This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Imports and housekeeping | |
| import logging | |
| logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', | |
| level=logging.INFO) | |
| from gensim import corpora, models, similarities | |
| import numpy as np | |
| import scipy.stats as stats | |
| import matplotlib.pyplot as plt | |
| from subprocess import call |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| def get_wordnet_pos(treebank_tag): | |
| if treebank_tag.startswith('J'): | |
| return wordnet.ADJ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| def get_wordnet_pos(treebank_tag): | |
| if treebank_tag.startswith('J'): | |
| return wordnet.ADJ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Imports and housekeeping | |
| import logging | |
| logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', | |
| level=logging.INFO) | |
| from gensim import corpora, models, similarities, matutils | |
| import numpy as np | |
| import scipy.stats as stats | |
| import matplotlib.pyplot as plt | |
| # Define KL function |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/bin/bash | |
| sudo apt-get install python-dev build-essential checkinstall cvs subversion git-core mercurial unzip gfortran autoconf automake libz-dev libsqlite3-dev libncursesw5-dev libssl-dev libgdbm-dev libc6-dev libsqlite3-dev | |
| sudo apt-get install python-setuptools libblas-dev libblas-doc libblas-test libblas3 libblas3gf liblapack-dev liblapack-doc liblapack-doc-man liblapack-pic liblapack-test liblapack3 liblapack3gf liblapacke liblapacke-dev libatlas-base-dev libatlas-dev libatlas-doc libatlas-test libatlas3-base libatlas3gf-base | |
| sudo apt-get -y install libx11-dev | |
| sudo apt-get install r-base r-base-dev | |
| sudo easy_install numpy | |
| sudo easy_install scipy | |
| sudo easy_install gensim[distributed] | |
| sudo apt-get install python-matplotlib | |
| sudo easy_install pandas |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| def get_wordnet_pos(treebank_tag): | |
| if treebank_tag.startswith('J'): | |
| return wordnet.ADJ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| import logging | |
| logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', | |
| level=logging.INFO) | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| import logging | |
| logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', | |
| level=logging.INFO) | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| import logging | |
| logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', | |
| level=logging.INFO) | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| import logging | |
| logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', | |
| level=logging.INFO) | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') |