def test_get_df_for_words_with_no_results(words_no_results):
"""
This test case fails for some unknown reason
Fails. Palmetto can not handle underscores.
"""
palmetto = Palmetto()
doc_ids = palmetto.get_df_for_words(words_no_results)
for i in range(0, len(words_no_results)):
assert (doc_ids[i][0] == words_no_results[i])
def build_weighted_graph(synset_packs):
"""
Build a weighted graph out of synset packs.
Return a list of tuples with weights such as:
[
[((item_a, item_b), 1.534), (item_a, item_c), 1.1234],
[((item_c, item_d), 1.34), (item_c, item_f), 1.24],
...
]
"""
# get all document frequencies
# collect all terms
words = []
for i in range(0, len(synset_packs)):
for j in range(0, len(synset_packs[i][1])):
synset_packs[i][1][j] = synset_packs[i][1][j].name().split(".")[0]
words.append(synset_packs[i][1][j])
if len(synset_packs[i][1]) == 0:
synset_packs[i][1].append(synset_packs[i][0])
words.append(synset_packs[i][0])
palmetto = Palmetto()
doc_id_tuples = palmetto.get_df_for_words(words)
doc_id_tuples_dict = dict(doc_id_tuples)
edges = []
for i in range(0, len(synset_packs)):
for j in range(i + 1, len(synset_packs)):
edge = []
for that_word in synset_packs[j][1]:
for this_word in synset_packs[i][1]:
edge_item = (
(
this_word,
that_word
),
calculate_coherence(
this_word,
that_word,
doc_id_tuples_dict
)
)
edge.append(edge_item)
edges.append(sorted(edge, key=lambda x: x[1], reverse=True))
return edges
def build_weighted_graph(synset_packs):
"""
Build a weighted graph out of synset packs.
Return a list of tuples with weights such as:
[
[((item_a, item_b), 1.534), (item_a, item_c), 1.1234],
[((item_c, item_d), 1.34), (item_c, item_f), 1.24],
...
]
"""
# get all document frequencies
# collect all terms
words = []
for i in range(0, len(synset_packs)):
for j in range(0, len(synset_packs[i][1])):
synset_packs[i][1][j] = synset_packs[i][1][j].name().split(".")[0]
words.append(synset_packs[i][1][j])
if len(synset_packs[i][1]) == 0:
synset_packs[i][1].append(synset_packs[i][0])
words.append(synset_packs[i][0])
palmetto = Palmetto()
doc_id_tuples = palmetto.get_df_for_words(words)
doc_id_tuples_dict = dict(doc_id_tuples)
edges = []
for i in range(0, len(synset_packs)):
for j in range(i + 1, len(synset_packs)):
edge = []
for that_word in synset_packs[j][1]:
for this_word in synset_packs[i][1]:
edge_item = ((this_word, that_word),
calculate_coherence(this_word, that_word,
doc_id_tuples_dict))
edge.append(edge_item)
edges.append(sorted(edge, key=lambda x: x[1], reverse=True))
return edges
def test_get_df_for_words(words):
palmetto = Palmetto()
doc_ids = palmetto.get_df_for_words(words)
for i in range(0, len(words)):
assert (doc_ids[i][0] == words[i])
import sys
import palmettopy.exceptions
from palmettopy.palmetto import Palmetto
words = [
"cherry", "pie", "cr_eam", "apple", "orange", "banana", "pineapple",
"plum", "pig", "cra_cker", "so_und", "kit"
]
palmetto = Palmetto()
try:
result = palmetto.get_df_for_words(words)
sys.exit(0)
except palmettopy.exceptions.EndpointDown:
sys.exit(1)
from palmettopy.palmetto import Palmetto
words = [
"cherry", "pie", "cr_eam", "apple", "orange", "banana", "pineapple",
"plum", "pig", "cra_cker", "so_und", "kit"
]
#words = ['label', 'type', 'character', 'subject', 'discipline', 'topic', 'national', 'home_page', 'foundation', 'basis', 'foundation_garment', 'initiation']
#words = ['label', 'type', 'character', 'subject', 'discipline', 'topic', 'national', 'home_page', 'foundation', 'basis', 'foundation_garment']
#words = ['label', 'type', 'character', 'subject', 'discipline', 'topic', 'national', 'home_page', 'foundation', 'basis']
palmetto = Palmetto()
palmetto.get_df_for_words(words)
#print(palmetto.get_coherence_fast(words))
#print(palmetto.get_coherence(words))
