node-RAPIDS regex example

node-RAPIDS regex ex.js

// Using https://github.com/rapidsai/node-rapids/  

const cudf = require('@rapidsai/cudf');
 
const regexps = [
 /Cloud|Overcast/,
 /Rain|T-Storm|Thunderstorm|Squalls|Drizzle/,
 /Snow/,
 /Fog/,
 /Ice|Hail|Freezing|Sleet/,
 /Dust|Smoke|Sand/,
];
​
console.log('');
​
const weather_condition_gpu = cudf.DataFrame.readCSV({
 header: 0,
 sourceType: 'files',
 sources: [`${__dirname}/US_Accidents_Dec20.csv`],
 dataTypes: {
   id: 'str', source: 'str', tmc: 'float64', severity: 'int32', start_time: 'str', end_time: 'str',
   start_lat: 'float64', start_lng: 'float64', end_lat: 'float64', end_lng: 'float64',
   distance: 'float64', description: 'str', number: 'int32', street: 'str', side: 'str',
   city: 'str', county: 'str', state: 'str', zipcode: 'str', country: 'str', timezone: 'str', airport_code: 'str',
   weather_timestamp: 'str', temperature: 'float64', wind_chill: 'float64', humidity: 'float64', pressure: 'float64',
   visibility: 'float64', wind_direction: 'str', wind_speed: 'float64', precipitation: 'float64', weather_condition: 'str',
   amenity: 'bool', bump: 'bool', crossing: 'bool', give_way: 'bool', junction: 'bool', no_exit: 'bool', railway: 'bool',
   roundabout: 'bool', station: 'bool', stop: 'bool', traffic_calming: 'bool', traffic_signal: 'bool', turning_loop: 'bool',
   sunrise_sunset: 'str', civil_twilight: 'str', nautical_twighlight: 'str', astronomical_twighlight: 'str'
 },
}).get('weather_condition');
​
console.time(`GPU time`);
​
regexps.forEach((regexp) => {
 console.time(`${regexp.source} time`);
 const matches = weather_condition_gpu.containsRe(regexp.source).sum();
 console.timeEnd(`${regexp.source} time`);
 console.log(`${regexp.source} matches: ${matches.toLocaleString()}`);
});
​
console.timeEnd(`GPU time`);
​
console.log('');
​
const weather_condition_cpu = (() => {
 const categorical = weather_condition_gpu.cast(new cudf.Categorical(new cudf.Utf8String));
 const categories = [...categorical.categories];
 const codes = [...categorical.codes];
 return codes.map((i) => categories[i]);
})();
​
console.time(`CPU time`);
​
regexps.forEach((regexp) => {
 console.time(`${regexp.source} time`);
 const matches = weather_condition_cpu.reduce((matches, weather_condition) => {
   return matches + (regexp.exec(weather_condition) || []).length;
 }, 0);
 console.timeEnd(`${regexp.source} time`);
 console.log(`${regexp.source} matches: ${matches.toLocaleString()}`);
});
​
console.timeEnd(`CPU time`);
​
console.log('');
 
/* OUTPUT:
--------------------------- 
// 1.6GB .CSV
// GPU: Titan RTX

Cloud|Overcast time: 26.819ms
Cloud|Overcast matches: 1,896,354
Rain|T-Storm|Thunderstorm|Squalls|Drizzle time: 63.813ms
Rain|T-Storm|Thunderstorm|Squalls|Drizzle matches: 326,441
Snow time: 6.396ms
Snow matches: 68,101
Fog time: 6.997ms
Fog matches: 52,063
Ice|Hail|Freezing|Sleet time: 44.031ms
Ice|Hail|Freezing|Sleet matches: 4,698
Dust|Smoke|Sand time: 29.932ms
Dust|Smoke|Sand matches: 8,846
GPU time: 190.457ms
 

// CPU: AMD Ryzen Threadripper 1900X 8-Core (3.8GHZ)
Cloud|Overcast time: 244.493ms
Cloud|Overcast matches: 1,896,354
Rain|T-Storm|Thunderstorm|Squalls|Drizzle time: 192.591ms
Rain|T-Storm|Thunderstorm|Squalls|Drizzle matches: 326,441
Snow time: 206.071ms
Snow matches: 68,101
Fog time: 204.61ms
Fog matches: 52,063
Ice|Hail|Freezing|Sleet time: 214.325ms
Ice|Hail|Freezing|Sleet matches: 4,698
Dust|Smoke|Sand time: 164.633ms
Dust|Smoke|Sand matches: 8,846
CPU time: 1.230s 

--------------------------- 
// GPU is 6.45x faster than CPU
*/

Full example from https://github.com/rapidsai/node-rapids/tree/main/modules/cudf/notebooks