diff --git a/hnq-research/1-percentage-by-site.sql b/hnq-research/1-percentage-by-site.sql new file mode 100644 index 0000000..0599ff9 --- /dev/null +++ b/hnq-research/1-percentage-by-site.sql @@ -0,0 +1,17 @@ +SELECT RANK() OVER (ORDER BY percentage DESC), * FROM ( +SELECT site, + ROUND(100.0 * SUM(CASE + WHEN timestamp BETWEEN '2018-11-02 18:36:00' AND '2018-11-05 05:30:00' + OR timestamp >= '2018-11-06 06:27:00' THEN 3 -- minutes + ELSE 10 -- minutes + END) / + (SELECT SUM(CASE + WHEN timestamp BETWEEN '2018-11-02 18:36:00' AND '2018-11-05 05:30:00' + OR timestamp >= '2018-11-06 06:27:00' THEN 3 -- minutes + ELSE 10 -- minutes + END) FROM snapshots), 2) + AS "percentage" + -- COUNT(DISTINCT(question)) AS "questions" + FROM snapshots + GROUP BY site +) AS temp ORDER BY percentage DESC \ No newline at end of file diff --git a/hnq-research/2-percentage-of-total-questions-by-site.sql b/hnq-research/2-percentage-of-total-questions-by-site.sql new file mode 100644 index 0000000..924ed51 --- /dev/null +++ b/hnq-research/2-percentage-of-total-questions-by-site.sql @@ -0,0 +1,10 @@ +SELECT RANK() OVER (ORDER BY ROUND(100.0 * temp.questions / t.number_of_questions, 2) DESC), + temp.site, ROUND(100.0 * temp.questions / t.number_of_questions, 2) AS "% of all Q on site" + FROM ( +SELECT site, + COUNT(DISTINCT(question)) AS "questions" + FROM snapshots + GROUP BY site +) AS temp +INNER JOIN total_question_count AS t on t.site = temp.site +ORDER BY 3 DESC \ No newline at end of file diff --git a/hnq-research/3-average-time-by-site.sql b/hnq-research/3-average-time-by-site.sql new file mode 100644 index 0000000..96060ae --- /dev/null +++ b/hnq-research/3-average-time-by-site.sql @@ -0,0 +1,12 @@ +SELECT site, ROUND(AVG(time), 2) AS "average time", COUNT(*) AS "# of Q" + FROM ( + SELECT site, question, SUM(CASE + WHEN timestamp BETWEEN '2018-11-02 18:36:00' AND '2018-11-05 05:30:00' + OR timestamp >= '2018-11-06 06:27:00' THEN 3 -- minutes + ELSE 10 -- minutes + END) / 60.0 AS time + FROM snapshots + GROUP BY site, question + ORDER BY COUNT(*) DESC + ) AS subquery GROUP BY site +ORDER BY AVG(time) DESC \ No newline at end of file diff --git a/hnq-research/HNQ-average-time-by-site-results.csv b/hnq-research/HNQ-average-time-by-site-results.csv deleted file mode 100644 index d10c96c..0000000 --- a/hnq-research/HNQ-average-time-by-site-results.csv +++ /dev/null @@ -1,131 +0,0 @@ -site,average time,# of Q -gamedev,91.37,5 -parenting,72.97,5 -ux,72.43,7 -skeptics,64.99,20 -money,60.77,28 -security,60.46,31 -chess,57.64,6 -interpersonal,54.46,50 -politics,42.81,33 -workplace,40.68,62 -law,39.40,10 -softwareengineering,36.72,13 -pets,36.06,3 -codegolf,34.62,61 -worldbuilding,31.48,183 -crafts,31.00,1 -academia,30.81,102 -writing,29.42,34 -serverfault,29.02,15 -superuser,27.91,31 -movies,27.76,12 -retrocomputing,27.38,27 -aviation,27.34,39 -history,24.43,31 -christianity,24.27,5 -devops,24.17,1 -scifi,22.29,111 -travel,21.88,83 -space,21.08,40 -ell,20.88,83 -mechanics,20.14,11 -photo,20.13,22 -german,20.06,14 -outdoors,19.98,19 -ukrainian,19.67,1 -cooking,19.43,12 -english,19.00,89 -physics,18.66,71 -sqa,17.25,2 -rpg,17.13,222 -diy,16.17,27 -hsm,16.00,1 -mathoverflow,15.17,86 -bicycles,15.15,26 -french,14.79,4 -music,14.78,36 -graphicdesign,14.30,14 -vi,13.92,2 -electronics,13.82,112 -unix,13.47,124 -puzzling,12.81,228 -boardgames,12.60,21 -astronomy,12.10,8 -cs,11.83,17 -crypto,11.69,26 -codereview,11.48,61 -pm,11.08,6 -anime,11.06,3 -philosophy,10.79,15 -ham,10.77,5 -matheducators,10.67,1 -biology,10.26,12 -askubuntu,10.01,75 -math,9.63,300 -chemistry,9.46,13 -tex,9.42,242 -scicomp,9.17,1 -stackoverflow,8.95,163 -stats,8.94,47 -dba,8.71,42 -mathematica,8.68,97 -cseducators,8.50,2 -arduino,8.35,9 -russian,8.33,1 -judaism,7.97,24 -japanese,7.59,22 -latin,7.51,12 -quantumcomputing,7.47,5 -gaming,7.32,16 -bricks,7.22,3 -apple,6.73,40 -linguistics,6.70,10 -expatriates,6.67,1 -engineering,6.37,4 -blender,6.23,27 -literature,6.10,7 -gardening,5.89,21 -computergraphics,5.67,1 -ai,5.65,10 -datascience,5.62,10 -3dprinting,5.36,11 -salesforce,5.33,65 -martialarts,5.33,1 -wordpress,5.13,21 -sharepoint,5.03,5 -korean,4.93,5 -hinduism,4.90,16 -cstheory,4.71,4 -sitecore,4.60,13 -buddhism,4.51,18 -networkengineering,4.42,11 -economics,4.33,1 -drupal,4.30,15 -bitcoin,4.23,8 -magento,4.19,30 -ethereum,3.76,21 -stellar,3.73,5 -islam,3.56,3 -emacs,3.56,6 -raspberrypi,3.43,10 -craftcms,3.26,7 -quant,3.08,2 -homebrew,3.00,2 -dsp,3.00,6 -gis,2.95,40 -eosio,2.87,5 -earthscience,2.83,4 -webapps,2.67,3 -tridion,2.63,5 -webmasters,2.56,3 -chinese,2.44,12 -hermeneutics,2.33,1 -android,2.17,1 -civicrm,1.67,1 -fitness,1.50,1 -genealogy,1.33,2 -spanish,0.83,1 -iot,0.67,1 -monero,0.33,1 -robotics,0.17,1 diff --git a/hnq-research/HNQ-average-time-by-site.sql b/hnq-research/HNQ-average-time-by-site.sql deleted file mode 100644 index bfef375..0000000 --- a/hnq-research/HNQ-average-time-by-site.sql +++ /dev/null @@ -1,8 +0,0 @@ -SELECT site, ROUND(AVG(time), 2) AS "average time", COUNT(*) AS "# of Q" - FROM ( - SELECT site, question, COUNT(*) / 6.0 AS time - FROM snapshots - GROUP BY site, question - ORDER BY COUNT(*) DESC - ) AS subquery GROUP BY site -ORDER BY AVG(time) DESC \ No newline at end of file diff --git a/hnq-research/HNQ-snapshots-by-site-results.csv b/hnq-research/HNQ-snapshots-by-site-results.csv deleted file mode 100644 index cd467b0..0000000 --- a/hnq-research/HNQ-snapshots-by-site-results.csv +++ /dev/null @@ -1,131 +0,0 @@ -site,% of HNQ,# of HNQ,# of all Q on site,% of all Q on site -worldbuilding,8.32,183,579,31.61 -rpg,5.50,222,733,30.29 -academia,4.54,102,464,21.98 -puzzling,4.22,228,648,35.19 -math,4.18,300,13510,2.22 -interpersonal,3.94,50,186,26.88 -workplace,3.65,62,381,16.27 -scifi,3.57,111,626,17.73 -tex,3.29,242,2053,11.79 -codegolf,3.05,61,119,51.26 -security,2.71,31,859,3.61 -travel,2.62,83,744,11.16 -ell,2.50,83,1232,6.74 -money,2.46,28,382,7.33 -english,2.44,89,1580,5.63 -unix,2.41,124,2646,4.69 -electronics,2.24,112,1971,5.68 -stackoverflow,2.11,163,215805,0.08 -politics,2.04,33,211,15.64 -physics,1.91,71,2509,2.83 -skeptics,1.88,20,107,18.69 -mathoverflow,1.88,86,1168,7.36 -aviation,1.54,39,256,15.23 -writing,1.45,34,117,29.06 -superuser,1.25,31,4187,0.74 -mathematica,1.22,97,745,13.02 -space,1.22,40,227,17.62 -history,1.09,31,177,17.51 -askubuntu,1.08,75,5159,1.45 -retrocomputing,1.07,27,64,42.19 -codereview,1.01,61,1031,5.92 -music,0.77,36,293,12.29 -ux,0.73,7,245,2.86 -softwareengineering,0.69,13,650,2.00 -gamedev,0.66,5,475,1.05 -photo,0.64,22,197,11.17 -diy,0.63,27,702,3.85 -serverfault,0.63,15,2217,0.68 -stats,0.61,47,2668,1.76 -law,0.57,10,351,2.85 -bicycles,0.57,26,197,13.20 -outdoors,0.55,19,72,26.39 -dba,0.53,42,1196,3.51 -parenting,0.53,5,61,8.20 -salesforce,0.50,65,1544,4.21 -chess,0.50,6,68,8.82 -movies,0.48,12,231,5.19 -crypto,0.44,26,342,7.60 -german,0.41,14,152,9.21 -apple,0.39,40,1119,3.57 -boardgames,0.38,21,102,20.59 -cooking,0.34,12,187,6.42 -mechanics,0.32,11,401,2.74 -graphicdesign,0.29,14,485,2.89 -cs,0.29,17,480,3.54 -judaism,0.28,24,290,8.28 -japanese,0.24,22,285,7.72 -blender,0.24,27,1176,2.30 -philosophy,0.23,15,246,6.10 -chemistry,0.18,13,589,2.21 -christianity,0.18,5,156,3.21 -biology,0.18,12,340,3.53 -magento,0.18,30,1778,1.69 -gardening,0.18,21,195,10.77 -gaming,0.17,16,490,3.27 -gis,0.17,40,1580,2.53 -pets,0.16,3,78,3.85 -wordpress,0.16,21,1480,1.42 -astronomy,0.14,8,124,6.45 -latin,0.13,12,56,21.43 -buddhism,0.12,18,116,15.52 -hinduism,0.11,16,174,9.20 -arduino,0.11,9,359,2.51 -ethereum,0.11,21,1033,2.03 -pm,0.10,6,56,10.71 -linguistics,0.10,10,112,8.93 -french,0.09,4,155,2.58 -sitecore,0.09,13,227,5.73 -drupal,0.09,15,988,1.52 -3dprinting,0.09,11,79,13.92 -datascience,0.08,10,695,1.44 -ham,0.08,5,61,8.20 -ai,0.08,10,140,7.14 -networkengineering,0.07,11,364,3.02 -literature,0.06,7,92,7.61 -sqa,0.05,2,151,1.32 -quantumcomputing,0.05,5,67,7.46 -bitcoin,0.05,8,450,1.78 -raspberrypi,0.05,10,495,2.02 -anime,0.05,3,195,1.54 -vi,0.04,2,142,1.41 -korean,0.04,5,27,18.52 -sharepoint,0.04,5,761,0.66 -crafts,0.04,1,28,3.57 -chinese,0.04,12,100,12.00 -engineering,0.04,4,241,1.66 -stellar,0.03,5,59,8.47 -emacs,0.03,6,295,2.03 -cstheory,0.03,4,93,4.30 -devops,0.03,1,92,1.09 -craftcms,0.03,7,209,3.35 -ukrainian,0.03,1,59,1.69 -bricks,0.03,3,39,7.69 -dsp,0.03,6,346,1.73 -cseducators,0.02,2,20,10.00 -eosio,0.02,5,155,3.23 -earthscience,0.02,4,116,3.45 -hsm,0.02,1,35,2.86 -tridion,0.02,5,35,14.29 -matheducators,0.02,1,30,3.33 -islam,0.02,3,198,1.52 -economics,0.01,1,185,0.54 -martialarts,0.01,1,13,7.69 -webapps,0.01,3,373,0.80 -russian,0.01,1,52,1.92 -homebrew,0.01,2,37,5.41 -webmasters,0.01,3,337,0.89 -computergraphics,0.01,1,67,1.49 -scicomp,0.01,1,92,1.09 -quant,0.01,2,250,0.80 -expatriates,0.01,1,103,0.97 -monero,0.00,1,82,1.22 -robotics,0.00,1,58,1.72 -genealogy,0.00,2,33,6.06 -android,0.00,1,648,0.15 -fitness,0.00,1,91,1.10 -iot,0.00,1,47,2.13 -civicrm,0.00,1,163,0.61 -spanish,0.00,1,89,1.12 -hermeneutics,0.00,1,87,1.15 diff --git a/hnq-research/HNQ-snapshots-by-site.sql b/hnq-research/HNQ-snapshots-by-site.sql deleted file mode 100644 index 5e9c8ec..0000000 --- a/hnq-research/HNQ-snapshots-by-site.sql +++ /dev/null @@ -1,10 +0,0 @@ -SELECT temp.site, temp.percentage AS "% of HNQ", temp.questions AS "# of HNQ", t.number_of_questions AS "# of all Q on site", - ROUND(100.0 * questions / t.number_of_questions, 2) AS "% of all Q on site" - FROM (SELECT site, ROUND(100.0 * COUNT(*) / (SELECT COUNT(*) FROM snapshots), 2) AS "percentage", - COUNT(DISTINCT(question)) AS "questions" - FROM snapshots - GROUP BY site - ORDER BY COUNT(*) DESC - ) AS temp - INNER JOIN total_question_count AS t on t.site = temp.site - ORDER BY 2 DESC \ No newline at end of file diff --git a/hnq-research/HNQ.backup b/hnq-research/HNQ.backup index c9f2df0..c5fd827 100644 Binary files a/hnq-research/HNQ.backup and b/hnq-research/HNQ.backup differ