Spaces:
Configuration error
Configuration error
| import operator | |
| import numpy as np | |
| import pandas as pd | |
| from numpy import dot | |
| from gensim import matutils | |
| from modules.module_ann import Ann | |
| from memory_profiler import profile | |
| from sklearn.neighbors import NearestNeighbors | |
| class Embedding: | |
| def __init__(self, subset_name): | |
| # Dataset info | |
| self.ds_subset = subset_name | |
| self.ds_path = f"data/{subset_name}_embedding_v6.zip" | |
| # Pandas dataset | |
| self.ds = None | |
| # All Words embedding List[List[float]] | |
| self.embedding = None | |
| # Estimate AproximateNearestNeighbors | |
| self.ann = None | |
| # Load embedding and pca dataset | |
| self.__load() | |
| def __contains__(self, word): | |
| return word in self.ds['word'].to_list() | |
| def __load(self): | |
| print(f"Preparing {self.ds_subset} embedding...") | |
| # --- Download dataset --- | |
| self.ds = pd.read_json(self.ds_path) | |
| # --- Get embedding from string | |
| self.embedding = self.ds['embedding'].to_list() | |
| # --- Get forest tree to estimate Nearest Neighbors --- | |
| self.ann = Ann( | |
| words=self.ds['word'], | |
| vectors=self.ds['embedding'], | |
| coord=self.ds['pca'] | |
| ) | |
| self.ann.init(n_trees=20, metric='dot', n_jobs=-1) | |
| # --- Fit Sklearn NN method --- | |
| self.neigh = NearestNeighbors(n_neighbors=20) | |
| self.neigh.fit(self.embedding) | |
| def __getValue(self, word, feature): | |
| word_id, value = None, None | |
| if word in self: | |
| word_id = self.ds['word'].to_list().index(word) | |
| if word_id != None: | |
| value = self.ds[feature].to_list()[word_id] | |
| return value | |
| def getEmbedding(self, word): | |
| return self.__getValue(word, 'embedding') | |
| def getPCA(self, word): | |
| return self.__getValue(word, 'pca') | |
| def cosineSimilarities(self, vector_1, vectors_all): | |
| norm = np.linalg.norm(vector_1) | |
| all_norms = np.linalg.norm(vectors_all, axis=1) | |
| dot_products = dot(vectors_all, vector_1) | |
| similarities = dot_products / (norm * all_norms) | |
| return similarities | |
| def getNearestNeighbors(self, word, n_neighbors=10, nn_method='sklearn'): | |
| if nn_method == 'ann': | |
| words = self.ann.get(word, n_neighbors) | |
| elif nn_method == 'sklearn': | |
| word_emb = self.getEmbedding(word) | |
| neighbors = self.neigh.kneighbors([word_emb], n_neighbors)[1][0] | |
| words = operator.itemgetter(*neighbors)(self.ds['word']) | |
| else: | |
| words = [] | |
| return words | |
| def getCosineSimilarities(self, w1, w2): | |
| return dot( | |
| matutils.unitvec(self.getEmbedding(w1)), | |
| matutils.unitvec(self.getEmbedding(w2)) | |
| ) |