- Update HISTORY.rst
- Update version number in
my_project/__init__.py
- Update version number in
setup.py
- Install the package again for local development, but with the new version number:
python setup.py develop
- Run the tests:
python setup.py test
#netaporter_bookmarklet_table{ | |
border: 3px solid #333; | |
position: fixed; | |
_position:absolute; | |
top: 0; | |
right: 0; | |
width: 570px; | |
height: 80px; | |
z-index: 10000000; | |
margin: 0; |
my_project/__init__.py
setup.py
python setup.py develop
python setup.py test
#!/usr/bin/python | |
# crf.py (by Graham Neubig) | |
# This script trains conditional random fields (CRFs) | |
# stdin: A corpus of WORD_POS WORD_POS WORD_POS sentences | |
# stdout: Feature vectors for emission and transition properties | |
from collections import defaultdict | |
from math import log, exp | |
import sys |
diff --git a/webstruct/model.py b/webstruct/model.py | |
index f77ab36..941cd8f 100644 | |
--- a/webstruct/model.py | |
+++ b/webstruct/model.py | |
@@ -111,6 +111,13 @@ class NER(object): | |
Return annotated HTML data in WebAnnotator format. | |
""" | |
html_tokens, tags = self.extract_raw(bytes_data) | |
+ return self.annotate_tokens(html_tokens, tags) | |
+ |
Loosely ordered with the commands I use most towards the top. Sublime also offer full documentation.
Ctrl+C | copy current line (if no selection) |
Ctrl+X | cut current line (if no selection) |
Ctrl+⇧+K | delete line |
Ctrl+↩ | insert line after |
diff --git a/configure.in b/configure.in | |
index dafbcf6..743037c 100644 | |
--- a/configure.in | |
+++ b/configure.in | |
@@ -30,7 +30,7 @@ dnl ------------------------------------------------------------------ | |
AM_INIT_AUTOMAKE(crfsuite, 0.12) | |
AC_CONFIG_HEADERS(config.h) | |
AM_MAINTAINER_MODE | |
-AM_C_PROTOTYPES | |
+ |
#CC = x86_64-linux-g++-4.6 | |
CC = llvm-gcc | |
WEIGHTTYPE = float | |
CFLAGS = -D WEIGHTTYPE=$(WEIGHTTYPE) -lm -O2 -Wall -funroll-loops -ffast-math -lstdc++ | |
#CFLAGS = -D WEIGHTTYPE=$(WEIGHTTYPE) -lm -O2 -Wall -funroll-loops -ffast-math | |
#CFLAGS = -lm -O2 -Wall | |
all: rnnlmlib.o rnnlm | |
rnnlmlib.o : rnnlmlib.cpp |
import re | |
_SPACING_RE = re.compile(ur'\n[\s]+', re.DOTALL) | |
text = "\r\n Grand Hotel, Malahide, County Dublin, Ireland\r\n Tel. +353 1 845 0000 Fax +353 1 816 8225\r\n Email: [email protected]" | |
print _SPACING_RE.sub(u'', text) | |
print _SPACING_RE.sub(u'\n', text) | |
# output on my machine: | |
#Email: [email protected] +353 1 816 8225eland |
# MDS example from http://www.analytictech.com/networks/mds.htm | |
import numpy as np | |
from sklearn import manifold | |
import matplotlib.pyplot as plt | |
cities = ["BOST", "NY", "DC", "MIAM", "CHIC", "SEAT", "SF", "LA", "DENV"] | |
dis = np.array([[0, 206, 429, 1504, 963, 2976, 3095, 2979, 1949], | |
[206, 0, 233, 1308, 802, 2815, 2934, 2786, 1771], | |
[429, 233, 0, 1075, 671, 2684, 2799, 2631, 1616], | |
[1504, 1308, 1075, 0, 1329, 3273, 3053, 2687, 2037], |