In [1]:
#Read in Redlist
import pandas as pd
import py_entitymatching as em
import math
import matplotlib.pyplot as plt
import numpy as np
from matplotlib import style
import re
style.use('ggplot')
# Read in csv as dataframe
rl = em.read_csv_metadata("../finalRedlist.csv", encoding="ISO-8859-1", key='id')
# glance at first few rows
ar = em.read_csv_metadata("../trying.csv", encoding="ISO-8859-1", key='id')
c:\users\aparn\anaconda\envs\my_first_env\lib\site-packages\sklearn\cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
"This module will be removed in 0.20.", DeprecationWarning)
Metadata file is not present in the given path; proceeding to read the csv file.
Metadata file is not present in the given path; proceeding to read the csv file.
In [2]:
rl['block'] = 'yes'
ar['block'] = 'yes'
In [3]:
rl.rename(columns={'Unnamed: 0':'Unnamed'}, inplace=True)
ar.rename(columns={'Unnamed: 0':'Unnamed'}, inplace=True)
ar.columns
Out[3]:
Index(['id', 'scientific_name', 'name', 'kingdom', 'phylum', 'class', 'order',
'family', 'genus', 'size', 'threats', 'conservation', 'threat_keywords',
'conservation_keywords', 'status', 'countries', 'country_count',
'tCount', 'block'],
dtype='object')
In [4]:
columns = ar.columns
#newColumns = []
#for column in columns:
#new_column = column.replace(' ','')
#ar=ar.rename(columns = {column:new_column})
#ar.to_csv('finalArkives.csv')
In [5]:
#Block on bogus attribute so that we can actually do
#blocking on genus
ob = em.OverlapBlocker()
C0 = ob.block_tables(rl, ar,'block', 'block',
l_output_attrs=list(rl.columns.values),
r_output_attrs=list(ar.columns.values))
0% 100%
[##############################] | ETA: 00:00:00
Total time elapsed: 00:01:12
In [6]:
C1 = ob.block_candset(C0, 'genus', 'genus')
0% 100%
[##############################] | ETA: 00:00:00
Total time elapsed: 00:02:30
In [7]:
#C1.head()
feat = em.get_features_for_matching(rl, ar)
feat
Out[7]:
feature_name
left_attribute
right_attribute
left_attr_tokenizer
right_attr_tokenizer
simfunction
function
function_source
is_auto_generated
0
name_name_jac_qgm_3_qgm_3
name
name
qgm_3
qgm_3
jaccard
<function name_name_jac_qgm_3_qgm_3 at 0x00000235DEFC3EA0>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
1
name_name_cos_dlm_dc0_dlm_dc0
name
name
dlm_dc0
dlm_dc0
cosine
<function name_name_cos_dlm_dc0_dlm_dc0 at 0x00000235DFA29D08>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
2
name_name_jac_dlm_dc0_dlm_dc0
name
name
dlm_dc0
dlm_dc0
jaccard
<function name_name_jac_dlm_dc0_dlm_dc0 at 0x00000235DFA29F28>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
3
name_name_mel
name
name
None
None
monge_elkan
<function name_name_mel at 0x00000235DF327840>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
4
name_name_lev_dist
name
name
None
None
lev_dist
<function name_name_lev_dist at 0x00000235DF327400>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
5
name_name_lev_sim
name
name
None
None
lev_sim
<function name_name_lev_sim at 0x00000235DF327488>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
6
name_name_nmw
name
name
None
None
needleman_wunsch
<function name_name_nmw at 0x00000235DF327048>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
7
name_name_sw
name
name
None
None
smith_waterman
<function name_name_sw at 0x00000235DF327158>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
8
family_family_jac_qgm_3_qgm_3
family
family
qgm_3
qgm_3
jaccard
<function family_family_jac_qgm_3_qgm_3 at 0x00000235DF3270D0>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
9
family_family_cos_dlm_dc0_dlm_dc0
family
family
dlm_dc0
dlm_dc0
cosine
<function family_family_cos_dlm_dc0_dlm_dc0 at 0x00000235DF3278C8>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
10
family_family_jac_dlm_dc0_dlm_dc0
family
family
dlm_dc0
dlm_dc0
jaccard
<function family_family_jac_dlm_dc0_dlm_dc0 at 0x00000235DF327620>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
11
family_family_mel
family
family
None
None
monge_elkan
<function family_family_mel at 0x00000235DF3277B8>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
12
family_family_lev_dist
family
family
None
None
lev_dist
<function family_family_lev_dist at 0x00000235DF3276A8>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
13
family_family_lev_sim
family
family
None
None
lev_sim
<function family_family_lev_sim at 0x00000235DF327950>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
14
family_family_nmw
family
family
None
None
needleman_wunsch
<function family_family_nmw at 0x00000235DF3279D8>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
15
family_family_sw
family
family
None
None
smith_waterman
<function family_family_sw at 0x00000235DF327A60>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
16
countries_countries_jac_qgm_3_qgm_3
countries
countries
qgm_3
qgm_3
jaccard
<function countries_countries_jac_qgm_3_qgm_3 at 0x00000235DF327AE8>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
17
countries_countries_cos_dlm_dc0_dlm_dc0
countries
countries
dlm_dc0
dlm_dc0
cosine
<function countries_countries_cos_dlm_dc0_dlm_dc0 at 0x00000235DF327B70>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
18
countries_countries_jac_dlm_dc0_dlm_dc0
countries
countries
dlm_dc0
dlm_dc0
jaccard
<function countries_countries_jac_dlm_dc0_dlm_dc0 at 0x00000235DF327BF8>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
19
countries_countries_mel
countries
countries
None
None
monge_elkan
<function countries_countries_mel at 0x00000235DF327C80>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
20
countries_countries_lev_dist
countries
countries
None
None
lev_dist
<function countries_countries_lev_dist at 0x00000235DF327D08>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
21
countries_countries_lev_sim
countries
countries
None
None
lev_sim
<function countries_countries_lev_sim at 0x00000235DF327D90>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
22
countries_countries_nmw
countries
countries
None
None
needleman_wunsch
<function countries_countries_nmw at 0x00000235DF327E18>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
23
countries_countries_sw
countries
countries
None
None
smith_waterman
<function countries_countries_sw at 0x00000235DF327EA0>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
24
country_count_country_count_exm
country_count
country_count
None
None
exact_match
<function country_count_country_count_exm at 0x00000235DF327F28>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
25
country_count_country_count_anm
country_count
country_count
None
None
abs_norm
<function country_count_country_count_anm at 0x00000236587CB048>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
26
country_count_country_count_lev_dist
country_count
country_count
None
None
lev_dist
<function country_count_country_count_lev_dist at 0x00000236587CB0D0>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
27
country_count_country_count_lev_sim
country_count
country_count
None
None
lev_sim
<function country_count_country_count_lev_sim at 0x00000236587CB158>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
28
scientific_name_scientific_name_jac_qgm_3_qgm_3
scientific_name
scientific_name
qgm_3
qgm_3
jaccard
<function scientific_name_scientific_name_jac_qgm_3_qgm_3 at 0x00000236587CB1E0>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
29
scientific_name_scientific_name_cos_dlm_dc0_dlm_dc0
scientific_name
scientific_name
dlm_dc0
dlm_dc0
cosine
<function scientific_name_scientific_name_cos_dlm_dc0_dlm_dc0 at 0x00000236587CB268>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
30
scientific_name_scientific_name_jac_dlm_dc0_dlm_dc0
scientific_name
scientific_name
dlm_dc0
dlm_dc0
jaccard
<function scientific_name_scientific_name_jac_dlm_dc0_dlm_dc0 at 0x00000236587CB2F0>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
31
scientific_name_scientific_name_mel
scientific_name
scientific_name
None
None
monge_elkan
<function scientific_name_scientific_name_mel at 0x00000236587CB378>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
32
scientific_name_scientific_name_lev_dist
scientific_name
scientific_name
None
None
lev_dist
<function scientific_name_scientific_name_lev_dist at 0x00000236587CB400>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
33
scientific_name_scientific_name_lev_sim
scientific_name
scientific_name
None
None
lev_sim
<function scientific_name_scientific_name_lev_sim at 0x00000236587CB488>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
34
scientific_name_scientific_name_nmw
scientific_name
scientific_name
None
None
needleman_wunsch
<function scientific_name_scientific_name_nmw at 0x00000236587CB510>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
35
scientific_name_scientific_name_sw
scientific_name
scientific_name
None
None
smith_waterman
<function scientific_name_scientific_name_sw at 0x00000236587CB598>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
36
block_block_lev_dist
block
block
None
None
lev_dist
<function block_block_lev_dist at 0x00000236587CB620>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
37
block_block_lev_sim
block
block
None
None
lev_sim
<function block_block_lev_sim at 0x00000236587CB6A8>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
38
block_block_jar
block
block
None
None
jaro
<function block_block_jar at 0x00000236587CB730>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
39
block_block_jwn
block
block
None
None
jaro_winkler
<function block_block_jwn at 0x00000236587CB7B8>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
40
block_block_exm
block
block
None
None
exact_match
<function block_block_exm at 0x00000236587CB840>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
41
block_block_jac_qgm_3_qgm_3
block
block
qgm_3
qgm_3
jaccard
<function block_block_jac_qgm_3_qgm_3 at 0x00000236587CB8C8>
from py_entitymatching.feature.simfunctions import *\nfrom py_entitymatching.feature.tokenizers ...
True
In [18]:
H = em.extract_feature_vecs(C1,
feature_table=feat,
attrs_after='rtable_block',
show_progress=False)
In [19]:
#C1 = C1.drop('rtable_block', 1)
#C1 = C1.drop('ltable_block', 1)
result = pd.concat([C1, H], axis=1)
#result = result.drop('rtable_block',1)
In [20]:
cols_to_drop = ['family_',
'scientific_name_',
'block',
'Unnamed',
'name_name_cos_dlm_dc0_dlm_dc0',
'name_name_mel',
'name_name_lev_dist',
'name_name_lev_sim',
'name_name_nmw',
'name_name_sw'
]
for n in result.columns:
for c in cols_to_drop:
if c in n:
result = result.drop(n,1)
result.columns
Out[20]:
Index(['_id', 'ltable_id', 'rtable_id', 'ltable_name', 'ltable_genus',
'ltable_family', 'ltable_ecology', 'ltable_countries',
'ltable_threat_paragraph', 'ltable_conservation_paragraph',
'ltable_pop_trend', 'ltable_status', 'ltable_country_count',
'ltable_scientific_name', 'rtable_scientific_name', 'rtable_name',
'rtable_kingdom', 'rtable_phylum', 'rtable_class', 'rtable_order',
'rtable_family', 'rtable_genus', 'rtable_size', 'rtable_threats',
'rtable_conservation', 'rtable_threat_keywords',
'rtable_conservation_keywords', 'rtable_status', 'rtable_countries',
'rtable_country_count', 'rtable_tCount', '_id', 'ltable_id',
'rtable_id', 'name_name_jac_qgm_3_qgm_3',
'name_name_jac_dlm_dc0_dlm_dc0', 'countries_countries_jac_qgm_3_qgm_3',
'countries_countries_cos_dlm_dc0_dlm_dc0',
'countries_countries_jac_dlm_dc0_dlm_dc0', 'countries_countries_mel',
'countries_countries_lev_dist', 'countries_countries_lev_sim',
'countries_countries_nmw', 'countries_countries_sw',
'country_count_country_count_exm', 'country_count_country_count_anm',
'country_count_country_count_lev_dist',
'country_count_country_count_lev_sim'],
dtype='object')
In [11]:
label = em.split_train_test(C1, train_proportion=0.1039)
gold = label['train']
DS = label['test']
#Automatically label the training data
labels = []
matches = 0;
nonmatches = 0;
for index, row in gold.iterrows():
if row['rtable_scientific_name'].strip().lower() == row['ltable_scientific_name'].strip().lower():
labels.append(1)
matches = matches + 1
else:
labels.append(0)
nonmatches = nonmatches + 1
gold['label'] = labels
print('number of matches in training set:', matches)
print('number of nonmatches in training set:', nonmatches)
number of matches in training set: 28
number of nonmatches in training set: 239
In [12]:
gold
Out[12]:
_id
ltable_id
rtable_id
ltable_Unnamed
ltable_name
ltable_genus
ltable_family
ltable_ecology
ltable_countries
ltable_threat_paragraph
...
rtable_threats
rtable_conservation
rtable_threat_keywords
rtable_conservation_keywords
rtable_status
rtable_countries
rtable_country_count
rtable_tCount
rtable_block
label
2111715
2111715
6325
266
6325
dark red meranti
Shorea
Dipterocarpaceae
Terrestrial
Brunei Darussalam; Malaysia (Sarawak);
\r\r\n It is particularly threatened by logging operations because it grows too slowly to rea...
...
Dipterocarp forests have become amongst the most endangered in the world widely logged for use i...
Some subpopulations of this species are found in primary forest reserves where they receive vary...
Endangered
['Tunisia', 'Algeria', 'Morocco']
3
0
yes
0
1167885
1167885
4380
147
4380
kerangas bubblenest frog
Philautus
Rhacophoridae
Terrestrial; Freshwater
Malaysia;
\r\r\n Loss of habitat due to the deforestation and fragmentation of peat swamps is the major...
...
The blue-eyed bush frog has lost a great amount of suitable habitat due to dam construction agri...
Some areas within the range of the blue-eyed bush frog are protected including the Sharavathi Va...
invasive;
protected;
Endangered
['Cameroon', 'Gabon']
2
1
yes
0
2192219
2192219
7679
276
7679
ebners skink
Chalcides
Scincidae
Terrestrial
Morocco;
\r\r\n This species has a restricted range, and is highly threatened by habitat loss principa...
...
Relatively little is known about the threats to Doumergue's skink. It is believed to be uncommon...
Doumergueâ??s skink occurs in the Chafarine Hunting Reserve in the Chafarinas islands Spain as w...
protected;
Endangered
['China']
1
0
yes
0
5893603
5893603
4843
744
4843
orangebellied racer, redbellied racer, saba racer
Alsophis
Dipsadidae
NaN
Saint Kitts and Nevis; Bonaire, Sint Eustatius and Saba (Saba, Sint Eustatius);
\r\r\n Extirpated historically from Nevis and St Kitts due to the introduction of mongooses. ...
...
The red-bellied racer now occupies only 11 percent of its original range (5) largely due to the ...
Fortunately there are some systems in place to conserve the red-bellied racer. For example on St...
protected;
Critically Endangered
['Italy', 'Mexico']
2
0
yes
1
1369617
1369617
322
173
322
NaN
Mammillaria
Cactaceae
Terrestrial
Mexico (Sonora);
\r\r\n The species' range is impacted by urban development, including tourism facilities, and...
...
Collectors have prized this distinctive and unusual cactus over the years and well-known sites h...
International trade in plants and seeds of wild origin is banned by the listing of <i>Mammillari...
cites;
Endangered
['Tunisia', 'Morocco', 'Algeria']
3
0
yes
0
7278065
7278065
4180
919
4180
NaN
Eleutherodactylus
Eleutherodactylidae
Terrestrial
Cuba;
\r\r\n The major threat to the species is disturbance of its habitat by tourists.\r\r\n\r\r\n...
...
Currently almost a quarter of all amphibian species on the British Virgin Islands are categorise...
A number of conservation recommendations have been made to protect the native fauna of the Briti...
protected;
Critically Endangered
['Dominican Republic', 'Haiti']
2
0
yes
0
8970546
8970546
2851
1133
2851
NaN
Encephalartos
Zamiaceae
Terrestrial
Tanzania, United Republic of;
\r\r\n This species is affected by too frequent fires, which may affect regeneration. Changes...
...
Over the past few decades many South African cycads have become increasingly scarce in the wild ...
There are not known to be any specific conservation measures in place for this Critically Endang...
loss;
cites;protected;
Critically Endangered
['South Africa']
1
1
yes
0
1199440
1199440
4275
151
4275
bernhards mantella, black mantella, tolongoina golden frog
Mantella
Mantellidae
Terrestrial; Freshwater
Madagascar;
\r\r\n The area where the species occurs is being degraded rapidly due to subsistence agricul...
...
Several thousand blue-legged mantellas are thought to be collected every year from some regions ...
Listing on Appendix II of the Convention on International Trade in Endangered Species provides t...
loss;
Endangered
['Turkey']
1
1
yes
0
5788641
5788641
2776
731
2776
germains langur, germains silver langur, indochinese lutung, indochinese silvered langur
Trachypithecus
Cercopithecidae
Terrestrial
Cambodia; Lao People's Democratic Republic; Myanmar; Thailand; Viet Nam;
\r\r\n The major threats to this species are hunting, mainly for subsistence use and traditio...
...
The purple-faced langurâ??s range has contracted greatly in the face of human encroachment. Defo...
The commercial exploitation of purple-faced langurs is regulated by their listing on Appendix II...
loss;fragmentation;hunting;
cites;protected;
Critically Endangered
['British Virgin Islands']
1
3
yes
0
8905563
8905563
1188
1125
1188
silverybrown bareface tamarin, silverybrown tamarin, whitefooted tamarin
Saguinus
Callitrichidae
Terrestrial
Colombia (Colombia (mainland));
\r\r\n This species occurs in an area of intensive colonization and forest loss. Cuartas-Call...
...
Deforestation is this speciesâ?? greatest threat (6). It has already lost most of its habitat th...
The cotton-headed tamarin has been protected in Colombia since 1969 and export of this species h...
protected;
Critically Endangered
['Bulgaria']
1
0
yes
0
2103518
2103518
6043
265
6043
NaN
Shorea
Dipterocarpaceae
NaN
Malaysia (Peninsular Malaysia);
NaN
...
Dipterocarp forests have become amongst the most endangered in the world widely logged for use i...
Some subpopulations of this species are found in primary forest reserves where they receive vary...
Endangered
['Seychelles']
1
0
yes
0
2099475
2099475
2000
265
2000
light red meranti, meranti
Shorea
Dipterocarpaceae
NaN
Indonesia (Sumatera); Malaysia (Peninsular Malaysia); Singapore; Thailand;
\r\r\n Has suffered a massive population reduction mainly because of the rates of exploitatio...
...
Dipterocarp forests have become amongst the most endangered in the world widely logged for use i...
Some subpopulations of this species are found in primary forest reserves where they receive vary...
Endangered
['Seychelles']
1
0
yes
0
5282145
5282145
2840
667
2840
magnificent broodfrog
Pseudophryne
Myobatrachidae
Terrestrial; Freshwater
Australia;
\r\r\n Habitat loss and degradation appears to be the major threat. Its habitat occurs on lan...
...
The decline of the northern corroboree frog has been monitored with despair as the exact cause o...
Much of the habitat occupied by northern corroboree frogs is within reserves providing protectio...
loss;
Endangered
['Gabon', 'Equatorial Guinea', 'Cameroon']
3
1
yes
0
9125918
9125918
7838
1152
7838
delta green ground beetle
Elaphrus
Carabidae
NaN
United States;
NaN
...
The historical distribution of the delta ground beetle is unknown but it is thought reasonable t...
The delta green ground beetle is protected by the Lacey Act which prohibits its import export tr...
protected;
Critically Endangered
['Angola', 'Equatorial Guinea', 'Gabon', 'Central African Republic', 'Cameroon']
5
0
yes
1
4885590
4885590
2035
617
2035
NaN
Shorea
Dipterocarpaceae
Terrestrial
Brunei Darussalam; Malaysia (Sarawak);
\r\r\n This tree is threatened by forest conversion and habitat degradation.\r\r\n\r\r\n \...
...
Unrestricted exploitation of <strong>dipterocarps</strong> for their high quality timber has lef...
There are no specific conservation measures in place for <i>Shorea roxburghii</i> but several po...
Endangered
['Indonesia']
1
0
yes
0
4885373
4885373
1818
617
1818
white meranti
Shorea
Dipterocarpaceae
Terrestrial
Indonesia (Kalimantan); Malaysia (Sarawak);
NaN
...
Unrestricted exploitation of <strong>dipterocarps</strong> for their high quality timber has lef...
There are no specific conservation measures in place for <i>Shorea roxburghii</i> but several po...
Endangered
['Indonesia']
1
0
yes
0
1136407
1136407
4562
143
4562
conchos shiner
Cyprinella
Cyprinidae
NaN
Mexico;
NaN
...
Numbering no more than 2500 individuals the blue shiner population is suspected to have undergon...
The future of the blue shiner very much depends on the protection of its habitat particularly th...
loss;pollution;
Endangered
['United Kingdom', 'New Zealand']
2
2
yes
0
3736393
3736393
513
472
513
NaN
Partulina
Achatinellidae
NaN
United States (Hawaiian Is.);
NaN
...
As a result of human disturbances the Hawaiian Islands have seen devastating extinction rates an...
Like many other Hawaiian snail species the restricted geographic range and small population size...
loss;
captive breeding;
Endangered
['Angola']
1
1
yes
1
9013976
9013976
6706
1138
6706
NaN
Scalesia
Compositae
NaN
Ecuador (Galápagos);
\r\r\n The plants are subject to grazing by introduced goats.\r\r\n\r\r\n \r\r\n
...
Since humans arrived on the Galapagos dramatic ecological changes have been caused by agricultur...
Scientists at the Charles Darwin Research Station are involved in several projects to restore an...
Critically Endangered
['Tanzania']
1
0
yes
0
7692935
7692935
7470
971
7470
NaN
Eleutherodactylus
Eleutherodactylidae
Terrestrial
Cuba;
\r\r\n This species is threatened mainly by habitat loss as a result of the deforestation tak...
...
Already restricted in range Wightmanâ??s robber frog populations are in a continuing decline est...
Despite not being the target of any known conservation measures Wightmanâ??s robber frog is affo...
disease;pollution;
protected;
Critically Endangered
['Turkey', 'Greece', 'Mauritania']
3
2
yes
0
1963598
1963598
678
248
678
cuviers hutia, hispaniolan hutia, hispanolan hutia
Plagiodontia
Capromyidae
Terrestrial
Dominican Republic; Haiti;
\r\r\n Often killed as a crop pest and opportunistically hunted for food in Haiti. Increasing...
...
Hutias were once a diverse group that occurred across the Caribbean islands but over half of all...
Cuvierâ??s hutia occurs in a number of protected areas although habitat destruction may still be...
loss;hunting;
protected;
Endangered
['Seychelles']
1
2
yes
1
7692897
7692897
7432
971
7432
bartons robber frog
Eleutherodactylus
Eleutherodactylidae
Terrestrial
Cuba;
\r\r\n This species is threatened by habitat degradation and deforestation due to subsistence...
...
Already restricted in range Wightmanâ??s robber frog populations are in a continuing decline est...
Despite not being the target of any known conservation measures Wightmanâ??s robber frog is affo...
disease;pollution;
protected;
Critically Endangered
['Turkey', 'Greece', 'Mauritania']
3
2
yes
0
8387785
8387785
5800
1059
5800
black sea bass, giant sea bass
Stereolepis
Polyprionidae
Marine
<div>Pacific â?? eastern central</div>; Mexico (Baja California, Sonora); United States (Califor...
\r\r\n The major threat is from overfishing; however, the species is protected in California ...
...
The black sea bass has been massively over-fished in both California and Mexican waters leaving ...
The black sea bass has been protected in California since 1981 and in Mexico since 1992. Both co...
fishing;
protected;
Critically Endangered
['Venezuela', 'Mexico']
2
1
yes
1
8642587
8642587
7322
1091
7322
NaN
Colophon
Lucanidae
NaN
South Africa;
NaN
...
Collectors appear to pose the greatest threat to this enigmatic group of beetles (4) (6). The Ca...
All <i>Colophon</i> species were given provincial legal protection in 1992 which served to limit...
loss;
cites;
Critically Endangered
['Russia', 'Iran', 'China', 'India']
4
1
yes
1
8236739
8236739
5139
1040
5139
NaN
Aloe
Aloaceae
Terrestrial
Tanzania, United Republic of;
\r\r\n The population is accessible so could be impacted by collectors for medicinal use and ...
...
Recent surveys of the bastard quiver tree in the Richtersveld region of the Northern Cape Provin...
Bastard quiver trees are protected in South Africa and Namibia (10) and are listed on Appendix I...
environment;
cites;protected;
Critically Endangered
[]
0
1
yes
0
5685738
5685738
2768
718
2768
NaN
Nepenthes
Nepenthaceae
Terrestrial
Malaysia;
NaN
...
As fascinating and unusual plants <i>Nepenthes</i> spp. have been collected from the wild for ce...
<i>Nepenthes rajah</i> is listed on Appendix I of the Convention on International Trade in Endan...
loss;
cites;
Endangered
['China']
1
1
yes
1
2200134
2200134
7679
277
7679
ebners skink
Chalcides
Scincidae
Terrestrial
Morocco;
\r\r\n This species has a restricted range, and is highly threatened by habitat loss principa...
...
Relatively little is known about the threats to Doumergue's skink. It is believed to be uncommon...
Doumergueâ??s skink occurs in the Chafarine Hunting Reserve in the Chafarinas islands Spain as w...
protected;
Endangered
['El Salvador', 'Peru']
2
0
yes
0
2111336
2111336
5946
266
5946
NaN
Shorea
Dipterocarpaceae
Terrestrial
Sri Lanka;
NaN
...
Dipterocarp forests have become amongst the most endangered in the world widely logged for use i...
Some subpopulations of this species are found in primary forest reserves where they receive vary...
Endangered
['Tunisia', 'Algeria', 'Morocco']
3
0
yes
0
2103736
2103736
6261
265
6261
NaN
Shorea
Dipterocarpaceae
Terrestrial
Philippines;
\r\r\n It is now very nearly extinct because of habitat loss.\r\r\n\r\r\n \r\r\n
...
Dipterocarp forests have become amongst the most endangered in the world widely logged for use i...
Some subpopulations of this species are found in primary forest reserves where they receive vary...
Endangered
['Seychelles']
1
0
yes
0
540208
540208
1988
68
1988
cherry mahogany
Tieghemella
Sapotaceae
Terrestrial
Cameroon; Côte d'Ivoire; Gabon; Ghana; Liberia; Nigeria; Sierra Leone;
\r\r\n Overexploitation in some countries is leading to serious population declines, notably ...
...
The beautiful baku is threatened by over-exploitation for its attractive wood (8) which is used ...
Baku trees are protected by law in Côte d'Ivoire and due to the problem of overexploitation of ...
protected;
Endangered
['United States', 'Barbados', 'United Kingdom']
3
0
yes
1
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
6186035
6186035
4420
781
4420
black webfotted salamander , cordillera central salamander
Bolitoglossa
Plethodontidae
Terrestrial
Costa Rica;
\r\r\n Outside of protected areas the main threat to it is habitat loss due to the destructio...
...
Salvinâ??s mushroomtongue salamander was once relatively common but has undergone a decline as a...
No specific conservation measures are currently known to be in place for Salvinâ??s mushroomtong...
loss;fragmentation;environment;disease;
protected;
Critically Endangered
['Bermuda']
1
4
yes
0
1023881
1023881
2846
129
2846
blackfaced black spider monkey, chamek spider monkey, peruvian black spider monkey, peruvian spi...
Ateles
Atelidae
Terrestrial
Bolivia, Plurinational States of; Brazil (Acre, Amazonas, Mato Grosso, Rondônia); Peru;
\r\r\n The major threat is subsistence and market hunting for food (with guns). An additional...
...
The black-handed spider monkey which depends upon large areas of tall forest has suffered from h...
A Species Survival Plan has been created for the black-handed spider monkey which involves a coo...
pet;
Endangered
['Mexico', 'Portugal']
2
1
yes
0
7140275
7140275
945
902
945
NaN
Barbus
Cyprinidae
Freshwater
Benin; Nigeria;
\r\r\n Oil exploration in the Niger Delta and deforestation and urban development in Benin.\r...
...
The main reason for the decline of the Treur River barb population is believed to have been the ...
In 1970 the only area in which the Treur River barb occured Bendigospruit was declared an Intern...
Critically Endangered
['Greece', 'Albania']
2
0
yes
0
1777562
1777562
4602
224
4602
boxer pupfish
Cyprinodon
Cyprinodontidae
NaN
Mexico;
NaN
...
The small range of the Comanche Springs pupfish means that small changes in the environment can ...
Current conservation efforts for this species are focussed on moderating water level fluctuation...
loss;environment;invasive;pet;
Endangered
['Malaysia', 'Indonesia', 'Thailand']
3
4
yes
0
7270085
7270085
4115
918
4115
NaN
Eleutherodactylus
Eleutherodactylidae
Terrestrial
Cuba;
\r\r\n The major threat to this species is habitat loss due to fires and clear-cut logging of...
...
Currently almost a quarter of all amphibian species on the British Virgin Islands are categorise...
A number of conservation recommendations have been made to protect the native fauna of the Briti...
protected;
Critically Endangered
['Somalia', 'Kenya']
2
0
yes
0
3400458
3400458
4923
429
4923
ginger tree frog, golden frog, golden mantella, madagascan golden frog, malagasy golden mantella...
Mantella
Mantellidae
Terrestrial; Freshwater
Madagascar;
\r\r\n It is restricted to a fragment of forest surrounded by degraded land, and the remainin...
...
Having suffered over-collection for the pet trade in the past populations of green mantellas are...
Trade regulations have successfully reduced collection of this species but trade must continue t...
loss;pet;
protected;
Endangered
['Madagascar', 'Mauritius']
2
2
yes
0
2111695
2111695
6305
266
6305
yellow meranti
Shorea
Dipterocarpaceae
Terrestrial
Indonesia (Sumatera); Malaysia (Peninsular Malaysia);
\r\r\n Threatened directly by logging; the tree is unlikely to reach reproductive maturity wi...
...
Dipterocarp forests have become amongst the most endangered in the world widely logged for use i...
Some subpopulations of this species are found in primary forest reserves where they receive vary...
Endangered
['Tunisia', 'Algeria', 'Morocco']
3
0
yes
0
5689780
5689780
6810
718
6810
NaN
Nepenthes
Nepenthaceae
Terrestrial
Malaysia;
NaN
...
As fascinating and unusual plants <i>Nepenthes</i> spp. have been collected from the wild for ce...
<i>Nepenthes rajah</i> is listed on Appendix I of the Convention on International Trade in Endan...
loss;
cites;
Endangered
['China']
1
1
yes
0
7689604
7689604
4139
971
4139
NaN
Eleutherodactylus
Eleutherodactylidae
Terrestrial
Haiti;
\r\r\n Severe habitat destruction is taking place in the Formon-Macaya region, including thro...
...
Already restricted in range Wightmanâ??s robber frog populations are in a continuing decline est...
Despite not being the target of any known conservation measures Wightmanâ??s robber frog is affo...
disease;pollution;
protected;
Critically Endangered
['Turkey', 'Greece', 'Mauritania']
3
2
yes
0
5709485
5709485
2770
721
2770
NaN
Nepenthes
Nepenthaceae
Terrestrial
Philippines;
NaN
...
<i>Nepenthes</i> species are threatened by a combination of over-collection and habitat loss (2)...
<i>Nepenthes burbidgeae</i> is found only on Mount Kinabalu which is situated within Kinabalu Na...
loss;environmental;environment;
cites;protected;
Critically Endangered
['Mali', 'Chad', 'Niger', 'Mauritania']
4
3
yes
0
2111712
2111712
6322
266
6322
NaN
Shorea
Dipterocarpaceae
Terrestrial
Indonesia (Maluku, Sulawesi);
NaN
...
Dipterocarp forests have become amongst the most endangered in the world widely logged for use i...
Some subpopulations of this species are found in primary forest reserves where they receive vary...
Endangered
['Tunisia', 'Algeria', 'Morocco']
3
0
yes
0
6459702
6459702
1062
816
1062
eber gudgeon
Gobio
Cyprinidae
Freshwater
Turkey (Turkey-in-Asia);
\r\r\n Pollution and water abstraction are the major threats in the area which have almost te...
...
The Skadar gudgeon occupies only a relatively small area where it is under threat from water abs...
Skadar Lake is a designated Ramsar site or Wetland of International Importance (6). However ther...
Critically Endangered
['Brazil']
1
0
yes
0
8846926
8846926
5871
1117
5871
cape cedar, clanwilliam cedar, clanwilliam cypress
Widdringtonia
Cupressaceae
Terrestrial
South Africa (Western Cape);
\r\r\n Historical exploitation for its valuable timber during the 19th centry led to a reduct...
...
At the time of European settlement of South Africa the Clanwilliam cedar became massively logged...
Logging of the Clanwilliam cedar was banned at the turn of the 20th Century but under various pr...
Critically Endangered
['Indonesia']
1
0
yes
1
4410499
4410499
1844
557
1844
NaN
Shorea
Dipterocarpaceae
Terrestrial
India (Andhra Pradesh, Tamil Nadu);
\r\r\n This species is threatened due to loss of habitat, human interference and unregulated ...
...
Light red meranti has been heavily exploited for its valuable timber leaving populations of this...
The light red meranti is known to occur in some forest reserves (1).
Endangered
['India']
1
0
yes
0
2111635
2111635
6245
266
6245
NaN
Shorea
Dipterocarpaceae
Terrestrial
Malaysia (Sarawak);
\r\r\n Habitat destruction.\r\r\n\r\r\n \r\r\n
...
Dipterocarp forests have become amongst the most endangered in the world widely logged for use i...
Some subpopulations of this species are found in primary forest reserves where they receive vary...
Endangered
['Tunisia', 'Algeria', 'Morocco']
3
0
yes
0
8647087
8647087
3907
1092
3907
NaN
Colophon
Lucanidae
NaN
South Africa;
NaN
...
Collectors appear to pose the greatest threat to this enigmatic group of beetles (4) (6). The Ca...
All <i>Colophon</i> species were given provincial legal protection in 1992 which served to limit...
loss;
cites;
Critically Endangered
[]
0
1
yes
0
1372113
1372113
2818
173
2818
NaN
Mammillaria
Cactaceae
Terrestrial
Mexico (Guanajuato);
\r\r\n This species is found very close to several cities and towns and is declining due to u...
...
Collectors have prized this distinctive and unusual cactus over the years and well-known sites h...
International trade in plants and seeds of wild origin is banned by the listing of <i>Mammillari...
cites;
Endangered
['Tunisia', 'Morocco', 'Algeria']
3
0
yes
0
4414605
4414605
5950
557
5950
NaN
Shorea
Dipterocarpaceae
Terrestrial
Sri Lanka;
\r\r\n It is an important component of plywood, which is mainly used to make tea chests.\r\r\...
...
Light red meranti has been heavily exploited for its valuable timber leaving populations of this...
The light red meranti is known to occur in some forest reserves (1).
Endangered
['India']
1
0
yes
0
1376132
1376132
6837
173
6837
NaN
Mammillaria
Cactaceae
Terrestrial
Mexico (Tamaulipas);
\r\r\n This species is threatened by illegal collecting because of its very small population ...
...
Collectors have prized this distinctive and unusual cactus over the years and well-known sites h...
International trade in plants and seeds of wild origin is banned by the listing of <i>Mammillari...
cites;
Endangered
['Tunisia', 'Morocco', 'Algeria']
3
0
yes
0
3614076
3614076
4836
456
4836
black howling monkey, guatemalan black howler, guatemalan black howler monkey, guatemalan howler...
Alouatta
Atelidae
Terrestrial
Belize; Guatemala; Mexico (Campeche, Chiapas, Quintana Roo, Tabasco, Yucatán);
\r\r\n The main threats to this species are deforestation, hunting (for food and for capture ...
...
The Guatemalan black howler is threatened throughout most of its range from hunting and habitat ...
The Guatemalan black howler is known to occur in six protected areas: Cockscomb Basin Wildlife S...
hunting;
protected;
Endangered
['Hong Kong', 'Bangladesh', 'Russia', 'China', 'South Korea', 'Myanmar', 'Taiwan', 'Cambodia', '...
17
1
yes
1
8887036
8887036
6406
1122
6406
NaN
Ilex
Aquifoliaceae
NaN
Jamaica;
NaN
...
Having last been reviewed on the IUCN Red List in 1998 the conservation status of Cookâ??s holly...
Cookâ??s holly was listed on the US Endangered Species Act in 1987 and a Recovery Plan was drawn...
endangered species act;
Critically Endangered
['Kenya']
1
0
yes
0
4889904
4889904
6349
617
6349
NaN
Shorea
Dipterocarpaceae
NaN
Viet Nam;
NaN
...
Unrestricted exploitation of <strong>dipterocarps</strong> for their high quality timber has lef...
There are no specific conservation measures in place for <i>Shorea roxburghii</i> but several po...
Endangered
['Indonesia']
1
0
yes
0
8962630
8962630
2850
1132
2850
chimanimani cycad
Encephalartos
Zamiaceae
Terrestrial
Mozambique;
\r\r\n This species is threatened due to over-collecting for ornamental purposes.\r\r\n\r\r\n...
...
Over the past few decades many South African cycads have become increasingly scarce in the wild ...
There are not known to be any specific conservation measures in place for this Critically Endang...
loss;
cites;protected;
Critically Endangered
['Australia', 'South Africa', 'Brazil']
3
1
yes
0
7281392
7281392
7507
919
7507
NaN
Eleutherodactylus
Eleutherodactylidae
Terrestrial; Freshwater
Cuba;
\r\r\n The main threat to this species is habitat destruction that is taking place due to agr...
...
Currently almost a quarter of all amphibian species on the British Virgin Islands are categorise...
A number of conservation recommendations have been made to protect the native fauna of the Briti...
protected;
Critically Endangered
['Dominican Republic', 'Haiti']
2
0
yes
0
5044745
5044745
2890
637
2890
NaN
Podocarpus
Podocarpaceae
Terrestrial
Philippines;
\r\r\n In three of the four known localities Google Earth satellite imagery indicates encroac...
...
Little information is available on the threats faced by <em>Podocarpus nakaii</em>. However its ...
There are no specific conservation measures currently known to be in place for <em>Podocarpus na...
Endangered
[]
0
0
yes
0
3171387
3171387
5387
400
5387
perriers sifaka
Propithecus
Indriidae
Terrestrial
Madagascar;
\r\r\n Slash-and-burn activities resulting in forest loss represents the greatest threat to t...
...
Of all lemurs the golden-crowned sifaka has one of the most limited distributions (3). Vast trac...
Recent studies have shown that these sifakas are fairly abundant in some of the remaining forest...
loss;hunting;
protected;
Endangered
['Guatemala', 'United States', 'Argentina']
3
2
yes
0
8974557
8974557
6862
1133
6862
ngotshe cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (KwaZulu-Natal);
\r\r\n This species' occurrence at a single site means the plants are vulnerable to environme...
...
Over the past few decades many South African cycads have become increasingly scarce in the wild ...
There are not known to be any specific conservation measures in place for this Critically Endang...
loss;
cites;protected;
Critically Endangered
['South Africa']
1
1
yes
0
1710700
1710700
1060
216
1060
ceyhan spined loach
Cobitis
Cobitidae
Freshwater
Turkey (Turkey-in-Asia);
\r\r\n The construction of reservoirs seems to be the major threat for this species. The Adat...
...
The distribution of <em>Cobitis turcica</em> can be split into five separate populations all of ...
<em>Cobitis turcica</em> has not been the target of any known conservation measures.
pet;pollution;
Endangered
['Falkland Islands']
1
2
yes
0
8232952
8232952
1352
1040
1352
NaN
Aloe
Aloaceae
Terrestrial
Somalia;
\r\r\n Threats affecting this species may be habitat degradation from herded animals as well ...
...
Recent surveys of the bastard quiver tree in the Richtersveld region of the Northern Cape Provin...
Bastard quiver trees are protected in South Africa and Namibia (10) and are listed on Appendix I...
environment;
cites;protected;
Critically Endangered
[]
0
1
yes
0
3600227
3600227
6817
454
6817
bornean banded langur
Presbytis
Cercopithecidae
Terrestrial
Brunei Darussalam; Indonesia (Kalimantan); Malaysia (Sarawak);
\r\r\n Habitat conversion has historically been the main threat to this species, resulting in...
...
Habitat loss is the main threat to the grizzled leaf monkey with the clearance of Indonesian rai...
Remaining populations of the grizzled leaf monkey occur in a number of protected areas in wester...
loss;hunting;
cites;protected;
Endangered
['India']
1
2
yes
0
267 rows × 35 columns
In [13]:
#em.to_csv_metadata(gold, './gold.csv')
#em.to_csv_metadata(DS, './unlabelled.csv')
File already exists at ./gold.csv; Overwriting it
Metadata file already exists at ./gold.metadata. Overwriting it
File already exists at ./unlabelled.csv; Overwriting it
Metadata file already exists at ./unlabelled.metadata. Overwriting it
Out[13]:
True
In [14]:
test_train = em.split_train_test(gold, train_proportion=0.7)
train = test_train['train']
test = test_train['test']
len(train)
Out[14]:
186
In [15]:
#em.to_csv_metadata(gold, './train.csv')
#em.to_csv_metadata(DS, './test.csv')
File already exists at ./train.csv; Overwriting it
Metadata file already exists at ./train.metadata. Overwriting it
File already exists at ./test.csv; Overwriting it
Metadata file already exists at ./test.metadata. Overwriting it
Out[15]:
True
In [21]:
em.to_csv_metadata(result, './candidate_set.csv')
File already exists at ./candidate_set.csv; Overwriting it
Metadata file already exists at ./candidate_set.metadata. Overwriting it
Out[21]:
True
In [22]:
result
Out[22]:
_id
ltable_id
rtable_id
ltable_name
ltable_genus
ltable_family
ltable_ecology
ltable_countries
ltable_threat_paragraph
ltable_conservation_paragraph
...
countries_countries_jac_dlm_dc0_dlm_dc0
countries_countries_mel
countries_countries_lev_dist
countries_countries_lev_sim
countries_countries_nmw
countries_countries_sw
country_count_country_count_exm
country_count_country_count_anm
country_count_country_count_lev_dist
country_count_country_count_lev_sim
25215
25215
1470
3
adelaide pigmy bluetongue skink, pygmy bluetongue
Tiliqua
Scincidae
NaN
Australia;
NaN
NaN
...
0.0
0.511818
21
0.160000
-10.0
3.0
0
0.5
1.0
0.0
75598
75598
4363
9
albanian water frog
Pelophylax
Ranidae
Terrestrial; Freshwater
Albania; Montenegro;
\r\r\n The major threat is drainage of wetland habitats and aquatic pollution of many waterwa...
["\n It is listed on Appendix III of the Bern Convention. 'Green frogs', including ", <em>R. ...
...
0.0
0.531032
21
0.160000
-2.0
10.0
1
1.0
0.0
1.0
75600
75600
4365
9
NaN
Pelophylax
Ranidae
Terrestrial; Freshwater
China;
\r\r\n The major threat is over-collecting for food; other threats include drought and water ...
['\n The Shapotou location is within a national nature reserve. There is a need to manage the...
...
0.0
0.455238
23
0.080000
-16.0
1.0
0
0.5
1.0
0.0
78778
78778
7543
9
karpathos frog
Pelophylax
Ranidae
Terrestrial; Freshwater
Greece;
\r\r\n The major threat is habitat loss and degradation of suitable aquatic habitats. Althoug...
['\n It is listed on Appendix III of the Bern Convention. It probably occurs in a protected a...
...
0.0
0.470000
22
0.120000
-14.0
2.0
0
0.5
1.0
0.0
83513
83513
4363
10
albanian water frog
Pelophylax
Ranidae
Terrestrial; Freshwater
Albania; Montenegro;
\r\r\n The major threat is drainage of wetland habitats and aquatic pollution of many waterwa...
["\n It is listed on Appendix III of the Bern Convention. 'Green frogs', including ", <em>R. ...
...
0.0
0.531032
21
0.160000
-2.0
10.0
1
1.0
0.0
1.0
83515
83515
4365
10
NaN
Pelophylax
Ranidae
Terrestrial; Freshwater
China;
\r\r\n The major threat is over-collecting for food; other threats include drought and water ...
['\n The Shapotou location is within a national nature reserve. There is a need to manage the...
...
0.0
0.455238
23
0.080000
-16.0
1.0
0
0.5
1.0
0.0
86693
86693
7543
10
karpathos frog
Pelophylax
Ranidae
Terrestrial; Freshwater
Greece;
\r\r\n The major threat is habitat loss and degradation of suitable aquatic habitats. Althoug...
['\n It is listed on Appendix III of the Bern Convention. It probably occurs in a protected a...
...
0.0
0.470000
22
0.120000
-14.0
2.0
0
0.5
1.0
0.0
105744
105744
2849
13
alexandria cycad, dune cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (Eastern Cape Province);
\r\r\n The major threat to this species is removal by collectors. This has been the main caus...
['\n This species is listed on Appendix I of the CITES Appendices. Populations occur within t...
...
0.0
0.470760
35
0.078947
-26.0
2.0
1
1.0
0.0
1.0
105745
105745
2850
13
chimanimani cycad
Encephalartos
Zamiaceae
Terrestrial
Mozambique;
\r\r\n This species is threatened due to over-collecting for ornamental purposes.\r\r\n\r\r\n...
['\n This species is listed on Appendix I of the CITES Appendices.\n\n \n ']
...
0.0
0.398148
11
0.083333
-2.0
1.0
1
1.0
0.0
1.0
105746
105746
2851
13
NaN
Encephalartos
Zamiaceae
Terrestrial
Tanzania, United Republic of;
\r\r\n This species is affected by too frequent fires, which may affect regeneration. Changes...
['\n This species is listed on Appendix I of the CITES Appendices. This species possibly occu...
...
0.0
0.366667
27
0.100000
-18.0
2.0
1
1.0
0.0
1.0
105747
105747
2852
13
umbeluzi cycad
Encephalartos
Zamiaceae
Terrestrial
Mozambique; Swaziland;
\r\r\n Illegal removal of plants from the wild has been recorded, even within reserves.\r\r\n...
['\n This species is listed on Appendix I of the CITES Appendices. Populations are protected ...
...
0.0
0.436393
20
0.130435
-11.0
2.0
0
0.5
1.0
0.0
109757
109757
6862
13
ngotshe cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (KwaZulu-Natal);
\r\r\n This species' occurrence at a single site means the plants are vulnerable to environme...
['\n This species is listed on Appendix I of the CITES Appendices. A large part of the popula...
...
0.0
0.429630
28
0.066667
-19.0
2.0
1
1.0
0.0
1.0
109758
109758
6863
13
waxen cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (KwaZulu-Natal);
\r\r\n This species has been severely affected due to over-collection of plants from the wild...
['\n This species is listed on Appendix I of the CITES Appendices.\n\n \n ']
...
0.0
0.429630
28
0.066667
-19.0
2.0
1
1.0
0.0
1.0
109759
109759
6864
13
blyde river cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (Limpopo Province - Regionally Extinct, Mpumalanga);
\r\r\n This species has suffered greatly as a result of over-collecting for ornamental purpos...
['\n This species is listed on Appendix I of the CITES Appendices. Most of the remaining plan...
...
0.0
0.459596
62
0.060606
-53.0
3.0
1
1.0
0.0
1.0
109760
109760
6865
13
wolkberg cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (Limpopo Province);
\r\r\n Illegal collection from wild populations has had a drastic effect on the number of pla...
['\n This species is listed on Appendix I of the CITES Appendices. This species possibly occu...
...
0.0
0.427609
30
0.090909
-21.0
1.0
1
1.0
0.0
1.0
109761
109761
6866
13
lillie cycad, lowveld cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (Limpopo Province);
\r\r\n Reproductive failure may occur if more mature individuals are removed from the populat...
['\n This species is listed on Appendix I of the CITES Appendices. The low granite hill falls...
...
0.0
0.427609
30
0.090909
-21.0
1.0
1
1.0
0.0
1.0
109762
109762
6867
13
NaN
Encephalartos
Zamiaceae
Terrestrial
Uganda;
\r\r\n No young plants or seedlings were seen and this could indicate that the pollinator cou...
['\n This species is listed on Appendix I of the CITES Appendices.\n\n \n ']
...
0.0
0.458333
8
0.111111
0.0
2.0
1
1.0
0.0
1.0
109763
109763
6868
13
heenans cycad, woolly cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (Mpumalanga); Swaziland;
\r\r\n This species is threatened due to over-collecting for ornamental purposes and the few ...
['\n This species is listed on Appendix I of the CITES Appendices. Populations are protected ...
...
0.0
0.516569
34
0.105263
-25.0
3.0
0
0.5
1.0
0.0
109764
109764
6869
13
venda cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (Limpopo Province);
\r\r\n This species is threatened due to over-collecting for ornamental purposes.\r\r\n\r\r\n...
['\n This species is listed on Appendix I of the CITES Appendices. Plants occur (or occurred)...
...
0.0
0.427609
30
0.090909
-21.0
1.0
1
1.0
0.0
1.0
109765
109765
6870
13
lydenburg cycad
Encephalartos
Zamiaceae
Terrestrial
South Africa (Limpopo Province);
\r\r\n This species has suffered much from the activities of collectors and in addition, larg...
['\n This species is listed on Appendix I of the CITES Appendices.\n\n \n ']
...
0.0
0.427609
30
0.090909
-21.0
1.0
1
1.0
0.0
1.0
109766
109766
6871
13
munchs cycad
Encephalartos
Zamiaceae
Terrestrial
Mozambique;
\r\r\n This species has been affected by over-collecting for ornamental purposes. Reproductiv...
['\n This species is listed on Appendix I of the CITES Appendices.\n\n \n ']
...
0.0
0.398148
11
0.083333
-2.0
1.0
1
1.0
0.0
1.0
109767
109767
6872
13
toothedcone cycad
Encephalartos
Zamiaceae
Terrestrial
Mozambique;
\r\r\n This species has been severely affected by over-collecting for ornamental purposes. Th...
['\n This species is listed on Appendix I of the CITES Appendices.\n\n \n ']
...
0.0
0.398148
11
0.083333
-2.0
1.0
1
1.0
0.0
1.0
109768
109768
6873
13
sclavos cycad
Encephalartos
Zamiaceae
Terrestrial
Tanzania, United Republic of;
\r\r\n The seeds are harvested for medicinal purposes by traditional healers and there is als...
['\n Occurs in the Shume Magamba Forest Reserve.', <br/>, <br/>, 'Listed in CITES Appendix I....
...
0.0
0.366667
27
0.100000
-18.0
2.0
1
1.0
0.0
1.0
109769
109769
6874
13
NaN
Encephalartos
Zamiaceae
Terrestrial
Tanzania, United Republic of;
\r\r\n Illegal collection of seedlings poses the main threat. Further fires could also impact...
['\n Occurs in the Kanga Forest Reserve.', <br/>, <br/>, 'Although listed in CITES Appendix I...
...
0.0
0.366667
27
0.100000
-18.0
2.0
1
1.0
0.0
1.0
166554
166554
339
21
blind swamp eel
Ophisternon
Synbranchidae
NaN
Mexico;
NaN
NaN
...
0.0
0.378472
30
0.062500
-22.0
2.0
0
0.5
1.0
0.0
174469
174469
339
22
blind swamp eel
Ophisternon
Synbranchidae
NaN
Mexico;
NaN
NaN
...
0.0
0.399854
17
0.105263
-9.0
1.0
0
0.5
1.0
0.0
182690
182690
645
23
NaN
Brookesia
Chamaeleonidae
Terrestrial
Madagascar;
\r\r\n The main threat to this species is logging for rosewood within Marojejy National Park ...
["\n This species is restricted to the Parc National de Marojejy, from where collection of ch...
...
0.0
0.455556
11
0.083333
-1.0
1.0
1
1.0
0.0
1.0
182694
182694
649
23
NaN
Brookesia
Chamaeleonidae
Terrestrial
Madagascar;
\r\r\n This species is threatened by the loss and degradation of humid forest due to slash-an...
['\n The species occurs in Réserve Spéciale Analamazaotra and Parc National Mantadia. A lar...
...
0.0
0.455556
11
0.083333
-1.0
1.0
1
1.0
0.0
1.0
182697
182697
652
23
NaN
Brookesia
Chamaeleonidae
Terrestrial
Madagascar;
\r\r\n The main threats to this species are the loss, degradation and fragmentation of lowlan...
['\n This species is known to occur in two protected areas (Parc National de Masoala and Rés...
...
0.0
0.455556
11
0.083333
-1.0
1.0
1
1.0
0.0
1.0
182700
182700
655
23
NaN
Brookesia
Chamaeleonidae
Terrestrial
Madagascar;
\r\r\n The major threats to Ankarafantsika include bush fires, cattle grazing, and deforestat...
["\n This species is protected under Malagasy law but collection from the wild is permitted w...
...
0.0
0.455556
11
0.083333
-1.0
1.0
1
1.0
0.0
1.0
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
9097111
9097111
2776
1149
germains langur, germains silver langur, indochinese lutung, indochinese silvered langur
Trachypithecus
Cercopithecidae
Terrestrial
Cambodia; Lao People's Democratic Republic; Myanmar; Thailand; Viet Nam;
\r\r\n The major threats to this species are hunting, mainly for subsistence use and traditio...
['\n This species is listed on CITES Appendix II. It has been recorded from Phu Quoc National...
...
0.0
0.429016
65
0.109589
-43.0
3.0
0
0.4
1.0
0.0
9100153
9100153
5818
1149
delacours langur
Trachypithecus
Cercopithecidae
Terrestrial
Viet Nam;
\r\r\n Hunting for the purposes of traditional "medicine" is the primary threat facing this s...
["\n This species is currently listed only as CITES Appendix II. It is considered 'endangered...
...
0.0
0.367677
19
0.136364
-9.0
2.0
0
0.5
1.0
0.0
9105025
9105025
2775
1150
shortridges capped langur, shortridges langur
Trachypithecus
Cercopithecidae
Terrestrial
China; Myanmar;
\r\r\n These animals are hunted for food and traditional â??medicine,â?? sometimes as illegal...
['\n This species is listed in CITES Appendix I. In Myanmar it is a protected species under t...
...
0.0
0.435606
14
0.125000
-3.0
1.0
0
0.5
1.0
0.0
9105026
9105026
2776
1150
germains langur, germains silver langur, indochinese lutung, indochinese silvered langur
Trachypithecus
Cercopithecidae
Terrestrial
Cambodia; Lao People's Democratic Republic; Myanmar; Thailand; Viet Nam;
\r\r\n The major threats to this species are hunting, mainly for subsistence use and traditio...
['\n This species is listed on CITES Appendix II. It has been recorded from Phu Quoc National...
...
0.0
0.410751
68
0.068493
-57.0
2.0
0
0.2
1.0
0.0
9108068
9108068
5818
1150
delacours langur
Trachypithecus
Cercopithecidae
Terrestrial
Viet Nam;
\r\r\n Hunting for the purposes of traditional "medicine" is the primary threat facing this s...
["\n This species is currently listed only as CITES Appendix II. It is considered 'endangered...
...
0.0
0.396970
11
0.000000
-1.0
1.0
1
1.0
0.0
1.0
9118003
9118003
7838
1151
delta green ground beetle
Elaphrus
Carabidae
NaN
United States;
NaN
NaN
...
0.0
0.441204
72
0.100000
-57.0
4.0
0
0.2
1.0
0.0
9125918
9125918
7838
1152
delta green ground beetle
Elaphrus
Carabidae
NaN
United States;
NaN
NaN
...
0.0
0.441204
72
0.100000
-57.0
4.0
0
0.2
1.0
0.0
9133833
9133833
7838
1153
delta green ground beetle
Elaphrus
Carabidae
NaN
United States;
NaN
NaN
...
0.0
0.618519
11
0.388889
4.0
7.0
1
1.0
0.0
1.0
9137159
9137159
3249
1154
NaN
Trachycystis
Charopidae
Terrestrial
South Africa (KwaZulu-Natal);
\r\r\n Both forests are formally conserved areas under the control of KZN Wildlife. As such t...
['\n Although both forests are formally protected areas, the degree of protection afforded by...
...
0.0
0.381481
28
0.066667
-10.0
2.0
1
1.0
0.0
1.0
9141009
9141009
7099
1154
dlinza forest pinwheel
Trachycystis
Charopidae
Terrestrial
South Africa (KwaZulu-Natal);
\r\r\n The Dlinza Forest is a formally conserved area under the control of KZN Wildlife. As s...
['\n Although the forest is a formally conserved area, supported by an enthusiastic local com...
...
0.0
0.381481
28
0.066667
-10.0
2.0
1
1.0
0.0
1.0
9141010
9141010
7100
1154
NaN
Trachycystis
Charopidae
Terrestrial
South Africa (KwaZulu-Natal);
\r\r\n Nkandla Forest is a formally conserved area under the control of KZN Wildlife. As such...
['\n Although the forest is a formally conserved area, it is situated in a remote region and ...
...
0.0
0.381481
28
0.066667
-10.0
2.0
1
1.0
0.0
1.0
9145074
9145074
3249
1155
NaN
Trachycystis
Charopidae
Terrestrial
South Africa (KwaZulu-Natal);
\r\r\n Both forests are formally conserved areas under the control of KZN Wildlife. As such t...
['\n Although both forests are formally protected areas, the degree of protection afforded by...
...
0.0
0.381481
28
0.066667
-10.0
2.0
1
1.0
0.0
1.0
9148924
9148924
7099
1155
dlinza forest pinwheel
Trachycystis
Charopidae
Terrestrial
South Africa (KwaZulu-Natal);
\r\r\n The Dlinza Forest is a formally conserved area under the control of KZN Wildlife. As s...
['\n Although the forest is a formally conserved area, supported by an enthusiastic local com...
...
0.0
0.381481
28
0.066667
-10.0
2.0
1
1.0
0.0
1.0
9148925
9148925
7100
1155
NaN
Trachycystis
Charopidae
Terrestrial
South Africa (KwaZulu-Natal);
\r\r\n Nkandla Forest is a formally conserved area under the control of KZN Wildlife. As such...
['\n Although the forest is a formally conserved area, it is situated in a remote region and ...
...
0.0
0.381481
28
0.066667
-10.0
2.0
1
1.0
0.0
1.0
9157066
9157066
7326
1156
NaN
Adetomyrma
Formicidae
NaN
Madagascar;
\r\r\n Habitat is extremely threatened by settlers (D. Agosti pers. comm. 1995).\r\r\n\r\r\n ...
NaN
...
0.0
0.296296
11
0.083333
-2.0
1.0
1
1.0
0.0
1.0
9164981
9164981
7326
1157
NaN
Adetomyrma
Formicidae
NaN
Madagascar;
\r\r\n Habitat is extremely threatened by settlers (D. Agosti pers. comm. 1995).\r\r\n\r\r\n ...
NaN
...
0.0
0.383333
15
0.000000
-3.0
1.0
1
1.0
0.0
1.0
9169927
9169927
4357
1158
patzcuaro frog
Lithobates
Ranidae
Freshwater
Mexico;
\r\r\n This species is locally exploited for human consumption, particularly around the Lake ...
['\n It is not known from any protected areas. The effect of the local trade on the populatio...
...
0.0
0.397222
14
0.066667
-6.0
1.0
1
1.0
0.0
1.0
9169928
9169928
4358
1158
moores frog
Lithobates
Ranidae
Terrestrial; Freshwater
Mexico;
\r\r\n The major threat to this species is habitat loss and disturbance due to clear-cutting ...
['\n It is not known from any protected areas, and there is a need for immediate protection o...
...
0.0
0.397222
14
0.066667
-6.0
1.0
1
1.0
0.0
1.0
9171058
9171058
5488
1158
ramsey canyon leopard frog
Lithobates
Ranidae
Terrestrial; Freshwater
United States;
\r\r\n Chytrid fungus has been found in dead frogs at several sites that have declined and th...
["\n It is protected in The Nature Conservancy's Ramsey Canyon Preserve and the Coronado Nati...
...
0.0
0.466667
13
0.133333
2.0
2.0
1
1.0
0.0
1.0
9171059
9171059
5489
1158
tlalocs leopard frog
Lithobates
Ranidae
Freshwater
Mexico;
\r\r\n The rapid and intense growth of Mexico City with its high rate of urbanization has cau...
['\n It seems that no individuals of this species survive in the wild, but an intensive surve...
...
0.0
0.397222
14
0.066667
-6.0
1.0
1
1.0
0.0
1.0
9173116
9173116
7546
1158
lago de las minas frog
Lithobates
Ranidae
Terrestrial; Freshwater
Mexico;
\r\r\n The water-level in the lake has dropped approximately 2m since the 1950s, principally ...
['\n The species is not present in any protected areas, and maintenance of the vegetation sur...
...
0.0
0.397222
14
0.066667
-6.0
1.0
1
1.0
0.0
1.0
9173120
9173120
7550
1158
guerreran leopard frog
Lithobates
Ranidae
Terrestrial; Freshwater
Mexico;
\r\r\n Although generally affected by habitat loss, the most likely cause of the extinction o...
['\n A survey of the Omiltemi State Park is recommended in order to confirm whether or not th...
...
0.0
0.397222
14
0.066667
-6.0
1.0
1
1.0
0.0
1.0
9173121
9173121
7551
1158
puebla frog
Lithobates
Ranidae
Terrestrial; Freshwater
Mexico;
\r\r\n The disappearance of these permanent rivers has contributed to its decline, and perhap...
['\n The species is not known to occur in any protected areas. An extensive search within the...
...
0.0
0.397222
14
0.066667
-6.0
1.0
1
1.0
0.0
1.0
9177842
9177842
4357
1159
patzcuaro frog
Lithobates
Ranidae
Freshwater
Mexico;
\r\r\n This species is locally exploited for human consumption, particularly around the Lake ...
['\n It is not known from any protected areas. The effect of the local trade on the populatio...
...
0.0
0.384259
25
0.074074
-17.0
1.0
0
0.5
1.0
0.0
9177843
9177843
4358
1159
moores frog
Lithobates
Ranidae
Terrestrial; Freshwater
Mexico;
\r\r\n The major threat to this species is habitat loss and disturbance due to clear-cutting ...
['\n It is not known from any protected areas, and there is a need for immediate protection o...
...
0.0
0.384259
25
0.074074
-17.0
1.0
0
0.5
1.0
0.0
9178973
9178973
5488
1159
ramsey canyon leopard frog
Lithobates
Ranidae
Terrestrial; Freshwater
United States;
\r\r\n Chytrid fungus has been found in dead frogs at several sites that have declined and th...
["\n It is protected in The Nature Conservancy's Ramsey Canyon Preserve and the Coronado Nati...
...
0.0
0.401852
22
0.185185
-7.0
3.0
0
0.5
1.0
0.0
9178974
9178974
5489
1159
tlalocs leopard frog
Lithobates
Ranidae
Freshwater
Mexico;
\r\r\n The rapid and intense growth of Mexico City with its high rate of urbanization has cau...
['\n It seems that no individuals of this species survive in the wild, but an intensive surve...
...
0.0
0.384259
25
0.074074
-17.0
1.0
0
0.5
1.0
0.0
9181031
9181031
7546
1159
lago de las minas frog
Lithobates
Ranidae
Terrestrial; Freshwater
Mexico;
\r\r\n The water-level in the lake has dropped approximately 2m since the 1950s, principally ...
['\n The species is not present in any protected areas, and maintenance of the vegetation sur...
...
0.0
0.384259
25
0.074074
-17.0
1.0
0
0.5
1.0
0.0
9181035
9181035
7550
1159
guerreran leopard frog
Lithobates
Ranidae
Terrestrial; Freshwater
Mexico;
\r\r\n Although generally affected by habitat loss, the most likely cause of the extinction o...
['\n A survey of the Omiltemi State Park is recommended in order to confirm whether or not th...
...
0.0
0.384259
25
0.074074
-17.0
1.0
0
0.5
1.0
0.0
9181036
9181036
7551
1159
puebla frog
Lithobates
Ranidae
Terrestrial; Freshwater
Mexico;
\r\r\n The disappearance of these permanent rivers has contributed to its decline, and perhap...
['\n The species is not known to occur in any protected areas. An extensive search within the...
...
0.0
0.384259
25
0.074074
-17.0
1.0
0
0.5
1.0
0.0
2578 rows × 48 columns
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
Content source: andrewedstrom/cs638project
Similar notebooks: