risk-network 0.0.9b39__tar.gz → 0.0.9b40__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/PKG-INFO +1 -1
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/__init__.py +1 -1
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/annotations/annotations.py +70 -46
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/neighborhoods/domains.py +21 -12
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/graph/api.py +7 -5
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk_network.egg-info/PKG-INFO +1 -1
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk_network.egg-info/SOURCES.txt +0 -1
- risk_network-0.0.9b39/risk/constants.py +0 -31
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/LICENSE +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/MANIFEST.in +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/README.md +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/pyproject.toml +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/annotations/__init__.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/annotations/io.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/log/__init__.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/log/console.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/log/parameters.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/neighborhoods/__init__.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/neighborhoods/api.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/neighborhoods/community.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/neighborhoods/neighborhoods.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/__init__.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/geometry.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/graph/__init__.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/graph/graph.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/graph/summary.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/io.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/plotter/__init__.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/plotter/api.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/plotter/canvas.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/plotter/contour.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/plotter/labels.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/plotter/network.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/plotter/plotter.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/plotter/utils/colors.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/network/plotter/utils/layout.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/risk.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/stats/__init__.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/stats/permutation/__init__.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/stats/permutation/permutation.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/stats/permutation/test_functions.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/stats/significance.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk/stats/stat_tests.py +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk_network.egg-info/dependency_links.txt +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk_network.egg-info/requires.txt +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/risk_network.egg-info/top_level.txt +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/setup.cfg +0 -0
- {risk_network-0.0.9b39 → risk_network-0.0.9b40}/setup.py +0 -0
@@ -12,8 +12,9 @@ import networkx as nx
|
|
12
12
|
import nltk
|
13
13
|
import numpy as np
|
14
14
|
import pandas as pd
|
15
|
-
from nltk.tokenize import word_tokenize
|
16
15
|
from nltk.corpus import stopwords
|
16
|
+
from nltk.stem import WordNetLemmatizer
|
17
|
+
from nltk.tokenize import word_tokenize
|
17
18
|
|
18
19
|
from risk.log import logger
|
19
20
|
from scipy.sparse import coo_matrix
|
@@ -31,11 +32,17 @@ def _setup_nltk():
|
|
31
32
|
except LookupError:
|
32
33
|
nltk.download("stopwords")
|
33
34
|
|
35
|
+
try:
|
36
|
+
nltk.data.find("corpora/wordnet")
|
37
|
+
except LookupError:
|
38
|
+
nltk.download("wordnet")
|
39
|
+
|
34
40
|
|
35
41
|
# Ensure you have the necessary NLTK data
|
36
42
|
_setup_nltk()
|
37
|
-
#
|
38
|
-
|
43
|
+
# Use NLTK's stopwords
|
44
|
+
STOP_WORDS = set(stopwords.words("english"))
|
45
|
+
LEMMATIZER = WordNetLemmatizer()
|
39
46
|
|
40
47
|
|
41
48
|
def load_annotations(
|
@@ -208,104 +215,121 @@ def define_top_annotations(
|
|
208
215
|
|
209
216
|
def get_weighted_description(words_column: pd.Series, scores_column: pd.Series) -> str:
|
210
217
|
"""Generate a weighted description from words and their corresponding scores,
|
211
|
-
|
218
|
+
using improved weighting logic with normalization, lemmatization, and aggregation.
|
212
219
|
|
213
220
|
Args:
|
214
|
-
words_column (pd.Series): A pandas Series containing strings to process.
|
221
|
+
words_column (pd.Series): A pandas Series containing strings (phrases) to process.
|
215
222
|
scores_column (pd.Series): A pandas Series containing significance scores to weigh the terms.
|
216
223
|
|
217
224
|
Returns:
|
218
|
-
str: A coherent description formed from the most frequent and significant words
|
225
|
+
str: A coherent description formed from the most frequent and significant words.
|
219
226
|
"""
|
220
|
-
#
|
227
|
+
# Normalize significance scores to [0,1]. If all scores are identical, use 1.
|
221
228
|
if scores_column.max() == scores_column.min():
|
222
|
-
normalized_scores = pd.Series([1] * len(scores_column))
|
229
|
+
normalized_scores = pd.Series([1] * len(scores_column), index=scores_column.index)
|
223
230
|
else:
|
224
|
-
# Normalize the significance scores to be between 0 and 1
|
225
231
|
normalized_scores = (scores_column - scores_column.min()) / (
|
226
232
|
scores_column.max() - scores_column.min()
|
227
233
|
)
|
228
234
|
|
229
|
-
#
|
235
|
+
# Accumulate weighted counts for each token (after cleaning and lemmatization)
|
236
|
+
weighted_counts = {}
|
237
|
+
for phrase, score in zip(words_column, normalized_scores):
|
238
|
+
# Tokenize the phrase
|
239
|
+
tokens = word_tokenize(str(phrase))
|
240
|
+
# Determine the weight (scale factor; here multiplying normalized score by 10)
|
241
|
+
weight = max(1, int((0 if pd.isna(score) else score) * 10))
|
242
|
+
for token in tokens:
|
243
|
+
# Clean token: lowercase and remove extraneous punctuation (but preserve intra-word hyphens)
|
244
|
+
token_clean = re.sub(r"[^\w\-]", "", token.lower()).strip()
|
245
|
+
if not token_clean:
|
246
|
+
continue
|
247
|
+
# Skip tokens that are pure numbers
|
248
|
+
if token_clean.isdigit():
|
249
|
+
continue
|
250
|
+
# Skip stopwords
|
251
|
+
if token_clean in STOP_WORDS:
|
252
|
+
continue
|
253
|
+
# Lemmatize the token to merge similar forms
|
254
|
+
token_norm = LEMMATIZER.lemmatize(token_clean)
|
255
|
+
weighted_counts[token_norm] = weighted_counts.get(token_norm, 0) + weight
|
256
|
+
|
257
|
+
# Reconstruct a weighted token list by repeating each token by its aggregated count.
|
230
258
|
weighted_words = []
|
231
|
-
for
|
232
|
-
|
233
|
-
|
234
|
-
|
235
|
-
weighted_words.extend([word] * weight)
|
236
|
-
|
237
|
-
# Tokenize the weighted words, but preserve number-word patterns like '4-alpha'
|
238
|
-
tokens = word_tokenize(" ".join(weighted_words))
|
239
|
-
# Ensure we treat "4-alpha" or other "number-word" patterns as single tokens
|
259
|
+
for token, count in weighted_counts.items():
|
260
|
+
weighted_words.extend([token] * count)
|
261
|
+
|
262
|
+
# Combine tokens that match number-word patterns (e.g. "4-alpha") and remove pure numeric tokens.
|
240
263
|
combined_tokens = []
|
241
|
-
for token in
|
242
|
-
# Match patterns like '4-alpha' or '5-hydroxy' and keep them together
|
264
|
+
for token in weighted_words:
|
243
265
|
if re.match(r"^\d+-\w+", token):
|
244
266
|
combined_tokens.append(token)
|
245
|
-
elif token.replace(".", "", 1).isdigit():
|
246
|
-
# Ignore pure numbers as descriptions unless necessary
|
267
|
+
elif token.replace(".", "", 1).isdigit():
|
247
268
|
continue
|
248
269
|
else:
|
249
270
|
combined_tokens.append(token)
|
250
271
|
|
251
|
-
#
|
272
|
+
# If the only token is numeric, return a default value.
|
252
273
|
if len(combined_tokens) == 1 and combined_tokens[0].isdigit():
|
253
|
-
return "N/A"
|
274
|
+
return "N/A"
|
254
275
|
|
255
|
-
# Simplify the
|
276
|
+
# Simplify the token list to remove near-duplicates based on the Jaccard index.
|
256
277
|
simplified_words = _simplify_word_list(combined_tokens)
|
278
|
+
# Generate a coherent description from the simplified words.
|
257
279
|
description = _generate_coherent_description(simplified_words)
|
258
280
|
|
259
281
|
return description
|
260
282
|
|
261
283
|
|
262
284
|
def _simplify_word_list(words: List[str], threshold: float = 0.80) -> List[str]:
|
263
|
-
"""Filter out words that are too similar based on the Jaccard index,
|
285
|
+
"""Filter out words that are too similar based on the Jaccard index,
|
286
|
+
keeping the word with the higher aggregated count.
|
264
287
|
|
265
288
|
Args:
|
266
|
-
words (
|
289
|
+
words (List[str]): The list of tokens to be filtered.
|
267
290
|
threshold (float, optional): The similarity threshold for the Jaccard index. Defaults to 0.80.
|
268
291
|
|
269
292
|
Returns:
|
270
|
-
|
293
|
+
List[str]: A list of filtered words, where similar words are reduced to the most frequent one.
|
271
294
|
"""
|
272
|
-
# Count the occurrences
|
295
|
+
# Count the occurrences (which reflect the weighted importance)
|
273
296
|
word_counts = Counter(words)
|
274
297
|
filtered_words = []
|
275
298
|
used_words = set()
|
276
|
-
|
277
|
-
|
299
|
+
|
300
|
+
# Iterate through words sorted by descending weighted frequency
|
301
|
+
for word in sorted(word_counts, key=lambda w: word_counts[w], reverse=True):
|
278
302
|
if word in used_words:
|
279
303
|
continue
|
280
304
|
|
281
305
|
word_set = set(word)
|
282
|
-
# Find similar words based on the Jaccard index
|
306
|
+
# Find similar words (including the current word) based on the Jaccard index
|
283
307
|
similar_words = [
|
284
308
|
other_word
|
285
309
|
for other_word in word_counts
|
286
310
|
if _calculate_jaccard_index(word_set, set(other_word)) >= threshold
|
287
311
|
]
|
288
|
-
#
|
312
|
+
# Choose the word with the highest weighted count among the similar group
|
289
313
|
similar_words.sort(key=lambda w: word_counts[w], reverse=True)
|
290
314
|
best_word = similar_words[0]
|
291
315
|
filtered_words.append(best_word)
|
292
316
|
used_words.update(similar_words)
|
293
317
|
|
318
|
+
# Preserve the original order (by frequency) from the filtered set
|
294
319
|
final_words = [word for word in words if word in filtered_words]
|
295
320
|
|
296
321
|
return final_words
|
297
322
|
|
298
323
|
|
299
324
|
def _calculate_jaccard_index(set1: Set[Any], set2: Set[Any]) -> float:
|
300
|
-
"""Calculate the Jaccard
|
325
|
+
"""Calculate the Jaccard index between two sets.
|
301
326
|
|
302
327
|
Args:
|
303
|
-
set1 (
|
304
|
-
set2 (
|
328
|
+
set1 (Set[Any]): The first set.
|
329
|
+
set2 (Set[Any]): The second set.
|
305
330
|
|
306
331
|
Returns:
|
307
|
-
float: The Jaccard
|
308
|
-
Returns 0 if the union of the sets is empty.
|
332
|
+
float: The Jaccard index (intersection over union). Returns 0 if the union is empty.
|
309
333
|
"""
|
310
334
|
intersection = len(set1.intersection(set2))
|
311
335
|
union = len(set1.union(set2))
|
@@ -313,28 +337,28 @@ def _calculate_jaccard_index(set1: Set[Any], set2: Set[Any]) -> float:
|
|
313
337
|
|
314
338
|
|
315
339
|
def _generate_coherent_description(words: List[str]) -> str:
|
316
|
-
"""Generate a coherent description from a list of words
|
340
|
+
"""Generate a coherent description from a list of words.
|
341
|
+
|
317
342
|
If there is only one unique entry, return it directly.
|
343
|
+
Otherwise, order the words by frequency and join them into a single string.
|
318
344
|
|
319
345
|
Args:
|
320
|
-
words (List): A list of
|
346
|
+
words (List[str]): A list of tokens.
|
321
347
|
|
322
348
|
Returns:
|
323
|
-
str: A coherent description
|
349
|
+
str: A coherent, space-separated description.
|
324
350
|
"""
|
325
|
-
# If there are no words, return a keyword indicating no data is available
|
326
351
|
if not words:
|
327
352
|
return "N/A"
|
328
353
|
|
329
|
-
# If there
|
354
|
+
# If there is only one unique word, return it directly
|
330
355
|
unique_words = set(words)
|
331
356
|
if len(unique_words) == 1:
|
332
357
|
return list(unique_words)[0]
|
333
358
|
|
334
|
-
# Count
|
359
|
+
# Count weighted occurrences and sort in descending order.
|
335
360
|
word_counts = Counter(words)
|
336
361
|
most_common_words = [word for word, _ in word_counts.most_common()]
|
337
|
-
# Join the most common words to form a coherent description based on frequency
|
338
362
|
description = " ".join(most_common_words)
|
339
363
|
|
340
364
|
return description
|
@@ -14,17 +14,27 @@ from sklearn.metrics import silhouette_score
|
|
14
14
|
from tqdm import tqdm
|
15
15
|
|
16
16
|
from risk.annotations import get_weighted_description
|
17
|
-
from risk.constants import GROUP_LINKAGE_METHODS, GROUP_DISTANCE_METRICS
|
18
17
|
from risk.log import logger
|
19
18
|
|
20
19
|
|
20
|
+
# Define constants for clustering
|
21
|
+
# fmt: off
|
22
|
+
LINKAGE_METHODS = {"single", "complete", "average", "weighted", "centroid", "median", "ward"}
|
23
|
+
LINKAGE_METRICS = {
|
24
|
+
"braycurtis","canberra", "chebyshev", "cityblock", "correlation", "cosine", "dice", "euclidean",
|
25
|
+
"hamming", "jaccard", "jensenshannon", "kulczynski1", "mahalanobis", "matching", "minkowski",
|
26
|
+
"rogerstanimoto", "russellrao", "seuclidean", "sokalmichener", "sokalsneath", "sqeuclidean", "yule",
|
27
|
+
}
|
28
|
+
# fmt: on
|
29
|
+
|
30
|
+
|
21
31
|
def define_domains(
|
22
32
|
top_annotations: pd.DataFrame,
|
23
33
|
significant_neighborhoods_significance: np.ndarray,
|
24
34
|
linkage_criterion: str,
|
25
35
|
linkage_method: str,
|
26
36
|
linkage_metric: str,
|
27
|
-
linkage_threshold: float,
|
37
|
+
linkage_threshold: Union[float, str],
|
28
38
|
) -> pd.DataFrame:
|
29
39
|
"""Define domains and assign nodes to these domains based on their significance scores and clustering,
|
30
40
|
handling errors by assigning unique domains when clustering fails.
|
@@ -33,9 +43,9 @@ def define_domains(
|
|
33
43
|
top_annotations (pd.DataFrame): DataFrame of top annotations data for the network nodes.
|
34
44
|
significant_neighborhoods_significance (np.ndarray): The binary significance matrix below alpha.
|
35
45
|
linkage_criterion (str): The clustering criterion for defining groups.
|
36
|
-
linkage_method (str): The linkage method for clustering.
|
37
|
-
linkage_metric (str): The linkage metric for clustering.
|
38
|
-
linkage_threshold (float): The threshold for clustering.
|
46
|
+
linkage_method (str): The linkage method for clustering. Choose "auto" to optimize.
|
47
|
+
linkage_metric (str): The linkage metric for clustering. Choose "auto" to optimize.
|
48
|
+
linkage_threshold (float, str): The threshold for clustering. Choose "auto" to optimize.
|
39
49
|
|
40
50
|
Returns:
|
41
51
|
pd.DataFrame: DataFrame with the primary domain for each node.
|
@@ -55,9 +65,8 @@ def define_domains(
|
|
55
65
|
# Perform hierarchical clustering
|
56
66
|
Z = linkage(m, method=best_linkage, metric=best_metric)
|
57
67
|
logger.warning(
|
58
|
-
f"Linkage criterion: '{linkage_criterion}'\nLinkage method: '{best_linkage}'\nLinkage metric: '{best_metric}'"
|
68
|
+
f"Linkage criterion: '{linkage_criterion}'\nLinkage method: '{best_linkage}'\nLinkage metric: '{best_metric}'\nLinkage threshold: {round(best_threshold, 3)}"
|
59
69
|
)
|
60
|
-
logger.debug(f"Optimal linkage threshold: {round(best_threshold, 3)}")
|
61
70
|
# Calculate the optimal threshold for clustering
|
62
71
|
max_d_optimal = np.max(Z[:, 2]) * best_threshold
|
63
72
|
# Assign domains to the annotations matrix
|
@@ -209,9 +218,9 @@ def _optimize_silhouette_across_linkage_and_metrics(
|
|
209
218
|
Args:
|
210
219
|
m (np.ndarray): Data matrix.
|
211
220
|
linkage_criterion (str): Clustering criterion.
|
212
|
-
linkage_method (str): Linkage method for clustering.
|
213
|
-
linkage_metric (str): Linkage metric for clustering.
|
214
|
-
linkage_threshold (Union[str, float]): Threshold for clustering.
|
221
|
+
linkage_method (str): Linkage method for clustering. Choose "auto" to optimize.
|
222
|
+
linkage_metric (str): Linkage metric for clustering. Choose "auto" to optimize.
|
223
|
+
linkage_threshold (Union[str, float]): Threshold for clustering. Choose "auto" to optimize.
|
215
224
|
|
216
225
|
Returns:
|
217
226
|
Tuple[str, str, float]:
|
@@ -226,8 +235,8 @@ def _optimize_silhouette_across_linkage_and_metrics(
|
|
226
235
|
best_overall_score = -np.inf
|
227
236
|
|
228
237
|
# Set linkage methods and metrics to all combinations if "auto" is selected
|
229
|
-
linkage_methods =
|
230
|
-
linkage_metrics =
|
238
|
+
linkage_methods = LINKAGE_METHODS if linkage_method == "auto" else [linkage_method]
|
239
|
+
linkage_metrics = LINKAGE_METRICS if linkage_metric == "auto" else [linkage_metric]
|
231
240
|
total_combinations = len(linkage_methods) * len(linkage_metrics)
|
232
241
|
|
233
242
|
# Evaluating optimal linkage method and metric
|
@@ -4,7 +4,7 @@ risk/network/graph/api
|
|
4
4
|
"""
|
5
5
|
|
6
6
|
import copy
|
7
|
-
from typing import Any, Dict
|
7
|
+
from typing import Any, Dict, Union
|
8
8
|
|
9
9
|
import networkx as nx
|
10
10
|
import pandas as pd
|
@@ -42,7 +42,7 @@ class GraphAPI:
|
|
42
42
|
linkage_criterion: str = "distance",
|
43
43
|
linkage_method: str = "average",
|
44
44
|
linkage_metric: str = "yule",
|
45
|
-
linkage_threshold: float = 0.2,
|
45
|
+
linkage_threshold: Union[float, str] = 0.2,
|
46
46
|
min_cluster_size: int = 5,
|
47
47
|
max_cluster_size: int = 1000,
|
48
48
|
) -> Graph:
|
@@ -58,9 +58,11 @@ class GraphAPI:
|
|
58
58
|
impute_depth (int, optional): Depth for imputing neighbors. Defaults to 0.
|
59
59
|
prune_threshold (float, optional): Distance threshold for pruning neighbors. Defaults to 0.0.
|
60
60
|
linkage_criterion (str, optional): Clustering criterion for defining domains. Defaults to "distance".
|
61
|
-
linkage_method (str, optional): Clustering method to use. Defaults to "average".
|
62
|
-
linkage_metric (str, optional): Metric to use for calculating distances.
|
63
|
-
|
61
|
+
linkage_method (str, optional): Clustering method to use. Choose "auto" to optimize. Defaults to "average".
|
62
|
+
linkage_metric (str, optional): Metric to use for calculating distances. Choose "auto" to optimize.
|
63
|
+
Defaults to "yule".
|
64
|
+
linkage_threshold (float, str, optional): Threshold for clustering. Choose "auto" to optimize.
|
65
|
+
Defaults to 0.2.
|
64
66
|
min_cluster_size (int, optional): Minimum size for clusters. Defaults to 5.
|
65
67
|
max_cluster_size (int, optional): Maximum size for clusters. Defaults to 1000.
|
66
68
|
|
@@ -1,31 +0,0 @@
|
|
1
|
-
"""
|
2
|
-
risk/constants
|
3
|
-
~~~~~~~~~~~~~~
|
4
|
-
"""
|
5
|
-
|
6
|
-
GROUP_LINKAGE_METHODS = ["single", "complete", "average", "weighted", "centroid", "median", "ward"]
|
7
|
-
|
8
|
-
GROUP_DISTANCE_METRICS = [
|
9
|
-
"braycurtis",
|
10
|
-
"canberra",
|
11
|
-
"chebyshev",
|
12
|
-
"cityblock",
|
13
|
-
"correlation",
|
14
|
-
"cosine",
|
15
|
-
"dice",
|
16
|
-
"euclidean",
|
17
|
-
"hamming",
|
18
|
-
"jaccard",
|
19
|
-
"jensenshannon",
|
20
|
-
"kulczynski1",
|
21
|
-
"mahalanobis",
|
22
|
-
"matching",
|
23
|
-
"minkowski",
|
24
|
-
"rogerstanimoto",
|
25
|
-
"russellrao",
|
26
|
-
"seuclidean",
|
27
|
-
"sokalmichener",
|
28
|
-
"sokalsneath",
|
29
|
-
"sqeuclidean",
|
30
|
-
"yule",
|
31
|
-
]
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|