anova

.vscode/launch.json

@@ -12,9 +12,8 @@
             "console": "integratedTerminal",
             "justMyCode": true,
             "args": [
-                "--exp", "without_exp",
+                "--exp", "with_exp",
                 "--job", "24",
-                "--reset_db", "True",
             ]
         }
     ]

SQL_running_check.sql

@@ -1,4 +1,34 @@
 select id, e_id, idx_sample, seed, ts_done from iiabmdb.without_exp_sample where is_done_flag != -1 order by ts_done;
 select count(id) from iiabmdb.without_exp_sample where is_done_flag != -1;
-select count(id) from iiabmdb.without_exp_sample;
+select count(id) from iiabmdb.without_exp_sample‘;
-select count(id) from iiabmdb.without_exp_sample where is_done_flag != -1;
+select count(id) from iiabmdb.with_exp_sample where is_done_flag != -1;
+
+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;
+

analysis/experiment_result.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

anova.py

@@ -0,0 +1,156 @@
+import numpy as np
+import pandas as pd
+from orm import engine
+from scipy.stats import f
+
+
+"""
+    This file needs to define the info in the *main* block,
+    and then run the anova function.
+"""
+
+
+def do_print(lst_value, str_col):
+    """
+    Just for friendly-looking printing
+
+    :param lst_value:
+    :param str_col:
+    :return:
+    """
+    str_data = '\t'.join(
+        [str(round(e, 4 if 'P value' in str_col else 3)) for e in lst_value])
+    print(f'{str_col}\t{str_data}')
+
+
+def anova(lst_col_seg, n_level, oa_file, result_file, alpha=0.1):
+    """
+    Give the files and info, compute the significance of each X for each Y
+
+    :param lst_col_seg: record the number of X, E, and Y.
+    :param n_level:
+    :param oa_file:
+    :param result_file:
+    :param alpha: significance level, usually 0.1, 0.05, 0.01
+    :return:
+    """
+    # read and check the files
+    df_oa = pd.read_csv("oa_with_exp.csv", index_col=None)
+    df_res = result_file
+    assert df_res.shape[1] == sum(lst_col_seg), 'the column number is wrong'
+    assert df_oa.shape[1] == lst_col_seg[0] + \
+        lst_col_seg[1], 'the column number is wrong'
+    lst_head = [f"{idx+1}_{ind_name}" for idx,
+                ind_name in enumerate(df_res.columns)]
+
+    # The three lines below define some coefficients for further computation
+    n_col_input = lst_col_seg[0] + lst_col_seg[1]
+    n_exp_row = df_res.shape[0]
+    n_degree_error = n_exp_row - 1 - (n_level - 1) * lst_col_seg[0]
+
+    df_output = df_res.iloc[:, n_col_input:]
+
+    print("Source\tSource\t" + '\t'.join(lst_head[:lst_col_seg[0]]) + "\te")
+    print("DOF\tDOF\t" + '\t'.join([str(n_level-1)]
+          * lst_col_seg[0]) + f"\t{n_degree_error}")
+
+    lst_report = []
+
+    # start to loop each Y
+    for idx_col in range(lst_col_seg[2]):
+        str_ind_name = lst_head[idx_col+n_col_input]
+
+        df_y_col = df_output.iloc[:, idx_col]  # the y column
+        df_y_col_repeated = np.tile(
+            df_y_col, (n_col_input, 1)).T  # repeat the y column
+        big_t = df_y_col.sum()  # the big T
+
+        # generate T1, ..., T(n_levels)
+        lst_2d_big_t = []  # Table 1, row 10, 11, 12
+        for level in range(n_level):
+            arr_big_t = np.sum(df_y_col_repeated *
+                               np.where(df_oa == level, 1, 0), axis=0)
+            lst_2d_big_t.append(arr_big_t.tolist())
+        arr_big_t_2 = np.power(np.array(lst_2d_big_t), 2)
+        arr_s = np.sum(arr_big_t_2, axis=0) / (n_exp_row / n_level) - \
+            big_t * big_t / n_exp_row  # Table 1, last row
+        assert arr_s.size == n_col_input, 'wrong arr_s size'
+
+        # so far, the first table is computed. Now, compute the second table
+        df_s = pd.DataFrame(arr_s.reshape((1, n_col_input)),
+                            columns=lst_head[:n_col_input])
+        do_print(arr_s.tolist(), f'{str_ind_name}\tS')  # Table 2, col 2
+
+        df_s_non_error = df_s.iloc[:, :lst_col_seg[0]] / (n_level - 1)
+        ms_of_error = \
+            df_s.iloc[:, lst_col_seg[0]:].sum().sum() / n_degree_error
+
+        do_print(df_s_non_error.values.tolist()[
+                 0] + [ms_of_error], f'{str_ind_name}\tMS')  # Table 2, col 4
+
+        arr_f = df_s_non_error / ms_of_error
+        # Table 2, col 5
+        do_print(arr_f.values.tolist()[0], f'{str_ind_name}\tF ratio')
+
+        # from scipy.stats import f
+        arr_p_value = f.sf(arr_f, n_level - 1, n_degree_error)
+        # Table 2, col 6
+        do_print(arr_p_value.tolist()[0], f'{str_ind_name}\tP value')
+
+        lst_sig = [c for c, p in zip(
+            lst_head[:lst_col_seg[0]], arr_p_value[0].tolist()) if p < alpha]
+
+        if len(lst_sig) > 0:
+            lst_report.append(
+                f"For indicator {str_ind_name}, the sig factors are {lst_sig}")
+
+    for s in lst_report:
+        print(s)
+
+
+if __name__ == '__main__':
+    # prep data
+    str_sql = """
+    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(
+        [result.iloc[:, 0:9], 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)
+    the_lst_col_seg = [9, 4, 2]
+    the_n_level = 3
+    anova(the_lst_col_seg, the_n_level, "oa25.txt", result, 0.1)

conf_db_prefix.yaml

@@ -1 +1 @@
-db_name_prefix: without_exp
+db_name_prefix: with_exp

controller_db.py

@@ -94,6 +94,7 @@ class ControllerDB:
         df_xv = pd.read_csv("xv.csv", index_col=None)
         # read the OA table
         df_oa = pd.read_csv("oa_with_exp.csv", index_col=None)
+        df_oa = df_oa.iloc[:, 0:9]
         for idx_scenario, row in df_oa.iterrows():
             dct_exp_para = {}
             for idx_col, para_level in enumerate(row):

oa_with_exp.csv

@@ -1,28 +1,28 @@
-X1,X2,X3,X4,X5,X6,X7,X8,X9
+X1,X2,X3,X4,X5,X6,X7,X8,X9,X10,X11,X12,X13
-0,0,0,0,0,0,0,0,0
+0,0,0,0,0,0,0,0,0,0,0,0,0
-0,0,0,0,1,1,1,1,1
+0,0,0,0,1,1,1,1,1,1,1,1,1
-0,0,0,0,2,2,2,2,2
+0,0,0,0,2,2,2,2,2,2,2,2,2
-0,1,1,1,0,0,0,1,1
+0,1,1,1,0,0,0,1,1,1,2,2,2
-0,1,1,1,1,1,1,2,2
+0,1,1,1,1,1,1,2,2,2,0,0,0
-0,1,1,1,2,2,2,0,0
+0,1,1,1,2,2,2,0,0,0,1,1,1
-0,2,2,2,0,0,0,2,2
+0,2,2,2,0,0,0,2,2,2,1,1,1
-0,2,2,2,1,1,1,0,0
+0,2,2,2,1,1,1,0,0,0,2,2,2
-0,2,2,2,2,2,2,1,1
+0,2,2,2,2,2,2,1,1,1,0,0,0
-1,0,1,2,0,1,2,0,1
+1,0,1,2,0,1,2,0,1,2,0,1,2
-1,0,1,2,1,2,0,1,2
+1,0,1,2,1,2,0,1,2,0,1,2,0
-1,0,1,2,2,0,1,2,0
+1,0,1,2,2,0,1,2,0,1,2,0,1
-1,1,2,0,0,1,2,1,2
+1,1,2,0,0,1,2,1,2,0,2,0,1
-1,1,2,0,1,2,0,2,0
+1,1,2,0,1,2,0,2,0,1,0,1,2
-1,1,2,0,2,0,1,0,1
+1,1,2,0,2,0,1,0,1,2,1,2,0
-1,2,0,1,0,1,2,2,0
+1,2,0,1,0,1,2,2,0,1,1,2,0
-1,2,0,1,1,2,0,0,1
+1,2,0,1,1,2,0,0,1,2,2,0,1
-1,2,0,1,2,0,1,1,2
+1,2,0,1,2,0,1,1,2,0,0,1,2
-2,0,2,1,0,2,1,0,2
+2,0,2,1,0,2,1,0,2,1,0,2,1
-2,0,2,1,1,0,2,1,0
+2,0,2,1,1,0,2,1,0,2,1,0,2
-2,0,2,1,2,1,0,2,1
+2,0,2,1,2,1,0,2,1,0,2,1,0
-2,1,0,2,0,2,1,1,0
+2,1,0,2,0,2,1,1,0,2,2,1,0
-2,1,0,2,1,0,2,2,1
+2,1,0,2,1,0,2,2,1,0,0,2,1
-2,1,0,2,2,1,0,0,2
+2,1,0,2,2,1,0,0,2,1,1,0,2
-2,2,1,0,0,2,1,2,1
+2,2,1,0,0,2,1,2,1,0,1,0,2
-2,2,1,0,1,0,2,0,2
+2,2,1,0,1,0,2,0,2,1,2,1,0
-2,2,1,0,2,1,0,1,0
+2,2,1,0,2,1,0,1,0,2,0,2,1

oa_without_exp.csv

@@ -1,2 +1,2 @@
-X1,X2,X3,X4,X5,X6,X7,X8,X9
+X1,X2,X3,X4,X5,X6,X7,X8,X9,X10,X11,X12,X13
-1,1,1,1,1,1,1,1,1
+1,1,1,1,1,1,1,1,1,1,1,1,1

xv.csv

@@ -1,4 +1,4 @@
 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
 15,2,2,2,0.5,2,4,0.5,0.5
 10,1,1,1,1,1,2,1,1
-5,0.5,0.5,0.5,2,0.5,0,2,2
+5,0.5,0.5,0.5,2,0.5,1,2,2