df_tag = pd.read_csv(C.CONTENT_PATH/C.TAGS_FILENAME)
- df_genome_score = pd.read_csv("data/hackathon/content/genome-scores.csv")
- df_genome_tag = pd.read_csv("data/hackathon/content/genome-tags.csv")
-
- if features_method is None:
- df_features = None
-
- elif features_method == "relevance" :
- df_features = df_genome_score.groupby('movieId')["relevance"].transform('mean').to_frame('avg_relevance')
-
- elif features_method == "title_length": # a naive method that creates only 1 feature based on title length
- df_features = df_items[C.LABEL_COL].apply(lambda x: len(x)).to_frame('n_character_title')
-
- elif features_method == "movie_year" :
- df_features = df_items['movie_year'] = df_items['title'].str.extract(r'\((\d{4})\)', expand=False).to_frame('movie_year')
-
- elif features_method == "genres" :
- genres_list = df_items['genres'].str.split('|').explode().unique()
- for genre in genres_list:
- df_features = df_items['genres'].str.contains(genre).astype(int).to_frame('genres')
-
- elif features_method == "combination" :
- genres_list = df_items['genres'].str.split('|').explode().unique()
- for genre in genres_list:
- df_features = df_items['genres'].str.contains(genre).astype(int).to_frame('genres')
-
- df_features = df_items['movie_year'] = df_items['title'].str.extract(r'\((\d{4})\)', expand=False).to_frame('movie_year')
-
-
- elif features_method == "rating" :
- df_features = df_ratings.groupby('movieId')['rating'].transform('mean').to_frame('avg_rating')
-
- elif features_method == "tags" :
- df_features = df_tag['tag'].apply(lambda x: len(x.split(',')) if isinstance(x, str) else 0).to_frame('tags')
-
- elif features_method == "tags_length" :
-
- df_features = df_tag['tag'].apply(lambda x: sum(len(tag) for tag in x.split(','))if isinstance(x, str) else 0).to_frame('n_character_tags')
-
- else: # (implement other feature creations here)
- raise NotImplementedError(f'Feature method {features_method} not yet implemented')
-
- # Handle missing values in df_features
- if df_features is not None:
- df_features.fillna(0, inplace=True)
-
- return df_features
-
-
- def fit(self, trainset):
- """Profile Learner"""
- AlgoBase.fit(self, trainset)
-
- # Preallocate user profiles
- self.user_profile = {u: None for u in trainset.all_users()}
-
- self.user_profile_explain = {}
-
- # Loop over all internal user IDs in the trainset
- for u in trainset.all_users():
- # Convert internal user ID to raw user ID
- raw_user_id = trainset.to_raw_uid(u)
-
- # Initialize feature importance dictionary for the raw user ID
- self.user_profile_explain[raw_user_id] = {}
-
- # Extract user ratings for the current user
- user_ratings = np.array([rating for _, rating in trainset.ur[u]])
-
- # Compute feature importance based on content features and user ratings
- feature_values = self.content_features.values.astype(int)
- weighted_features = feature_values / np.linalg.norm(feature_values)
- feature_importance = weighted_features / np.sum(user_ratings)
-
- # Map feature importance scores to feature names and store in user_profile_explain
- self.user_profile_explain[raw_user_id] = dict(zip(self.content_features.columns, feature_importance))
-
-
- if self.regressor_method == 'random_score':
- for u in self.user_profile :
- self.user_profile[u] = rd.uniform(0.5,5)
-
- elif self.regressor_method == 'random_sample':
- for u in self.user_profile:
- self.user_profile[u] = [rating for _, rating in self.trainset.ur[u]]
-
- elif self.regressor_method == 'linear_regression' :
- for u in self.user_profile:
-
- user_ratings = [rating for _, rating in trainset.ur[u]]
- item_ids = [iid for iid, _ in trainset.ur[u]]
-
- df_user = pd.DataFrame({'item_id': item_ids, 'user_ratings': user_ratings})
-
- df_user["item_id"] = df_user["item_id"].map(trainset.to_raw_iid)
-
- df_user = df_user.merge(self.content_features, left_on = "item_id", right_index = True, how = 'left')
-
- if 'n_character_title' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['n_character_title'].values.reshape(-1, 1)
-
- elif 'avg_relevance' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['avg_relevance'].values.reshape(-1, 1)
-
- elif 'movie_year' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['movie_year'].values.reshape(-1, 1)
-
- elif 'combination' in df_user.columns :
- X = df_user['movie_year','genres' ].values.reshape(-1, 1)
-
- elif 'genres' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['genres'].values.reshape(-1, 1)
-
- elif 'avg_rating' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['avg_rating'].values.reshape(-1, 1)
-
- elif 'tags' in df_user.columns:
- # Si une autre caractéristique est disponible (remplace 'other_feature' par le nom de ta caractéristique)
- X = df_user['tags'].values.reshape(-1, 1)
-
- elif 'n_character_tags' in df_user.columns:
- # Si une autre caractéristique est disponible (remplace 'other_feature' par le nom de ta caractéristique)
- X = df_user['n_character_tags'].values.reshape(-1, 1)
-
- else:
- # Si aucune caractéristique appropriée n'est disponible
- continue # Ou gère le cas d'erreur/exception ici
-
- y = df_user['user_ratings'].values
-
- linear_regressor = LinearRegression(fit_intercept = False)
-
- linear_regressor.fit(X,y)
-
- # Store the computed user profile
- self.user_profile[u] = linear_regressor
-
- elif self.regressor_method == 'svr_regression':
- for u in self.user_profile:
-
- user_ratings = [rating for _, rating in trainset.ur[u]]
- item_ids = [iid for iid, _ in trainset.ur[u]]
-
- df_user = pd.DataFrame({'item_id': item_ids, 'user_ratings': user_ratings})
-
- df_user["item_id"] = df_user["item_id"].map(trainset.to_raw_iid)
-
- df_user = df_user.merge(self.content_features, left_on = "item_id", right_index = True, how = 'left')
-
- if 'n_character_title' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['n_character_title'].values.reshape(-1, 1)
-
- elif 'avg_relevance' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['avg_relevance'].values.reshape(-1, 1)
-
- elif 'movie_year' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['movie_year'].values.reshape(-1, 1)
-
- elif 'genres' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['genres'].values.reshape(-1, 1)
-
- elif 'avg_rating' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['avg_rating'].values.reshape(-1, 1)
-
- elif 'tags' in df_user.columns:
- # Si une autre caractéristique est disponible (remplace 'other_feature' par le nom de ta caractéristique)
- X = df_user['tags'].values.reshape(-1, 1)
-
- elif 'n_character_tags' in df_user.columns:
- # Si une autre caractéristique est disponible (remplace 'other_feature' par le nom de ta caractéristique)
- X = df_user['n_character_tags'].values.reshape(-1, 1)
-
- else:
- # Si aucune caractéristique appropriée n'est disponible
- continue # Ou gère le cas d'erreur/exception ici
-
- y = df_user['user_ratings'].values
- svr_regressor = SVR(kernel='rbf', C=10, epsilon=0.2)
- svr_regressor.fit(X, y)
- self.user_profile[u] = svr_regressor
-
- elif self.regressor_method == 'gradient_boosting':
- for u in self.user_profile:
-
- user_ratings = [rating for _, rating in trainset.ur[u]]
- item_ids = [iid for iid, _ in trainset.ur[u]]
-
- df_user = pd.DataFrame({'item_id': item_ids, 'user_ratings': user_ratings})
-
- df_user["item_id"] = df_user["item_id"].map(trainset.to_raw_iid)
-
- df_user = df_user.merge(self.content_features, left_on = "item_id", right_index = True, how = 'left')
-
- if 'n_character_title' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['n_character_title'].values.reshape(-1, 1)
-
- elif 'avg_relevance' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['avg_relevance'].values.reshape(-1, 1)
-
- elif 'movie_year' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['movie_year'].values.reshape(-1, 1)
-
- elif 'genres' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['genres'].values.reshape(-1, 1)
-
- elif 'avg_rating' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['avg_rating'].values.reshape(-1, 1)
-
- elif 'tags' in df_user.columns:
- # Si une autre caractéristique est disponible (remplace 'other_feature' par le nom de ta caractéristique)
- X = df_user['tags'].values.reshape(-1, 1)
-
- elif 'n_character_tags' in df_user.columns:
- # Si une autre caractéristique est disponible (remplace 'other_feature' par le nom de ta caractéristique)
- X = df_user['n_character_tags'].values.reshape(-1, 1)
-
- else:
- # Si aucune caractéristique appropriée n'est disponible
- continue # Ou gère le cas d'erreur/exception ici
-
- y = df_user['user_ratings'].values
- gb_regressor = GradientBoostingRegressor(n_estimators=100, learning_rate=0.1, max_depth=3)
- gb_regressor.fit(X, y)
- self.user_profile[u] = gb_regressor
-
-
- elif self.regressor_method == 'random_forest':
- for u in self.user_profile:
-
- user_ratings = [rating for _, rating in trainset.ur[u]]
- item_ids = [iid for iid, _ in trainset.ur[u]]
-
- df_user = pd.DataFrame({'item_id': item_ids, 'user_ratings': user_ratings})
-
- df_user["item_id"] = df_user["item_id"].map(trainset.to_raw_iid)
-
- df_user = df_user.merge(self.content_features, left_on = "item_id", right_index = True, how = 'left')
-
- if 'n_character_title' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['n_character_title'].values.reshape(-1, 1)
-
- elif 'avg_relevance' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['avg_relevance'].values.reshape(-1, 1)
-
- elif 'movie_year' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['movie_year'].values.reshape(-1, 1)
-
- elif 'genres' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['genres'].values.reshape(-1, 1)
-
- elif 'avg_rating' in df_user.columns:
- # Si 'n_character_title' est disponible comme caractéristique
- X = df_user['avg_rating'].values.reshape(-1, 1)
-
- elif 'tags' in df_user.columns:
- # Si une autre caractéristique est disponible (remplace 'other_feature' par le nom de ta caractéristique)
- X = df_user['tags'].values.reshape(-1, 1)
-
- elif 'n_character_tags' in df_user.columns:
- # Si une autre caractéristique est disponible (remplace 'other_feature' par le nom de ta caractéristique)
- X = df_user['n_character_tags'].values.reshape(-1, 1)
-
- else:
- # Si aucune caractéristique appropriée n'est disponible
- continue # Ou gère le cas d'erreur/exception ici
-
- y = df_user['user_ratings'].values
- rf_regressor = RandomForestRegressor(n_estimators=100)
- rf_regressor.fit(X, y)
- self.user_profile[u] = rf_regressor
-
- else :
- pass
-
- # (implement here the regressor fitting)
-
- def estimate(self, u, i):
- """Scoring component used for item filtering"""
- # First, handle cases for unknown users and items
- if not (self.trainset.knows_user(u) and self.trainset.knows_item(i)):
- raise PredictionImpossible('User and/or item is unkown.')
-
-
- if self.regressor_method == 'random_score':
- rd.seed()
- score = rd.uniform(0.5,5)
-
- elif self.regressor_method == 'random_sample':
- rd.seed()
- score = rd.choice(self.user_profile[u])
-
- elif self.regressor_method == 'linear_regression':
-
- raw_item_id = self.trainset.to_raw_iid(i)
-
- item_features = self.content_features.loc[raw_item_id:raw_item_id, :].values
-
- linear_regressor = self.user_profile[u]
-
- score= linear_regressor.predict(item_features)[0]
-
- elif self.regressor_method == 'svr_regression':
-
- raw_item_id = self.trainset.to_raw_iid(i)
-
- item_features = self.content_features.loc[raw_item_id:raw_item_id, :].values
-
- svr_regressor = self.user_profile[u]
- score = svr_regressor.predict(item_features)[0]
-
- elif self.regressor_method == 'gradient_boosting':
-
- raw_item_id = self.trainset.to_raw_iid(i)
-
- item_features = self.content_features.loc[raw_item_id:raw_item_id, :].values
-
- gradient_boosting = self.user_profile[u]
- score = gradient_boosting.predict(item_features)[0]
-
- elif self.regressor_method == 'random_forest':
-
- raw_item_id = self.trainset.to_raw_iid(i)
-
- item_features = self.content_features.loc[raw_item_id:raw_item_id, :].values
-
- randomforest = self.user_profile[u]
- score = randomforest.predict(item_features)[0]
-
- else :
- score = None
-
- # (implement here the regressor prediction)
-
- return score
-
- def explain(self, u) :
- if u in self.user_profile_explain :
- return self.user_profile_explain[u]
- else :
- return None
-
-
-cb = ContentBased("combination", "")
-sp_ratings = load_ratings(surprise_format=True)
-train_set = sp_ratings.build_full_trainset()
-cb.fit(train_set)
-
-print(cb.explain(11))
-
-print(cb.explain(13))
-
-print(cb.explain(17))
-
-print(cb.explain(23))
-
-print(cb.explain(27))
-
-print(cb.explain(73))
\ No newline at end of file
--
GitLab