Christopher Akiki cakiki

## doc_embeddings_with_vectorizers.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                cakiki
                / doc_embeddings_with_vectorizers.ipynb
            
            
              Created
              June 19, 2021 10:41
                — forked from lmcinnes/doc_embeddings_with_vectorizers.ipynb
            
              
                Document Embeddings with the Vectorizers Library
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## document-embeddings-big_models.ipynb

      
              1 file
            
          
              1 fork
            
          
              0 comments
            
          
              0 stars
            
          
                cakiki
                / document-embeddings-big_models.ipynb
            
            
              Created
              July 1, 2021 10:37
                — forked from lmcinnes/document-embeddings-big_models.ipynb
            
              
                Document Embeddings with Vectorizers and Large USE and BERT models
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## tpu_topology_env_vars.py
# 4x 1 chip (2 cores) per process:
os.environ["TPU_CHIPS_PER_HOST_BOUNDS"] = "1,1,1"
os.environ["TPU_HOST_BOUNDS"] = "1,1,1"
# Different per process:
os.environ["TPU_VISIBLE_DEVICES"] = "0" # "1", "2", "3"
# Pick a unique port per process
os.environ["TPU_MESH_CONTROLLER_ADDRESS"] = "localhost:8476"
os.environ["TPU_MESH_CONTROLLER_PORT"] = "8476"

# 1-liner for bash: TPU_CHIPS_PER_HOST_BOUNDS=1,1,1 TPU_HOST_BOUNDS=1,1,1 TPU_VISIBLE_DEVICES=0 TPU_MESH_CONTROLLER_ADDRESS=localhost:8476 TPU_MESH_CONTROLLER_PORT=8476

## AlignedUMAP Demo.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                cakiki
                / AlignedUMAP Demo.ipynb
            
            
              Created
              February 5, 2022 21:44
                — forked from lmcinnes/AlignedUMAP Demo.ipynb
            
              
                Demonstration of experimental Aligned UMAP in 0.5dev
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## stopword-bn.txt

অবশ্য
অনেক
অনেকে
অনেকেই
অন্তত
অথবা
অথচ
অর্থাত
অন্য

## bm25.py
""" Implementation of OKapi BM25 with sklearn's TfidfVectorizer
Distributed as CC-0 (https://creativecommons.org/publicdomain/zero/1.0/)
"""

import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from scipy import sparse


class BM25(object):
	# 4x 1 chip (2 cores) per process:
	os.environ["TPU_CHIPS_PER_HOST_BOUNDS"] = "1,1,1"
	os.environ["TPU_HOST_BOUNDS"] = "1,1,1"
	# Different per process:
	os.environ["TPU_VISIBLE_DEVICES"] = "0" # "1", "2", "3"
	# Pick a unique port per process
	os.environ["TPU_MESH_CONTROLLER_ADDRESS"] = "localhost:8476"
	os.environ["TPU_MESH_CONTROLLER_PORT"] = "8476"

	# 1-liner for bash: TPU_CHIPS_PER_HOST_BOUNDS=1,1,1 TPU_HOST_BOUNDS=1,1,1 TPU_VISIBLE_DEVICES=0 TPU_MESH_CONTROLLER_ADDRESS=localhost:8476 TPU_MESH_CONTROLLER_PORT=8476

	অবশ্য
	অনেক
	অনেকে
	অনেকেই
	অন্তত
	অথবা
	অথচ
	অর্থাত
	অন্য
	""" Implementation of OKapi BM25 with sklearn's TfidfVectorizer
	Distributed as CC-0 (https://creativecommons.org/publicdomain/zero/1.0/)
	"""

	import numpy as np
	from sklearn.feature_extraction.text import TfidfVectorizer
	from scipy import sparse


	class BM25(object):