def test_fisher_alpha(self):
exp = 2.7823795367398798
arr = np.array([4, 3, 4, 0, 1, 0, 2])
obs = fisher_alpha(arr)
self.assertAlmostEqual(obs, exp)
# Should depend only on S and N (number of OTUs, number of
# individuals / seqs), so we should obtain the same output as above.
obs = fisher_alpha([1, 6, 1, 0, 1, 0, 5])
self.assertAlmostEqual(obs, exp)
# Should match another by hand:
# 2 OTUs, 62 seqs, alpha is 0.39509
obs = fisher_alpha([61, 0, 0, 1])
self.assertAlmostEqual(obs, 0.39509, delta=0.0001)
# Test case where we have >1000 individuals (SDR-IV makes note of this
# case). Verified against R's vegan::fisher.alpha.
obs = fisher_alpha([999, 0, 10])
self.assertAlmostEqual(obs, 0.2396492)
def test_fisher_alpha(self):
exp = 2.7823795367398798
arr = np.array([4, 3, 4, 0, 1, 0, 2])
obs = fisher_alpha(arr)
self.assertAlmostEqual(obs, exp)
# Should depend only on S and N (number of OTUs, number of
# individuals / seqs), so we should obtain the same output as above.
obs = fisher_alpha([1, 6, 1, 0, 1, 0, 5])
self.assertAlmostEqual(obs, exp)
# Should match another by hand:
# 2 OTUs, 62 seqs, alpha is 0.39509
obs = fisher_alpha([61, 0, 0, 1])
self.assertAlmostEqual(obs, 0.39509, delta=0.0001)
# Test case where we have >1000 individuals (SDR-IV makes note of this
# case). Verified against R's vegan::fisher.alpha.
obs = fisher_alpha([999, 0, 10])
self.assertAlmostEqual(obs, 0.2396492)
def sentence_start(text):
#Count variables
ratio_dict = {
"nouns": 0,
"pronouns": 0,
"verbs": 0,
"adjectives": 0,
"adverbs": 0,
"conjunctions": 0,
"particles": 0,
"pronouns": 0,
"prepositions": 0,
"others": 0,
"simpson": 0,
"fisher": 0,
"brillouin": 0,
"berger_parker": 0
}
#Tokenize into sentences
sentences = nltk.tokenize.sent_tokenize(text)
problem_sentences = []
#Loop through sentences
for sentence in sentences:
tags = identify_speech(sentence)
ratio_dict[tags[0]] = ratio_dict[tags[0]] + 1
if tags[0] == "nouns" or tags[0] == "pronouns":
problem_sentences.append(sentence)
#Calculate diversity
simpson = simpson_e(list(ratio_dict.values())[0:7])
fisher = fisher_alpha(list(ratio_dict.values())[0:7])
brillouin = brillouin_d(list(ratio_dict.values())[0:7])
berger_parker = berger_parker_d(list(ratio_dict.values())[0:7])
#Convert to percentage
#ratio_dict = {k: "".join([str(round(v / len(sentences),4)*100),"%"]) for k, v in ratio_dict.items()}
#Update diversity metric
ratio_dict['simpson'] = simpson
ratio_dict['fisher'] = fisher
ratio_dict['brillouin'] = brillouin
ratio_dict['berger_parker'] = berger_parker
return (ratio_dict, problem_sentences)
def mercat_compute_alpha_beta_diversity(counts,bif):
abm = dict()
abm['shannon'] = skbio_alpha.shannon(counts)
abm['simpson'] = skbio_alpha.simpson(counts)
abm['simpson_e'] = skbio_alpha.simpson_e(counts)
abm['goods_coverage'] = skbio_alpha.goods_coverage(counts)
abm['fisher_alpha'] = skbio_alpha.fisher_alpha(counts)
abm['dominance'] = skbio_alpha.dominance(counts)
abm['chao1'] = skbio_alpha.chao1(counts)
abm['chao1_ci'] = skbio_alpha.chao1_ci(counts)
abm['ace'] = skbio_alpha.ace(counts)
with open(bif + "_diversity_metrics.txt", 'w') as dmptr:
for abmetric in abm:
dmptr.write(abmetric + " = " + str(abm[abmetric]) + "\n")