From 01e725a93eeb7ad76e8843e0cfe83205a57282dd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ricardo=20Montan=CC=83ana?= <rmontanana@gmail.com>
Date: Thu, 1 Apr 2021 01:52:08 +0200
Subject: [PATCH] Reformat table.tex in analysis_mysql

---
 .gitignore        |   3 +-
 analysis_mysql.py | 108 +++++++++++++++++++++++++++++++++++++++++++---
 report.csv        |  53 ++++++++++++++++++++++-
 3 files changed, 154 insertions(+), 10 deletions(-)

diff --git a/.gitignore b/.gitignore
index 2fea4c8..0bdb8a9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -135,4 +135,5 @@ experimentation/.myconfig
 experimentation/.tunnel
 results
 report_score.sql
-datasets_types
\ No newline at end of file
+datasets_types
+table.tex
\ No newline at end of file
diff --git a/analysis_mysql.py b/analysis_mysql.py
index 2c0d692..be65f9d 100644
--- a/analysis_mysql.py
+++ b/analysis_mysql.py
@@ -6,6 +6,7 @@ from experimentation.Utils import TextColor
 from experimentation.Database import MySQL
 
 report_csv = "report.csv"
+table_tex = "table.tex"
 models_tree = [
     "stree",
     "stree_default",
@@ -47,6 +48,13 @@ def parse_arguments() -> Tuple[str, str, str, bool, bool]:
         required=False,
         default=False,
     )
+    ap.add_argument(
+        "-t",
+        "--tex-output",
+        type=bool,
+        required=False,
+        default=False,
+    )
     ap.add_argument(
         "-o",
         "--compare",
@@ -55,7 +63,74 @@ def parse_arguments() -> Tuple[str, str, str, bool, bool]:
         default=False,
     )
     args = ap.parse_args()
-    return (args.experiment, args.model, args.csv_output, args.compare)
+    return (
+        args.experiment,
+        args.model,
+        args.csv_output,
+        args.tex_output,
+        args.compare,
+    )
+
+
+def print_header_tex(file_tex, second=False):
+    # old_header = (
+    #     "\\begin{table}[ht]\n"
+    #     "\\centering"
+    #     "\\resizebox{\\textwidth}{!}{\\begin{tabular}{|r|l|r|r|r|c|c|c|c|c|c|
+    # c"
+    #     "|}"
+    #     "\\hline\n"
+    #     "\\# & Dataset & Samples & Features & Classes & stree & stree def. &
+    #  "
+    #     "wodt & j48svm & oc1 & cart & baseRaF\\\\\n"
+    #     "\\hline"
+    # )
+    cont = ""
+    num = ""
+    if second:
+        cont = " (cont.)"
+        num = "2"
+    header = (
+        "\\begin{sidewaystable}[ht]\n"
+        "\\centering\n"
+        "\\renewcommand{\\arraystretch}{1.2}\n"
+        "\\renewcommand{\\tabcolsep}{0.07cm}\n"
+        "\\caption{Datasets used during the experimentation" + cont + "}\n"
+        "\\label{table:datasets" + num + "}\n"
+        "\\resizebox{0.95\\textwidth}{!}{\n"
+        "\\begin{tabular}{rlrrrccccccc}\\hline\n"
+        "\\# & Dataset & \\#S & \\#F & \\#L & stree & stree default & wodt & "
+        "j48svm & oc1 & cart & baseRaF\\\\\n"
+        "\\hline\n"
+    )
+    print(header, file=file_tex)
+
+
+def print_line_tex(number, dataset, line, file_tex):
+    dataset_name = dataset.replace("_", "\\_")
+    print_line = (
+        f"{number} & {dataset_name} & {line['samp']} & {line['var']} "
+        f"& {line['cls']}"
+    )
+    for model in models:
+        item = line[model]
+        print_line += f" & {item}"
+    print_line += "\\\\"
+    print(f"{print_line}", file=file_tex)
+
+
+def print_footer_tex(file_tex):
+    # old_footer = (
+    #     "\\hline\n"
+    #     "\\csname @@input\\endcsname wintieloss\n"
+    #     "\\hline\n"
+    #     "\\end{tabular}}\n"
+    #     "\\caption{Datasets used during the experimentation}\n"
+    #     "\\label{table:datasets}\n"
+    #     "\\end{table}"
+    # )
+    footer = "\\hline\n\\end{tabular}}\n\\end{sidewaystable}\n"
+    print(f"{footer}", file=file_tex)
 
 
 def report_header_content(title, experiment, model_type):
@@ -110,7 +185,7 @@ def report_footer(agg):
         )
 
 
-(experiment, model_type, csv_output, compare) = parse_arguments()
+(experiment, model_type, csv_output, tex_output, compare) = parse_arguments()
 dbh = MySQL()
 database = dbh.get_connection()
 dt = Datasets(False, False, "tanveer")
@@ -123,6 +198,9 @@ fields = (
     "Lea",
     "Dep",
 )
+if tex_output:
+    # We need the stree_std column for the tex output
+    compare = True
 if not compare:
     # remove stree_default from fields list and lengths
     models_tree.pop(1)
@@ -140,9 +218,12 @@ for item in [
     agg[item] = {}
     agg[item]["best"] = 0
 if csv_output:
-    f = open(report_csv, "w")
-    print("dataset, classifier, accuracy", file=f)
-for dataset in dt:
+    file_csv = open(report_csv, "w")
+    print("dataset, classifier, accuracy", file=file_csv)
+if tex_output:
+    file_tex = open(table_tex, "w")
+    print_header_tex(file_tex, second=False)
+for number, dataset in enumerate(dt):
     find_one = False
     # Look for max accuracy for any given dataset
     line = {"dataset": color + dataset[0]}
@@ -154,6 +235,7 @@ for dataset in dt:
     line["nodes"] = 0
     line["leaves"] = 0
     line["depth"] = 0
+    line_tex = line.copy()
     for model in models:
         record = dbh.find_best(dataset[0], model, experiment)
         if record is None:
@@ -168,6 +250,9 @@ for dataset in dt:
             acc_std = record[11]
             find_one = True
             item = f"{accuracy:.4f}±{acc_std:.3f}"
+            line_tex[model] = item
+            if round(accuracy, 4) == round(max_accuracy, 4):
+                line_tex[model] = "\\textbf{" + item + "}"
             if accuracy == max_accuracy:
                 line[model] = (
                     TextColor.GREEN + TextColor.BOLD + item + TextColor.ENDC
@@ -176,7 +261,12 @@ for dataset in dt:
             else:
                 line[model] = color + item
             if csv_output:
-                print(f"{dataset[0]}, {model}, {accuracy}", file=f)
+                print(f"{dataset[0]}, {model}, {accuracy}", file=file_csv)
+    if tex_output:
+        print_line_tex(number + 1, dataset[0], line_tex, file_tex)
+        if number == 24:
+            print_footer_tex(file_tex)
+            print_header_tex(file_tex, second=True)
     if not find_one:
         print(TextColor.FAIL + f"*No results found for {dataset[0]}")
     else:
@@ -186,6 +276,10 @@ for dataset in dt:
         print(report_line(line))
 report_footer(agg)
 if csv_output:
-    f.close()
+    file_csv.close()
     print(f"{report_csv} file generated")
+if tex_output:
+    print_footer_tex(file_tex)
+    file_tex.close()
+    print(f"{table_tex} file generated")
 dbh.close()
diff --git a/report.csv b/report.csv
index 48aef0a..8718ed5 100644
--- a/report.csv
+++ b/report.csv
@@ -1,293 +1,342 @@
 dataset, classifier, accuracy
 balance-scale, stree, 0.97056
+balance-scale, stree_default, 0.91184
 balance-scale, wodt, 0.912
 balance-scale, j48svm, 0.94
 balance-scale, oc1, 0.9192
 balance-scale, cart, 0.78816
 balance-scale, baseRaF, 0.706738
 balloons, stree, 0.86
+balloons, stree_default, 0.653333
 balloons, wodt, 0.688333
 balloons, j48svm, 0.595
 balloons, oc1, 0.62
 balloons, cart, 0.671667
 balloons, baseRaF, 0.605
 breast-cancer-wisc-diag, stree, 0.972764
+breast-cancer-wisc-diag, stree_default, 0.968898
 breast-cancer-wisc-diag, wodt, 0.967317
 breast-cancer-wisc-diag, j48svm, 0.952878
 breast-cancer-wisc-diag, oc1, 0.933477
 breast-cancer-wisc-diag, cart, 0.93953
 breast-cancer-wisc-diag, baseRaF, 0.965694
 breast-cancer-wisc-prog, stree, 0.811128
+breast-cancer-wisc-prog, stree_default, 0.802051
 breast-cancer-wisc-prog, wodt, 0.710141
 breast-cancer-wisc-prog, j48svm, 0.724038
 breast-cancer-wisc-prog, oc1, 0.71
 breast-cancer-wisc-prog, cart, 0.699833
 breast-cancer-wisc-prog, baseRaF, 0.74485
 breast-cancer-wisc, stree, 0.966661
+breast-cancer-wisc, stree_default, 0.966661
 breast-cancer-wisc, wodt, 0.946208
 breast-cancer-wisc, j48svm, 0.967674
 breast-cancer-wisc, oc1, 0.940194
 breast-cancer-wisc, cart, 0.940629
 breast-cancer-wisc, baseRaF, 0.942857
 breast-cancer, stree, 0.734211
+breast-cancer, stree_default, 0.734211
 breast-cancer, wodt, 0.650236
 breast-cancer, j48svm, 0.707719
 breast-cancer, oc1, 0.649728
 breast-cancer, cart, 0.65444
 breast-cancer, baseRaF, 0.656438
 cardiotocography-10clases, stree, 0.712009
+cardiotocography-10clases, stree_default, 0.552558
 cardiotocography-10clases, wodt, 0.773706
 cardiotocography-10clases, j48svm, 0.830812
 cardiotocography-10clases, oc1, 0.795528
 cardiotocography-10clases, cart, 0.818864
 cardiotocography-10clases, baseRaF, 0.774788
 cardiotocography-3clases, stree, 0.891956
+cardiotocography-3clases, stree_default, 0.35207
 cardiotocography-3clases, wodt, 0.897509
 cardiotocography-3clases, j48svm, 0.927327
 cardiotocography-3clases, oc1, 0.899811
 cardiotocography-3clases, cart, 0.929258
 cardiotocography-3clases, baseRaF, 0.896715
 conn-bench-sonar-mines-rocks, stree, 0.755528
+conn-bench-sonar-mines-rocks, stree_default, 0.755528
 conn-bench-sonar-mines-rocks, wodt, 0.824959
 conn-bench-sonar-mines-rocks, j48svm, 0.73892
 conn-bench-sonar-mines-rocks, oc1, 0.710798
 conn-bench-sonar-mines-rocks, cart, 0.728711
 conn-bench-sonar-mines-rocks, baseRaF, 0.772981
 cylinder-bands, stree, 0.715049
+cylinder-bands, stree_default, 0.715049
 cylinder-bands, wodt, 0.704074
 cylinder-bands, j48svm, 0.726351
 cylinder-bands, oc1, 0.67106
 cylinder-bands, cart, 0.712703
 cylinder-bands, baseRaF, 0.675117
 dermatology, stree, 0.971833
+dermatology, stree_default, 0.966087
 dermatology, wodt, 0.965557
 dermatology, j48svm, 0.955735
 dermatology, oc1, 0.916087
 dermatology, cart, 0.932766
 dermatology, baseRaF, 0.970723
 echocardiogram, stree, 0.814758
+echocardiogram, stree_default, 0.808832
 echocardiogram, wodt, 0.733875
 echocardiogram, j48svm, 0.805527
 echocardiogram, oc1, 0.748291
 echocardiogram, cart, 0.745043
 echocardiogram, baseRaF, 0.753522
 fertility, stree, 0.88
+fertility, stree_default, 0.866
 fertility, wodt, 0.785
 fertility, j48svm, 0.857
 fertility, oc1, 0.793
 fertility, cart, 0.8
 fertility, baseRaF, 0.798
 haberman-survival, stree, 0.735637
+haberman-survival, stree_default, 0.735637
 haberman-survival, wodt, 0.664707
 haberman-survival, j48svm, 0.714056
 haberman-survival, oc1, 0.651634
 haberman-survival, cart, 0.65
 haberman-survival, baseRaF, 0.720133
 heart-hungarian, stree, 0.827522
+heart-hungarian, stree_default, 0.817674
 heart-hungarian, wodt, 0.764909
 heart-hungarian, j48svm, 0.785026
 heart-hungarian, oc1, 0.758298
 heart-hungarian, cart, 0.760508
 heart-hungarian, baseRaF, 0.779804
 hepatitis, stree, 0.824516
+hepatitis, stree_default, 0.796129
 hepatitis, wodt, 0.785806
 hepatitis, j48svm, 0.761935
 hepatitis, oc1, 0.756774
 hepatitis, cart, 0.765161
 hepatitis, baseRaF, 0.773671
 ilpd-indian-liver, stree, 0.723498
+ilpd-indian-liver, stree_default, 0.723498
 ilpd-indian-liver, wodt, 0.676176
 ilpd-indian-liver, j48svm, 0.690339
 ilpd-indian-liver, oc1, 0.660139
 ilpd-indian-liver, cart, 0.663423
 ilpd-indian-liver, baseRaF, 0.696685
 ionosphere, stree, 0.953276
+ionosphere, stree_default, 0.866056
 ionosphere, wodt, 0.88008
 ionosphere, j48svm, 0.891984
 ionosphere, oc1, 0.879742
 ionosphere, cart, 0.895771
 ionosphere, baseRaF, 0.875389
 iris, stree, 0.965333
+iris, stree_default, 0.965333
 iris, wodt, 0.946
 iris, j48svm, 0.947333
 iris, oc1, 0.948
 iris, cart, 0.938667
 iris, baseRaF, 0.953413
 led-display, stree, 0.703
+led-display, stree_default, 0.7007
 led-display, wodt, 0.7049
 led-display, j48svm, 0.7204
 led-display, oc1, 0.6993
 led-display, cart, 0.7037
 led-display, baseRaF, 0.70178
 libras, stree, 0.788333
+libras, stree_default, 0.747778
 libras, wodt, 0.764167
 libras, j48svm, 0.66
 libras, oc1, 0.645
 libras, cart, 0.655
 libras, baseRaF, 0.726722
 low-res-spect, stree, 0.865713
+low-res-spect, stree_default, 0.853102
 low-res-spect, wodt, 0.856459
 low-res-spect, j48svm, 0.83358
 low-res-spect, oc1, 0.824671
 low-res-spect, cart, 0.829206
 low-res-spect, baseRaF, 0.790875
 lymphography, stree, 0.823425
+lymphography, stree_default, 0.77046
 lymphography, wodt, 0.808782
 lymphography, j48svm, 0.778552
 lymphography, oc1, 0.734634
 lymphography, cart, 0.766276
 lymphography, baseRaF, 0.761622
 mammographic, stree, 0.81915
+mammographic, stree_default, 0.81915
 mammographic, wodt, 0.759839
 mammographic, j48svm, 0.821435
 mammographic, oc1, 0.768805
 mammographic, cart, 0.757131
 mammographic, baseRaF, 0.780206
 molec-biol-promoter, stree, 0.767056
+molec-biol-promoter, stree_default, 0.764416
 molec-biol-promoter, wodt, 0.798528
 molec-biol-promoter, j48svm, 0.744935
 molec-biol-promoter, oc1, 0.734805
 molec-biol-promoter, cart, 0.748701
 molec-biol-promoter, baseRaF, 0.667239
 musk-1, stree, 0.916388
+musk-1, stree_default, 0.843463
 musk-1, wodt, 0.838914
 musk-1, j48svm, 0.82693
 musk-1, oc1, 0.776401
 musk-1, cart, 0.780215
 musk-1, baseRaF, 0.834034
 oocytes_merluccius_nucleus_4d, stree, 0.835125
+oocytes_merluccius_nucleus_4d, stree_default, 0.810657
 oocytes_merluccius_nucleus_4d, wodt, 0.737673
 oocytes_merluccius_nucleus_4d, j48svm, 0.741766
 oocytes_merluccius_nucleus_4d, oc1, 0.743199
 oocytes_merluccius_nucleus_4d, cart, 0.728265
 oocytes_merluccius_nucleus_4d, baseRaF, 0.792313
 oocytes_merluccius_states_2f, stree, 0.912434
+oocytes_merluccius_states_2f, stree_default, 0.912434
 oocytes_merluccius_states_2f, wodt, 0.895115
 oocytes_merluccius_states_2f, j48svm, 0.901374
 oocytes_merluccius_states_2f, oc1, 0.889223
 oocytes_merluccius_states_2f, cart, 0.891193
 oocytes_merluccius_states_2f, baseRaF, 0.910551
 oocytes_trisopterus_nucleus_2f, stree, 0.800986
+oocytes_trisopterus_nucleus_2f, stree_default, 0.800986
 oocytes_trisopterus_nucleus_2f, wodt, 0.751431
 oocytes_trisopterus_nucleus_2f, j48svm, 0.756587
 oocytes_trisopterus_nucleus_2f, oc1, 0.747697
 oocytes_trisopterus_nucleus_2f, cart, 0.734313
 oocytes_trisopterus_nucleus_2f, baseRaF, 0.76193
 oocytes_trisopterus_states_5b, stree, 0.924441
+oocytes_trisopterus_states_5b, stree_default, 0.9023
 oocytes_trisopterus_states_5b, wodt, 0.89165
 oocytes_trisopterus_states_5b, j48svm, 0.887943
 oocytes_trisopterus_states_5b, oc1, 0.86393
 oocytes_trisopterus_states_5b, cart, 0.870263
 oocytes_trisopterus_states_5b, baseRaF, 0.922149
 parkinsons, stree, 0.882051
+parkinsons, stree_default, 0.882051
 parkinsons, wodt, 0.901538
 parkinsons, j48svm, 0.844615
 parkinsons, oc1, 0.865641
 parkinsons, cart, 0.855897
 parkinsons, baseRaF, 0.87924
 pima, stree, 0.766651
+pima, stree_default, 0.766651
 pima, wodt, 0.681591
 pima, j48svm, 0.749876
 pima, oc1, 0.693027
 pima, cart, 0.701172
 pima, baseRaF, 0.697005
 pittsburg-bridges-MATERIAL, stree, 0.867749
+pittsburg-bridges-MATERIAL, stree_default, 0.787446
 pittsburg-bridges-MATERIAL, wodt, 0.79961
 pittsburg-bridges-MATERIAL, j48svm, 0.855844
 pittsburg-bridges-MATERIAL, oc1, 0.81026
 pittsburg-bridges-MATERIAL, cart, 0.783593
 pittsburg-bridges-MATERIAL, baseRaF, 0.81136
 pittsburg-bridges-REL-L, stree, 0.62519
+pittsburg-bridges-REL-L, stree_default, 0.62519
 pittsburg-bridges-REL-L, wodt, 0.617143
 pittsburg-bridges-REL-L, j48svm, 0.645048
 pittsburg-bridges-REL-L, oc1, 0.604957
 pittsburg-bridges-REL-L, cart, 0.625333
 pittsburg-bridges-REL-L, baseRaF, 0.622107
 pittsburg-bridges-SPAN, stree, 0.658713
+pittsburg-bridges-SPAN, stree_default, 0.630234
 pittsburg-bridges-SPAN, wodt, 0.606959
 pittsburg-bridges-SPAN, j48svm, 0.621579
 pittsburg-bridges-SPAN, oc1, 0.579333
 pittsburg-bridges-SPAN, cart, 0.557544
 pittsburg-bridges-SPAN, baseRaF, 0.630217
 pittsburg-bridges-T-OR-D, stree, 0.861619
+pittsburg-bridges-T-OR-D, stree_default, 0.861619
 pittsburg-bridges-T-OR-D, wodt, 0.818429
 pittsburg-bridges-T-OR-D, j48svm, 0.838333
 pittsburg-bridges-T-OR-D, oc1, 0.831545
 pittsburg-bridges-T-OR-D, cart, 0.821619
 pittsburg-bridges-T-OR-D, baseRaF, 0.821007
 planning, stree, 0.73527
+planning, stree_default, 0.70455
 planning, wodt, 0.576847
 planning, j48svm, 0.711381
 planning, oc1, 0.566988
 planning, cart, 0.586712
 planning, baseRaF, 0.590586
 post-operative, stree, 0.703333
+post-operative, stree_default, 0.573333
 post-operative, wodt, 0.535556
 post-operative, j48svm, 0.701111
 post-operative, oc1, 0.542222
 post-operative, cart, 0.567778
 post-operative, baseRaF, 0.539375
 seeds, stree, 0.952857
+seeds, stree_default, 0.949048
 seeds, wodt, 0.940476
 seeds, j48svm, 0.909524
 seeds, oc1, 0.932381
 seeds, cart, 0.900476
 seeds, baseRaF, 0.942518
 statlog-australian-credit, stree, 0.678261
+statlog-australian-credit, stree_default, 0.667246
 statlog-australian-credit, wodt, 0.561594
 statlog-australian-credit, j48svm, 0.66029
 statlog-australian-credit, oc1, 0.573913
 statlog-australian-credit, cart, 0.595507
 statlog-australian-credit, baseRaF, 0.678261
 statlog-german-credit, stree, 0.7625
+statlog-german-credit, stree_default, 0.7625
 statlog-german-credit, wodt, 0.6929
 statlog-german-credit, j48svm, 0.7244
 statlog-german-credit, oc1, 0.6874
 statlog-german-credit, cart, 0.6738
 statlog-german-credit, baseRaF, 0.68762
 statlog-heart, stree, 0.822963
+statlog-heart, stree_default, 0.822963
 statlog-heart, wodt, 0.777778
 statlog-heart, j48svm, 0.795926
 statlog-heart, oc1, 0.749259
 statlog-heart, cart, 0.762222
 statlog-heart, baseRaF, 0.747605
 statlog-image, stree, 0.956623
+statlog-image, stree_default, 0.850649
 statlog-image, wodt, 0.954632
 statlog-image, j48svm, 0.967403
 statlog-image, oc1, 0.95013
 statlog-image, cart, 0.964892
 statlog-image, baseRaF, 0.953604
 statlog-vehicle, stree, 0.788537
+statlog-vehicle, stree_default, 0.695151
 statlog-vehicle, wodt, 0.726492
 statlog-vehicle, j48svm, 0.729651
 statlog-vehicle, oc1, 0.708496
 statlog-vehicle, cart, 0.728367
 statlog-vehicle, baseRaF, 0.789572
 synthetic-control, stree, 0.95
+synthetic-control, stree_default, 0.938833
 synthetic-control, wodt, 0.973167
 synthetic-control, j48svm, 0.922333
 synthetic-control, oc1, 0.863167
 synthetic-control, cart, 0.908333
 synthetic-control, baseRaF, 0.971567
 tic-tac-toe, stree, 0.984444
+tic-tac-toe, stree_default, 0.983296
 tic-tac-toe, wodt, 0.93905
 tic-tac-toe, j48svm, 0.983295
 tic-tac-toe, oc1, 0.91849
 tic-tac-toe, cart, 0.951558
 tic-tac-toe, baseRaF, 0.974906
 vertebral-column-2clases, stree, 0.852903
+vertebral-column-2clases, stree_default, 0.852903
 vertebral-column-2clases, wodt, 0.801935
 vertebral-column-2clases, j48svm, 0.84871
 vertebral-column-2clases, oc1, 0.815161
 vertebral-column-2clases, cart, 0.784839
 vertebral-column-2clases, baseRaF, 0.822601
-wine, stree, 0.97581
+wine, stree, 0.979159
+wine, stree_default, 0.97581
 wine, wodt, 0.973048
 wine, j48svm, 0.979143
 wine, oc1, 0.916165
 wine, cart, 0.921937
 wine, baseRaF, 0.97748
-zoo, stree, 0.955524
+zoo, stree, 0.957524
+zoo, stree_default, 0.947619
 zoo, wodt, 0.954429
 zoo, j48svm, 0.92381
 zoo, oc1, 0.890952