8 changed files with 595 additions and 14 deletions
@ -0,0 +1,424 @@ |
|||||||
|
{ |
||||||
|
"cells": [ |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "28a0673e-96b5-43f2-8a8b-bd033bf851b0", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"# The Product Pricer Continued\n", |
||||||
|
"\n", |
||||||
|
"A model that can estimate how much something costs, from its description.\n", |
||||||
|
"\n", |
||||||
|
"## Data Curation Part 2\n", |
||||||
|
"\n", |
||||||
|
"Today we'll extend our dataset to a greater coverage, and craft it into an excellent dataset for training.\n", |
||||||
|
"\n", |
||||||
|
"The dataset is here: \n", |
||||||
|
"https://huggingface.co/datasets/McAuley-Lab/Amazon-Reviews-2023\n", |
||||||
|
"\n", |
||||||
|
"And the folder with all the product datasets is here: \n", |
||||||
|
"https://huggingface.co/datasets/McAuley-Lab/Amazon-Reviews-2023/tree/main/raw/meta_categories\n", |
||||||
|
"\n", |
||||||
|
"## The Lite dataset\n", |
||||||
|
"\n", |
||||||
|
"This notebook is an alternative to `day2.ipynb` that creates a smaller dataset for Home Appliances only, to keep training fast and costs low. You may need to update names of future notebooks to reflect that you have built the \"lite\" dataset not the full dataset." |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "67cedf85-8125-4322-998e-9375fe745597", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# imports\n", |
||||||
|
"\n", |
||||||
|
"import os\n", |
||||||
|
"import random\n", |
||||||
|
"from dotenv import load_dotenv\n", |
||||||
|
"from huggingface_hub import login\n", |
||||||
|
"from datasets import load_dataset, Dataset, DatasetDict\n", |
||||||
|
"from items import Item\n", |
||||||
|
"from loaders import ItemLoader\n", |
||||||
|
"import matplotlib.pyplot as plt\n", |
||||||
|
"from collections import Counter, defaultdict\n", |
||||||
|
"import numpy as np\n", |
||||||
|
"import pickle" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "7390a6aa-79cb-4dea-b6d7-de7e4b13e472", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# environment\n", |
||||||
|
"\n", |
||||||
|
"load_dotenv()\n", |
||||||
|
"os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')\n", |
||||||
|
"os.environ['ANTHROPIC_API_KEY'] = os.getenv('ANTHROPIC_API_KEY', 'your-key-if-not-using-env')\n", |
||||||
|
"os.environ['HF_TOKEN'] = os.getenv('HF_TOKEN', 'your-key-if-not-using-env')" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "0732274a-aa6a-44fc-aee2-40dc8a8e4451", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Log in to HuggingFace\n", |
||||||
|
"\n", |
||||||
|
"hf_token = os.environ['HF_TOKEN']\n", |
||||||
|
"login(hf_token, add_to_git_credential=True)" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "1adcf323-de9d-4c24-a9c3-d7ae554d06ca", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"%matplotlib inline" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "01065d69-765c-42c8-9f90-68b8c8754068", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"## The ItemLoader code\n", |
||||||
|
"\n", |
||||||
|
"Look in loaders.py - there's some useful code to make life easier for us" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "e2b6dc50-ac5c-4cf2-af2e-968ed8ef86d7", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"## Now to SCALE UP\n", |
||||||
|
"\n", |
||||||
|
"Let's look at all datasets of all the items that you might find in a large home retail store - electrical, electronic, office and related, but not clothes / beauty / books." |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "d1d06cd3-f3c2-44f0-a9f2-13b54ff8be5c", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"dataset_names = [\n", |
||||||
|
" # \"Automotive\",\n", |
||||||
|
" # \"Electronics\",\n", |
||||||
|
" # \"Office_Products\",\n", |
||||||
|
" # \"Tools_and_Home_Improvement\",\n", |
||||||
|
" # \"Cell_Phones_and_Accessories\",\n", |
||||||
|
" # \"Toys_and_Games\",\n", |
||||||
|
" \"Appliances\",\n", |
||||||
|
" # \"Musical_Instruments\",\n", |
||||||
|
"]" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "aa8fd0f0-509a-4298-8fcc-e499a061e1be", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"items = []\n", |
||||||
|
"for dataset_name in dataset_names:\n", |
||||||
|
" loader = ItemLoader(dataset_name)\n", |
||||||
|
" items.extend(loader.load())" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "3e29a5ab-ca61-41cc-9b33-22d374681b85", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"print(f\"A grand total of {len(items):,} items\")" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "89078cb1-9679-4eb0-b295-599b8586bcd1", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Plot the distribution of token counts again\n", |
||||||
|
"\n", |
||||||
|
"tokens = [item.token_count for item in items]\n", |
||||||
|
"plt.figure(figsize=(15, 6))\n", |
||||||
|
"plt.title(f\"Token counts: Avg {sum(tokens)/len(tokens):,.1f} and highest {max(tokens):,}\\n\")\n", |
||||||
|
"plt.xlabel('Length (tokens)')\n", |
||||||
|
"plt.ylabel('Count')\n", |
||||||
|
"plt.hist(tokens, rwidth=0.7, color=\"skyblue\", bins=range(0, 300, 10))\n", |
||||||
|
"plt.show()" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "c38e0c43-9f7a-450e-a911-c94d37d9b9c3", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Plot the distribution of prices\n", |
||||||
|
"\n", |
||||||
|
"prices = [item.price for item in items]\n", |
||||||
|
"plt.figure(figsize=(15, 6))\n", |
||||||
|
"plt.title(f\"Prices: Avg {sum(prices)/len(prices):,.1f} and highest {max(prices):,}\\n\")\n", |
||||||
|
"plt.xlabel('Price ($)')\n", |
||||||
|
"plt.ylabel('Count')\n", |
||||||
|
"plt.hist(prices, rwidth=0.7, color=\"blueviolet\", bins=range(0, 1000, 10))\n", |
||||||
|
"plt.show()" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "ac046cc1-2717-415b-96ad-b73b2950d235", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"# Dataset Curated!\n", |
||||||
|
"\n", |
||||||
|
"We've crafted an excellent dataset.\n", |
||||||
|
"\n", |
||||||
|
"Let's do some final checks" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "70219e99-22cc-4e08-9121-51f9707caef0", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# How does the price vary with the character count of the prompt?\n", |
||||||
|
"\n", |
||||||
|
"sample = items\n", |
||||||
|
"\n", |
||||||
|
"sizes = [len(item.prompt) for item in sample]\n", |
||||||
|
"prices = [item.price for item in sample]\n", |
||||||
|
"\n", |
||||||
|
"# Create the scatter plot\n", |
||||||
|
"plt.figure(figsize=(15, 8))\n", |
||||||
|
"plt.scatter(sizes, prices, s=0.2, color=\"red\")\n", |
||||||
|
"\n", |
||||||
|
"# Add labels and title\n", |
||||||
|
"plt.xlabel('Size')\n", |
||||||
|
"plt.ylabel('Price')\n", |
||||||
|
"plt.title('Is there a simple correlation?')\n", |
||||||
|
"\n", |
||||||
|
"# Display the plot\n", |
||||||
|
"plt.show()" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "30ae1453-b9fc-40db-8310-65d850c4b1da", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"def report(item):\n", |
||||||
|
" prompt = item.prompt\n", |
||||||
|
" tokens = Item.tokenizer.encode(item.prompt)\n", |
||||||
|
" print(prompt)\n", |
||||||
|
" print(tokens[-10:])\n", |
||||||
|
" print(Item.tokenizer.batch_decode(tokens[-10:]))" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "d9998b8d-d746-4541-9ac2-701108e0e8fb", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"report(sample[50])" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "7aa0a3fc-d2fe-4e6e-8fdb-96913df2f588", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"## Observation\n", |
||||||
|
"\n", |
||||||
|
"An interesting thing about the Llama tokenizer is that every number from 1 to 999 gets mapped to 1 token, much as we saw with gpt-4o. The same is not true of qwen2, gemma and phi3, which all map individual digits to tokens. This does turn out to be a bit useful for our project, although it's not an essential requirement." |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "0f03c0ee-3103-4603-af5c-b484884a3aa2", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"# Finally\n", |
||||||
|
"\n", |
||||||
|
"It's time to break down our data into a training, test and validation dataset.\n", |
||||||
|
"\n", |
||||||
|
"It's typical to use 5%-10% of your data for testing purposes, but actually we have far more than we need at this point. We'll take 25,000 points for training, and we'll reserve 2,000 for testing, although we won't use all of them.\n" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "3b163ca2-18ef-4c26-8e9d-88eb55f114f6", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"random.seed(42)\n", |
||||||
|
"random.shuffle(sample)\n", |
||||||
|
"train = sample[:25_000]\n", |
||||||
|
"test = sample[25_000:27_000]\n", |
||||||
|
"print(f\"Divided into a training set of {len(train):,} items and test set of {len(test):,} items\")" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "299b9816-8885-4798-829a-69d66d60eb01", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"print(train[0].prompt)" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "97222da3-9f2c-4d15-a5cd-5e5f8dbde6cc", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"print(test[0].test_prompt())" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "7a116369-335a-412b-b70c-2add6675c2e3", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Plot the distribution of prices in the first 250 test points\n", |
||||||
|
"\n", |
||||||
|
"prices = [float(item.price) for item in test[:250]]\n", |
||||||
|
"plt.figure(figsize=(15, 6))\n", |
||||||
|
"plt.title(f\"Avg {sum(prices)/len(prices):.2f} and highest {max(prices):,.2f}\\n\")\n", |
||||||
|
"plt.xlabel('Price ($)')\n", |
||||||
|
"plt.ylabel('Count')\n", |
||||||
|
"plt.hist(prices, rwidth=0.7, color=\"darkblue\", bins=range(0, 1000, 10))\n", |
||||||
|
"plt.show()" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "d522d752-6f66-4786-a4dc-8ef51842558c", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"# Finally - upload your brand new dataset\n", |
||||||
|
"\n", |
||||||
|
"Convert to prompts and upload to HuggingFace hub" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "fa11b3e5-fcf4-4efc-a573-f6f67fec3e73", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"train_prompts = [item.prompt for item in train]\n", |
||||||
|
"train_prices = [item.price for item in train]\n", |
||||||
|
"test_prompts = [item.test_prompt() for item in test]\n", |
||||||
|
"test_prices = [item.price for item in test]" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "b020ab1b-7153-4e5f-b8a3-d5bc2fafb6df", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# Create a Dataset from the lists\n", |
||||||
|
"\n", |
||||||
|
"train_dataset = Dataset.from_dict({\"text\": train_prompts, \"price\": train_prices})\n", |
||||||
|
"test_dataset = Dataset.from_dict({\"text\": test_prompts, \"price\": test_prices})\n", |
||||||
|
"dataset = DatasetDict({\n", |
||||||
|
" \"train\": train_dataset,\n", |
||||||
|
" \"test\": test_dataset\n", |
||||||
|
"})" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "17639641-fb55-44e2-a463-b0b394d00f32", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"DATASET_NAME = \"ed-donner/lite-data\"\n", |
||||||
|
"dataset.push_to_hub(DATASET_NAME, private=True)" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "code", |
||||||
|
"execution_count": null, |
||||||
|
"id": "b85733ba-d165-4f07-b055-46803543edfe", |
||||||
|
"metadata": {}, |
||||||
|
"outputs": [], |
||||||
|
"source": [ |
||||||
|
"# One more thing!\n", |
||||||
|
"# Let's pickle the training and test dataset so we don't have to execute all this code next time!\n", |
||||||
|
"\n", |
||||||
|
"with open('train_lite.pkl', 'wb') as file:\n", |
||||||
|
" pickle.dump(train, file)\n", |
||||||
|
"\n", |
||||||
|
"with open('test_lite.pkl', 'wb') as file:\n", |
||||||
|
" pickle.dump(test, file)" |
||||||
|
] |
||||||
|
}, |
||||||
|
{ |
||||||
|
"cell_type": "markdown", |
||||||
|
"id": "2b58dc61-747f-46f7-b9e0-c205db4f3e5e", |
||||||
|
"metadata": {}, |
||||||
|
"source": [ |
||||||
|
"## Todos for you:\n", |
||||||
|
"\n", |
||||||
|
"- Investigate the dataset more!\n", |
||||||
|
"- Confirm that the tokenizer tokenizes all 3 digit prices into 1 token" |
||||||
|
] |
||||||
|
} |
||||||
|
], |
||||||
|
"metadata": { |
||||||
|
"kernelspec": { |
||||||
|
"display_name": "Python 3 (ipykernel)", |
||||||
|
"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": "3.11.10" |
||||||
|
} |
||||||
|
}, |
||||||
|
"nbformat": 4, |
||||||
|
"nbformat_minor": 5 |
||||||
|
} |
Loading…
Reference in new issue