SSH-Master-Thesis/ethan_data_processing_scripts/nearestneighbors.py

from sklearn.neighbors import NearestNeighbors, KNeighborsClassifier
import numpy as np
import sys
from Vector import *


def main():
    # a test of this method using an arbitrarily generated list of 5 vectors with 3 features each
    # nearestNeighbors([[1, 1, 0], [1, 0, 0], [0, 0, 0], [0, 5, 5]], [[1, 1, 4]])
    print(len(sys.argv))
    if len(sys.argv) != 4:
        print("Usage: nearestneighbors.py datafile classificationsfile testdatafile")
        exit()
    data = readPickledData(sys.argv[1])
    classifcations = readPickledData(sys.argv[2])
    testdata = readPickledData(sys.argv[3])
    newdata, newtest = [], []
    for d in data:
        newdata.append(d.features)
    for d in testdata:
        newtest.append(d.features)
    print(newdata)
    print(classifcations)
    print(newtest)
    kNearestNeighbors(newdata, classifcations, newtest)
    # kNearestNeighbors([[1, 1, 0], [1, 0, 0], [0, 0, 0], [0, 5, 5]], ["three", 2, 3, "5"], [[1, 1, 0], [0, 5, 5]])


def kNearestNeighbors(data: list, classifications: list, test_data: list):
    kn = KNeighborsClassifier(n_neighbors=2)
    kn.fit(data, classifications)
    print("Predictions, matching test_data by index: ")
    print(test_data)
    print(kn.predict(test_data))


def nearestNeighbors(data: list, test_data: list):
    x = np.array(data)
    nbrs = NearestNeighbors(n_neighbors=1, algorithm='ball_tree').fit(x)
    dist, indicies = nbrs.kneighbors(test_data)
    print("Indicies:")
    print(indicies)
    print("Distances:")
    print(dist)
    return indicies, dist


if __name__ == '__main__':
    main()