Imported datasets and used gradio]

app.py

@@ -1,7 +1,142 @@
+import pandas as pd
+import numpy as np
+from zipfile import ZipFile
+import tensorflow as tf
+from tensorflow import keras
+from pathlib import Path
+import matplotlib.pyplot as plt
 import gradio as gr
+from huggingface_hub import from_pretrained_keras
+from datasets import load_dataset
 
-def greet(name):
-    return "Hello " + name + "!!"
+book_data_load = load_dataset("hqasmei/ml-capstone-project-dataset", data_files="book_data.csv")
+filtered_data_load = load_dataset("hqasmei/ml-capstone-project-dataset", data_files="filtered_data.csv")
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+book_data_arr = []
+filtered_data_arr = []
+
+for item in book_data_load['train']:
+  book_data_arr.append(item)
+
+for item in filtered_data_load['train']:
+  filtered_data_arr.append(item)
+
+book_df = pd.DataFrame(book_data_arr)
+filtered_df = pd.DataFrame(filtered_data_arr)
+
+# Make the encodings for users
+user_ids            = filtered_df["user_id"].unique().tolist()
+user2user_encoded   = {x: i for i, x in enumerate(user_ids)}
+user_encoded2user   = {i: x for i, x in enumerate(user_ids)}
+filtered_df["user"] = filtered_df["user_id"].map(user2user_encoded)
+num_users           = len(user2user_encoded)
+
+# Make the encodings for books
+book_ids            = filtered_df["book_id"].unique().tolist()
+book2book_encoded   = {x: i for i, x in enumerate(book_ids)}
+book_encoded2book   = {i: x for i, x in enumerate(book_ids)}
+filtered_df["book"] = filtered_df["book_id"].map(book2book_encoded)
+num_books           = len(book_encoded2book)
+
+# Set ratings type
+filtered_df["rating"] = filtered_df["rating"].values.astype(np.float32)
+
+# Load model
+model = from_pretrained_keras('hqasmei/ml-model')
+
+
+def update_user(id):
+  return get_top_rated_books_from_user(id), get_recommendations(id)
+  
+
+def get_top_rated_books_from_user(id):
+  decoded_id = user_encoded2user.get(id)
+  
+  # Get the top rated books by this user
+  books_read_by_user = filtered_df[filtered_df.user_id == decoded_id]
+  top_books_user     = (books_read_by_user.sort_values(by="rating", ascending=False).head(5).book_id.values)
+  book_df_rows       = book_df[book_df["book_id"].isin(top_books_user)]
+  book_df_rows       = book_df_rows.drop('book_id', axis=1)
+  return book_df_rows
+
+def random_user():
+  return update_user(np.random.randint(0, num_users-1))
+
+def get_recommendations(id):
+  decoded_id = user_encoded2user.get(id)
+  
+  # Get the top 10 recommended books for this user
+  books_read_by_user = filtered_df[filtered_df.user_id == decoded_id]
+  books_not_read     = book_df[~book_df["book_id"].isin(books_read_by_user.book_id.values)]["book_id"]
+  books_not_read     = list(set(books_not_read).intersection(set(book2book_encoded.keys())))
+  books_not_read     = [[book2book_encoded.get(x)] for x in books_not_read]
+
+  # Encoded user id
+  encoded_id = id
+
+  # Create data [[user_id, book_id],...]
+  user_book_array = np.hstack(([[encoded_id]] * len(books_not_read), books_not_read))
+
+  # Predict ratings for books not read
+  ratings = model.predict(user_book_array).flatten()
+
+  # Get indices of top ten books
+  top_ratings_indices = ratings.argsort()[-10:][::-1]
+
+  # Decode each book
+  recommended_book_ids = [book_encoded2book.get(books_not_read[x][0]) for x in top_ratings_indices]
+  recommended_books    = book_df[book_df["book_id"].isin(recommended_book_ids)]
+  recommended_books    = recommended_books.drop('book_id', axis=1)
+
+  return recommended_books
+
+demo = gr.Blocks()
+
+with demo:
+  gr.Markdown("""
+  <div>
+  <h1 style='text-align: center'>Book Recommender</h1>
+  Collaborative Filtering is used to predict the top 10 recommended books for a particular user from the dataset based on that user and previous books they have rated.
+  
+  Note: Currently there is a bug with sliders. If you "click and drag" on the slider it will not use the correct user. Please only "click" on the slider.
+  </div>
+  """)
+    
+  with gr.Box():
+    gr.Markdown(
+    """
+    ### Input
+    #### Select a user to get recommendations for.
+    """)
+
+    inp1 = gr.Slider(0, num_users-1, value=0, label='User')
+    # btn1 = gr.Button('Random User')
+
+    # top_rated_from_user = get_top_rated_from_user(0)
+    gr.Markdown(
+    """
+    <br>
+    """)
+    gr.Markdown(
+    """
+    #### Books with the Highest Ratings from this user
+    """)
+    df1 = gr.DataFrame(headers=["title"], datatype=["str"], interactive=False)
+
+  with gr.Box():
+    # recommendations = get_recommendations(0)
+    gr.Markdown(
+    """
+    ### Output
+    #### Top 10 book recommendations
+    """)
+    df2 = gr.DataFrame(headers=["title"], datatype=["str"], interactive=False)
+
+  
+  
+  inp1.change(fn=update_user,
+              inputs=inp1,
+              outputs=[df1, df2])
+  
+
+demo.launch(debug=True)

requirements.txt

@@ -1 +1,3 @@
-tensorflow
+tensorflow
+gdown
+datasets