Update Wishlist_create.py

Wishlist_create.py

+from main_imports import MDScreen
+from ProjectFiles.applibs import utils
+import warnings
+from kivy.core.audio import SoundLoader
 import pandas as pd
 import numpy as np
 from sklearn.metrics.pairwise import cosine_similarity
 
-# Load the song data
-song_ratings = pd.read_csv("song_ratings.csv")
+import os
+warnings.filterwarnings('ignore')
+utils.load_kv("Wish_list.kv")
 
-# Create a user-song matrix
-user_song_ratings = song_ratings.pivot_table(index='user_id', columns='song_id', values='rating')
-user_song_ratings.fillna(0, inplace=True)
 
-# Calculate the cosine similarity between songs
-song_similarity = cosine_similarity(user_song_ratings.T)
 
-# Define a function to generate song recommendations for a user
-def generate_song_recommendations(user_id, num_recommendations=10):
-    if user_id not in user_song_ratings.index:
-        print(f"User ID {user_id} not found.")
-        return []
+class Wish_list_Screen(MDScreen):
+    def __init__(self, **kwargs):
+        super(Wish_list_Screen, self).__init__(**kwargs)
 
-    user_ratings = user_song_ratings.loc[user_id].values
-    song_scores = np.dot(user_ratings, song_similarity) / np.sum(np.abs(song_similarity), axis=1)
-    recommended_song_indices = np.argsort(-song_scores)[:num_recommendations]
-    recommended_song_ids = user_song_ratings.columns[recommended_song_indices].tolist()
-    return recommended_song_ids
+    def btnA(self):
 
-# Example: Generate song recommendations for user 98549
-user_id = 98549
-recommended_songs = generate_song_recommendations(user_id, num_recommendations=5)
 
-if recommended_songs:
-    print(f"Recommended songs for user {user_id}:")
-    print(recommended_songs)
-else:
-    print("No recommendations available for this user.")
 
+        class RecommendationSystem:
+
+            def __init__(self, song_ratings_file):
+                data = pd.read_csv(song_ratings_file)
+                with open("mood_label.txt", "r") as file:
+                    readdata = file.read()
+                self.song_ratings = data[data['types'] == readdata]
+
+           #     self.song_ratings = pd.read_csv(song_ratings_file)
+
+
+
+
+                self.user_song_ratings = self.preprocess_data()
+
+            def preprocess_data(self):
+                # Pivot the data to create a user-song matrix
+                user_song_ratings = self.song_ratings.pivot_table(index='user_id', columns='song_id', values='rating')
+                user_song_ratings.fillna(0, inplace=True)
+                return user_song_ratings
+
+            def content_based_recommendations(self, user_id, num_recommendations=10):
+                user_songs = self.user_song_ratings.loc[user_id]
+                recommended_songs = user_songs.sort_values(ascending=False).head(num_recommendations)
+
+                return recommended_songs.index.tolist()
+
+        # Initialize the recommendation system
+        recommendation_system = RecommendationSystem("song_ratings_new.csv")
+
+
+
+        user_ids = [1]
+
+        for user_id in user_ids:
+            # Get content-based recommendations for each user
+            recommended_songs = recommendation_system.content_based_recommendations(user_id, num_recommendations=5)
+
+            if recommended_songs:
+                print(f"Recommended songs for user {user_id}:")
+                print(recommended_songs)
+                self.l1.text = str(recommended_songs)
+            else:
+                print(f"No recommendations available for user {user_id}")
+
+        self.ids.play.opacity = 1
+        self.ids.pause.opacity = 1
+        self.ids.next.opacity = 1
+        self.ids.previous.opacity = 1
+        self.ids.current_audio_label.opacity = 1
+
+
+
+        audio_files = recommended_songs
+        static_part = 'wishlistData/'
+
+        self.audio_files = [static_part + file + '.mp3' for file in audio_files]
+        file_path = 'audio_files.txt'
+
+        # Open the file in write mode and write the audio files
+        with open(file_path, 'w') as file:
+            for item in self.audio_files:
+                file.write("%s\n" % item)
+
+        self.current_audio_index = 0
+        self.sound = None
+
+        if self.current_audio_index < len(self.audio_files):
+            self.sound = SoundLoader.load(self.audio_files[self.current_audio_index])
+
+    def play_audio(self):
+        if self.sound and self.sound.state == 'stop':
+            self.sound.play()
+            self.ids.current_audio_label.text = f"Current Audio: {self.audio_files[self.current_audio_index]}"
+
+    def play_next_audio(self):
+        if self.sound:
+            self.sound.stop()
+            self.current_audio_index += 1
+
+            if self.current_audio_index >= len(self.audio_files):
+                self.current_audio_index = 0
+
+            self.sound.unload()
+            self.sound = SoundLoader.load(self.audio_files[self.current_audio_index])
+            self.sound.play()
+
+            self.ids.current_audio_label.text = f"Current Audio: {self.audio_files[self.current_audio_index]}"
+
+    def pause_audio(self):
+        if self.sound and self.sound.state == 'play':
+            self.sound.stop()
+
+    def play_previous_audio(self):
+        if self.sound:
+            self.sound.stop()
+            self.current_audio_index -= 1
+
+            if self.current_audio_index < 0:
+                self.current_audio_index = len(self.audio_files) - 1
+
+            self.sound.unload()
+            self.sound = SoundLoader.load(self.audio_files[self.current_audio_index])
+            self.sound.play()
+
+            self.ids.current_audio_label.text = f"Current Audio: {self.audio_files[self.current_audio_index]}"
\ No newline at end of file