orico

example: SortedStringTrie({'ate': 3, 'cat': 5, 'do': 1, 'dog': 2, 'gate': 4, 'the': 0})
prefixes example: ['do', 'dog']
starting..

recoursively working on string: thedogatethecat
progress: t
progress: th
progress: the
found: ['the'] for: the
possible sentences {}

orico

#https://pytrie.readthedocs.io/en/latest/#trie-methods
from pytrie import SortedStringTrie as Trie

s = Trie(the=0, do=1, dog=2, ate=3, gate=4, cat=5)
print('example:',s)
print('prefixes example:',s.keys(prefix='do'))

sentence = "thedogatethecat"

def generator_string(s):

orico

import numpy as np

rolls = 10000
n = 6  
E = [0] * rolls 
     
for i in range(0,rolls):
  flag = False
  ar = []
  while flag == False:

orico

import pandas as pd
import numpy as np  

#nltk v1
from nltk.tag.stanford import StanfordNERTagger
from nltk.tokenize import word_tokenize  

path_to_data = './data/'

cities = pd.read_csv(path_to_data + 'us_cities_states_counties.csv')  

orico

import pandas as pd
import numpy as np 

from nltk.parse import CoreNLPParser
import datetime

path_to_data = './data/'
cities = pd.read_csv(path_to_data + 'us_cities_states_counties.csv')  
cities['City alias'] = cities['City alias'].apply(lambda x: str(x))
ner_tagger = CoreNLPParser(url='http://localhost:9000', tagtype='ner') 

orico

import pandas as pd
import numpy as np 

import spacy 
import en_core_web_sm

path_to_data = './data/'

spacy.prefer_gpu()
nlp = en_core_web_sm.load()

orico

orico

def plot3clusters(X, title, vtitle):
  plt.figure()
  colors = ['navy', 'turquoise', 'darkorange']
  lw = 2

  for color, i, target_name in zip(colors, [0, 1, 2], target_names):
      plt.scatter(X[y == i, 0], X[y == i, 1], color=color, alpha=1., lw=lw,
                  label=target_name)
  plt.legend(loc='best', shadow=False, scatterpoints=1)
  plt.title(title)  

orico

labels_true = y 
titles = ['PCA', 'Linear AE', 'Sigmoid AE', 'Relu AE']
for n_clusters_ in [2,3]:
  estimators = [('PCA'    , KMeans(n_clusters=n_clusters_), pca_transformed),
                ('AE linear' , KMeans(n_clusters=n_clusters_), encoded_data),
                ('AE sigmoid' , KMeans(n_clusters=n_clusters_), encoded_data2),
                ('AE relu', KMeans(n_clusters=n_clusters_), encoded_data3)]

  print(type(y))
  print('Number of clusters: %d' % n_clusters_)

orico

plot3clusters(pca_transformed[:,:2], 'PCA', 'PC')  
plot3clusters(encoded_data[:,:2], 'Linear AE', 'AE')  
plot3clusters(encoded_data2[:,:2], 'Non-Linear sigmoid-based AE', 'AE')  
plot3clusters(encoded_data3[:,:2], 'Non-Linear relu-based AE', 'AE')