Skip to content

Commit

Permalink
Add graphml files.
Browse files Browse the repository at this point in the history
  • Loading branch information
Ryan Deschamps committed May 5, 2017
1 parent 36a45cb commit 266441e
Show file tree
Hide file tree
Showing 3 changed files with 84 additions and 54 deletions.
66 changes: 41 additions & 25 deletions descriptor/PopulateSeedsCPP.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,8 @@
"- Selected Description of Most Interesting Seeds\n",
"- Time-series analysis of the main domains through Crawl-viz (https://github.com/web-archive-group/WALK-CrawlVis)\n",
"- Including some field notes to help others get a \"feel\" for what's in the collection.\n",
"- Possibly utilizing some annotation software like Hypothes.is to take advantage of crowd sourcing."
"- Possibly utilizing some annotation software like Hypothes.is to take advantage of crowd sourcing.\n",
"- hello!!!!\n"
]
},
{
Expand Down Expand Up @@ -55,7 +56,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 4,
"metadata": {
"collapsed": true
},
Expand All @@ -75,7 +76,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"metadata": {
"collapsed": true
},
Expand All @@ -84,14 +85,18 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'seed_main', '_default', 'seed_backup', 'collections_backup', 'collections'}\n"
"ename": "AttributeError",
"evalue": "'module' object has no attribute 'tables'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-5-57e8c867209d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 7\u001b[0m \u001b[0;31m################# db.purge_tables()\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[0;31m################# default = db.table(\"_default\")\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m \u001b[0mprint\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mtdb\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtables\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m: 'module' object has no attribute 'tables'"
]
}
],
Expand All @@ -104,7 +109,7 @@
"################# collections_backup.purge()\n",
"################# db.purge_tables()\n",
"################# default = db.table(\"_default\")\n",
"print (db.tables())"
"print (tdb.tables())"
]
},
{
Expand Down Expand Up @@ -148,13 +153,13 @@
},
{
"cell_type": "code",
"execution_count": 49,
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "26c5dc62dc054c1eb90867b3dd3cea05"
"model_id": "3368340371c14cee942ffb2f151d9a7a"
}
},
"metadata": {},
Expand All @@ -163,7 +168,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "d1d0d6d5600d4ac7a2918c5e68138b00"
"model_id": "a2e0914d3b0d44c19fce0ba9317eba3e"
}
},
"metadata": {},
Expand All @@ -172,7 +177,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9b5c7d0bd0ad40e99d62b2f9332110e1"
"model_id": "5a8783ad0b3147eb8a0fb93e10cec49f"
}
},
"metadata": {},
Expand All @@ -181,7 +186,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "bcfa03846ca9482e806f11383e1cb581"
"model_id": "5945b19339ee42be97a33592b9e60e46"
}
},
"metadata": {},
Expand All @@ -190,7 +195,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ba9a74f7a88e4bbbb5e2b4829718fbf6"
"model_id": "727602c4816343b5951e1aae05b9cfaf"
}
},
"metadata": {},
Expand All @@ -199,7 +204,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "7021cd8a226f4387b7c60f9ff9b80bfd"
"model_id": "254150134a6649db92a1e351cf9566a4"
}
},
"metadata": {},
Expand All @@ -208,7 +213,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c8c77a336a7f431d988edc5c1ecf2342"
"model_id": "42cd2a918e314913852f1d9bf031ac58"
}
},
"metadata": {},
Expand All @@ -217,7 +222,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2bf745e2088f4aaea9773a8626554354"
"model_id": "6be5dcec3d8041ab934a022f8e3ab5c3"
}
},
"metadata": {},
Expand All @@ -226,7 +231,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "228c9854e4724fd9b7ba321e61f01943"
"model_id": "21f5bfde3b394db9b7e40c01b94b92fb"
}
},
"metadata": {},
Expand All @@ -235,7 +240,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "90ce7327488e423ab6865b96d58fa349"
"model_id": "ceb1eee1908e42018e581d0d81bacee5"
}
},
"metadata": {},
Expand Down Expand Up @@ -268,8 +273,10 @@
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"description = {\n",
Expand Down Expand Up @@ -347,7 +354,7 @@
},
{
"cell_type": "code",
"execution_count": 51,
"execution_count": 4,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -380,7 +387,7 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "791f1cc8ad264bfbbeff3a9cb7d3adfc"
"model_id": "7c1538aa4d7741dba6446bbed2ea7420"
}
},
"metadata": {},
Expand All @@ -389,11 +396,20 @@
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9c9e1d727e524a74867a3a491ed6cd82"
"model_id": "ef22879974704072aea5d92bfc4655bc"
}
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"submitted!\n",
"{'collection_title': '', 'TIMESTAMP': 1493132177.0740445, 'institutional_description': '', 'crawl_viz_description': '', 'WALK_description': '', 'WALK_collection_folder': ''}\n",
"inserted!\n"
]
}
],
"source": [
Expand Down
70 changes: 42 additions & 28 deletions descriptor/create_graphs_in_R.ipynb
View file

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion descriptor/data/WALK.json
View file
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"collections_backup": {"1": {"WALK_description": "Inst", "crawl_viz_description": "lelsjdkl", "collection_title": "Hello", "institutional_description": "Whatever", "TIMESTAMP": 1492461423.4946241, "WALK_collection_folder": "Goodbye"}}, "seed_backup": {"2": {"times_captured": 59, "videos": 0, "url": "http://agoracosmopolite.com", "TIMESTAMP": 1488049284.002535, "collection_title": "Canadian Political Parties and Political Interest Groups", "seed_name": "Cosmopolitan Party of Canada", "first_crawl": "2005-10-04", "description": "\n Also called the \"Progressive Nationalist Party\", it is a \"progressive and environment protection oriented\n political party\" that seeks the \"political, economic and cultural assimilation of Canada, into the\n United States, under the _Security and Prosperity Partnership_ (SPP).\"\n ", "latest_crawl": "2012-11-03", "WALK_collection_folder": "TORONTO_Canadian_Political_Parties"}, "1": {"times_captured": 59, "videos": 0, "url": "http://agoracosmopolite.com", "TIMESTAMP": 1488049265.426975, "collection_title": "Canadian Political Parties and Political Interest Groups", "seed_name": "Cosmopolitan Party of Canada", "first_crawl": "2005-10-04", "description": "\n Also called the \"Progressive Nationalist Party\", it is a \"progressive and environment protection oriented\n political party\" that seeks the \"political, economic and cultural assimilation of Canada, into the\n United States, under the _Security and Prosperity Partnership_ (SPP).\"\n ", "latest_crawl": "2012-11-03", "WALK_collection_folder": "TORONTO_Canadian_Political_Parties"}}, "collections": {"2": {"WALK_description": "Inst", "crawl_viz_description": "lelsjdkl", "collection_title": "Hello", "institutional_description": "Whatever", "TIMESTAMP": 1492461423.4946241, "WALK_collection_folder": "Goodbye"}, "1": {"crawl_viz_description": "\n \n - Between March 06 and January 07 and then again between July 09 & November 09, Policy Alternatives had the\n largest amount of activity.\n - A rise in activity for equalvoice.ca (advocacy for women in political leadership) between December 09 and \n November 2011.\n - Of the major parties, the Liberal Party of Canada and the Green Party had the most activity.\n \n ", "collection_title": "Canadian Political Parties and Political Interest Groups", "gephi_avg_degree": 0, "something wrong": false, "crawl_viz_link_file": "TORONTO_Canadian_Political_Parties-urls.html", "gephi_file_name": "", "gephi_clustering_coefficient": 0, "WALK_collection_folder": "TORONTO_Canadian_Political_Parties", "WALK_description": "\n \n Contains the web archives for the main parties (Liberal, Conservatives, NDP, Bloc, Green) but \n also a wide range marginal parties (Cosmopolitan Party, Canadian Action, Christian Heritage and\n so on). The \"special interest groups\" include the David Suzuki Foundation (an environmental \n advocacy group) and fairvote.ca (advocacy for changing the electoral system).\n \n ", "TIMESTAMP": 1488049223.72829, "gephi_avg_weighted_degree": 0, "gephi_description": "\n ", "institutional_description": "\n \n Canadian Political Parties and Political Interest Groups will archive the websites of all \n the national Canadian political parties, and a number of special interest groups across \n the political spectrum.\n \n "}}, "seed_main": {"1": {"times_captured": 59, "videos": 0, "url": "http://agoracosmopolite.com", "TIMESTAMP": 1488049284.002535, "collection_title": "Canadian Political Parties and Political Interest Groups", "seed_name": "Cosmopolitan Party of Canada", "first_crawl": "2005-10-04", "description": "\n Also called the \"Progressive Nationalist Party\", it is a \"progressive and environment protection oriented\n political party\" that seeks the \"political, economic and cultural assimilation of Canada, into the\n United States, under the _Security and Prosperity Partnership_ (SPP).\"\n ", "latest_crawl": "2012-11-03", "WALK_collection_folder": "TORONTO_Canadian_Political_Parties"}}, "_default": {}}
{"_default": {}, "seed_main": {"1": {"collection_title": "Canadian Political Parties and Political Interest Groups", "TIMESTAMP": 1488049284.002535, "latest_crawl": "2012-11-03", "url": "http://agoracosmopolite.com", "WALK_collection_folder": "TORONTO_Canadian_Political_Parties", "seed_name": "Cosmopolitan Party of Canada", "times_captured": 59, "description": "\n Also called the \"Progressive Nationalist Party\", it is a \"progressive and environment protection oriented\n political party\" that seeks the \"political, economic and cultural assimilation of Canada, into the\n United States, under the _Security and Prosperity Partnership_ (SPP).\"\n ", "videos": 0, "first_crawl": "2005-10-04"}}, "seed_backup": {"1": {"collection_title": "Canadian Political Parties and Political Interest Groups", "TIMESTAMP": 1488049265.426975, "latest_crawl": "2012-11-03", "url": "http://agoracosmopolite.com", "WALK_collection_folder": "TORONTO_Canadian_Political_Parties", "seed_name": "Cosmopolitan Party of Canada", "times_captured": 59, "description": "\n Also called the \"Progressive Nationalist Party\", it is a \"progressive and environment protection oriented\n political party\" that seeks the \"political, economic and cultural assimilation of Canada, into the\n United States, under the _Security and Prosperity Partnership_ (SPP).\"\n ", "videos": 0, "first_crawl": "2005-10-04"}, "2": {"collection_title": "Canadian Political Parties and Political Interest Groups", "TIMESTAMP": 1488049284.002535, "latest_crawl": "2012-11-03", "url": "http://agoracosmopolite.com", "WALK_collection_folder": "TORONTO_Canadian_Political_Parties", "seed_name": "Cosmopolitan Party of Canada", "times_captured": 59, "description": "\n Also called the \"Progressive Nationalist Party\", it is a \"progressive and environment protection oriented\n political party\" that seeks the \"political, economic and cultural assimilation of Canada, into the\n United States, under the _Security and Prosperity Partnership_ (SPP).\"\n ", "videos": 0, "first_crawl": "2005-10-04"}}, "collections": {"1": {"collection_title": "Canadian Political Parties and Political Interest Groups", "institutional_description": "\n \n Canadian Political Parties and Political Interest Groups will archive the websites of all \n the national Canadian political parties, and a number of special interest groups across \n the political spectrum.\n \n ", "WALK_collection_folder": "TORONTO_Canadian_Political_Parties", "crawl_viz_link_file": "TORONTO_Canadian_Political_Parties-urls.html", "something wrong": false, "TIMESTAMP": 1488049223.72829, "gephi_avg_degree": 0, "crawl_viz_description": "\n \n - Between March 06 and January 07 and then again between July 09 & November 09, Policy Alternatives had the\n largest amount of activity.\n - A rise in activity for equalvoice.ca (advocacy for women in political leadership) between December 09 and \n November 2011.\n - Of the major parties, the Liberal Party of Canada and the Green Party had the most activity.\n \n ", "WALK_description": "\n \n Contains the web archives for the main parties (Liberal, Conservatives, NDP, Bloc, Green) but \n also a wide range marginal parties (Cosmopolitan Party, Canadian Action, Christian Heritage and\n so on). The \"special interest groups\" include the David Suzuki Foundation (an environmental \n advocacy group) and fairvote.ca (advocacy for changing the electoral system).\n \n ", "gephi_clustering_coefficient": 0, "gephi_file_name": "", "gephi_avg_weighted_degree": 0, "gephi_description": "\n "}, "2": {"collection_title": "Hello", "TIMESTAMP": 1492461423.4946241, "institutional_description": "Whatever", "crawl_viz_description": "lelsjdkl", "WALK_description": "Inst", "WALK_collection_folder": "Goodbye"}, "3": {"collection_title": "", "TIMESTAMP": 1493132177.0740445, "institutional_description": "", "crawl_viz_description": "", "WALK_description": "", "WALK_collection_folder": ""}}, "collections_backup": {"1": {"collection_title": "Hello", "TIMESTAMP": 1492461423.4946241, "institutional_description": "Whatever", "crawl_viz_description": "lelsjdkl", "WALK_description": "Inst", "WALK_collection_folder": "Goodbye"}}}

0 comments on commit 266441e

Please sign in to comment.