Create app.py

app.py

@@ -0,0 +1,76 @@
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import gradio as gr
+
+class BookRecommender:
+    def __init__(self):
+        self.df = None
+        self.similarity_matrix = None
+
+    def load_data(self, file_obj):
+        try:
+            if file_obj.name.endswith('.csv'):
+                df = pd.read_csv(file_obj)
+            elif file_obj.name.endswith(('.xls', '.xlsx')):
+                df = pd.read_excel(file_obj)
+            else:
+                raise ValueError("Unsupported file format. Please provide a CSV or Excel file.")
+            return df
+        except Exception as e:
+            return str(e)
+
+    def preprocess_data(self, df):
+        df['summary'] = df['summary'].fillna('')
+        df['title'] = df['title'].fillna('')
+        df = df.drop_duplicates(subset=['title', 'summary'])
+        return df
+
+    def create_tfidf_matrix(self, df):
+        tfidf = TfidfVectorizer(stop_words='english')
+        tfidf_matrix = tfidf.fit_transform(df['summary'])
+        return tfidf_matrix
+
+    def calculate_similarity(self, tfidf_matrix):
+        return cosine_similarity(tfidf_matrix)
+
+    def recommend_books(self, book_title):
+        if self.df is None or self.similarity_matrix is None:
+            return ["Please upload and process a file first."]
+        try:
+            book_index = self.df[self.df['title'] == book_title].index[0]
+        except IndexError:
+            return ["Book title not found."]
+        
+        similar_books_indices = self.similarity_matrix[book_index].argsort()[::-1][1:6]
+        return self.df['title'].iloc[similar_books_indices].tolist()
+
+    def create_interface(self):
+        def process_file(file_obj):
+            if file_obj is None:
+                return "Please upload a file first.", None
+            self.df = self.load_data(file_obj)
+            self.df = self.preprocess_data(self.df)
+            tfidf_matrix = self.create_tfidf_matrix(self.df)
+            self.similarity_matrix = self.calculate_similarity(tfidf_matrix)
+            return "File uploaded and processed successfully!", gr.update(interactive=True)
+
+        def recommend_interface(book_title):
+            recommendations = self.recommend_books(book_title)
+            return recommendations
+
+        with gr.Blocks() as iface:
+            file_input = gr.File(label="Upload CSV or Excel file")
+            process_button = gr.Button("Process File")
+            status_text = gr.Textbox(label="Status", interactive=False)
+            text_input = gr.Textbox(lines=1, placeholder="Enter book title", interactive=False)
+            output_list = gr.Textbox(label="Recommended Books", interactive=False)
+
+            process_button.click(process_file, inputs=file_input, outputs=[status_text, text_input])
+            text_input.submit(recommend_interface, inputs=text_input, outputs=output_list)
+
+        return iface
+
+recommender = BookRecommender()
+interface = recommender.create_interface()
+interface.launch()