Stuart Axelbrooke soaxelbrooke

systemd Talk

First, let's make ourselves a simple python web server with flask:

from flask import Flask
app = Flask(__name__)
import os

PORT = int(os.getenv('FLASK_PORT', 5000))

	<!-- Shamelessly borrowed from bulma docs -->
	<div class="container">
	<div class="card">
	<header class="card-header">
	<p class="card-header-title is-translated" translate="cardTitle">
	Component
	</p>
	</header>
	<div class="card-content">
	<div class="content">


	def ensure_subscription(subscription_name: str, subscriber: Optional[pubsub_v1.SubscriberClient]=None):
	subscriber = subscriber or pubsub_v1.SubscriberClient()
	subscription_path = subscriber.subscription_path('MY_GCP_PROJECT', subscription_name)
	try:
	return subscriber.get_subscription(subscription_path)
	except GoogleAPICallError:
	logging.warning(f'No subscription {subscription_path} found, creating...')
	# ensure topic exists
	topic_path = get_pubsub_topic_path(get_publisher('my-topic-name'))


	import pandas
	import numpy
	import csv
	from typing import List, Optional

	class WordVectorizer:
	def __init__(self, embeddings_path: str, embedding_dim: int, limit=None):
	with open(embeddings_path) as infile:
	# Skip header if this was produced by fasttext, which has metadata on first line

	#!/usr/bin/env python3.6
	"""
	Example usage:

	$ python3.6 wvsqlite.py glove.840B.300d.txt

	Produces an sqlite database at with byte strings of floats for each word vector, indexed by
	token for fast lookup for vocabs much smaller than the embedding vocab (aka most real vocabs).

	Float size can be set via FLOAT_BYTES env var, and can be 4 or 8, and LIMIT can be set to take

	FROM rustlang/rust:nightly AS builder
	WORKDIR /app
	COPY src/ src/
	COPY Cargo.* ./
	RUN cargo build --release

	FROM debian:stretch-slim
	COPY --from=builder /app/target/release/api .
	CMD ["./api"]

	# Need wf - install with `cargo install wf`

	mkdir splits wfs
	echo 'Splitting file into parts...'
	split -a 5 -l 200000 $1 splits/split
	ls splits/ \| parallel 'echo "Counting {}..."; cat splits/{} \| wf > wfs/{}_wf.txt'
	echo 'Combining split counts...'
	python -c 'from tqdm import tqdm; from functools import reduce; from glob import glob; from collections import Counter; of = open("wfs.txt", "w"); wf = reduce(lambda a, b: a + b, (Counter(dict((pair[0], int(pair[1])) for pair in (line.strip().split() for line in open(fpath)))) for fpath in tqdm(glob("wfs/*"))), Counter()); [of.write("{} {}\n".format(key, count)) for key, count in sorted(wf.items(), key=lambda p: -p[1])]'
	rm -rf wfs splits
	echo 'Word frequencies written to wfs.txt.'

	import keras
	import tensorflow
	import numpy
	import re

	# Capturing group is important so it can be left padded with space (token splitter)
	token_pattern = r"([\w']+\|[,\.\?;\-\(\)])"
	substitution = r" \1"