:2: PerformanceWarning:\n",
"\n",
"DataFrame is highly fragmented. This is usually the result of calling `frame.insert` many times, which has poor performance. Consider using pd.concat instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
"\n"
@@ -10822,7 +10918,7 @@
" [eprints, nan, nan] | \n",
" [geoname_2_MX, nan, nan] | \n",
" [3.3.15 eps, nan, nan] | \n",
- " [[H1, HX, GF, HC, HD, HT, HB, HM, G1, JA, T1, ... | \n",
+ " [[HB, HD, HT, GF, HC, HF, HJ, HN, HX, H1, HG, ... | \n",
" [2012-02-03 05:18:16, nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
@@ -10835,7 +10931,7 @@
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
- " [[celestial, opendoar], nan, nan] | \n",
+ " [[opendoar, celestial], nan, nan] | \n",
" [[4818, 2429], nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
@@ -11018,8 +11114,8 @@
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
- " [nan, nan, [celestial, opendoar]] | \n",
- " [nan, nan, [5621, 3087]] | \n",
+ " [nan, nan, [opendoar, celestial]] | \n",
+ " [nan, nan, [3087, 5621]] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
@@ -11201,8 +11297,8 @@
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
- " [nan, [celestial, opendoar], [celestial, opend... | \n",
- " [nan, [4672, 2318], [4672, 2318]] | \n",
+ " [nan, [opendoar, celestial], [opendoar, celest... | \n",
+ " [nan, [2318, 4672], [2318, 4672]] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
@@ -11384,7 +11480,7 @@
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
- " [[celestial, opendoar], [celestial, opendoar],... | \n",
+ " [[opendoar, celestial], [opendoar, celestial],... | \n",
" [[1509, 1430], [1509, 1430], nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
@@ -11567,8 +11663,8 @@
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
- " [celestial, [celestial, opendoar], nan] | \n",
- " [4668, [2306, 4668], nan] | \n",
+ " [celestial, [opendoar, celestial], nan] | \n",
+ " [4668, [4668, 2306], nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
" [nan, nan, nan] | \n",
@@ -12156,7 +12252,7 @@
"4 [geoname_2_CN, geoname_2_CN, nan] [other, other, nan] \n",
"\n",
" roar_subjects \\\n",
- "0 [[H1, HX, GF, HC, HD, HT, HB, HM, G1, JA, T1, ... \n",
+ "0 [[HB, HD, HT, GF, HC, HF, HJ, HN, HX, H1, HG, ... \n",
"1 [nan, nan, nan] \n",
"2 [nan, nan, nan] \n",
"3 [nan, nan, nan] \n",
@@ -12191,18 +12287,18 @@
"4 [nan, nan, nan] [nan, nan, nan] [nan, nan, nan] \n",
"\n",
" roar_fulltexts_rdocs roar_registry_name \\\n",
- "0 [nan, nan, nan] [[celestial, opendoar], nan, nan] \n",
- "1 [nan, nan, nan] [nan, nan, [celestial, opendoar]] \n",
- "2 [nan, nan, nan] [nan, [celestial, opendoar], [celestial, opend... \n",
- "3 [nan, nan, nan] [[celestial, opendoar], [celestial, opendoar],... \n",
- "4 [nan, nan, nan] [celestial, [celestial, opendoar], nan] \n",
+ "0 [nan, nan, nan] [[opendoar, celestial], nan, nan] \n",
+ "1 [nan, nan, nan] [nan, nan, [opendoar, celestial]] \n",
+ "2 [nan, nan, nan] [nan, [opendoar, celestial], [opendoar, celest... \n",
+ "3 [nan, nan, nan] [[opendoar, celestial], [opendoar, celestial],... \n",
+ "4 [nan, nan, nan] [celestial, [opendoar, celestial], nan] \n",
"\n",
" roar_registry_id roar_submit_to roar_submitted_to_name \\\n",
"0 [[4818, 2429], nan, nan] [nan, nan, nan] [nan, nan, nan] \n",
- "1 [nan, nan, [5621, 3087]] [nan, nan, nan] [nan, nan, nan] \n",
- "2 [nan, [4672, 2318], [4672, 2318]] [nan, nan, nan] [nan, nan, nan] \n",
+ "1 [nan, nan, [3087, 5621]] [nan, nan, nan] [nan, nan, nan] \n",
+ "2 [nan, [2318, 4672], [2318, 4672]] [nan, nan, nan] [nan, nan, nan] \n",
"3 [[1509, 1430], [1509, 1430], nan] [nan, nan, nan] [nan, nan, nan] \n",
- "4 [4668, [2306, 4668], nan] [nan, nan, nan] [nan, nan, nan] \n",
+ "4 [4668, [4668, 2306], nan] [nan, nan, nan] [nan, nan, nan] \n",
"\n",
" roar_submitted_to_done roar_webometrics_rank roar_webometrics_size \\\n",
"0 [nan, nan, nan] [nan, nan, nan] [nan, nan, nan] \n",
@@ -12233,7 +12329,7 @@
"4 [nan, nan, nan] [roar_4379, roar_4266, nan] {OpenDOAR, roar} "
]
},
- "execution_count": 25,
+ "execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
@@ -12246,18 +12342,18 @@
},
{
"cell_type": "code",
- "execution_count": 26,
+ "execution_count": 29,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
- ":1: PerformanceWarning:\n",
+ ":1: PerformanceWarning:\n",
"\n",
"DataFrame is highly fragmented. This is usually the result of calling `frame.insert` many times, which has poor performance. Consider using pd.concat instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
"\n",
- ":2: PerformanceWarning:\n",
+ ":2: PerformanceWarning:\n",
"\n",
"DataFrame is highly fragmented. This is usually the result of calling `frame.insert` many times, which has poor performance. Consider using pd.concat instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
"\n"
@@ -12648,7 +12744,7 @@
" [nan, nan] | \n",
" [nan, nan] | \n",
" [nan, nan] | \n",
- " {re3data, FAIRsharing} | \n",
+ " {FAIRsharing, re3data} | \n",
" \n",
" \n",
" 1 | \n",
@@ -12804,7 +12900,7 @@
" [nan, dspace] | \n",
" [nan, geoname_2_UA] | \n",
" [nan, other] | \n",
- " [nan, [H1, D1, D204, BL, DK, D901, AC, BF, L1,... | \n",
+ " [nan, [B1, BS, BL, AC, D204, DK, HM, BF, L1, D... | \n",
" [nan, 2015-07-07 12:38:37] | \n",
" [nan, nan] | \n",
" [nan, nan] | \n",
@@ -12817,8 +12913,8 @@
" [nan, nan] | \n",
" [nan, nan] | \n",
" [nan, nan] | \n",
- " [nan, [celestial, opendoar]] | \n",
- " [nan, [3410, 5883]] | \n",
+ " [nan, [opendoar, celestial]] | \n",
+ " [nan, [5883, 3410]] | \n",
" [nan, nan] | \n",
" [nan, nan] | \n",
" [nan, nan] | \n",
@@ -13014,7 +13110,7 @@
" [nan, nan] | \n",
" [nan, nan] | \n",
" [nan, nan] | \n",
- " {re3data, FAIRsharing} | \n",
+ " {FAIRsharing, re3data} | \n",
"
\n",
" \n",
" 3 | \n",
@@ -13366,7 +13462,7 @@
" [nan, nan] | \n",
" [nan, nan] | \n",
" [nan, nan] | \n",
- " [[celestial, opendoar], nan] | \n",
+ " [[opendoar, celestial], nan] | \n",
" [[1426, 1294], nan] | \n",
" [nan, nan] | \n",
" [nan, nan] | \n",
@@ -13991,7 +14087,7 @@
"\n",
" roar_subjects \\\n",
"0 [nan, nan] \n",
- "1 [nan, [H1, D1, D204, BL, DK, D901, AC, BF, L1,... \n",
+ "1 [nan, [B1, BS, BL, AC, D204, DK, HM, BF, L1, D... \n",
"2 [nan, nan] \n",
"3 [nan, nan] \n",
"4 [nan, nan] \n",
@@ -14033,10 +14129,10 @@
"\n",
" roar_registry_name roar_registry_id \\\n",
"0 [nan, nan] [nan, nan] \n",
- "1 [nan, [celestial, opendoar]] [nan, [3410, 5883]] \n",
+ "1 [nan, [opendoar, celestial]] [nan, [5883, 3410]] \n",
"2 [nan, nan] [nan, nan] \n",
"3 [roarmap, nan] [http://roarmap.eprints.org/1046/, nan] \n",
- "4 [[celestial, opendoar], nan] [[1426, 1294], nan] \n",
+ "4 [[opendoar, celestial], nan] [[1426, 1294], nan] \n",
"\n",
" roar_submit_to roar_submitted_to_name roar_submitted_to_done \\\n",
"0 [nan, nan] [nan, nan] [nan, nan] \n",
@@ -14067,14 +14163,14 @@
"4 [nan, nan] [nan, nan] [roar_610, nan] \n",
"\n",
" source_set \n",
- "0 {re3data, FAIRsharing} \n",
+ "0 {FAIRsharing, re3data} \n",
"1 {OpenDOAR, roar} \n",
- "2 {re3data, FAIRsharing} \n",
+ "2 {FAIRsharing, re3data} \n",
"3 {OpenDOAR, roar} \n",
"4 {OpenDOAR, roar} "
]
},
- "execution_count": 26,
+ "execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
@@ -14087,7 +14183,7 @@
},
{
"cell_type": "code",
- "execution_count": 27,
+ "execution_count": 30,
"metadata": {},
"outputs": [],
"source": [