initial commit

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/dataset/book_tags.csv filter=lfs diff=lfs merge=lfs -text
+data/dataset/goodbooks-10k.csv filter=lfs diff=lfs merge=lfs -text
+data/dataset/ratings.csv filter=lfs diff=lfs merge=lfs -text
+models/recommendation_model_2.keras filter=lfs diff=lfs merge=lfs -text
+models/recommendation_model_3.keras filter=lfs diff=lfs merge=lfs -text
+models/recommendation_model.keras filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,4 @@
 ---
 license: apache-2.0
+library: tensorflow
 ---

data/dataset/book_tags.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff2f0659be9ddbe10bf47ba33b5b69024f893f017ac665236f15bc97d862950
+size 16665883

data/dataset/goodbooks-10k.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78139caa6f50bce2373d5fd82e3479e24b51a715d52a5782b073b0e4fa054674
+size 78103306

data/dataset/ratings.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee8a97172bd6d97147a30d9cfb3029ac240bd27ba2aa9365981c051c65113f8
+size 72126826

inference.py

@@ -0,0 +1,47 @@
+import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity
+
+from model import build_model
+from utils import map_book_name_to_id
+
+# Load the saved model for inference
+loaded_model = build_model(
+    num_users=len(ratings["user_id"].unique()),
+    num_books=len(ratings["book_id"].unique()),
+)
+loaded_model.load_weights("recommendation_model.h5")
+
+
+# Function to recommend books for a user based on input book name or author name
+def recommend_books_for_user(input_name, model, num_recommendations=10):
+    """
+    Recommend books for a user based on input book name or author name.
+
+    Args:
+        input_name (str): The input book name or author name.
+        model: The trained recommendation model.
+        num_recommendations (int): The number of books to recommend.
+
+    Returns:
+        tuple: A tuple containing the recommended book names and their similarity scores.
+    """
+    # Check if input_name is a book name or author name
+    is_author = input_name.lower() in books["authors"].str.lower().values
+
+    # Rest of the code...
+
+
+# Recommend books for a user based on input name along with similarity score.
+
+input_name = "Harry Potter and the Sorcerer's Stone"
+recommended_books, similarity_scores = recommend_books_for_user(
+    input_name, loaded_model
+)
+
+if recommended_books is not None:
+    print("Recommended Books:")
+    print("------------------")
+    for book, score in zip(recommended_books, similarity_scores):
+        print(f"{book:<60} {score:.4f}")
+else:
+    print("No recommendations found.")

model.py

@@ -0,0 +1,89 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics.pairwise import cosine_similarity
+import matplotlib.pyplot as plt
+from tensorflow.keras.models import Model
+from tensorflow.keras.layers import Input, Embedding, Flatten, concatenate, Dense
+from tensorflow.keras.optimizers import Adam
+
+# Load datasets
+books = pd.read_csv("../data/dataset/books.csv")
+ratings = pd.read_csv("../data/dataset/ratings.csv")
+
+# Preprocess data
+user_encoder = LabelEncoder()
+book_encoder = LabelEncoder()
+
+ratings["user_id"] = user_encoder.fit_transform(ratings["user_id"])
+ratings["book_id"] = book_encoder.fit_transform(ratings["book_id"])
+
+# Split the data into training and testing sets
+train, test = train_test_split(ratings, test_size=0.2, random_state=42)
+
+
+# Define the neural network model
+def build_model(num_users, num_books, embedding_size=50):
+    """
+    Build a recommendation model.
+
+    Args:
+        num_users (int): The number of users in the dataset.
+        num_books (int): The number of books in the dataset.
+        embedding_size (int, optional): The size of the embedding vectors. Defaults to 50.
+
+    Returns:
+        keras.Model: The compiled recommendation model.
+    """
+    user_input = Input(shape=(1,))
+    book_input = Input(shape=(1,))
+
+    user_embedding = Embedding(input_dim=num_users, output_dim=embedding_size)(
+        user_input
+    )
+    book_embedding = Embedding(input_dim=num_books, output_dim=embedding_size)(
+        book_input
+    )
+
+    user_flat = Flatten()(user_embedding)
+    book_flat = Flatten()(book_embedding)
+
+    merged = concatenate([user_flat, book_flat])
+    dense1 = Dense(128, activation="relu")(merged)
+    output = Dense(1)(dense1)
+
+    model = Model(inputs=[user_input, book_input], outputs=output)
+    model.compile(loss="mean_squared_error", optimizer=Adam(learning_rate=0.001))
+
+    return model
+
+
+# Train the model
+model = build_model(
+    num_users=len(ratings["user_id"].unique()),
+    num_books=len(ratings["book_id"].unique()),
+)
+history = model.fit(
+    [train["user_id"], train["book_id"]],
+    train["rating"],
+    epochs=5,
+    batch_size=128,
+    validation_split=0.1,
+)
+
+# Plot training and validation loss
+plt.figure(figsize=(12, 6))
+plt.plot(history.history["loss"], label="Training Loss")
+plt.plot(history.history["val_loss"], label="Validation Loss")
+plt.xlabel("Epoch")
+plt.ylabel("Loss")
+plt.legend()
+plt.show()
+
+# Save the model
+model.save("recommendation_model.h5")
+
+# Evaluate the model
+test_loss = model.evaluate([test["user_id"], test["book_id"]], test["rating"])
+print(f"Test Loss: {test_loss}")

models/authors_w2v.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254a7bb6b32780bbc3df2575c65fad32042738af828cf11b634f5bc9066f817d
+size 4978284

models/recommendation_model.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04908f5db3844db15d02c6142c9bb27cd43cd4a0cca67dc0edf91c7a5c94e06
+size 38266810

models/recommendation_model_2.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a605732f83df3df5f30d0ff20375bb873b3366e9d89123d3ef39749299cb6eae
+size 38266842

models/recommendation_model_3.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813736e08ec0713d5b7e2bdbd6cbbb88ab2b7e4bd33ae540da81267d4cc5178d
+size 38248024

models/title_w2v.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05d399ab55578c046a190d2d3015bcfc36fc0e7289f09c257eb17c0e78035ce
+size 6747050

tfidf_models/tfidf_model_authors.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace0fd2a9e5165c218e4d211206596fbe0798a8f9977af5981b95f76ffce30ea
+size 170167

tfidf_models/tfidf_model_titles.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e93e399430ea1ba19833d5b5dc4172a8bdf5e5cec23fc2efabddec52974b37
+size 233964