Commit 36b1fe28e1062bbea78be96668058f52f37b4a5d
1 parent
44060889b7
Exists in
master
Reduice the reduction of given features using tsne algorithm
Showing 1 changed file with 37 additions and 0 deletions Side-by-side Diff
scripts/dimreduction/tsne.py
| 1 | +''' | |
| 2 | +The goal of this script is to display calculate tsne of pvectors. | |
| 3 | +''' | |
| 4 | + | |
| 5 | +import os | |
| 6 | +from os.path import isfile | |
| 7 | +import argparse | |
| 8 | +import numpy as np | |
| 9 | +from sklearn.manifold import TSNE | |
| 10 | + | |
| 11 | +from volia.data_io import read_features | |
| 12 | + | |
| 13 | +if __name__ == "__main__": | |
| 14 | + # Defining argparse | |
| 15 | + parser = argparse.ArgumentParser(prog='pvector tsne', description='Calculate the tsne representation of pvector in 3 or 2d') | |
| 16 | + parser.add_argument('features', type=str, | |
| 17 | + help='the path of the file you want to calculate tsne') | |
| 18 | + parser.add_argument('-o', '--outfile', type=str, | |
| 19 | + default='.', | |
| 20 | + help='the path of the output file.') | |
| 21 | + parser.add_argument('-n', '--n-comp', type=int, choices=[2, 3], | |
| 22 | + default='2', | |
| 23 | + help='number of components output of tsne') | |
| 24 | + | |
| 25 | + args = parser.parse_args() | |
| 26 | + | |
| 27 | + assert isfile(args.features) | |
| 28 | + | |
| 29 | + features_list = read_features(args.features) | |
| 30 | + tuples_key_feat = np.vstack([ (key, feats) for key, feats in features_list.items()]) | |
| 31 | + keys, features = zip(*tuples_key_feat) | |
| 32 | + feat_tsne = TSNE(n_components=args.n_comp).fit_transform(features) | |
| 33 | + | |
| 34 | + with open(args.outfile, "w") as of: | |
| 35 | + for i in range(len(keys)): | |
| 36 | + of.write(keys[i] + " " + " ".join([str(feat) for feat in feat_tsne[i]]) + "\n") | |
| 37 | + print("TSNE finished. Check if everything has been done well.") |