Uppdatera main samd README

README.md

@@ -14,7 +14,7 @@ I will use 4 datasets from kaggle, 3 datasets from streaming-sites Netflix,
 Amazon Prime and Disney Plus, also 1 from a IMDB dataset.
 
 ### Model:
-I will use k-Nearest Neighbors (k-NN) alhorithm that can help me find other titles based on features 
+I will use NearestNeighbors (NN) alhorithm that can help me find other titles based on features 
 like Title, Release year, Description, Cast, Director and genres.
 
 ### Features:

main.py

@@ -1,9 +1,11 @@
 import pandas as pd
 import re
 import os
+from sklearn.neighbors import NearestNeighbors
+from sklearn.feature_extraction.text import TfidfVectorizer
+from textwrap import dedent
 
 class LoadData:
-
     def __init__(self):
         self.data = None
         self.loaded_datasets = []
@@ -18,8 +20,7 @@ class LoadData:
     def clean_text(self, text):
         if isinstance(text, str):
             cleaned = re.sub(r'[^\x00-\x7F]+', '', text)
-            cleaned = cleaned.replace('#', '')
+            cleaned = cleaned.replace('#', '').replace('"', '')
-            cleaned = cleaned.replace('"', '')
             return cleaned.strip()
         return '' 
 
@@ -27,7 +28,7 @@ class LoadData:
         try:
             df = pd.read_csv(f'dataset/{dataset_path}')
             df['stream'] = stream
-            if stream not in 'IMDB':
+            if stream != 'IMDB':
                 df = df.drop(columns=['show_id', 'date_added', 'duration', 'rating'], errors='ignore')
                 df = df.rename(columns={'listed_in': 'genres'})
             else:
@@ -58,47 +59,121 @@ class LoadData:
         print(f'Data from {", ".join(self.loaded_datasets)} imported.')
 
     def clean_data(self):
+        self.data.dropna(subset=['title', 'genres', 'description'], inplace=True)
         string_columns = self.data.select_dtypes(include=['object'])
         self.data[string_columns.columns] = string_columns.apply(lambda col: col.map(self.clean_text, na_action='ignore'))
         self.data = self.data[~self.data['title'].str.strip().isin(['', ':'])]
-        print(f'Data cleaned')
+        self.data['genres'] = self.data['genres'].str.split(', ').apply(lambda x: [genre.strip() for genre in x])
+        self.data = self.data[self.data['genres'].map(lambda x: len(x) > 0)]
+        print(f'Data cleaned. {self.data.shape[0]} records remaining.')
 
 
 class UserData:
-
     def __init__(self):
         self.user_data = None
 
     def input(self):
-        self.user_data = input("Which Movie or TV-Serie do you prefer: ")
+        self.user_data = input("Which Movie or TV Series do you prefer: ")
-        return self.user_data.lower()
+        return self.user_data.strip().lower()
 
 
-class Recommendations:
+class TrainModel:
+    def __init__(self, title_data):
+        self.recommendation_model = None
+        self.title_data = title_data
+        self.title_vectors = None 
+        self.vectorizer = TfidfVectorizer() 
+        self.preprocess_data()
 
-    def __init__(self):
+    def preprocess_data(self):
-        self.result = None
+        self.title_data['genres'] = self.title_data['genres'].apply(lambda x: ', '.join(x) if isinstance(x, list) else '')
+        self.title_data['combined_text'] = (
+            self.title_data['title'].fillna('') + ' ' +
+            self.title_data['director'].fillna('') + ' ' +
+            self.title_data['cast'].fillna('') + ' ' +
+            self.title_data['genres'] + ' ' + 
+            self.title_data['description'].fillna('')
+        )
+        self.title_data['combined_text'] = self.title_data['combined_text'].str.lower()
+        self.title_data['combined_text'] = self.title_data['combined_text'].str.replace(r'[^a-z\s]', '', regex=True)
+        self.title_vectors = self.vectorizer.fit_transform(self.title_data['combined_text'])
 
-    def get_recommendations(self, user_data, title_data):
+    def preprocess_user_input(self, user_input):
-        if title_data is not None and not title_data.empty: 
+        user_vector = self.vectorizer.transform([user_input])
+        return user_vector
 
-            self.results = "Här ska de komma rekommendationer"
+    def train(self):
+        self.recommendation_model = NearestNeighbors(n_neighbors=10, metric='cosine')
+        self.recommendation_model.fit(self.title_vectors)
 
-            print(self.results)
+
+class RecommendationLoader:
+    def __init__(self, model, title_data):
+        self.model = model
+        self.title_data = title_data
+
+    def run(self):
+        while True: 
+            user_data = UserData()
+            user_input = user_data.input()
+
+            if user_input in ['exit', 'quit']:
+                print("Program will exit now. Thanks for using!")
+                break
+
+            self.get_recommendations(user_input) 
+            print("\nWrite 'exit' or 'quit' to end the program.")
+            
+    def get_recommendations(self, user_data):
+        user_vector = self.model.preprocess_user_input(user_data)   
+        distances, indices = self.model.recommendation_model.kneighbors(user_vector, n_neighbors=10) 
+        recommendations = self.title_data.iloc[indices[0]]
+
+        self.display_recommendations(user_data, recommendations)
+
+    def display_recommendations(self, user_data, recommendations):
+        print(f'\nRecommendations based on "{user_data}":\n')
+
+        if not recommendations.empty:
+            movie_recommendations = recommendations[recommendations['type'] == 'Movie']
+            tv_show_recommendations = recommendations[recommendations['type'] == 'TV Show']
+
+            if not movie_recommendations.empty:
+                print("\n#################### Recommended Movies: ####################")
+                for i, (_, row) in enumerate(movie_recommendations.iterrows(), start=1):
+                    print(dedent(f"""
+                        {i}. {row['title']} ({row['release_year']}) ({row['genres']})
+                        Description: {row['description']}
+                        Director: {row['director']}
+                        Cast: {row['cast']}
+                        
+                        ===============================================================
+                    """))
+
+            if not tv_show_recommendations.empty:
+                print("\n#################### Recommended TV Shows: ####################")
+                for i, (_, row) in enumerate(tv_show_recommendations.iterrows(), start=1):
+                    print(dedent(f"""
+                        {i}. {row['title']} ({row['release_year']}) ({row['genres']})
+                        Description: {row['description']}
+                        Director: {row['director']}
+                        Cast: {row['cast']}
+                        
+                        ===============================================================
+                    """))
         else:
-            print("No data available to search.")
+            print("No recommendations found.")
 
 
 def main():
-
     data_loader = LoadData()
     title_data = data_loader.load_data()
 
-    user_data = UserData()
+    model = TrainModel(title_data)
-    user_input = user_data.input()
+    model.train()
 
-    recommendations = Recommendations()
+    recommendations = RecommendationLoader(model, title_data)
-    recommendations.get_recommendations(user_data, title_data)
+    recommendations.run()
 
 if __name__ == "__main__":
     main()