#51

- text features dict
- feat extraction
- bash update (spacy models)

requirements.txt

@@ -0,0 +1,151 @@
+absl-py==0.9.0
+appnope==0.1.0
+asgiref==3.2.7
+astor==0.8.1
+async-generator==1.10
+attrs==19.3.0
+backcall==0.1.0
+bleach==3.1.0
+blis==0.4.1
+boto==2.49.0
+boto3==1.12.49
+botocore==1.15.49
+cachetools==4.1.0
+catalogue==1.0.0
+certifi==2019.9.11
+chardet==3.0.4
+colorama==0.4.3
+configparser==5.0.0
+crayons==0.3.0
+cycler==0.10.0
+cymem==2.0.3
+decorator==4.4.1
+defusedxml==0.6.0
+Django==3.0.5
+dlib==19.19.0
+docutils==0.15.2
+eli5==0.10.1
+entrypoints==0.3
+fastscript==0.1.4
+gast==0.2.2
+gensim==3.8.2
+google-api-core==1.17.0
+google-auth==1.14.0
+google-auth-oauthlib==0.4.1
+google-cloud-bigquery==1.24.0
+google-cloud-core==1.3.0
+google-pasta==0.2.0
+google-resumable-media==0.5.0
+googleapis-common-protos==1.51.0
+graphviz==0.13.2
+grpcio==1.28.1
+h5py==2.10.0
+idna==2.9
+imageio==2.8.0
+importlib-metadata==0.23
+ipykernel==5.1.3
+ipython==7.9.0
+ipython-genutils==0.2.0
+ipywidgets==7.5.1
+jedi==0.15.1
+Jinja2==2.10.3
+jmespath==0.9.5
+joblib==0.14.1
+json5==0.9.4
+jsonpickle==1.3
+jsonschema==3.2.0
+jupyter==1.0.0
+jupyter-client==5.3.4
+jupyter-console==6.0.0
+jupyter-core==4.6.1
+jupyter-server==0.1.1
+jupyterlab==2.1.0
+jupyterlab-pygments==0.1.0
+jupyterlab-server==1.1.1
+Keras==2.3.1
+Keras-Applications==1.0.8
+Keras-Preprocessing==1.1.0
+kiwisolver==1.2.0
+Markdown==3.2.1
+MarkupSafe==1.1.1
+matplotlib==3.2.1
+mistune==0.8.4
+more-itertools==7.2.0
+murmurhash==1.0.2
+nbconvert==5.6.1
+nbformat==4.4.0
+networkx==2.4
+nltk==3.4.5
+notebook==6.0.2
+numpy==1.18.2
+oauthlib==3.1.0
+opencv-contrib-python==4.2.0.34
+opencv-python==4.2.0.34
+opt-einsum==3.2.1
+packaging==20.3
+pandas==1.0.3
+pandas-gbq==0.13.1
+pandocfilters==1.4.2
+parso==0.5.1
+pexpect==4.7.0
+pickleshare==0.7.5
+Pillow==7.1.2
+pipenv==2018.11.26
+plac==1.1.3
+preshed==3.0.2
+prometheus-client==0.7.1
+prompt-toolkit==2.0.10
+protobuf==3.11.3
+ptyprocess==0.6.0
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pydata-google-auth==1.0.0
+pyfiglet==0.8.post1
+Pygments==2.4.2
+pyparsing==2.4.7
+pyrsistent==0.15.5
+python-crfsuite==0.9.7
+python-dateutil==2.8.1
+pytz==2019.3
+PyWavelets==1.1.1
+PyYAML==5.3.1
+pyzmq==18.1.1
+qtconsole==4.6.0
+QtPy==1.9.0
+requests==2.23.0
+requests-oauthlib==1.3.0
+rsa==4.0
+s3transfer==0.3.3
+scikit-image==0.16.2
+scikit-learn==0.22.2.post1
+scipy==1.4.1
+Send2Trash==1.5.0
+six==1.13.0
+sklearn==0.0
+sklearn-crfsuite==0.3.6
+smart-open==2.0.0
+spacy==2.2.4
+sqlparse==0.3.1
+srsly==1.0.2
+tabulate==0.8.7
+tensorboard==2.1.1
+tensorflow==2.1.0
+tensorflow-estimator==2.1.0
+termcolor==1.1.0
+terminado==0.8.3
+testpath==0.4.4
+thinc==7.4.0
+tornado==6.0.3
+tqdm==4.44.1
+traitlets==4.3.3
+urllib3==1.25.9
+virtualenv==16.7.5
+virtualenv-clone==0.5.3
+voila==0.1.21
+wasabi==0.6.0
+wcwidth==0.1.7
+webencodings==0.5.1
+Werkzeug==1.0.1
+widgetsnbextension==3.5.1
+wrapt==1.12.1
+zipp==0.6.0

scripts/00_initialize.sh

@@ -68,4 +68,6 @@ pipenv run python ./00_initialize.py
 
 pipenv run python /Users/diego.esteves/git/horus-ner/src/utils/CMUTweetTagger.py
 
+python -m spacy download en_core_web_sm
+
 echo "end bash ok"

src/algorithms/computer_vision/cnnlogo.py

@@ -5,8 +5,9 @@
 import torch
 import torch.nn as nn
 from torch.autograd import Variable
-from src.classifiers.computer_vision.places365 import Places365CV
-from src.config import HorusConfig
+
+from config import HorusConfig
+from src.algorithms.computer_vision.places365 import Places365CV
 #import PIL
 #from PIL import Image
 

src/algorithms/computer_vision/places365.py

@@ -6,7 +6,7 @@
 import os
 from PIL import Image
 
-from src.config import HorusConfig
+from config import HorusConfig
 
 
 class Places365CV():

src/algorithms/text_classification/topic_modeling_short_cnn.py

@@ -2,16 +2,17 @@
 import en_core_web_sm
 import os
 import shorttext
-from src.config import HorusConfig
 import tensorflow as tf
-
-from src.util.nlp_tools import NLPTools
+from config import HorusConfig
+from src.utils.nlp_tools import NLPTools
 
 os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
 nlp = en_core_web_sm.load()
 #spacy.load('en')
 
-class TopicModelingShortCNN():
+
+class TopicModelingShortCNN(object):
+
     def __init__(self, config, w2v, mode='test'):
         try:
             self.config = config
@@ -110,7 +111,6 @@ def train(self, epochs=5000):
     topic = TopicModelingShortCNN(config, tools.word2vec_google, mode='test')
     #topic.train()
 
-
     print(topic.predict('orlando'))
     print(topic.predict('river'))
     print(topic.predict('chile'))