midify file name and data file path

Anime_RecSys.py → app.py

@@ -1,203 +1,204 @@
-import pandas as pd
-import numpy as np
-import requests
-from bs4 import BeautifulSoup
-from googletrans import Translator
-import tensorflow as tf
-import gradio as gr
-class AnimeRecommender:
-    def __init__(self, rating_path, anime_path, synopsis_path, model_path):
-        self.rating_df = pd.read_csv(rating_path)
-        self.df_anime = pd.read_csv(anime_path, low_memory=True)
-        self.sypnopsis_df = pd.read_csv(synopsis_path, usecols=["MAL_ID", "Name", "Genres", "sypnopsis"])
-        self.model = tf.keras.models.load_model(model_path)
-        self.translator = Translator()
-
-        self._preprocess_data()
-
-    def _preprocess_data(self):
-        # User and anime ID encoding
-        user_ids = self.rating_df["user_id"].unique().tolist()
-        user2user_encoded = {x: i for i, x in enumerate(user_ids)}
-        anime_ids = self.rating_df["anime_id"].unique().tolist()
-        anime2anime_encoded = {x: i for i, x in enumerate(anime_ids)}
-
-        self.rating_df["user"] = self.rating_df["user_id"].map(user2user_encoded)
-        self.rating_df["anime"] = self.rating_df["anime_id"].map(anime2anime_encoded)
-
-        self.n_users = len(user2user_encoded)
-        self.n_animes = len(anime2anime_encoded)
-
-        self.anime2anime_encoded = anime2anime_encoded
-        self.anime_encoded2anime = {i: x for i, x in enumerate(anime_ids)}
-
-        # Normalize anime weights
-        self.anime_weights = self._extract_weights('anime_embedding')
-
-        # Fix anime names
-        self.df_anime['anime_id'] = self.df_anime['MAL_ID']
-        self.df_anime["eng_version"] = self.df_anime['English name']
-        self.df_anime['eng_version'] = self.df_anime.anime_id.apply(self._get_anime_name)
-
-        self.df_anime.sort_values(by=['Score'], inplace=True, ascending=False, kind='quicksort', na_position='last')
-        self.df_anime = self.df_anime[["anime_id", "eng_version", "Score", "Genres", "Episodes", "Type", "Premiered", "Members"]]
-
-    def _extract_weights(self, name):
-        weight_layer = self.model.get_layer(name)
-        weights = weight_layer.get_weights()[0]
-        weights = weights / np.linalg.norm(weights, axis=1).reshape((-1, 1))
-        return weights
-
-    def _get_anime_name(self, anime_id):
-        try:
-            name = self.df_anime[self.df_anime.anime_id == anime_id].eng_version.values[0]
-            if name is np.nan:
-                name = self.df_anime[self.df_anime.anime_id == anime_id].Name.values[0]
-        except:
-            name = 'Unknown'
-        return name
-
-    def get_anime_frame(self, anime):
-        if isinstance(anime, int):
-            return self.df_anime[self.df_anime.anime_id == anime]
-        if isinstance(anime, str):
-            return self.df_anime[self.df_anime.eng_version == anime]
-
-    def get_sypnopsis(self, anime):
-        if isinstance(anime, int):
-            return self.sypnopsis_df[self.sypnopsis_df.MAL_ID == anime].sypnopsis.values[0]
-        if isinstance(anime, str):
-            return self.sypnopsis_df[self.sypnopsis_df.Name == anime].sypnopsis.values[0]
-
-    def find_similar_animes_combined(self, anime_names, n=3, return_dist=False, neg=False):
-        try:
-            encoded_indices = []
-            input_anime_ids = []
-            for name in anime_names:
-                index = self.get_anime_frame(name).anime_id.values[0]
-                input_anime_ids.append(index)
-                encoded_index = self.anime2anime_encoded.get(index)
-                encoded_indices.append(encoded_index)
-
-            combined_weights = np.mean(self.anime_weights[encoded_indices], axis=0)
-            combined_weights = combined_weights / np.linalg.norm(combined_weights)
-
-            dists = np.dot(self.anime_weights, combined_weights)
-            sorted_dists = np.argsort(dists)
-            n = n + len(input_anime_ids)
-
-            if neg:
-                closest = sorted_dists[:n]
-            else:
-                closest = sorted_dists[-n:]
-
-            if return_dist:
-                return dists, closest
-
-            rindex = self.df_anime
-            SimilarityArr = []
-            for close in closest:
-                decoded_id = self.anime_encoded2anime.get(close)
-                if decoded_id in input_anime_ids:
-                    continue
-                sypnopsis = self.get_sypnopsis(decoded_id)
-                anime_frame = self.get_anime_frame(decoded_id)
-                anime_name = anime_frame.eng_version.values[0]
-                genre = anime_frame.Genres.values[0]
-                similarity = dists[close]
-                SimilarityArr.append({"anime_id": decoded_id, "name": anime_name, "similarity": similarity, "genre": genre, 'sypnopsis': sypnopsis})
-
-            Frame = pd.DataFrame(SimilarityArr).sort_values(by="similarity", ascending=False)
-            return Frame.drop(index=0)
-        except Exception as e:
-            print('{}!, Not Found in Anime list'.format(anime_names))
-            print(str(e))
-            return pd.DataFrame()
-
-    def get_anime_url(self, name):
-        anime = self.df_anime[self.df_anime['eng_version'] == name]
-        if not anime.empty:
-            mal_id = anime['anime_id'].values[0]
-            anime_name = anime['eng_version'].values[0].replace(' ', '_').replace(':', '_').replace('!', '_')
-            return f"https://myanimelist.net/anime/{mal_id}/{anime_name}"
-        else:
-            print(f"{name}에 해당하는 애니메이션을 찾을 수 없습니다.")
-            return None
-
-    def extract_image_url(self, url):
-        try:
-            response = requests.get(url)
-            response.raise_for_status()
-        except requests.RequestException as e:
-            print(f"페이지를 가져올 수 없습니다: {e}")
-            return None
-
-        soup = BeautifulSoup(response.text, 'html.parser')
-        image_tag = soup.find('img', {'data-src': True})
-
-        if image_tag:
-            return image_tag['data-src']
-        else:
-            print("이미지를 찾을 수 없습니다.")
-            return None
-
-    def NCF_Recommendation(self, a, b, c):
-        anime_list = [a, b, c]
-        anime_result = self.find_similar_animes_combined(anime_list, n=3)
-
-        result1 = anime_result.loc[3, 'name']
-        result2 = anime_result.loc[2, 'name']
-        result3 = anime_result.loc[1, 'name']
-
-        explain1 = anime_result.loc[3, 'sypnopsis']
-        explain2 = anime_result.loc[2, 'sypnopsis']
-        explain3 = anime_result.loc[1, 'sypnopsis']
-
-        url1 = self.get_anime_url(result1)
-        url2 = self.get_anime_url(result2)
-        url3 = self.get_anime_url(result3)
-
-        image1 = self.extract_image_url(url1)
-        image2 = self.extract_image_url(url2)
-        image3 = self.extract_image_url(url3)
-
-        return result1, explain1, image1, result2, explain2, image2, result3, explain3, image3
-
-# 파일 경로 설정
-rating_path = 'C:/Users\PC\PycharmProjects/DNA_Anime_RecSys/Anime_RecSys/data/rating_complete.csv'
-anime_path = 'C:/Users\PC\PycharmProjects/DNA_Anime_RecSys/Anime_RecSys/data/anime.csv'
-synopsis_path = 'C:/Users\PC\PycharmProjects/DNA_Anime_RecSys/Anime_RecSys/data/anime_with_synopsis.csv'
-model_path = 'C:/Users\PC\PycharmProjects/DNA_Anime_RecSys/Anime_RecSys/data/anime_model.h5'
-
-# 객체 생성
-recommender = AnimeRecommender(rating_path, anime_path, synopsis_path, model_path)
-
-with gr.Blocks() as app:
-    with gr.Row():
-        a = gr.Textbox(label="너의 최애 애니 첫 번째를 작성해봐!")
-        b = gr.Textbox(label="너의 최애 애니 두 번째를 작성해봐!")
-        c = gr.Textbox(label="너의 최애 애니 세 번째를 작성해봐!")
-
-    with gr.Row():
-        with gr.Column():
-            img1 = gr.Image(label="1번째 애니 추천")
-            output1 = gr.Textbox(label="1️⃣ 첫번째 애니 추천!")
-            output2 = gr.Textbox(label="첫 번째 애니 설명", interactive=False)
-        with gr.Column():
-            img2 = gr.Image(label="2번째 애니 추천")
-            output3 = gr.Textbox(label="2️⃣ 두번째 애니 추천!")
-            output4 = gr.Textbox(label="두 번째 애니 설명", interactive=False)
-        with gr.Column():
-            img3 = gr.Image(label="3번째 애니 추천")
-            output5 = gr.Textbox(label="3️⃣ 세번째 애니 추천!")
-            output6 = gr.Textbox(label="세 번째 애니 설명", interactive=False)
-
-    btn = gr.Button("추천을 받아봅시다!")
-
-    btn.click(
-        fn=recommender.NCF_Recommendation,
-        inputs=[a, b, c],
-        outputs=[output1, output2, img1, output3, output4, img2, output5, output6, img3]
-    )
-
-app.launch(share=True)
+import pandas as pd
+import numpy as np
+import requests
+from bs4 import BeautifulSoup
+from googletrans import Translator
+import tensorflow as tf
+import gradio as gr
+class AnimeRecommender:
+    def __init__(self, rating_path, anime_path, synopsis_path, model_path):
+        self.rating_df = pd.read_csv(rating_path)
+        self.df_anime = pd.read_csv(anime_path, low_memory=True)
+        self.sypnopsis_df = pd.read_csv(synopsis_path, usecols=["MAL_ID", "Name", "Genres", "sypnopsis"])
+        self.model = tf.keras.models.load_model(model_path)
+        self.translator = Translator()
+
+        self._preprocess_data()
+
+    def _preprocess_data(self):
+        # User and anime ID encoding
+        user_ids = self.rating_df["user_id"].unique().tolist()
+        user2user_encoded = {x: i for i, x in enumerate(user_ids)}
+        anime_ids = self.rating_df["anime_id"].unique().tolist()
+        anime2anime_encoded = {x: i for i, x in enumerate(anime_ids)}
+
+        self.rating_df["user"] = self.rating_df["user_id"].map(user2user_encoded)
+        self.rating_df["anime"] = self.rating_df["anime_id"].map(anime2anime_encoded)
+
+        self.n_users = len(user2user_encoded)
+        self.n_animes = len(anime2anime_encoded)
+
+        self.anime2anime_encoded = anime2anime_encoded
+        self.anime_encoded2anime = {i: x for i, x in enumerate(anime_ids)}
+
+        # Normalize anime weights
+        self.anime_weights = self._extract_weights('anime_embedding')
+
+        # Fix anime names
+        self.df_anime['anime_id'] = self.df_anime['MAL_ID']
+        self.df_anime["eng_version"] = self.df_anime['English name']
+        self.df_anime['eng_version'] = self.df_anime.anime_id.apply(self._get_anime_name)
+
+        self.df_anime.sort_values(by=['Score'], inplace=True, ascending=False, kind='quicksort', na_position='last')
+        self.df_anime = self.df_anime[["anime_id", "eng_version", "Score", "Genres", "Episodes", "Type", "Premiered", "Members"]]
+
+    def _extract_weights(self, name):
+        weight_layer = self.model.get_layer(name)
+        weights = weight_layer.get_weights()[0]
+        weights = weights / np.linalg.norm(weights, axis=1).reshape((-1, 1))
+        return weights
+
+    def _get_anime_name(self, anime_id):
+        try:
+            name = self.df_anime[self.df_anime.anime_id == anime_id].eng_version.values[0]
+            if name is np.nan:
+                name = self.df_anime[self.df_anime.anime_id == anime_id].Name.values[0]
+        except:
+            name = 'Unknown'
+        return name
+
+    def get_anime_frame(self, anime):
+        if isinstance(anime, int):
+            return self.df_anime[self.df_anime.anime_id == anime]
+        if isinstance(anime, str):
+            return self.df_anime[self.df_anime.eng_version == anime]
+
+    def get_sypnopsis(self, anime):
+        if isinstance(anime, int):
+            return self.sypnopsis_df[self.sypnopsis_df.MAL_ID == anime].sypnopsis.values[0]
+        if isinstance(anime, str):
+            return self.sypnopsis_df[self.sypnopsis_df.Name == anime].sypnopsis.values[0]
+
+    def find_similar_animes_combined(self, anime_names, n=3, return_dist=False, neg=False):
+        try:
+            encoded_indices = []
+            input_anime_ids = []
+            for name in anime_names:
+                index = self.get_anime_frame(name).anime_id.values[0]
+                input_anime_ids.append(index)
+                encoded_index = self.anime2anime_encoded.get(index)
+                encoded_indices.append(encoded_index)
+
+            combined_weights = np.mean(self.anime_weights[encoded_indices], axis=0)
+            combined_weights = combined_weights / np.linalg.norm(combined_weights)
+
+            dists = np.dot(self.anime_weights, combined_weights)
+            sorted_dists = np.argsort(dists)
+            n = n + len(input_anime_ids)
+
+            if neg:
+                closest = sorted_dists[:n]
+            else:
+                closest = sorted_dists[-n:]
+
+            if return_dist:
+                return dists, closest
+
+            rindex = self.df_anime
+            SimilarityArr = []
+            for close in closest:
+                decoded_id = self.anime_encoded2anime.get(close)
+                if decoded_id in input_anime_ids:
+                    continue
+                sypnopsis = self.get_sypnopsis(decoded_id)
+                anime_frame = self.get_anime_frame(decoded_id)
+                anime_name = anime_frame.eng_version.values[0]
+                genre = anime_frame.Genres.values[0]
+                similarity = dists[close]
+                SimilarityArr.append({"anime_id": decoded_id, "name": anime_name, "similarity": similarity, "genre": genre, 'sypnopsis': sypnopsis})
+
+            Frame = pd.DataFrame(SimilarityArr).sort_values(by="similarity", ascending=False)
+            return Frame.drop(index=0)
+        except Exception as e:
+            print('{}!, Not Found in Anime list'.format(anime_names))
+            print(str(e))
+            return pd.DataFrame()
+
+    def get_anime_url(self, name):
+        anime = self.df_anime[self.df_anime['eng_version'] == name]
+        if not anime.empty:
+            mal_id = anime['anime_id'].values[0]
+            anime_name = anime['eng_version'].values[0].replace(' ', '_').replace(':', '_').replace('!', '_')
+            return f"https://myanimelist.net/anime/{mal_id}/{anime_name}"
+        else:
+            print(f"{name}에 해당하는 애니메이션을 찾을 수 없습니다.")
+            return None
+
+    def extract_image_url(self, url):
+        try:
+            response = requests.get(url)
+            response.raise_for_status()
+        except requests.RequestException as e:
+            print(f"페이지를 가져올 수 없습니다: {e}")
+            return None
+
+        soup = BeautifulSoup(response.text, 'html.parser')
+        image_tag = soup.find('img', {'data-src': True})
+
+        if image_tag:
+            return image_tag['data-src']
+        else:
+            print("이미지를 찾을 수 없습니다.")
+            return None
+
+    def NCF_Recommendation(self, a, b, c):
+        anime_list = [a, b, c]
+        anime_result = self.find_similar_animes_combined(anime_list, n=3)
+
+        result1 = anime_result.loc[3, 'name']
+        result2 = anime_result.loc[2, 'name']
+        result3 = anime_result.loc[1, 'name']
+
+        explain1 = anime_result.loc[3, 'sypnopsis']
+        explain2 = anime_result.loc[2, 'sypnopsis']
+        explain3 = anime_result.loc[1, 'sypnopsis']
+
+        url1 = self.get_anime_url(result1)
+        url2 = self.get_anime_url(result2)
+        url3 = self.get_anime_url(result3)
+
+        image1 = self.extract_image_url(url1)
+        image2 = self.extract_image_url(url2)
+        image3 = self.extract_image_url(url3)
+
+        return result1, explain1, image1, result2, explain2, image2, result3, explain3, image3
+
+# 파일 경로 설정
+rating_path = 'https://huggingface.co/spaces/OhST/Anime_RecSys/data/rating_complete.csv'
+anime_path = 'https://huggingface.co/spaces/OhST/Anime_RecSys/data/anime.csv'
+synopsis_path = 'https://huggingface.co/spaces/OhST/Anime_RecSys/data/anime_with_synopsis.csv'
+model_path = 'https://huggingface.co/spaces/OhST/Anime_RecSys/data/anime_model.h5'
+
+
+# 객체 생성
+recommender = AnimeRecommender(rating_path, anime_path, synopsis_path, model_path)
+
+with gr.Blocks() as app:
+    with gr.Row():
+        a = gr.Textbox(label="너의 최애 애니 첫 번째를 작성해봐!")
+        b = gr.Textbox(label="너의 최애 애니 두 번째를 작성해봐!")
+        c = gr.Textbox(label="너의 최애 애니 세 번째를 작성해봐!")
+
+    with gr.Row():
+        with gr.Column():
+            img1 = gr.Image(label="1번째 애니 추천")
+            output1 = gr.Textbox(label="1️⃣ 첫번째 애니 추천!")
+            output2 = gr.Textbox(label="첫 번째 애니 설명", interactive=False)
+        with gr.Column():
+            img2 = gr.Image(label="2번째 애니 추천")
+            output3 = gr.Textbox(label="2️⃣ 두번째 애니 추천!")
+            output4 = gr.Textbox(label="두 번째 애니 설명", interactive=False)
+        with gr.Column():
+            img3 = gr.Image(label="3번째 애니 추천")
+            output5 = gr.Textbox(label="3️⃣ 세번째 애니 추천!")
+            output6 = gr.Textbox(label="세 번째 애니 설명", interactive=False)
+
+    btn = gr.Button("추천을 받아봅시다!")
+
+    btn.click(
+        fn=recommender.NCF_Recommendation,
+        inputs=[a, b, c],
+        outputs=[output1, output2, img1, output3, output4, img2, output5, output6, img3]
+    )
+
+app.launch(share=True)