\n",
" "
]
},
"metadata": {},
"execution_count": 7
}
],
"source": [
"sc"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "u6c83fJdzbk8"
},
"source": [
"# Create RDD from file\n",
"\n",
"The second parameter ($80$) indicates the desired number of partitions."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "iqrxf5FKzbk8",
"outputId": "0c1125b7-8b7d-480b-8b21-a3bfd6573a92"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"textFile is of type: \n",
"Number of partitions: 80\n"
]
}
],
"source": [
"textFile = sc.textFile(FILENAME, 80)\n",
"print(\"textFile is of type: {}\\nNumber of partitions: {}\".format(type(textFile), textFile.getNumPartitions()))"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "n7uGGEeHzbk8"
},
"source": [
"# Generate trigrams\n",
"\n",
"Change `n` to generate n-grams."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"id": "dn9J733hzbk9"
},
"outputs": [],
"source": [
"from operator import add\n",
"n = 3\n",
"ngrams = textFile \\\n",
" .flatMap(lambda x: [x.split()]) \\\n",
" .flatMap(lambda x: [tuple(y) for y in zip(*[x[i:] for i in range(n)])]) \\\n",
" .map(lambda x: (x, 1)) \\\n",
" .reduceByKey(add) \\\n",
" .sortBy(lambda x: x[1], ascending=False)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "VcICQlj3zbk9",
"outputId": "b592dc98-7301-4e65-8c2f-eca5c6a6002c"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"('said', 'Don', 'Quixote,'): 235\n",
"('one', 'of', 'the'): 152\n",
"('said', 'Don', 'Quixote;'): 114\n",
"('Sancho,”', 'said', 'Don'): 98\n",
"('Quixote', 'of', 'La'): 97\n",
"('Don', 'Quixote', 'of'): 94\n",
"('as', 'well', 'as'): 85\n",
"('out', 'of', 'the'): 82\n",
"('that', 'I', 'am'): 82\n",
"('that', 'he', 'was'): 78\n"
]
}
],
"source": [
"for (ngram, count) in ngrams.take(10):\n",
" print(\"%s: %i\" % (ngram, count))"
]
},
{
"cell_type": "markdown",
"source": [
"# View job in the Web UI\n",
"\n",
"Here's the link:"
],
"metadata": {
"id": "xQZw0lWkLONA"
}
},
{
"cell_type": "code",
"source": [
"if IN_COLAB:\n",
" output.serve_kernel_port_as_window(4040, path='/jobs/index.html')"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"id": "hQfQM-roLH4x",
"outputId": "3dcd6714-cb8e-449d-80bc-cc40015f9753"
},
"execution_count": 11,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"application/javascript": [
"(async (port, path, text, element) => {\n",
" if (!google.colab.kernel.accessAllowed) {\n",
" return;\n",
" }\n",
" element.appendChild(document.createTextNode(''));\n",
" const url = await google.colab.kernel.proxyPort(port);\n",
" const anchor = document.createElement('a');\n",
" anchor.href = new URL(path, url).toString();\n",
" anchor.target = '_blank';\n",
" anchor.setAttribute('data-href', url + path);\n",
" anchor.textContent = text;\n",
" element.appendChild(anchor);\n",
" })(4040, \"/jobs/index.html\", \"https://localhost:4040/jobs/index.html\", window.element)"
]
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
""
],
"metadata": {
"id": "aXNkGTiXLeKt"
}
},
{
"cell_type": "markdown",
"metadata": {
"id": "DaiVYhewzbk9"
},
"source": [
"# Stop context\n",
"\n",
"Stop the current Spark context to free resources. You also need to stop the current context to be able to create a new one."
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"id": "qoVFly_dzbk9"
},
"outputs": [],
"source": [
"sc.stop()"
]
},
{
"cell_type": "markdown",
"source": [
"# Appendix: ChatGPT on n-grams\n",
"\n",
"My prompt was: \"who better than you to answer the following question? Where can I locate n-grams in the timeline of nlp/language models?\""
],
"metadata": {
"id": "GDkLc5R2AS7m"
}
},
{
"cell_type": "code",
"source": [
"# @title\n",
"from IPython.core.display import HTML\n",
"HTML(\"\"\"\n",
"
\n",
"\n",
" N-grams have been a fundamental concept in natural language processing (NLP) and language modeling for quite some time. Here's a brief overview of their timeline:\n",
"\n",
"
Early Days (1950s-1960s):
The concept of n-grams was introduced in the early days of computational linguistics and information theory. Researchers like Claude Shannon laid the groundwork for the statistical analysis of language.\n",
"\n",
"
Traditional NLP (1970s-1990s):
N-grams became popular in traditional NLP during this period. Researchers used n-grams as a basic unit for language modeling and to capture local context in text. Simple n-gram models were widely used in tasks like machine translation and speech recognition.\n",
"\n",
"
Statistical Language Models (1990s-early 2000s):
N-grams played a crucial role in statistical language modeling. Techniques like N-gram models and Hidden Markov Models were prevalent. These models formed the backbone of various NLP applications.\n",
"\n",
"
Advent of Neural Networks (2010s):
With the resurgence of neural networks, traditional n-gram models faced competition from more sophisticated approaches. Neural network-based language models, such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), started to outperform traditional n-gram models by capturing long-range dependencies in language.\n",
"\n",
"
Deep Learning and Sequence Models (2010s-2020s):
Transformer-based architectures, like OpenAI's GPT series, further revolutionized NLP. These models, based on self-attention mechanisms, are capable of capturing contextual information effectively, making them more powerful than n-gram models. However, n-grams are still used in certain contexts and as components of more advanced models.\n",
"\n",
"
Current State (2020s and beyond):
State-of-the-art language models, such as GPT-3 and its successors, leverage large-scale transformer architectures and pre-training on massive datasets. These models have largely surpassed the need for explicit n-gram modeling, as they can capture complex language patterns and dependencies across long sequences.\n",
"\n",
"\n",
"While n-grams were crucial in the early development of language models, the field has progressed significantly, and contemporary models have evolved beyond simple n-gram approaches. Nonetheless, understanding n-grams remains essential for foundational knowledge in NLP and language modeling.\n",
"
\n",
"\n",
" N-grams have been a fundamental concept in natural language processing (NLP) and language modeling for quite some time. Here's a brief overview of their timeline:\n",
"\n",
"
Early Days (1950s-1960s):
The concept of n-grams was introduced in the early days of computational linguistics and information theory. Researchers like Claude Shannon laid the groundwork for the statistical analysis of language.\n",
"\n",
"
Traditional NLP (1970s-1990s):
N-grams became popular in traditional NLP during this period. Researchers used n-grams as a basic unit for language modeling and to capture local context in text. Simple n-gram models were widely used in tasks like machine translation and speech recognition.\n",
"\n",
"
Statistical Language Models (1990s-early 2000s):
N-grams played a crucial role in statistical language modeling. Techniques like N-gram models and Hidden Markov Models were prevalent. These models formed the backbone of various NLP applications.\n",
"\n",
"
Advent of Neural Networks (2010s):
With the resurgence of neural networks, traditional n-gram models faced competition from more sophisticated approaches. Neural network-based language models, such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), started to outperform traditional n-gram models by capturing long-range dependencies in language.\n",
"\n",
"
Deep Learning and Sequence Models (2010s-2020s):
Transformer-based architectures, like OpenAI's GPT series, further revolutionized NLP. These models, based on self-attention mechanisms, are capable of capturing contextual information effectively, making them more powerful than n-gram models. However, n-grams are still used in certain contexts and as components of more advanced models.\n",
"\n",
"
Current State (2020s and beyond):
State-of-the-art language models, such as GPT-3 and its successors, leverage large-scale transformer architectures and pre-training on massive datasets. These models have largely surpassed the need for explicit n-gram modeling, as they can capture complex language patterns and dependencies across long sequences.\n",
"\n",
"\n",
"While n-grams were crucial in the early development of language models, the field has progressed significantly, and contemporary models have evolved beyond simple n-gram approaches. Nonetheless, understanding n-grams remains essential for foundational knowledge in NLP and language modeling.\n",
"
\n"
]
},
"metadata": {},
"execution_count": 13
}
]
},
{
"cell_type": "markdown",
"source": [
"## What is the difference between n-grams and modern language models?\n",
"\n",
"The distinction between n-grams and more modern models like transformers lies in their underlying modeling paradigms. N-grams rely on traditional statistical methods, specifically frequency counts, for language modeling. In contrast, transformers leverage deep learning techniques, which include complex neural network architectures, embeddings, and attention mechanisms. While both approaches involve statistical concepts, transformers harness the power of deep learning to capture intricate patterns and dependencies within data, allowing for more sophisticated language understanding and generation\n",
"\n",
"## Comparing model sizes: a rough estimate of N-gram versus Transformer dimensions\n",
"\n",
"An interesting point to note is that n-gram models have an order of magnitude smaller storage footprint compared to transformer models, especially in terms of model size. This discrepancy is apparent because transformers learn more intricate patterns, relationships, and context-aware representations, resulting in significantly larger model sizes.\n",
"\n",
"Here are some rough estimates of model sizes just to get an idea:\n",
"\n",
"\n",
"\n",
"* **N-gram Model:** With a trigram model and a vocabulary of $50,000$ words, the model size might be in the megabyte range.\n",
"This is because the model primarily needs to store the counts for each trigram in the vocabulary, which is relatively straightforward.\n",
"* **Transformer Model:**\n",
"Even for smaller transformer models with a vocabulary of $50,000$ words, the model size can be in the gigabyte range.\n",
"Transformers have a large number of parameters, and the model size increases significantly with model depth, attention heads, and the embedding dimension.\n",
"For instance, GPT-3, a large transformer model, has 175 billion parameters and a model size that's several gigabytes.\n",
"\n",
"\n",
"\n"
],
"metadata": {
"id": "QPIU3THwCLUX"
}
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.6.8"
},
"colab": {
"provenance": [],
"toc_visible": true,
"include_colab_link": true
}
},
"nbformat": 4,
"nbformat_minor": 0
}
![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
![\"Logo](\"https://github.com/groda/big_data/blob/master/logo_bdb.png?raw=true\"){kind=logo}