def __init__(self, llwl='Brown', llNL=2, percen=80, NE = True, Col = True, Gram = True, Chu = True):
'''
@param llwl:LogLikleyHood Corpa name ('Brown','AmE06','BE06')
@param llNL:LogLikleyHood
@param percen: Presision of output default = 20, 20% returned
@param NE: Uses NE default True
@param Col: Uses Collocation default True
@param Gram: Uses N-Grams default True
@param Chu: Uses Chunking default True
'''
self.NEs = NE
self.Col = Col
self.Gram = Gram
self.Chu = Chu
self.p = percen
print 'Starting to build ', llwl
self.LL = LogLikelihood(wordlist=llwl, NLength=llNL)
print 'LL Loaded'
self.POS = POS()
print 'POS Loaded'
self.GD = GetData()
print 'GD Loaded'
self.Cu = Chunker(self.POS)
print 'Cu Loaded'
self.FL = Filter()
print 'FL Loaded'
self.CC = Collocation(self.POS)
print 'CC Loaded'
self.Ng = NGram()
print 'Ng Loaded'
self.S = Select(percentil=self.p)
print 'S Loaded'
self.To = Tokenize(self.FL)
print 'To Loaded'
def __init__(self,
llwl='Brown',
llNL=2,
percen=80,
NE=True,
Col=True,
Gram=True,
Chu=True):
'''
@param llwl:LogLikleyHood Corpa name ('Brown','AmE06','BE06')
@param llNL:LogLikleyHood
@param percen: Presision of output default = 20, 20% returned
@param NE: Uses NE default True
@param Col: Uses Collocation default True
@param Gram: Uses N-Grams default True
@param Chu: Uses Chunking default True
'''
self.NEs = NE
self.Col = Col
self.Gram = Gram
self.Chu = Chu
self.p = percen
print 'Starting to build ', llwl
self.LL = LogLikelihood(wordlist=llwl, NLength=llNL)
print 'LL Loaded'
self.POS = POS()
print 'POS Loaded'
self.GD = GetData()
print 'GD Loaded'
self.Cu = Chunker(self.POS)
print 'Cu Loaded'
self.FL = Filter()
print 'FL Loaded'
self.CC = Collocation(self.POS)
print 'CC Loaded'
self.Ng = NGram()
print 'Ng Loaded'
self.S = Select(percentil=self.p)
print 'S Loaded'
self.To = Tokenize(self.FL)
print 'To Loaded'
rhs = cs.vertcat([
x_biomass * (glucose_specific_growth * glucose_consumption +
xylose_specific_growth * xylose_consumption),
-x_biomass * glucose_consumption,
-x_biomass * xylose_consumption,
])
f = cs.SXFunction('f', [t,x,p], [rhs])
model = cs.SXFunction('f', [t,x,p], [rhs])
from Collocation import Collocation
new = Collocation(model, ['biomass', 'glucose', 'xylose'])
opts = {
'x0_max' : [0.1, 20, 50],
'p_init' : 1.,
}
new.initialize(opts)
## Growth Data
ts = np.array([ 0, 3, 6, 9, 12, 24, 36, 48, 59, 72, 96])
xs = np.array([[ 8.7, 46.6],
[ 8.2, 45.2],
[ 6.2, 41.7],
[ 4. , 35.4],
[ 1.8, 26.9],
class runable(object):
'''
Class for selecting keywords and extracting keywords from online contentent.
'''
def __init__(self,
llwl='Brown',
llNL=2,
percen=80,
NE=True,
Col=True,
Gram=True,
Chu=True):
'''
@param llwl:LogLikleyHood Corpa name ('Brown','AmE06','BE06')
@param llNL:LogLikleyHood
@param percen: Presision of output default = 20, 20% returned
@param NE: Uses NE default True
@param Col: Uses Collocation default True
@param Gram: Uses N-Grams default True
@param Chu: Uses Chunking default True
'''
self.NEs = NE
self.Col = Col
self.Gram = Gram
self.Chu = Chu
self.p = percen
print 'Starting to build ', llwl
self.LL = LogLikelihood(wordlist=llwl, NLength=llNL)
print 'LL Loaded'
self.POS = POS()
print 'POS Loaded'
self.GD = GetData()
print 'GD Loaded'
self.Cu = Chunker(self.POS)
print 'Cu Loaded'
self.FL = Filter()
print 'FL Loaded'
self.CC = Collocation(self.POS)
print 'CC Loaded'
self.Ng = NGram()
print 'Ng Loaded'
self.S = Select(percentil=self.p)
print 'S Loaded'
self.To = Tokenize(self.FL)
print 'To Loaded'
def Select(self, url, depth):
'''
Determin the best keywords for a webpage.
@param url: the base url to start sampaling from
@param depth: the depth of the website to be sampled
@return: the list of selected keywords, ordered with the highest rated words to the lower bownd of array.
'''
#Get data from web page
text = self.GD.getWebPage(url, depth)
#Tokonize sentance and words
tok = self.To.Tok(text)
#POS tag the text
pos = self.POS.POSTag(tok, 'tok')
#Log Likly Hood
log = self.LL.calcualte(tok)
#Collocations
if self.Col == True:
col = self.CC.col(pos, tok)
else:
col = []
#NE Extraction
if self.NEs == True:
ne = self.Cu.Chunks(pos,
nodes=['PERSON', 'ORGANIZATION', 'LOCATION'])
else:
ne = []
#Extract NP
if self.Chu == True:
chu = [self.Cu.parse(p) for p in pos]
else:
chu = []
#Creat N-gram
if self.Gram == True:
ga = self.Ng.Grams(pos, n=6)
else:
ga = []
return self.S.keywords(ne, ga, col, chu, log)
xylose_specific_growth = p[7]
rhs = cs.vertcat([
x_biomass * (glucose_specific_growth * glucose_consumption +
xylose_specific_growth * xylose_consumption),
-x_biomass * glucose_consumption,
-x_biomass * xylose_consumption,
])
f = cs.SXFunction('f', [t, x, p], [rhs])
model = cs.SXFunction('f', [t, x, p], [rhs])
from Collocation import Collocation
new = Collocation(model, ['biomass', 'glucose', 'xylose'])
opts = {
'x0_max': [0.1, 20, 50],
'p_init': 1.,
}
new.initialize(opts)
## Growth Data
ts = np.array([0, 3, 6, 9, 12, 24, 36, 48, 59, 72, 96])
xs = np.array([[8.7, 46.6], [8.2, 45.2], [6.2, 41.7], [4., 35.4], [1.8, 26.9],
[0.1, 13.1], [0., 8.3], [0., 4.3], [np.nan, 2.7], [0., 1.4],
[0., 0.1]])
data = pd.DataFrame(xs, index=ts, columns=['glucose', 'xylose'])
class runable(object):
'''
Class for selecting keywords and extracting keywords from online contentent.
'''
def __init__(self, llwl='Brown', llNL=2, percen=80, NE = True, Col = True, Gram = True, Chu = True):
'''
@param llwl:LogLikleyHood Corpa name ('Brown','AmE06','BE06')
@param llNL:LogLikleyHood
@param percen: Presision of output default = 20, 20% returned
@param NE: Uses NE default True
@param Col: Uses Collocation default True
@param Gram: Uses N-Grams default True
@param Chu: Uses Chunking default True
'''
self.NEs = NE
self.Col = Col
self.Gram = Gram
self.Chu = Chu
self.p = percen
print 'Starting to build ', llwl
self.LL = LogLikelihood(wordlist=llwl, NLength=llNL)
print 'LL Loaded'
self.POS = POS()
print 'POS Loaded'
self.GD = GetData()
print 'GD Loaded'
self.Cu = Chunker(self.POS)
print 'Cu Loaded'
self.FL = Filter()
print 'FL Loaded'
self.CC = Collocation(self.POS)
print 'CC Loaded'
self.Ng = NGram()
print 'Ng Loaded'
self.S = Select(percentil=self.p)
print 'S Loaded'
self.To = Tokenize(self.FL)
print 'To Loaded'
def Select(self, url, depth):
'''
Determin the best keywords for a webpage.
@param url: the base url to start sampaling from
@param depth: the depth of the website to be sampled
@return: the list of selected keywords, ordered with the highest rated words to the lower bownd of array.
'''
#Get data from web page
text = self.GD.getWebPage(url, depth)
#Tokonize sentance and words
tok = self.To.Tok(text)
#POS tag the text
pos = self.POS.POSTag(tok, 'tok')
#Log Likly Hood
log = self.LL.calcualte(tok)
#Collocations
if self.Col == True:
col = self.CC.col(pos, tok)
else:
col = []
#NE Extraction
if self.NEs == True:
ne = self.Cu.Chunks(pos, nodes=['PERSON', 'ORGANIZATION', 'LOCATION'])
else:
ne = []
#Extract NP
if self.Chu == True:
chu = [self.Cu.parse(p) for p in pos]
else:
chu = []
#Creat N-gram
if self.Gram == True:
ga = self.Ng.Grams(pos, n=6)
else:
ga = []
return self.S.keywords(ne, ga , col , chu, log)
rhs = cs.vertcat([
x_biomass * (glucose_specific_growth * glucose_consumption +
xylose_specific_growth * xylose_consumption),
-x_biomass * glucose_consumption,
-x_biomass * xylose_consumption,
])
f = cs.SXFunction('f', [t,x,p], [rhs])
model = cs.SXFunction('f', [t,x,p], [rhs])
from Collocation import Collocation
new = Collocation(model, ['biomass', 'glucose', 'xylose'])
opts = {
'x0_max' : [0.1, 20, 50],
'p_init' : 1.,
}
new.initialize(opts)
## Growth Data
ts = np.array([ 0, 3, 6, 9, 12, 24, 36, 48, 59, 72, 96])
xs = np.array([[ 8.7, 46.6],
[ 8.2, 45.2],
[ 6.2, 41.7],
[ 4. , 35.4],
[ 1.8, 26.9],
xylose_specific_growth = p[7]
rhs = cs.vertcat([
x_biomass * (glucose_specific_growth * glucose_consumption +
xylose_specific_growth * xylose_consumption),
-x_biomass * glucose_consumption,
-x_biomass * xylose_consumption,
])
f = cs.SXFunction('f', [t, x, p], [rhs])
model = cs.SXFunction('f', [t, x, p], [rhs])
from Collocation import Collocation
new = Collocation(model, ['biomass', 'glucose', 'xylose'])
opts = {
'x0_max': [0.1, 20, 50],
'p_init': 1.,
}
new.initialize(opts)
## Growth Data
ts = np.array([0, 3, 6, 9, 12, 24, 36, 48, 59, 72, 96])
xs = np.array([[8.7, 46.6], [8.2, 45.2], [6.2, 41.7], [4., 35.4], [1.8, 26.9],
[0.1, 13.1], [0., 8.3], [0., 4.3], [np.nan, 2.7], [0., 1.4],
[0., 0.1]])
data = pd.DataFrame(xs, index=ts, columns=['glucose', 'xylose'])