refactored pca methods

src/data/embeddings.py

@@ -1,14 +1,12 @@
 import os
 import pickle
-import numpy as np
 from torchtext.vocab import Vectors
 import torch
 from abc import ABC, abstractmethod
 from data.supervised import get_supervised_embeddings
-import matplotlib.pyplot as plt
-from sklearn.decomposition import PCA
 from util.decompositions import *
 
+
 class PretrainedEmbeddings(ABC):
 
     def __init__(self):
@@ -191,7 +189,6 @@ class FastTextMUSE(PretrainedEmbeddings):
         print(f'Loading fastText pretrained vectors from {path}')
         assert os.path.exists(path), print(f'pre-trained vectors not found in {path}')
         self.embed = FastTextWikiNews(path, lang, max_vectors=limit)
-        # print('Done')
 
     def vocabulary(self):
         return set(self.embed.stoi.keys())
@@ -277,59 +274,3 @@ class StorageEmbeddings:
             for lang in docs.keys():
                 _r[lang] = docs[lang].dot(self.lang_U[lang])
         return _r
-
-    # @staticmethod
-    # def get_optimal_supervised_components(docs, labels):
-    #     optimal_n = get_optimal_dim(docs, 'S')
-    #     return optimal_n
-        # _idx = []
-        #
-        # plt.figure(figsize=(15, 10))
-        # plt.title(f'WCE Explained Variance')
-        # plt.xlabel('Number of Components')
-        # plt.ylabel('Variance (%)')
-        #
-        # for lang in docs.keys():
-        #     _r = get_supervised_embeddings(docs[lang], labels[lang], reduction='PCA', max_label_space=0).tolist()
-        #     _r = np.cumsum(_r)
-        #     plt.plot(_r, label=lang)
-        #     for i in range(len(_r)-1, 1, -1):
-        #         delta = _r[i] - _r[i-1]
-        #         if delta > 0:
-        #             _idx.append(i)
-        #             break
-        # best_n = max(_idx)
-        # plt.axvline(best_n, color='r', label='optimal N')
-        # plt.legend()
-        # plt.show()
-        # return best_n
-    #
-    # def get_optimal_unsupervised_components(self, type):
-    #     _idx = []
-    #
-    #     plt.figure(figsize=(15, 10))
-    #     plt.title(f'Unsupervised Embeddings {type} Explained Variance')
-    #     plt.xlabel('Number of Components')
-    #     plt.ylabel('Variance (%)')
-    #
-    #     for lang in self.lang_U.keys():
-    #         pca = PCA(n_components=self.lang_U[lang].shape[1])
-    #         pca.fit(self.lang_U[lang])
-    #         _r = pca.explained_variance_ratio_
-    #         _r = np.cumsum(_r)
-    #         plt.plot(_r, label=lang)
-    #         for i in range(len(_r) - 1, 1, -1):
-    #             delta = _r[i] - _r[i - 1]
-    #             if delta > 0:
-    #                 _idx.append(i)
-    #                 break
-    #     best_n = max(_idx)
-    #     plt.axvline(best_n, color='r', label='optimal N')
-    #     plt.legend()
-    #     plt.show()
-    #
-    #     for lang in self.lang_U.keys():
-    #         pca = PCA(n_components=best_n)
-    #         self.lang_U[lang] = pca.fit_transform(self.lang_U[lang])
-    #     return
-

src/data/supervised.py

@@ -1,7 +1,7 @@
 from data.tsr_function__ import get_supervised_matrix, get_tsr_matrix, information_gain, chi_square
-from sklearn.decomposition import PCA
-from sklearn.manifold import TSNE
 import numpy as np
+# from sklearn.decomposition import PCA
+# from sklearn.manifold import TSNE
 
 
 def zscores(x, axis=0): #scipy.stats.zscores does not avoid division by 0, which can indeed occur

src/learning/learners.py

@@ -8,7 +8,7 @@ from sklearn.model_selection import KFold
 from joblib import Parallel, delayed
 from sklearn.feature_extraction.text import TfidfVectorizer
 from transformers.StandardizeTransformer import StandardizeTransformer
-from sklearn.decomposition import PCA
+# from sklearn.decomposition import PCA
 
 
 def _sort_if_sparse(X):