#A Collection of NLP notes
##N-grams
###Calculating unigram probabilities:
P( wi ) = count ( wi ) ) / count ( total number of words )
In english..
import numpy as np | |
from scipy.sparse import csr_matrix | |
import torch | |
__author__ = 'Andrea Esuli' | |
Acsr = csr_matrix([[1, 2, 0], [0, 0, 3], [4, 0, 5]]) | |
print('Acsr',Acsr) | |
Acoo = Acsr.tocoo() |
# Author: Jake VanderPlas | |
# LICENSE: MIT | |
from __future__ import division | |
import numpy as np | |
def convolution_matrix(x, N=None, mode='full'): | |
"""Compute the Convolution Matrix |
# required tensorflow 0.12 | |
# required gensim 0.13.3+ for new api model.wv.index2word or just use model.index2word | |
from gensim.models import Word2Vec | |
import tensorflow as tf | |
from tensorflow.contrib.tensorboard.plugins import projector | |
# loading your gensim | |
model = Word2Vec.load("YOUR-MODEL") |
#A Collection of NLP notes
##N-grams
###Calculating unigram probabilities:
P( wi ) = count ( wi ) ) / count ( total number of words )
In english..
"""Information Retrieval metrics | |
Useful Resources: | |
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt | |
http://www.nii.ac.jp/TechReports/05-014E.pdf | |
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf | |
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf | |
Learning to Rank for Information Retrieval (Tie-Yan Liu) | |
""" | |
import numpy as np |