anova

SQL_analysis_experiment.sql

@@ -0,0 +1,85 @@
+select distinct experiment.idx_scenario, 
+n_max_trial, prf_size, prf_conn, cap_limit_prob_type, cap_limit_level, diff_new_conn, crit_supplier, proactive_ratio, remove_t, netw_prf_n,
+mean_count_firm_prod, mean_count_firm, mean_count_prod,
+mean_max_ts_firm_prod, mean_max_ts_firm, mean_max_ts_prod,
+mean_n_remove_firm_prod, mean_n_all_prod_remove_firm, mean_end_ts
+from iiabmdb.with_exp_experiment as experiment
+left join 
+(
+select 
+idx_scenario,
+sum(count_firm_prod) / count(*) as mean_count_firm_prod, # Note to use count(*), to include NULL
+sum(count_firm) / count(*) as mean_count_firm,
+sum(count_prod) / count(*) as mean_count_prod,
+sum(max_ts_firm_prod) / count(*) as mean_max_ts_firm_prod,
+sum(max_ts_firm) / count(*) as mean_max_ts_firm,
+sum(max_ts_prod) / count(*) as mean_max_ts_prod,
+sum(n_remove_firm_prod) / count(*) as mean_n_remove_firm_prod,
+sum(n_all_prod_remove_firm) / count(*) as mean_n_all_prod_remove_firm,
+sum(end_ts) / count(*) as mean_end_ts
+from (
+select sample.id, idx_scenario,
+count_firm_prod, count_firm, count_prod,
+max_ts_firm_prod, max_ts_firm, max_ts_prod,
+n_remove_firm_prod, n_all_prod_remove_firm, end_ts
+from iiabmdb.with_exp_sample as sample
+# 1 2 3 + 9
+left join iiabmdb.with_exp_experiment as experiment
+on sample.e_id = experiment.id
+left join (select s_id, 
+count(distinct id_firm, id_product) as count_firm_prod,
+count(distinct id_firm) as count_firm,
+count(distinct id_product) as count_prod,
+max(ts) as end_ts
+from iiabmdb.with_exp_result group by s_id) as s_count
+on sample.id = s_count.s_id
+# 4
+left join # firm prod
+(select s_id, max(ts) as max_ts_firm_prod from
+(select s_id, id_firm, id_product, min(ts) as ts
+from iiabmdb.with_exp_result
+where `status` = "D"
+group by s_id, id_firm, id_product) as ts
+group by s_id) as s_max_ts_firm_prod
+on sample.id = s_max_ts_firm_prod.s_id
+# 5
+left join # firm
+(select s_id, max(ts) as max_ts_firm from
+(select s_id, id_firm, min(ts) as ts
+from iiabmdb.with_exp_result
+where `status` = "D"
+group by s_id, id_firm) as ts
+group by s_id) as s_max_ts_firm
+on sample.id = s_max_ts_firm.s_id
+# 6
+left join # prod
+(select s_id, max(ts) as max_ts_prod from
+(select s_id, id_product, min(ts) as ts
+from iiabmdb.with_exp_result
+where `status` = "D"
+group by s_id, id_product) as ts
+group by s_id) as s_max_ts_prod
+on sample.id = s_max_ts_prod.s_id
+# 7 
+left join
+(select s_id, count(distinct id_firm, id_product) as n_remove_firm_prod
+from iiabmdb.with_exp_result
+where `status` = "R"
+group by s_id) as s_n_remove_firm_prod
+on sample.id = s_n_remove_firm_prod.s_id
+# 8
+left join
+(select s_id, count(distinct id_firm) as n_all_prod_remove_firm from
+(select s_id, id_firm, count(distinct id_product) as n_remove_prod
+from iiabmdb.with_exp_result
+where `status` = "R"
+group by s_id, id_firm) as s_n_remove_prod
+left join iiabmdb_basic_info.firm_n_prod as firm_n_prod
+on s_n_remove_prod.id_firm = firm_n_prod.code
+where n_remove_prod = n_prod
+group by s_id) as s_n_all_prod_remove_firm
+on sample.id = s_n_all_prod_remove_firm.s_id
+) as secnario_count
+group by idx_scenario
+) as secnario_mean
+on experiment.idx_scenario = secnario_mean.idx_scenario;

SQL_analysis_experiment_test.sql

@@ -0,0 +1,94 @@
+select * from iiabmdb.with_exp_result limit 0, 20;
+select count(distinct s_id) from iiabmdb.with_exp_result;
+select count(*) from iiabmdb.with_exp_sample;
+
+select distinct s_id, id_firm, id_product from iiabmdb.with_exp_result order by s_id, id_firm, id_product;
+
+select distinct s_id, count(distinct id_firm, id_product) as count_firm_prod from iiabmdb.with_exp_result group by s_id;
+
+select distinct s_id, count(distinct id_firm, id_product) as count_firm_prod 
+from iiabmdb.with_exp_result group by s_id;
+
+select distinct s_id, 
+count(distinct id_firm, id_product) as count_firm_prod,
+count(distinct id_firm) as count_firm,
+count(distinct id_product) as count_prod
+from iiabmdb.with_exp_result group by s_id;
+
+# 控制问题需要处理，否则最后 experiment avg出来的东西不对
+# 1 2 3
+select 
+idx_scenario,
+sum(count_firm_prod) / count(*) as mean_count_firm_prod, # Note to use count(*), to include NULL
+sum(count_firm) / count(*) as mean_count_firm,
+sum(count_prod) / count(*) as mean_count_prod
+from (
+select sample.id, idx_scenario, count_firm_prod, count_firm, count_prod 
+from iiabmdb.with_exp_sample as sample
+left join iiabmdb.with_exp_experiment as experiment
+on sample.e_id = experiment.id
+left join (select s_id, 
+count(distinct id_firm, id_product) as count_firm_prod,
+count(distinct id_firm) as count_firm,
+count(distinct id_product) as count_prod
+from iiabmdb.with_exp_result group by s_id) as s_count
+on sample.id = s_count.s_id) as secnario_count
+group by idx_scenario;
+
+# 4 5 6
+select sample.id, idx_scenario, max_ts_firm_prod, max_ts_firm, max_ts_prod
+from iiabmdb.with_exp_sample as sample
+left join iiabmdb.with_exp_experiment as experiment
+on sample.e_id = experiment.id
+left join # firm prod
+(select s_id, max(ts) as max_ts_firm_prod from
+(select s_id, id_firm, id_product, min(ts) as ts
+from iiabmdb.with_exp_result
+where `status` = "D"
+group by s_id, id_firm, id_product) as ts
+group by s_id) as s_max_ts_firm_prod
+on sample.id = s_max_ts_firm_prod.s_id
+left join # firm
+(select s_id, max(ts) as max_ts_firm from
+(select s_id, id_firm, min(ts) as ts
+from iiabmdb.with_exp_result
+where `status` = "D"
+group by s_id, id_firm) as ts
+group by s_id) as s_max_ts_firm
+on sample.id = s_max_ts_firm.s_id
+left join # prod
+(select s_id, max(ts) as max_ts_prod from
+(select s_id, id_product, min(ts) as ts
+from iiabmdb.with_exp_result
+where `status` = "D"
+group by s_id, id_product) as ts
+group by s_id) as s_max_ts_prod
+on sample.id = s_max_ts_prod.s_id;
+
+# 7 8 9 
+select sample.id, idx_scenario, n_remove_firm_prod, n_all_prod_remove_firm, end_ts
+from iiabmdb.with_exp_sample as sample
+left join iiabmdb.with_exp_experiment as experiment
+on sample.e_id = experiment.id
+left join
+(select s_id, count(distinct id_firm, id_product) as n_remove_firm_prod
+from iiabmdb.with_exp_result
+where `status` = "R"
+group by s_id) as s_n_remove_firm_prod
+on sample.id = s_n_remove_firm_prod.s_id
+left join
+(select s_id, count(distinct id_firm) as n_all_prod_remove_firm from
+(select s_id, id_firm, count(distinct id_product) as n_remove_prod
+from iiabmdb.with_exp_result
+where `status` = "R"
+group by s_id, id_firm) as s_n_remove_prod
+left join iiabmdb_basic_info.firm_n_prod as firm_n_prod
+on s_n_remove_prod.id_firm = firm_n_prod.code
+where n_remove_prod = n_prod
+group by s_id) as s_n_all_prod_remove_firm
+on sample.id = s_n_all_prod_remove_firm.s_id
+left join
+(select s_id, max(ts) as end_ts 
+from iiabmdb.with_exp_result
+group by s_id) as s_end_ts
+on sample.id = s_end_ts.s_id;

analysis/anova.csv

@@ -0,0 +1,11 @@
+,mean_count_firm_prod,mean_count_firm,mean_count_prod,mean_max_ts_firm_prod,mean_max_ts_firm,mean_max_ts_prod,mean_n_remove_firm_prod,mean_n_all_prod_remove_firm,mean_end_ts
+prf_size,0.004,0.004,0.004,0.004,0.004,0.004,0.973,0.953,0.018
+prf_conn,0.884,0.884,0.841,0.841,0.841,0.841,0.821,0.888,0.63
+cap_limit_prob_type,0.708,0.723,0.517,0.517,0.517,0.517,0.002,0.001,0.002
+n_max_trial,0.611,0.613,0.724,0.724,0.724,0.724,0.898,0.869,0.796
+cap_limit_level,0.243,0.254,0.118,0.118,0.118,0.118,0,0,0
+diff_new_conn,0.216,0.229,0.058,0.058,0.058,0.058,0.002,0.002,0
+crit_supplier,0,0,0,0,0,0,0,0,0
+proactive_ratio,0.66,0.651,0.572,0.572,0.572,0.572,0.258,0.399,0.367
+remove_t,0.464,0.465,0.546,0.546,0.546,0.546,0.026,0.186,0
+netw_prf_n,0,0,0,0,0,0,0.019,0.069,0.003

analysis/anova_visualization.csv

@@ -0,0 +1,15 @@
+自变量,level,企业产品中断累计次数,企业产品中断最大传导次数,企业产品退出市场数量,网络恢复用时
+对规模较大企业的倾向,倾向,2.168,0.8939,0.7698,2.214
+对规模较大企业的倾向,不倾向,2.393,1.0197,0.7709,2.334
+额外产能,高,2.197,0.8991,0.6667,2.05
+额外产能,中,2.323,0.9772,0.7891,2.33
+额外产能,低,2.322,0.9941,0.8553,2.442
+可重构性,低,2.367,1.0258,0.8611,2.515
+可重构性,中,2.228,0.9255,0.7274,2.195
+可重构性,高,2.247,0.9191,0.7226,2.111
+单一供应商重要性,低,1.915,0.7324,0.6919,2.111
+单一供应商重要性,中,2.219,0.9477,0.7478,2.242
+单一供应商重要性,高,2.708,1.1902,0.8713,2.469
+多供应商策略,三供应商,2.066,0.8281,0.7193,2.189
+多供应商策略,双供应商,2.253,0.9342,0.7568,2.23
+多供应商策略,单供应商,2.523,1.1081,0.8349,2.402

analysis/experiment_result-L27.csv

@@ -0,0 +1,28 @@
+,n_max_trial,crit_supplier,firm_pref_request,firm_pref_accept,netw_pref_cust_n,netw_pref_cust_size,cap_limit,diff_new_conn,diff_remove,X10,X11,X12,X13,n_disrupt_s,n_disrupt_t
+0,15,2.0,2.0,2.0,0.5,2.0,4,0.5,0.5,0,0,0,0,888.0,2114.0
+1,15,2.0,2.0,2.0,1.0,1.0,2,1.0,1.0,1,1,1,1,1297.0,2810.0
+2,15,2.0,2.0,2.0,2.0,0.5,1,2.0,2.0,2,2,2,2,1826.0,3809.0
+3,15,1.0,1.0,1.0,0.5,2.0,4,1.0,1.0,1,2,2,2,1372.0,3055.0
+4,15,1.0,1.0,1.0,1.0,1.0,2,2.0,2.0,2,0,0,0,2118.0,4519.0
+5,15,1.0,1.0,1.0,2.0,0.5,1,0.5,0.5,0,1,1,1,815.0,2073.0
+6,15,0.5,0.5,0.5,0.5,2.0,4,2.0,2.0,2,1,1,1,2378.0,5528.0
+7,15,0.5,0.5,0.5,1.0,1.0,2,0.5,0.5,0,2,2,2,968.0,2300.0
+8,15,0.5,0.5,0.5,2.0,0.5,1,1.0,1.0,1,0,0,0,1531.0,3317.0
+9,10,2.0,1.0,0.5,0.5,1.0,1,0.5,1.0,2,0,1,2,881.0,1972.0
+10,10,2.0,1.0,0.5,1.0,0.5,4,1.0,2.0,0,1,2,0,1298.0,2763.0
+11,10,2.0,1.0,0.5,2.0,2.0,2,2.0,0.5,1,2,0,1,1717.0,3837.0
+12,10,1.0,0.5,2.0,0.5,1.0,1,1.0,2.0,0,2,0,1,1327.0,2855.0
+13,10,1.0,0.5,2.0,1.0,0.5,4,2.0,0.5,1,0,1,2,2126.0,4788.0
+14,10,1.0,0.5,2.0,2.0,2.0,2,0.5,1.0,2,1,2,0,801.0,1814.0
+15,10,0.5,2.0,1.0,0.5,1.0,1,2.0,0.5,1,1,2,0,2442.0,5980.0
+16,10,0.5,2.0,1.0,1.0,0.5,4,0.5,1.0,2,2,0,1,991.0,2186.0
+17,10,0.5,2.0,1.0,2.0,2.0,2,1.0,2.0,0,0,1,2,1311.0,2776.0
+18,5,2.0,0.5,1.0,0.5,0.5,2,0.5,2.0,1,0,2,1,879.0,1909.0
+19,5,2.0,0.5,1.0,1.0,2.0,1,1.0,0.5,2,1,0,2,1354.0,3132.0
+20,5,2.0,0.5,1.0,2.0,1.0,4,2.0,1.0,0,2,1,0,1727.0,3673.0
+21,5,1.0,2.0,0.5,0.5,0.5,2,1.0,0.5,2,2,1,0,1379.0,3184.0
+22,5,1.0,2.0,0.5,1.0,2.0,1,2.0,1.0,0,0,2,1,2145.0,4658.0
+23,5,1.0,2.0,0.5,2.0,1.0,4,0.5,2.0,1,1,0,2,810.0,1764.0
+24,5,0.5,1.0,2.0,0.5,0.5,2,2.0,1.0,0,1,0,2,2412.0,5783.0
+25,5,0.5,1.0,2.0,1.0,2.0,1,0.5,2.0,1,2,1,0,915.0,1973.0
+26,5,0.5,1.0,2.0,2.0,1.0,4,1.0,0.5,2,0,2,1,1336.0,3087.0

analysis/experiment_result.csv

@@ -1,28 +1,37 @@
-,n_max_trial,crit_supplier,firm_pref_request,firm_pref_accept,netw_pref_cust_n,netw_pref_cust_size,cap_limit,diff_new_conn,diff_remove,X10,X11,X12,X13,n_disrupt_s,n_disrupt_t
+idx_scenario,n_max_trial,prf_size,prf_conn,cap_limit_prob_type,cap_limit_level,diff_new_conn,crit_supplier,proactive_ratio,remove_t,netw_prf_n,mean_count_firm_prod,mean_count_firm,mean_count_prod,mean_max_ts_firm_prod,mean_max_ts_firm,mean_max_ts_prod,mean_n_remove_firm_prod,mean_n_all_prod_remove_firm,mean_end_ts
-0,15,2.0,2.0,2.0,0.5,2.0,4,0.5,0.5,0,0,0,0,888.0,2114.0
+0,15,1,1,uniform,5.0000,0.3000,2.0000,0.3000,3,3,1.5512,1.5509,1.4943,0.4943,0.4943,0.4943,0.6731,0.2280,1.6345
-1,15,2.0,2.0,2.0,1.0,1.0,2,1.0,1.0,1,1,1,1,1297.0,2810.0
+1,10,1,1,uniform,10.0000,0.5000,1.0000,0.5000,5,2,2.2707,2.2663,1.9623,0.9623,0.9623,0.9623,0.7522,0.2531,2.2764
-2,15,2.0,2.0,2.0,2.0,0.5,1,2.0,2.0,2,2,2,2,1826.0,3809.0
+2,5,1,1,uniform,15.0000,0.7000,0.5000,0.7000,7,1,2.5655,2.5608,2.1337,1.1337,1.1337,1.1337,0.9021,0.2926,2.9874
-3,15,1.0,1.0,1.0,0.5,2.0,4,1.0,1.0,1,2,2,2,1372.0,3055.0
+3,15,1,1,uniform,5.0000,0.3000,2.0000,0.5000,5,2,1.7114,1.7105,1.6135,0.6135,0.6135,0.6135,0.6200,0.2120,1.9855
-4,15,1.0,1.0,1.0,1.0,1.0,2,2.0,2.0,2,0,0,0,2118.0,4519.0
+4,10,1,1,uniform,10.0000,0.5000,1.0000,0.7000,7,1,2.5322,2.5274,2.1114,1.1114,1.1114,1.1114,0.7952,0.2648,2.8876
-5,15,1.0,1.0,1.0,2.0,0.5,1,0.5,0.5,0,1,1,1,815.0,2073.0
+5,5,1,1,uniform,15.0000,0.7000,0.5000,0.3000,3,3,2.6476,2.6406,2.1886,1.1886,1.1886,1.1886,1.0303,0.3255,1.9575
-6,15,0.5,0.5,0.5,0.5,2.0,4,2.0,2.0,2,1,1,1,2378.0,5528.0
+6,15,1,1,normal,5.0000,0.5000,0.5000,0.3000,5,1,2.5272,2.5240,2.1017,1.1017,1.1017,1.1017,0.6444,0.2194,2.1438
-7,15,0.5,0.5,0.5,1.0,1.0,2,0.5,0.5,0,2,2,2,968.0,2300.0
+7,10,1,1,normal,10.0000,0.7000,2.0000,0.5000,7,3,1.5282,1.5282,1.4699,0.4699,0.4699,0.4699,0.6044,0.2116,2.2133
-8,15,0.5,0.5,0.5,2.0,0.5,1,1.0,1.0,1,0,0,0,1531.0,3317.0
+8,5,1,1,normal,15.0000,0.3000,1.0000,0.7000,3,2,2.2128,2.2109,1.9781,0.9781,0.9781,0.9781,0.9743,0.3023,1.9869
-9,10,2.0,1.0,0.5,0.5,1.0,1,0.5,1.0,2,0,1,2,881.0,1972.0
+9,15,1,0,uniform,5.0000,0.7000,1.0000,0.3000,7,2,2.1539,2.1537,1.8821,0.8821,0.8821,0.8821,0.6004,0.2105,2.2248
-10,10,2.0,1.0,0.5,1.0,0.5,4,1.0,2.0,0,1,2,0,1298.0,2763.0
+10,10,1,0,uniform,10.0000,0.3000,0.5000,0.5000,3,1,2.6907,2.6804,2.2434,1.2434,1.2434,1.2434,1.2832,0.4072,2.3133
-11,10,2.0,1.0,0.5,2.0,2.0,2,2.0,0.5,1,2,0,1,1717.0,3837.0
+11,5,1,0,uniform,15.0000,0.5000,2.0000,0.7000,5,3,1.5537,1.5537,1.4971,0.4971,0.4971,0.4971,0.6411,0.2211,1.9853
-12,10,1.0,0.5,2.0,0.5,1.0,1,1.0,2.0,0,2,0,1,1327.0,2855.0
+12,15,1,0,normal,10.0000,0.7000,2.0000,0.7000,5,3,1.5175,1.5175,1.4638,0.4638,0.4638,0.4638,0.6046,0.2114,1.8941
-13,10,1.0,0.5,2.0,1.0,0.5,4,2.0,0.5,1,0,1,2,2126.0,4788.0
+13,10,1,0,normal,15.0000,0.3000,1.0000,0.3000,7,2,2.1682,2.1651,1.9512,0.9512,0.9512,0.9512,0.6973,0.2375,2.7838
-14,10,1.0,0.5,2.0,2.0,2.0,2,0.5,1.0,2,1,2,0,801.0,1814.0
+14,5,1,0,normal,5.0000,0.5000,0.5000,0.5000,3,1,2.5267,2.5240,2.1029,1.1029,1.1029,1.1029,0.7956,0.2457,1.7884
-15,10,0.5,2.0,1.0,0.5,1.0,1,2.0,0.5,1,1,2,0,2442.0,5980.0
+15,15,1,0,normal,10.0000,0.7000,1.0000,0.3000,3,1,2.4596,2.4587,2.0507,1.0507,1.0507,1.0507,0.6937,0.2295,1.6522
-16,10,0.5,2.0,1.0,1.0,0.5,4,0.5,1.0,2,2,0,1,991.0,2186.0
+16,10,1,0,normal,15.0000,0.3000,0.5000,0.5000,5,3,2.7004,2.6901,2.2154,1.2154,1.2154,1.2154,0.9398,0.3189,2.8446
-17,10,0.5,2.0,1.0,2.0,2.0,2,1.0,2.0,0,0,1,2,1311.0,2776.0
+17,5,1,0,normal,5.0000,0.5000,2.0000,0.7000,7,2,1.7141,1.7141,1.6295,0.6295,0.6295,0.6295,0.6053,0.2114,2.2872
-18,5,2.0,0.5,1.0,0.5,0.5,2,0.5,2.0,1,0,2,1,879.0,1909.0
+18,15,0,1,normal,10.0000,0.3000,0.5000,0.7000,7,3,2.8486,2.8417,2.2505,1.2505,1.2505,1.2505,0.7427,0.2592,3.1507
-19,5,2.0,0.5,1.0,1.0,2.0,1,1.0,0.5,2,1,0,2,1354.0,3132.0
+19,10,0,1,normal,15.0000,0.5000,2.0000,0.3000,3,2,1.7124,1.7124,1.6343,0.6343,0.6343,0.6343,0.6604,0.2232,1.6145
-20,5,2.0,0.5,1.0,2.0,1.0,4,2.0,1.0,0,2,1,0,1727.0,3673.0
+20,5,0,1,normal,5.0000,0.7000,1.0000,0.5000,5,1,2.4396,2.4394,2.0387,1.0387,1.0387,1.0387,0.6063,0.2114,1.9457
-21,5,1.0,2.0,0.5,0.5,0.5,2,1.0,0.5,2,2,1,0,1379.0,3184.0
+21,15,0,1,normal,10.0000,0.5000,0.5000,0.7000,3,2,2.8352,2.8280,2.2059,1.2059,1.2059,1.2059,0.8535,0.2636,1.8619
-22,5,1.0,2.0,0.5,1.0,2.0,1,2.0,1.0,0,0,2,1,2145.0,4658.0
+22,10,0,1,normal,15.0000,0.7000,2.0000,0.3000,5,1,2.4427,2.4400,2.0472,1.0472,1.0472,1.0472,0.7229,0.2371,2.1480
-23,5,1.0,2.0,0.5,2.0,1.0,4,0.5,2.0,1,1,0,2,810.0,1764.0
+23,5,0,1,normal,5.0000,0.3000,1.0000,0.5000,7,3,1.9760,1.9726,1.8200,0.8200,0.8200,0.8200,0.6333,0.2156,2.5817
-24,5,0.5,1.0,2.0,0.5,0.5,2,2.0,1.0,0,1,0,2,2412.0,5783.0
+24,15,0,1,uniform,15.0000,0.5000,2.0000,0.5000,7,1,2.4941,2.4874,2.0964,1.0964,1.0964,1.0964,0.8709,0.2819,3.1027
-25,5,0.5,1.0,2.0,1.0,2.0,1,0.5,2.0,1,2,1,0,915.0,1973.0
+25,10,0,1,uniform,5.0000,0.7000,1.0000,0.7000,3,3,1.8998,1.8989,1.7728,0.7728,0.7728,0.7728,0.6528,0.2213,1.6143
-26,5,0.5,1.0,2.0,2.0,1.0,4,1.0,0.5,2,0,2,1,1336.0,3087.0
+26,5,0,1,uniform,10.0000,0.3000,0.5000,0.3000,5,2,2.9478,2.9360,2.3718,1.3718,1.3718,1.3718,1.0644,0.3634,3.0396
+27,15,0,0,normal,15.0000,0.5000,1.0000,0.5000,3,3,1.9505,1.9486,1.7987,0.7987,0.7987,0.7987,0.7731,0.2469,1.7459
+28,10,0,0,normal,5.0000,0.7000,0.5000,0.7000,5,2,2.7389,2.7375,2.1211,1.1211,1.1211,1.1211,0.6069,0.2114,1.9503
+29,5,0,0,normal,10.0000,0.3000,2.0000,0.3000,7,1,2.5236,2.5166,2.1179,1.1179,1.1179,1.1179,0.6844,0.2288,2.8678
+30,15,0,0,uniform,15.0000,0.7000,0.5000,0.5000,7,2,2.8101,2.8011,2.2076,1.2076,1.2076,1.2076,0.9796,0.3160,3.1324
+31,10,0,0,uniform,5.0000,0.3000,2.0000,0.7000,3,1,2.4699,2.4632,2.0718,1.0718,1.0718,1.0718,0.9488,0.2821,1.9815
+32,5,0,0,uniform,10.0000,0.5000,1.0000,0.3000,5,3,1.9579,1.9571,1.8257,0.8257,0.8257,0.8257,0.7234,0.2457,2.1928
+33,15,0,0,uniform,15.0000,0.3000,1.0000,0.7000,5,1,2.6051,2.5958,2.1811,1.1811,1.1811,1.1811,1.0716,0.3459,3.0091
+34,10,0,0,uniform,5.0000,0.5000,0.5000,0.3000,7,3,2.6592,2.6562,2.1402,1.1402,1.1402,1.1402,0.6135,0.2147,2.4573
+35,5,0,0,uniform,10.0000,0.7000,2.0000,0.5000,3,2,1.7640,1.7640,1.6526,0.6526,0.6526,0.6526,0.6672,0.2246,1.6143

anova.py

@@ -110,49 +110,16 @@ def anova(lst_col_seg, n_level, oa_file, result_file, alpha=0.1):
 
 if __name__ == '__main__':
     # prep data
-    str_sql = """
+    result = pd.read_csv("experiment_result.csv", index_col=None)
-    select * from
-    (select distinct idx_scenario, n_max_trial, crit_supplier,
-    firm_pref_request, firm_pref_accept, netw_pref_cust_n,
-    netw_pref_cust_size, cap_limit, diff_new_conn, diff_remove
-    from iiabmdb.with_exp_experiment) as a
-    inner join
-    (
-    select idx_scenario,
-    sum(n_disrupt_s) as n_disrupt_s, sum(n_disrupt_t) as n_disrupt_t from
-    iiabmdb.with_exp_experiment as a
-    inner join
-    (
-    select e_id, count(n_s_disrupt_t) as n_disrupt_s,
-    sum(n_s_disrupt_t) as n_disrupt_t from
-    iiabmdb.with_exp_sample as a
-    inner join
-    (select a.s_id as s_id, count(id) as n_s_disrupt_t from
-    iiabmdb.with_exp_result as a
-    inner join
-    (select distinct s_id from iiabmdb.with_exp_result where ts > 0) as b
-    on a.s_id = b.s_id
-    group by s_id
-    ) as b
-    on a.id = b.s_id
-    group by e_id
-    ) as b
-    on a.id = b.e_id
-    group by idx_scenario) as b
-    on a.idx_scenario = b.idx_scenario;
-
-    """
-    result = pd.read_sql(sql=str_sql,
-                         con=engine)
     result.drop('idx_scenario', 1, inplace=True)
     df_oa = pd.read_csv("oa_with_exp.csv", index_col=None)
-    result = pd.concat(
+    scenario_result = pd.concat(
         [result.iloc[:, 0:10],
          df_oa.iloc[:, -4:],
          result.iloc[:, -2:]], axis=1)
     result.to_csv('analysis\\experiment_result.csv')
 
-    # 9 factors (X), 4 for error (E), and 2 indicators (Y)
+    # 10 factors (X), 13 for error (E), and 9 indicators (Y)
-    the_lst_col_seg = [10, 3, 2]
+    the_lst_col_seg = [10, 13, 9]
     the_n_level = 3
     anova(the_lst_col_seg, the_n_level, "oa25.txt", result, 0.1)

anova_visualization.py

@@ -0,0 +1,14 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+df_anova = pd.read_csv('analysis/anova.csv', index_col=0)
+df_anova = df_anova.stack().reset_index()
+df_anova.rename(columns={'level_0': 'x',
+                         'level_1': 'y type',
+                         0: 'p value'}, inplace=True)
+print(df_anova)
+sns.set_theme(style="whitegrid")
+g = sns.catplot(data=df_anova, kind="bar", x="x", y="p value", hue="y type")
+g.set_xticklabels(rotation=30)
+plt.show()

firm_n_prod.csv

@@ -0,0 +1,172 @@
+code,n_prod
+0,1
+1,1
+2,1
+3,4
+4,1
+5,4
+6,5
+7,1
+8,1
+9,2
+10,1
+11,1
+12,1
+13,17
+14,2
+15,1
+16,4
+17,1
+18,1
+19,1
+20,1
+21,1
+22,24
+23,10
+24,1
+25,1
+26,7
+27,1
+28,1
+29,1
+30,1
+31,7
+32,1
+33,4
+34,1
+35,1
+36,1
+37,6
+38,5
+39,1
+40,4
+41,7
+42,3
+43,2
+44,1
+45,9
+46,1
+47,9
+48,1
+49,8
+50,1
+51,1
+52,1
+53,15
+54,3
+55,6
+56,2
+57,4
+58,7
+59,1
+60,5
+61,1
+62,5
+63,3
+64,1
+65,1
+66,1
+67,1
+68,3
+69,1
+70,2
+71,1
+72,1
+73,1
+74,2
+75,1
+76,1
+77,2
+78,5
+79,16
+80,2
+81,4
+82,4
+83,1
+84,3
+85,2
+86,1
+87,1
+88,1
+89,3
+90,1
+91,1
+92,1
+93,1
+94,1
+95,2
+96,2
+97,3
+98,1
+99,6
+100,1
+101,1
+102,2
+103,1
+104,1
+105,1
+106,6
+107,1
+108,2
+109,1
+110,1
+111,3
+112,1
+113,1
+114,1
+115,2
+116,1
+117,11
+118,1
+119,1
+120,1
+121,1
+122,1
+123,1
+124,2
+125,1
+126,7
+127,2
+128,1
+129,2
+130,5
+131,5
+132,1
+133,2
+134,1
+135,11
+136,1
+137,6
+138,1
+139,1
+140,7
+141,1
+142,3
+143,5
+144,4
+145,1
+146,1
+147,1
+148,3
+149,4
+150,1
+151,1
+152,1
+153,2
+154,6
+155,1
+156,1
+157,1
+158,1
+159,1
+160,1
+161,3
+162,2
+163,6
+164,1
+165,4
+166,1
+167,1
+168,7
+169,1
+170,1