def get_log_likelihood(contingency_table): (n11,n12,n21,n22) = contingency_table g2 = n11*log_sec(n11)+n21*log_sec(n21)+n12*log_sec(n12)+n22*log_sec(n22)-(n11+n21)*log_sec(n11+n21)-(n11+n12)*log_sec(n11+n12)-(n21+n22)*log_sec(n21+n22)-(n12+n22)*log_sec(n12+n22)+(n11+n21+n12+n22)*log_sec(n11+n21+n12+n22) return 2*abs(g2)
def get_log_likelihood(contingency_table):
(n11, n12, n21, n22) = contingency_table
g2 = n11 * log_sec(n11) + n21 * log_sec(n21) + n12 * log_sec(
n12) + n22 * log_sec(n22) - (n11 + n21) * log_sec(n11 + n21) - (
n11 + n12) * log_sec(n11 + n12) - (n21 + n22) * log_sec(
n21 + n22) - (n12 + n22) * log_sec(n12 + n22) + (
n11 + n21 + n12 + n22) * log_sec(n11 + n21 + n12 + n22)
return 2 * abs(g2)
def calculate_log_likelihood(self,N_pos,N_neg):
"""
The calculus is taken from the paper:
"Comparing Corpora using Fequency Profiling". Paul Rayson and Roger Garside.
WCC '00 Proceedings of the workshop on Comparing corpora - Volume 9. 2000
The contingency table is:
Positive_set Negative_set
----------------------------
feature n11=no_pos n12=no_neg
not_feature n21=Npos-no_pos n22=Nneg-no_neg
no_pos = Number of items of the positive set where the feature appears.
no_neg = Number of items of the negative set where the feature appears.
Npos = Total number of items in the positive set
Nneg = Total number of items in the negative set
The log-likelihood (LL) measures the relative frequency difference between the positive and negative
sets. The higher the value the more significative the difference is.
On-line calculator: http://ucrel.lancs.ac.uk/llwizard.html
"""
n11 = float(self.no_positives)
n12 = float(self.no_negatives)
n21 = N_pos-n11
n22 = N_neg-n12
coeff = div_sec((n11+n12),(N_pos+N_neg))
E1 = N_pos*coeff
E2 = N_neg*coeff
try:
LL = 2*(n11*log_sec(div_sec(n11,E1))+n12*log_sec(div_sec(n12,E2)))
except:
print "aqui"
self.significance = LL
