init

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

AI-powered-Book-Recommender

@@ -0,0 +1 @@
+Subproject commit 199ada43ed60008f6a21c012a4d1b2c922ce8ad4

books.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38608249125de795a50a352c8cba7ccb4ee79d6a379628f6d100921faa6de14e
+size 1559650

books_cleaned.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a94b63957a665628ac24987fff5c27219e18374cb6d1d43ecac864125e7b6fe
+size 6467384

books_with_categories.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5149a2a65e0b9656d0262ba18cc67280922cebaee19b203a75d114f6315e76
+size 6520188

books_with_emotions.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2aa2c7b41fd373a47ac8d7ca255fa8135c1c64e14b1ae84d4ffde674138be7
+size 7238781

g_UI.py

@@ -0,0 +1,111 @@
+import pandas as pd
+import numpy as np
+
+
+from langchain_community.document_loaders import TextLoader
+from langchain_openai import OpenAIEmbeddings
+from langchain_text_splitters import CharacterTextSplitter
+from langchain_chroma import Chroma
+
+from langchain.embeddings import HuggingFaceEmbeddings
+
+model_name = "sentence-transformers/all-MiniLM-L6-v2"
+HF_embedding = HuggingFaceEmbeddings(model_name=model_name)
+
+
+
+import gradio as gr
+
+
+books = pd.read_csv("books_with_emotions.csv")
+books["large_thumbnail"] = books["thumbnail"] + "&fife=w800"
+books["large_thumbnail"] = np.where(
+    books["large_thumbnail"].isna(),
+    "cover_coming.jpg",
+    books["large_thumbnail"],
+)
+
+raw_documents = TextLoader("tagged_description.txt").load()
+text_splitter = CharacterTextSplitter(separator="\n", chunk_size=0, chunk_overlap=0)
+documents = text_splitter.split_documents(raw_documents)
+db_books = Chroma.from_documents(documents, HF_embedding)
+
+def retrieve_semantic_recommendations(
+        query:str,
+        category: str = None,
+        tone:str = None,
+        initial_top_k: int=50,
+        final_top_k: int=16
+
+):
+    recs = db_books.similarity_search(query, k=initial_top_k)
+    books_list = [int(rec.page_content.strip('"').split()[0]) for rec in recs]
+    book_recs = books[books["isbn13"].isin(books_list)].head(final_top_k)
+
+    if category != "All":
+        book_recs = book_recs[book_recs["simple_categories"] == category].head(final_top_k)
+    else:
+        book_recs = book_recs.head(final_top_k)
+
+    if tone == "Happy":
+        book_recs.sort_values(by="joy", ascending=False, inplace=True)
+    elif tone == "Surprising":
+        book_recs.sort_values(by="surprise", ascending=False, inplace=True)
+    elif tone == "Angry":
+        book_recs.sort_values(by="anger", ascending=False, inplace=True)
+    elif tone == "Suspenseful":
+        book_recs.sort_values(by="fear", ascending=False, inplace=True)
+    elif tone == "Sad":
+        book_recs.sort_values(by="sadness", ascending=False, inplace=True)
+
+    return book_recs
+
+def recommend_books(
+        query: str,
+        category: str,
+        tone: str
+):
+    recommendations = retrieve_semantic_recommendations(query, category, tone)
+    results = []
+
+    for _, row in recommendations.iterrows():
+        description = row["description"]
+        truncated_desc_split = description.split()
+        truncated_description = " ".join(truncated_desc_split[:30]) + "..."
+
+        authors_split = row["authors"].split(";")
+        if len(authors_split) == 2:
+            authors_str = f"{authors_split[0]} and {authors_split[1]}"
+        elif len(authors_split) > 2:
+            authors_str = f"{', '.join(authors_split[:-1])}, and {authors_split[-1]}"
+        else:
+            authors_str = row["authors"]
+
+        caption = f"{row['title']} by {authors_str}: {truncated_description}"
+        results.append((row["large_thumbnail"], caption))
+    return results
+
+categories = ["All"] + sorted(books["simple_categories"].unique())
+tones = ["All"] + ["Happy", "Surprising", "Angry", "Suspenseful", "Sad"]
+
+with gr.Blocks(theme = gr.themes.Glass()) as dashboard:
+    gr.Markdown("# Your AI-powered Book recommender")
+
+    with gr.Row():
+        user_query = gr.Textbox(label = "Please enter a description about the book:",
+                                placeholder = "e.g., A book exploring human resilience ")
+        category_dropdown = gr.Dropdown(choices = categories, label = "Select a category:", value = "All")
+        tone_dropdown = gr.Dropdown(choices = tones, label = "Select an emotional tone:", value = "All")
+        submit_button = gr.Button("Find recommendations")
+
+    gr.Markdown("## Recommendations")
+    output = gr.Gallery(label = "Recommended books", columns = 8, rows = 2)
+
+    submit_button.click(fn = recommend_books,
+                        inputs = [user_query, category_dropdown, tone_dropdown],
+                        outputs = output)
+
+
+if __name__ == "__main__":
+    dashboard.launch(share=True)
+

tagged_description.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec902e249d79948f8031e7e521315a2a17157d96ca084891321b4fbdc2622e3
+size 2641649

work.ipynb

@@ -0,0 +1,182 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "3e1d6318",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.metrics.pairwise import linear_kernel\n",
+    "import plotly.express as px\n",
+    "import plotly.graph_objects as go"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "1d8722fa",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   bookID                                              title  \\\n",
+      "0       1  Harry Potter and the Half-Blood Prince (Harry ...   \n",
+      "1       2  Harry Potter and the Order of the Phoenix (Har...   \n",
+      "2       4  Harry Potter and the Chamber of Secrets (Harry...   \n",
+      "3       5  Harry Potter and the Prisoner of Azkaban (Harr...   \n",
+      "4       8  Harry Potter Boxed Set  Books 1-5 (Harry Potte...   \n",
+      "\n",
+      "                      authors  average_rating        isbn         isbn13  \\\n",
+      "0  J.K. Rowling/Mary GrandPré            4.57  0439785960  9780439785969   \n",
+      "1  J.K. Rowling/Mary GrandPré            4.49  0439358078  9780439358071   \n",
+      "2                J.K. Rowling            4.42  0439554896  9780439554893   \n",
+      "3  J.K. Rowling/Mary GrandPré            4.56  043965548X  9780439655484   \n",
+      "4  J.K. Rowling/Mary GrandPré            4.78  0439682584  9780439682589   \n",
+      "\n",
+      "  language_code    num_pages  ratings_count  text_reviews_count  \\\n",
+      "0           eng          652        2095690               27591   \n",
+      "1           eng          870        2153167               29221   \n",
+      "2           eng          352           6333                 244   \n",
+      "3           eng          435        2339585               36325   \n",
+      "4           eng         2690          41428                 164   \n",
+      "\n",
+      "  publication_date        publisher  \n",
+      "0        9/16/2006  Scholastic Inc.  \n",
+      "1         9/1/2004  Scholastic Inc.  \n",
+      "2        11/1/2003       Scholastic  \n",
+      "3         5/1/2004  Scholastic Inc.  \n",
+      "4        9/13/2004       Scholastic  \n"
+     ]
+    }
+   ],
+   "source": [
+    "data = pd.read_csv(\"books.csv\", on_bad_lines='skip')\n",
+    "print(data.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "29eaf0ad",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 11123 entries, 0 to 11122\n",
+      "Data columns (total 12 columns):\n",
+      " #   Column              Non-Null Count  Dtype  \n",
+      "---  ------              --------------  -----  \n",
+      " 0   bookID              11123 non-null  int64  \n",
+      " 1   title               11123 non-null  object \n",
+      " 2   authors             11123 non-null  object \n",
+      " 3   average_rating      11123 non-null  float64\n",
+      " 4   isbn                11123 non-null  object \n",
+      " 5   isbn13              11123 non-null  int64  \n",
+      " 6   language_code       11123 non-null  object \n",
+      " 7     num_pages         11123 non-null  int64  \n",
+      " 8   ratings_count       11123 non-null  int64  \n",
+      " 9   text_reviews_count  11123 non-null  int64  \n",
+      " 10  publication_date    11123 non-null  object \n",
+      " 11  publisher           11123 non-null  object \n",
+      "dtypes: float64(1), int64(5), object(6)\n",
+      "memory usage: 1.0+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "data.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "1cc05570",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ValueError",
+     "evalue": "Mime type rendering requires nbformat>=4.2.0 but it is not installed",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[8], line 6\u001b[0m\n\u001b[1;32m      4\u001b[0m fig\u001b[38;5;241m.\u001b[39mupdate_xaxes(title_text\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mAverage Rating\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m      5\u001b[0m fig\u001b[38;5;241m.\u001b[39mupdate_yaxes(title_text\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mFrequency\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m----> 6\u001b[0m \u001b[43mfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mshow\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/Documents/github repos/Book_rec_system/.venv/lib/python3.10/site-packages/plotly/basedatatypes.py:3420\u001b[0m, in \u001b[0;36mBaseFigure.show\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   3387\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m   3388\u001b[0m \u001b[38;5;124;03mShow a figure using either the default renderer(s) or the renderer(s)\u001b[39;00m\n\u001b[1;32m   3389\u001b[0m \u001b[38;5;124;03mspecified by the renderer argument\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   3416\u001b[0m \u001b[38;5;124;03mNone\u001b[39;00m\n\u001b[1;32m   3417\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m   3418\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mplotly\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mio\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mpio\u001b[39;00m\n\u001b[0;32m-> 3420\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mpio\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mshow\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/Documents/github repos/Book_rec_system/.venv/lib/python3.10/site-packages/plotly/io/_renderers.py:415\u001b[0m, in \u001b[0;36mshow\u001b[0;34m(fig, renderer, validate, **kwargs)\u001b[0m\n\u001b[1;32m    410\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    411\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMime type rendering requires ipython but it is not installed\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    412\u001b[0m     )\n\u001b[1;32m    414\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m nbformat \u001b[38;5;129;01mor\u001b[39;00m Version(nbformat\u001b[38;5;241m.\u001b[39m__version__) \u001b[38;5;241m<\u001b[39m Version(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m4.2.0\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m--> 415\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    416\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMime type rendering requires nbformat>=4.2.0 but it is not installed\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    417\u001b[0m     )\n\u001b[1;32m    419\u001b[0m display_jupyter_version_warnings()\n\u001b[1;32m    421\u001b[0m ipython_display\u001b[38;5;241m.\u001b[39mdisplay(bundle, raw\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
+      "\u001b[0;31mValueError\u001b[0m: Mime type rendering requires nbformat>=4.2.0 but it is not installed"
+     ]
+    }
+   ],
+   "source": [
+    "fig = px.histogram(data, x='average_rating', \n",
+    "                   nbins=30, \n",
+    "                   title='Distribution of Average Ratings')\n",
+    "fig.update_xaxes(title_text='Average Rating')\n",
+    "fig.update_yaxes(title_text='Frequency')\n",
+    "fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a0686419",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "192cc248",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "412c1b95",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "792c4d40",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}