andrea.mannocci
/
registries_analysis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

renaming notebooks

This commit is contained in:
Andrea Mannocci 2022-03-17 10:33:11 +01:00
parent 9b7c2efc5d
commit c6e079d90b
6 changed files with 3970 additions and 2561 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2089
notebooks/01.1-exploration-fairsharing.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

0
notebooks/01.1-exploration-re3data.ipynb → notebooks/01.2-exploration-re3data.ipynb
View File

0
notebooks/01.2-exploration-opendoar.ipynb → notebooks/01.3-exploration-opendoar.ipynb
View File

1485
notebooks/01.4-exploration-fairsharing.ipynb
View File

File diff suppressed because it is too large Load Diff

140
notebooks/01.3-exploration-roar.ipynb → notebooks/01.4-exploration-roar.ipynb
View File

@ -1949,15 +1949,15 @@
" <tr>\n",
" <th>1</th>\n",
" <td>{nan, 633}</td>\n",
" <td>{archive, nan}</td>\n",
" <td>{1, nan}</td>\n",
" <td>{nan, archive}</td>\n",
" <td>{nan, 1}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan, disk0/00/00/00/01}</td>\n",
" <td>{nan, 2010-01-06 13:43:48}</td>\n",
" <td>{nan, 2011-07-18 05:40:07}</td>\n",
" <td>{nan, 2010-01-06 13:43:48}</td>\n",
" <td>{nan, subject}</td>\n",
" <td>{subject, nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan, show}</td>\n",
@ -2009,7 +2009,7 @@
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{opendoar, celestial}</td>\n",
" <td>{celestial, opendoar}</td>\n",
" <td>{669, 58}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
@ -2026,13 +2026,13 @@
" <tr>\n",
" <th>10</th>\n",
" <td>{nan, 511}</td>\n",
" <td>{archive, nan}</td>\n",
" <td>{1, nan}</td>\n",
" <td>{nan, archive}</td>\n",
" <td>{nan, 1}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{disk0/00/00/00/10, nan}</td>\n",
" <td>{nan, disk0/00/00/00/10}</td>\n",
" <td>{nan, 2010-01-06 13:43:48}</td>\n",
" <td>{2011-07-18 05:40:13, nan}</td>\n",
" <td>{nan, 2011-07-18 05:40:13}</td>\n",
" <td>{nan, 2010-01-06 13:43:48}</td>\n",
" <td>{nan, institutional}</td>\n",
" <td>{nan}</td>\n",
@ -2056,7 +2056,7 @@
" <td>{nan}</td>\n",
" <td>{nan, http://www.diva-portal.org/mdh/}</td>\n",
" <td>{nan, Academic Archive On-line (Mälardalen Uni...</td>\n",
" <td>{nan, http://www.diva-portal.org/oai/mdh/OAI}</td>\n",
" <td>{http://www.diva-portal.org/oai/mdh/OAI, nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
@ -2066,10 +2066,10 @@
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan, se}</td>\n",
" <td>{Uppsala, nan}</td>\n",
" <td>{se, nan}</td>\n",
" <td>{nan, Uppsala}</td>\n",
" <td>{nan, 59.8667}</td>\n",
" <td>{17.6333, nan}</td>\n",
" <td>{nan, 17.6333}</td>\n",
" <td>{nan, diva}</td>\n",
" <td>{nan, geoname_2_SE}</td>\n",
" <td>{nan, other}</td>\n",
@ -2086,8 +2086,8 @@
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{opendoar, celestial}</td>\n",
" <td>{258, 526}</td>\n",
" <td>{celestial, opendoar}</td>\n",
" <td>{526, 258}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
@ -2180,15 +2180,15 @@
" <tr>\n",
" <th>10001</th>\n",
" <td>{nan, 20}</td>\n",
" <td>{archive, nan}</td>\n",
" <td>{nan, archive}</td>\n",
" <td>{nan, 91}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan, disk0/00/01/00/01}</td>\n",
" <td>{nan, 2015-08-08 14:52:11}</td>\n",
" <td>{2015-08-08 14:52:11, nan}</td>\n",
" <td>{nan, 2016-03-21 19:44:01}</td>\n",
" <td>{nan, 2015-08-08 14:52:11}</td>\n",
" <td>{nan, subject}</td>\n",
" <td>{2015-08-08 14:52:11, nan}</td>\n",
" <td>{subject, nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan, show}</td>\n",
@ -2210,16 +2210,16 @@
" <td>{nan}</td>\n",
" <td>{nan, http://edoc.sub.uni-hamburg.de/klimawand...</td>\n",
" <td>{nan, Klimawandel Dokumentenserver}</td>\n",
" <td>{http://edoc.sub.uni-hamburg.de/klimawandel/oa...</td>\n",
" <td>{nan, http://edoc.sub.uni-hamburg.de/klimawand...</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan, The \"Documentenserver Klimawandel\" (Repo...</td>\n",
" <td>{The \"Documentenserver Klimawandel\" (Repositor...</td>\n",
" <td>{nan, TRUE}</td>\n",
" <td>{nan, TRUE}</td>\n",
" <td>{nan, TRUE}</td>\n",
" <td>{nan, Climate Service Center 2.0, Helmholtz-Ze...</td>\n",
" <td>{nan, http://www.climateservicecenter.de/, htt...</td>\n",
" <td>{KLIMZUG projects, nan, Climate Service Center...</td>\n",
" <td>{http://www.climateservicecenter.de/, http://w...</td>\n",
" <td>{nan, de}</td>\n",
" <td>{nan, Hamburg}</td>\n",
" <td>{nan, 53.5511}</td>\n",
@ -2227,7 +2227,7 @@
" <td>{nan, opus}</td>\n",
" <td>{nan, geoname_2_DE}</td>\n",
" <td>{nan, other}</td>\n",
" <td>{G1, GE, HD, S1, GF}</td>\n",
" <td>{GF, GE, G1, HD, S1}</td>\n",
" <td>{nan, 2015-07-02 08:08:31}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
@ -2240,8 +2240,8 @@
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan, opendoar, celestial}</td>\n",
" <td>{3408, nan, 5881}</td>\n",
" <td>{nan, celestial, opendoar}</td>\n",
" <td>{nan, 5881, 3408}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
" <td>{nan}</td>\n",
@ -2338,34 +2338,34 @@
"text/plain": [
" rev_number eprint_status userid importid source \\\n",
"eprintid \n",
"1 {nan, 633} {archive, nan} {1, nan} {nan} {nan} \n",
"10 {nan, 511} {archive, nan} {1, nan} {nan} {nan} \n",
"1 {nan, 633} {nan, archive} {nan, 1} {nan} {nan} \n",
"10 {nan, 511} {nan, archive} {nan, 1} {nan} {nan} \n",
"1000 {274} {archive} {1} {nan} {nan} \n",
"10001 {nan, 20} {archive, nan} {nan, 91} {nan} {nan} \n",
"10001 {nan, 20} {nan, archive} {nan, 91} {nan} {nan} \n",
"10008 {11} {archive} {404} {nan} {nan} \n",
"\n",
" dir datestamp \\\n",
"eprintid \n",
"1 {nan, disk0/00/00/00/01} {nan, 2010-01-06 13:43:48} \n",
"10 {disk0/00/00/00/10, nan} {nan, 2010-01-06 13:43:48} \n",
"10 {nan, disk0/00/00/00/10} {nan, 2010-01-06 13:43:48} \n",
"1000 {disk0/00/00/10/00} {2010-01-06 13:45:01} \n",
"10001 {nan, disk0/00/01/00/01} {nan, 2015-08-08 14:52:11} \n",
"10001 {nan, disk0/00/01/00/01} {2015-08-08 14:52:11, nan} \n",
"10008 {disk0/00/01/00/08} {2015-08-08 14:52:26} \n",
"\n",
" lastmod status_changed \\\n",
"eprintid \n",
"1 {nan, 2011-07-18 05:40:07} {nan, 2010-01-06 13:43:48} \n",
"10 {2011-07-18 05:40:13, nan} {nan, 2010-01-06 13:43:48} \n",
"10 {nan, 2011-07-18 05:40:13} {nan, 2010-01-06 13:43:48} \n",
"1000 {2011-07-06 08:21:21} {2010-01-06 13:45:01} \n",
"10001 {nan, 2016-03-21 19:44:01} {nan, 2015-08-08 14:52:11} \n",
"10001 {nan, 2016-03-21 19:44:01} {2015-08-08 14:52:11, nan} \n",
"10008 {2016-03-21 19:43:51} {2015-08-08 14:52:26} \n",
"\n",
" type succeeds commentary metadata_visibility \\\n",
"eprintid \n",
"1 {nan, subject} {nan} {nan} {nan, show} \n",
"1 {subject, nan} {nan} {nan} {nan, show} \n",
"10 {nan, institutional} {nan} {nan} {nan, show} \n",
"1000 {subject} {nan} {nan} {show} \n",
"10001 {nan, subject} {nan} {nan} {nan, show} \n",
"10001 {subject, nan} {nan} {nan} {nan, show} \n",
"10008 {institutional} {nan} {nan} {show} \n",
"\n",
" latitude longitude relation_type relation_uri item_issues_id \\\n",
@ -2419,9 +2419,9 @@
" oai_pmh sword_endpoint \\\n",
"eprintid \n",
"1 {nan, http://archivesic.ccsd.cnrs.fr/oai/oai.php} {nan} \n",
"10 {nan, http://www.diva-portal.org/oai/mdh/OAI} {nan} \n",
"10 {http://www.diva-portal.org/oai/mdh/OAI, nan} {nan} \n",
"1000 {nan} {nan} \n",
"10001 {http://edoc.sub.uni-hamburg.de/klimawandel/oa... {nan} \n",
"10001 {nan, http://edoc.sub.uni-hamburg.de/klimawand... {nan} \n",
"10008 {http://creativematter.skidmore.edu/do/oai/} {nan} \n",
"\n",
" rss_feed twitter_feed \\\n",
@ -2437,7 +2437,7 @@
"1 {nan} {nan} \n",
"10 {nan} {nan, TRUE} \n",
"1000 {nan} {TRUE} \n",
"10001 {nan, The \"Documentenserver Klimawandel\" (Repo... {nan, TRUE} \n",
"10001 {The \"Documentenserver Klimawandel\" (Repositor... {nan, TRUE} \n",
"10008 {Welcome to Creative Matter, a repository for ... {TRUE} \n",
"\n",
" open_access mandate \\\n",
@ -2453,21 +2453,21 @@
"1 {nan} \n",
"10 {nan} \n",
"1000 {nan} \n",
"10001 {nan, Climate Service Center 2.0, Helmholtz-Ze... \n",
"10001 {KLIMZUG projects, nan, Climate Service Center... \n",
"10008 {Skidmore College} \n",
"\n",
" organisation_home_page location_country \\\n",
"eprintid \n",
"1 {nan} {nan, fr} \n",
"10 {nan} {nan, se} \n",
"10 {nan} {se, nan} \n",
"1000 {nan} {pt} \n",
"10001 {nan, http://www.climateservicecenter.de/, htt... {nan, de} \n",
"10001 {http://www.climateservicecenter.de/, http://w... {nan, de} \n",
"10008 {http://www.skidmore.edu/} {us} \n",
"\n",
" location_city location_latitude location_longitude \\\n",
"eprintid \n",
"1 {nan} {nan} {nan} \n",
"10 {Uppsala, nan} {nan, 59.8667} {17.6333, nan} \n",
"10 {nan, Uppsala} {nan, 59.8667} {nan, 17.6333} \n",
"1000 {Bellevue, WA} {47.6034} {-122.155} \n",
"10001 {nan, Hamburg} {nan, 53.5511} {nan, 9.9937} \n",
"10008 {Saratoga Springs} {43.0961} {-73.7818} \n",
@ -2485,7 +2485,7 @@
"1 {nan} {nan, 2002-05-17 19:24:41} {nan} {nan} \n",
"10 {nan} {nan, 2005-12-08 13:15:22} {nan} {nan} \n",
"1000 {nan} {2006-05-04 10:48:14} {nan} {nan} \n",
"10001 {G1, GE, HD, S1, GF} {nan, 2015-07-02 08:08:31} {nan} {nan} \n",
"10001 {GF, GE, G1, HD, S1} {nan, 2015-07-02 08:08:31} {nan} {nan} \n",
"10008 {nan} {2015-07-06 17:35:50} {nan} {nan} \n",
"\n",
" activity_low activity_medium activity_high recordcount \\\n",
@ -2514,10 +2514,10 @@
"\n",
" registry_name registry_id submit_to \\\n",
"eprintid \n",
"1 {opendoar, celestial} {669, 58} {nan} \n",
"10 {opendoar, celestial} {258, 526} {nan} \n",
"1 {celestial, opendoar} {669, 58} {nan} \n",
"10 {celestial, opendoar} {526, 258} {nan} \n",
"1000 {nan} {nan} {nan} \n",
"10001 {nan, opendoar, celestial} {3408, nan, 5881} {nan} \n",
"10001 {nan, celestial, opendoar} {nan, 5881, 3408} {nan} \n",
"10008 {celestial} {5882} {nan} \n",
"\n",
" submitted_to_name submitted_to_done webometrics_rank \\\n",
@ -2798,7 +2798,7 @@
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[opendoar, celestial]</td>\n",
" <td>[celestial, opendoar]</td>\n",
" <td>[669, 58]</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
@ -2875,8 +2875,8 @@
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[opendoar, celestial]</td>\n",
" <td>[258, 526]</td>\n",
" <td>[celestial, opendoar]</td>\n",
" <td>[526, 258]</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
@ -3007,7 +3007,7 @@
" <td>TRUE</td>\n",
" <td>TRUE</td>\n",
" <td>TRUE</td>\n",
" <td>[Climate Service Center 2.0, Helmholtz-Zentrum...</td>\n",
" <td>[KLIMZUG projects, Climate Service Center 2.0,...</td>\n",
" <td>[http://www.climateservicecenter.de/, http://w...</td>\n",
" <td>de</td>\n",
" <td>Hamburg</td>\n",
@ -3016,7 +3016,7 @@
" <td>opus</td>\n",
" <td>geoname_2_DE</td>\n",
" <td>other</td>\n",
" <td>[G1, S1, GF, GE, HD]</td>\n",
" <td>[GE, GF, G1, HD, S1]</td>\n",
" <td>2015-07-02 08:08:31</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
@ -3029,8 +3029,8 @@
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[opendoar, celestial]</td>\n",
" <td>[3408, 5881]</td>\n",
" <td>[celestial, opendoar]</td>\n",
" <td>[5881, 3408]</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
@ -3234,7 +3234,7 @@
"1 NaN \n",
"10 NaN \n",
"1000 NaN \n",
"10001 [Climate Service Center 2.0, Helmholtz-Zentrum... \n",
"10001 [KLIMZUG projects, Climate Service Center 2.0,... \n",
"10008 Skidmore College \n",
"\n",
" organisation_home_page location_country \\\n",
@ -3258,7 +3258,7 @@
"1 geoname_2_FR other NaN 2002-05-17 19:24:41 \n",
"10 geoname_2_SE other NaN 2005-12-08 13:15:22 \n",
"1000 geoname_2_PT other NaN 2006-05-04 10:48:14 \n",
"10001 geoname_2_DE other [G1, S1, GF, GE, HD] 2015-07-02 08:08:31 \n",
"10001 geoname_2_DE other [GE, GF, G1, HD, S1] 2015-07-02 08:08:31 \n",
"10008 geoname_2_US other NaN 2015-07-06 17:35:50 \n",
"\n",
" note suggestions activity_low activity_medium activity_high \\\n",
@ -3287,10 +3287,10 @@
"\n",
" registry_name registry_id submit_to submitted_to_name \\\n",
"eprintid \n",
"1 [opendoar, celestial] [669, 58] NaN NaN \n",
"10 [opendoar, celestial] [258, 526] NaN NaN \n",
"1 [celestial, opendoar] [669, 58] NaN NaN \n",
"10 [celestial, opendoar] [526, 258] NaN NaN \n",
"1000 NaN NaN NaN NaN \n",
"10001 [opendoar, celestial] [3408, 5881] NaN NaN \n",
"10001 [celestial, opendoar] [5881, 3408] NaN NaN \n",
"10008 celestial 5882 NaN NaN \n",
"\n",
" submitted_to_done webometrics_rank webometrics_size \\\n",
@ -3505,8 +3505,8 @@
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>[opendoar, celestial, roarmap]</td>\n",
" <td>[166, 1106, 69]</td>\n",
" <td>[roarmap, celestial, opendoar]</td>\n",
" <td>[69, 166, 1106]</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
@ -3573,7 +3573,7 @@
"4259 NaN NaN NaN \n",
"\n",
" registry_name registry_id submit_to \\\n",
"4259 [opendoar, celestial, roarmap] [166, 1106, 69] NaN \n",
"4259 [roarmap, celestial, opendoar] [69, 166, 1106] NaN \n",
"\n",
" submitted_to_name submitted_to_done webometrics_rank webometrics_size \\\n",
"4259 NaN NaN 1 6 \n",
@ -3831,7 +3831,7 @@
" <td>31</td>\n",
" <td>126</td>\n",
" <td>53</td>\n",
" <td>938</td>\n",
" <td>937</td>\n",
" <td>4898</td>\n",
" <td>210</td>\n",
" <td>173</td>\n",
@ -3844,8 +3844,8 @@
" <td>118</td>\n",
" <td>134</td>\n",
" <td>117</td>\n",
" <td>9</td>\n",
" <td>4259</td>\n",
" <td>7</td>\n",
" <td>4260</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
@ -3922,9 +3922,9 @@
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>[opendoar, celestial]</td>\n",
" <td>[celestial, opendoar]</td>\n",
" <td>[1879, 2246]</td>\n",
" <td>[opendoar, celestial, roarmap]</td>\n",
" <td>[roarmap, celestial, opendoar]</td>\n",
" <td>opendoar</td>\n",
" <td>2021-01-25</td>\n",
" <td>24</td>\n",
@ -4775,7 +4775,7 @@
"\n",
" software geoname version subjects date \\\n",
"count 4700 4730 5444 1289 5429 \n",
"unique 31 126 53 938 4898 \n",
"unique 31 126 53 937 4898 \n",
"top dspace geoname_2_US other K1 2006-05-04 10:48:14 \n",
"freq 2341 845 4841 53 99 \n",
"mean NaN NaN NaN NaN NaN \n",
@ -4840,8 +4840,8 @@
"\n",
" fulltexts_docs fulltexts_rtotal fulltexts_rdocs registry_name \\\n",
"count 258 270 258 4605 \n",
"unique 118 134 117 9 \n",
"top 0 0 0 [opendoar, celestial] \n",
"unique 118 134 117 7 \n",
"top 0 0 0 [celestial, opendoar] \n",
"freq 114 113 114 2106 \n",
"mean NaN NaN NaN NaN \n",
"std NaN NaN NaN NaN \n",
@ -4853,8 +4853,8 @@
"\n",
" registry_id submit_to submitted_to_name \\\n",
"count 4580 375 205 \n",
"unique 4259 7 1 \n",
"top [1879, 2246] [opendoar, celestial, roarmap] opendoar \n",
"unique 4260 7 1 \n",
"top [1879, 2246] [roarmap, celestial, opendoar] opendoar \n",
"freq 4 119 205 \n",
"mean NaN NaN NaN \n",
"std NaN NaN NaN \n",

2705
notebooks/02-subjects&geographic.ipynb
View File

File diff suppressed because one or more lines are too long