def _get_similarity(doc1, doc2, vec1, vec2):
"""Returns similarity of two documents.
Parameters
----------
doc1 : list of (list of (tuple of int))
First document.
doc2 : list of (list of (tuple of int))
Second document.
vec1 : array
? of first document.
vec1 : array
? of secont document.
Returns
-------
float
Similarity of two documents.
"""
numerator = vec1.dot(vec2.transpose()).toarray()[0][0]
length_1 = _get_doc_length(doc1)
length_2 = _get_doc_length(doc2)
denominator = _log10(length_1) + _log10(
length_2) if length_1 > 0 and length_2 > 0 else 0
return numerator / denominator if denominator != 0 else 0
def get_similarity(str1, str2):
n1 = len(str1)
n2 = len(str2)
min = n2
if n1 < n2:
min = n1
i = 0
match = 0
l1 = 0
l2 = 0
while i < min:
if str1[i] == '1' and str2[i] == '1':
match = match + 1
if str1[i] == '1':
l1 = l1 + 1
if str2[i] == '1':
l2 = l2 + 1
i = i + 1
if l1 == 0 or l2 == 0:
return 0
if _log10(l1) + _log10(l2) == 0:
return 0
return match / (_log10(l1) + _log10(l2))
def _get_similarity(doc1, doc2, vec1, vec2):
numerator = vec1.dot(vec2.transpose()).toarray()[0][0]
length_1 = _get_doc_length(doc1)
length_2 = _get_doc_length(doc2)
denominator = _log10(length_1) + _log10(
length_2) if length_1 > 0 and length_2 > 0 else 0
return numerator / denominator if denominator != 0 else 0
def _get_similarity(doc1, doc2, vec1, vec2):
"""Returns similarity of two documents.
Parameters
----------
doc1 : list of (list of (tuple of int))
First document.
doc2 : list of (list of (tuple of int))
Second document.
vec1 : array
? of first document.
vec1 : array
? of secont document.
Returns
-------
float
Similarity of two documents.
"""
numerator = vec1.dot(vec2.transpose()).toarray()[0][0]
length_1 = _get_doc_length(doc1)
length_2 = _get_doc_length(doc2)
denominator = _log10(length_1) + _log10(length_2) if length_1 > 0 and length_2 > 0 else 0
return numerator / denominator if denominator != 0 else 0
def _get_similarity(doc1, doc2, vec1, vec2):
numerator = vec1.dot(vec2.transpose()).toarray()[0][0]
length_1 = _get_doc_length(doc1)
length_2 = _get_doc_length(doc2)
denominator = _log10(length_1) + _log10(length_2) if length_1 > 0 and length_2 > 0 else 0
return numerator / denominator if denominator != 0 else 0
def _get_similarity(s1, s2):
words_sentence_one = s1.split()
words_sentence_two = s2.split()
common_word_count = _count_common_words(words_sentence_one, words_sentence_two)
log_s1 = _log10(len(words_sentence_one))
log_s2 = _log10(len(words_sentence_two))
if log_s1 + log_s2 == 0:
return 0
return common_word_count / (log_s1 + log_s2)
def _get_similarity(s1, s2):
words_sentence_one = s1.split()
words_sentence_two = s2.split()
common_word_count = _count_common_words(words_sentence_one, words_sentence_two)
log_s1 = _log10(len(words_sentence_one))
log_s2 = _log10(len(words_sentence_two))
if log_s1 + log_s2 == 0:
return 0
return common_word_count / (log_s1 + log_s2)
def expand(series, min=1.0, max=10.0E6): ''' Expand a single decade series over multiple decades. series = single decade series to expand. min = minimum value of expanded series. max = maximum value of expanded series. eg. expand(E12, 10.0, 100E3) ''' # Calc range of multipliers required. # -3/-1: Adjusted because series arrays normalized to 1E2. exp_min = int(_log10(min)-3) exp_max = int(_log10(max)) # Expand series. return [x*10**m for m in range(exp_min, exp_max) for x in series if x*10**m >= min if x*10**m <= max]
def expand(series, min=1.0, max=10.0E6):
'''
Expand a single decade series over multiple decades.
series = single decade series to expand.
min = minimum value of expanded series.
max = maximum value of expanded series.
eg. expand(E12, 10.0, 100E3)
'''
# Calc range of multipliers required.
# -3/-1: Adjusted because series arrays normalized to 1E2.
exp_min = int(_log10(min) - 3)
exp_max = int(_log10(max))
# Expand series.
return [
x * 10**m for m in range(exp_min, exp_max) for x in series
if x * 10**m >= min if x * 10**m <= max
]
def _number_profile(value, precision):
'''
returns:
string of significant digits
10s exponent to get the dot to the proper location in the significant digits
bool that's true if value is less than zero else false
created by William Rusnack
github.com/BebeSparkelSparkel
linkedin.com/in/williamrusnack/
[email protected]
contributions by Thomas Hladish
github.com/tjhladish
Issue: github.com/BebeSparkelSparkel/to-precision/issues/5
'''
value = float(value)
is_neg = value < 0
value = abs(value)
if value == 0:
sig_digits = '0' * precision
power = -(1 - precision)
else:
if _math.isnan(value):
return _math.nan
power = -1 * _floor(_log10(value)) + precision - 1
# issue soved by Thomas Haladish
# github.com/BebeSparkelSparkel/to-precision/issues/5
value_power = value * 10.0**power
if value < 1 and \
_floor(_log10(int(round(value_power)))) > \
_floor(_log10(int(value_power))):
power -= 1
sig_digits = str(int(round(
value *
10.0**power))) # cannot use value_power because power is changed
return sig_digits, int(-power), is_neg
def _get_similarity(s1, s2):
common_word_count = 0
len_s1 = 0
len_s2 = 0
i = 0
while i < len(s1):
if s1[i] != '0' and s2[i] != '0':
common_word_count = common_word_count + 1
if s1[i] != '0':
len_s1 = len_s1 + 1
if s2[i] != '0':
len_s2 = len_s2 + 1
i = i + 1
if len_s1 == 0 or len_s2 == 0:
return 0
log_s1 = _log10(len_s1)
log_s2 = _log10(len_s2)
if log_s1 + log_s2 == 0:
return 0
return common_word_count / (log_s1 + log_s2)
def _get_similarity(su1, su2):
words1 = [ w for w in su1.processed if w[1] not in ['NNP', 'NNPS'] ]
words2 = [ w for w in su2.processed if w[1] not in ['NNP', 'NNPS'] ]
properNouns1 = [ w for w in su1.processed if w[1] in ['NNP', 'NNPS'] ]
properNouns2 = [ w for w in su2.processed if w[1] in ['NNP', 'NNPS'] ]
log_s1 = _log10(len(su1.processed)+1)
log_s2 = _log10(len(su2.processed)+1)
if log_s1 + log_s2 == 0:
return 0
eo = entail_overlap(words1, words2)
no = noun_overlap(properNouns1, properNouns2)
x = (eo + no) / (log_s1 + log_s2)
# if su1.index <= 3 and su2.index <= 5:
# print "HELLO!!!!!!!"
# print su1.text
# print su2.text
# print _count_common_words(su1.text.split(), su2.text.split())
# print log_s1, log_s2
# print eo, no
return x
def lg(x):
return _log10(x)
def lg(x):
return _log10(x)
MGPER : number of angles with atoms completely in perturbed group MDPER : number of dihedrals with atoms completely in perturbed groups IFBOX : set to 1 if standard periodic box, 2 when truncated octahedral NMXRS : number of atoms in the largest residue IFCAP : set to 1 if the CAP option from edit was specified NUMEXTRA: number of extra points NCOPY : Number of copies for advanded simulations """ # These global variables provide a more natural way of accessing # the various pointers. Most useful if they're loaded into the # top-level namespace. NATOM = 0; NTYPES = 1; NBONH = 2; MBONA = 3; NTHETH = 4 MTHETA = 5; NPHIH = 6; MPHIA = 7; NHPARM = 8; NPARM = 9 NEXT = 10; NRES = 11; NBONA = 12; NTHETA = 13; NPHIA = 14 NUMBND = 15; NUMANG = 16; NPTRA = 17; NATYP = 18; NPHB = 19 IFPERT = 20; NBPER = 21; NGPER = 22; NDPER = 23; MBPER = 24 MGPER = 25; MDPER = 26; IFBOX = 27; NMXRS = 28; IFCAP = 29 NUMEXTRA= 30; NCOPY = 31 # An alias NNB = NEXT RAD_TO_DEG = 180.0 / _pi DEG_TO_RAD = _pi / 180.0 # For use in floating point comparisons TINY = 1.0e-8 SMALL = 1.0e-4 TINY_DIGITS = int(_log10(TINY) + 0.5) SMALL_DIGITS = int(_log10(SMALL) + 0.5)
