File size: 1,480 Bytes
f0c2a78 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
import numpy as np
import json
class LabelEncoder(object):
"""Label encoder for tag labels."""
def __init__(self, class_to_index={}):
self.class_to_index = class_to_index
self.index_to_class = {v: k for k, v in self.class_to_index.items()}
self.classes = list(self.class_to_index.keys())
def __len__(self):
return len(self.class_to_index)
def __str__(self):
return f"<LabelEncoder(num_classes={len(self)})>"
def fit(self, y):
classes = np.unique(y)
for i, class_ in enumerate(classes):
self.class_to_index[class_] = i
self.index_to_class = {v: k for k, v in self.class_to_index.items()}
self.classes = list(self.class_to_index.keys())
return self
def encode(self, y):
encoded = np.zeros((len(y)), dtype=int)
for i, item in enumerate(y):
encoded[i] = self.class_to_index[item]
return encoded
def decode(self, y):
classes = []
for i, item in enumerate(y):
classes.append(self.index_to_class[item])
return classes
def save(self, fp):
with open(fp, "w") as fp:
contents = {'class_to_index': self.class_to_index}
json.dump(contents, fp, indent=4, sort_keys=False)
@classmethod
def load(cls, fp):
with open(fp, "r") as fp:
kwargs = json.load(fp=fp)
return cls(**kwargs) |