dice89

resource "google_compute_instance" "example-vm" {
  count = 1
  name = "example-vm"
  machine_type = "n1-standard-4" // 1 CPU 14 GB of RAM
  zone = "europe-west-1"
  boot_disk {
    initialize_params {
      image = "ubuntu-os-cloud/ubuntu-1604-lts" # ubuntu image
      size = 20 // 20 GB Storage
    }

dice89

ssh-keygen -t rsa -b 4096 -C "your_email@example.com"

dice89

## Install scala 2.11.8

export scalaVer="2.11.8"
sudo apt-get remove scala-library scala
wget www.scala-lang.org/files/archive/scala-"$scalaVer".deb
sudo dpkg -i scala-"$scalaVer".deb
sudo apt-get -y --force-yes update
sudo apt-get -y --force-yes install scala

dice89

dice89

import numpy as np
import random
n_samples_min = int(1e3)
n_samples_max = int(5e7)
lat_longs = np.array([[random.uniform(50, 52),
                       random.uniform(8, 15) ] 
                      for i in range(n_samples_max)])

dice89

from sklearn.neighbors import DistanceMetric
import numpy as np
RADIANT_TO_KM_CONSTANT = 6367
class BruteForce:
    def __init__(self,lat_longs):
        self.haversine =DistanceMetric.get_metric('haversine')
        self.lat_longs = np.radians(lat_longs)
        
    def query_radius(self,query,radius):
        radius_km = radius/1e3

dice89

from sklearn.neighbors import BallTree
import numpy as np
RADIANT_TO_KM_CONSTANT = 6367
class BallTreeIndex:
    def __init__(self,lat_longs):
        self.lat_longs = np.radians(lat_longs)
        self.ball_tree_index =BallTree(self.lat_longs, metric='haversine')
        
    def query_radius(self,query,radius):
        radius_km = radius/1e3

dice89

RADIANT_TO_KM_CONSTANT = 6367
import proximitypyhash as ppyh
import pygeohash as pgh
from sklearn.neighbors import DistanceMetric
import numpy as np
from collections import defaultdict


class GeoHashIndexer:
    def __init__(self, precision, lat_longs):

dice89

dice89

# Perform Dataset preparation and the comparison
import numpy as np
import random
import time
from collections import defaultdict
from sklearn.neighbors import BallTree
from sklearn.neighbors import DistanceMetric
n_samples_min = int(1e3)
n_samples_max = int(1e7)