Add tests notebook

isco_rel_results.json

@@ -0,0 +1 @@
+{"accuracy": 0.8695796975954173, "hierarchical_precision": 0.9876106194690265, "hierarchical_recall": 0.9911190053285968, "hierarchical_fmeasure": 0.9893617021276595}

isco_test_results.json

@@ -0,0 +1 @@
+{"accuracy": 0.8611914401388086, "hierarchical_precision": 0.989010989010989, "hierarchical_recall": 0.9836065573770492, "hierarchical_fmeasure": 0.9863013698630136}

isco_validation_results.json

@@ -0,0 +1 @@
+{"accuracy": 0.8576800694243564, "hierarchical_precision": 0.9757462686567164, "hierarchical_recall": 0.9812382739212008, "hierarchical_fmeasure": 0.9784845650140319}

language_results.csv

@@ -0,0 +1,13 @@
+Language,Accuracy,Hierarchical Precision,Hierarchical Recall,Hierarchical F1
+da,0.7149425287356321,0.9314641744548287,0.8898809523809523,0.9101978691019786
+en,0.9075297225891678,0.9578651685393258,0.9742857142857143,0.9660056657223796
+es,0.8794080604534005,0.9774590163934426,0.9655870445344129,0.9714867617107942
+fi,0.9286376274328082,0.9591836734693877,0.9733727810650887,0.9662261380323054
+fr,0.5772994129158513,0.8571428571428571,0.8808864265927978,0.8688524590163934
+it,0.9332579185520362,0.9616613418530351,0.9525316455696202,0.9570747217806042
+kk,0.9313346228239845,0.9816849816849816,0.9710144927536232,0.97632058287796
+ko,0.9369047619047619,0.9726962457337884,0.9827586206896551,0.9777015437392795
+pt,0.8936170212765957,0.9591836734693877,0.9563953488372093,0.957787481804949
+ru,0.9259259259259259,0.971875,0.9658385093167702,0.9688473520249222
+sv,0.9726027397260274,0.9927007299270073,1.0,0.9963369963369962
+Average,0.872860031121472,0.9566288056970947,0.9556865032750766,0.9560761429225966

tests.ipynb

@@ -9,7 +9,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -36,7 +36,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -163,22 +163,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ISCO CSV file downloaded\n",
-      "Weighted ISCO hierarchy dictionary created\n",
-      "{'1111': {'111': 0.75, '11': 0.5, '1': 0.25}, '1112': {'111': 0.75, '11': 0.5, '1': 0.25}, '1113': {'111': 0.75, '11': 0.5, '1': 0.25}, '1114': {'111': 0.75, '11': 0.5, '1': 0.25}, '1120': {'112': 0.75, '11': 0.5, '1': 0.25}, '1211': {'121': 0.75, '12': 0.5, '1': 0.25}, '1212': {'121': 0.75, '12': 0.5, '1': 0.25}, '1213': {'121': 0.75, '12': 0.5, '1': 0.25}, '1219': {'121': 0.75, '12': 0.5, '1': 0.25}, '1221': {'122': 0.75, '12': 0.5, '1': 0.25}, '1222': {'122': 0.75, '12': 0.5, '1': 0.25}, '1223': {'122': 0.75, '12': 0.5, '1': 0.25}, '1311': {'131': 0.75, '13': 0.5, '1': 0.25}, '1312': {'131': 0.75, '13': 0.5, '1': 0.25}, '1321': {'132': 0.75, '13': 0.5, '1': 0.25}, '1322': {'132': 0.75, '13': 0.5, '1': 0.25}, '1323': {'132': 0.75, '13': 0.5, '1': 0.25}, '1324': {'132': 0.75, '13': 0.5, '1': 0.25}, '1330': {'133': 0.75, '13': 0.5, '1': 0.25}, '1341': {'134': 0.75, '13': 0.5, '1': 0.25}, '1342': {'134': 0.75, '13': 0.5, '1': 0.25}, '1343': {'134': 0.75, '13': 0.5, '1': 0.25}, '1344': {'134': 0.75, '13': 0.5, '1': 0.25}, '1345': {'134': 0.75, '13': 0.5, '1': 0.25}, '1346': {'134': 0.75, '13': 0.5, '1': 0.25}, '1349': {'134': 0.75, '13': 0.5, '1': 0.25}, '1411': {'141': 0.75, '14': 0.5, '1': 0.25}, '1412': {'141': 0.75, '14': 0.5, '1': 0.25}, '1420': {'142': 0.75, '14': 0.5, '1': 0.25}, '1431': {'143': 0.75, '14': 0.5, '1': 0.25}, '1439': {'143': 0.75, '14': 0.5, '1': 0.25}, '2111': {'211': 0.75, '21': 0.5, '2': 0.25}, '2112': {'211': 0.75, '21': 0.5, '2': 0.25}, '2113': {'211': 0.75, '21': 0.5, '2': 0.25}, '2114': {'211': 0.75, '21': 0.5, '2': 0.25}, '2120': {'212': 0.75, '21': 0.5, '2': 0.25}, '2131': {'213': 0.75, '21': 0.5, '2': 0.25}, '2132': {'213': 0.75, '21': 0.5, '2': 0.25}, '2133': {'213': 0.75, '21': 0.5, '2': 0.25}, '2141': {'214': 0.75, '21': 0.5, '2': 0.25}, '2142': {'214': 0.75, '21': 0.5, '2': 0.25}, '2143': {'214': 0.75, '21': 0.5, '2': 0.25}, '2144': {'214': 0.75, '21': 0.5, '2': 0.25}, '2145': {'214': 0.75, '21': 0.5, '2': 0.25}, '2146': {'214': 0.75, '21': 0.5, '2': 0.25}, '2149': {'214': 0.75, '21': 0.5, '2': 0.25}, '2151': {'215': 0.75, '21': 0.5, '2': 0.25}, '2152': {'215': 0.75, '21': 0.5, '2': 0.25}, '2153': {'215': 0.75, '21': 0.5, '2': 0.25}, '2161': {'216': 0.75, '21': 0.5, '2': 0.25}, '2162': {'216': 0.75, '21': 0.5, '2': 0.25}, '2163': {'216': 0.75, '21': 0.5, '2': 0.25}, '2164': {'216': 0.75, '21': 0.5, '2': 0.25}, '2165': {'216': 0.75, '21': 0.5, '2': 0.25}, '2166': {'216': 0.75, '21': 0.5, '2': 0.25}, '2211': {'221': 0.75, '22': 0.5, '2': 0.25}, '2212': {'221': 0.75, '22': 0.5, '2': 0.25}, '2221': {'222': 0.75, '22': 0.5, '2': 0.25}, '2222': {'222': 0.75, '22': 0.5, '2': 0.25}, '2230': {'223': 0.75, '22': 0.5, '2': 0.25}, '2240': {'224': 0.75, '22': 0.5, '2': 0.25}, '2250': {'225': 0.75, '22': 0.5, '2': 0.25}, '2261': {'226': 0.75, '22': 0.5, '2': 0.25}, '2262': {'226': 0.75, '22': 0.5, '2': 0.25}, '2263': {'226': 0.75, '22': 0.5, '2': 0.25}, '2264': {'226': 0.75, '22': 0.5, '2': 0.25}, '2265': {'226': 0.75, '22': 0.5, '2': 0.25}, '2266': {'226': 0.75, '22': 0.5, '2': 0.25}, '2267': {'226': 0.75, '22': 0.5, '2': 0.25}, '2269': {'226': 0.75, '22': 0.5, '2': 0.25}, '2310': {'231': 0.75, '23': 0.5, '2': 0.25}, '2320': {'232': 0.75, '23': 0.5, '2': 0.25}, '2330': {'233': 0.75, '23': 0.5, '2': 0.25}, '2341': {'234': 0.75, '23': 0.5, '2': 0.25}, '2342': {'234': 0.75, '23': 0.5, '2': 0.25}, '2351': {'235': 0.75, '23': 0.5, '2': 0.25}, '2352': {'235': 0.75, '23': 0.5, '2': 0.25}, '2353': {'235': 0.75, '23': 0.5, '2': 0.25}, '2354': {'235': 0.75, '23': 0.5, '2': 0.25}, '2355': {'235': 0.75, '23': 0.5, '2': 0.25}, '2356': {'235': 0.75, '23': 0.5, '2': 0.25}, '2359': {'235': 0.75, '23': 0.5, '2': 0.25}, '2411': {'241': 0.75, '24': 0.5, '2': 0.25}, '2412': {'241': 0.75, '24': 0.5, '2': 0.25}, '2413': {'241': 0.75, '24': 0.5, '2': 0.25}, '2421': {'242': 0.75, '24': 0.5, '2': 0.25}, '2422': {'242': 0.75, '24': 0.5, '2': 0.25}, '2423': {'242': 0.75, '24': 0.5, '2': 0.25}, '2424': {'242': 0.75, '24': 0.5, '2': 0.25}, '2431': {'243': 0.75, '24': 0.5, '2': 0.25}, '2432': {'243': 0.75, '24': 0.5, '2': 0.25}, '2433': {'243': 0.75, '24': 0.5, '2': 0.25}, '2434': {'243': 0.75, '24': 0.5, '2': 0.25}, '2511': {'251': 0.75, '25': 0.5, '2': 0.25}, '2512': {'251': 0.75, '25': 0.5, '2': 0.25}, '2513': {'251': 0.75, '25': 0.5, '2': 0.25}, '2514': {'251': 0.75, '25': 0.5, '2': 0.25}, '2519': {'251': 0.75, '25': 0.5, '2': 0.25}, '2521': {'252': 0.75, '25': 0.5, '2': 0.25}, '2522': {'252': 0.75, '25': 0.5, '2': 0.25}, '2523': {'252': 0.75, '25': 0.5, '2': 0.25}, '2529': {'252': 0.75, '25': 0.5, '2': 0.25}, '2611': {'261': 0.75, '26': 0.5, '2': 0.25}, '2612': {'261': 0.75, '26': 0.5, '2': 0.25}, '2619': {'261': 0.75, '26': 0.5, '2': 0.25}, '2621': {'262': 0.75, '26': 0.5, '2': 0.25}, '2622': {'262': 0.75, '26': 0.5, '2': 0.25}, '2631': {'263': 0.75, '26': 0.5, '2': 0.25}, '2632': {'263': 0.75, '26': 0.5, '2': 0.25}, '2633': {'263': 0.75, '26': 0.5, '2': 0.25}, '2634': {'263': 0.75, '26': 0.5, '2': 0.25}, '2635': {'263': 0.75, '26': 0.5, '2': 0.25}, '2636': {'263': 0.75, '26': 0.5, '2': 0.25}, '2641': {'264': 0.75, '26': 0.5, '2': 0.25}, '2642': {'264': 0.75, '26': 0.5, '2': 0.25}, '2643': {'264': 0.75, '26': 0.5, '2': 0.25}, '2651': {'265': 0.75, '26': 0.5, '2': 0.25}, '2652': {'265': 0.75, '26': 0.5, '2': 0.25}, '2653': {'265': 0.75, '26': 0.5, '2': 0.25}, '2654': {'265': 0.75, '26': 0.5, '2': 0.25}, '2655': {'265': 0.75, '26': 0.5, '2': 0.25}, '2656': {'265': 0.75, '26': 0.5, '2': 0.25}, '2659': {'265': 0.75, '26': 0.5, '2': 0.25}, '3111': {'311': 0.75, '31': 0.5, '3': 0.25}, '3112': {'311': 0.75, '31': 0.5, '3': 0.25}, '3113': {'311': 0.75, '31': 0.5, '3': 0.25}, '3114': {'311': 0.75, '31': 0.5, '3': 0.25}, '3115': {'311': 0.75, '31': 0.5, '3': 0.25}, '3116': {'311': 0.75, '31': 0.5, '3': 0.25}, '3117': {'311': 0.75, '31': 0.5, '3': 0.25}, '3118': {'311': 0.75, '31': 0.5, '3': 0.25}, '3119': {'311': 0.75, '31': 0.5, '3': 0.25}, '3121': {'312': 0.75, '31': 0.5, '3': 0.25}, '3122': {'312': 0.75, '31': 0.5, '3': 0.25}, '3123': {'312': 0.75, '31': 0.5, '3': 0.25}, '3131': {'313': 0.75, '31': 0.5, '3': 0.25}, '3132': {'313': 0.75, '31': 0.5, '3': 0.25}, '3133': {'313': 0.75, '31': 0.5, '3': 0.25}, '3134': {'313': 0.75, '31': 0.5, '3': 0.25}, '3135': {'313': 0.75, '31': 0.5, '3': 0.25}, '3139': {'313': 0.75, '31': 0.5, '3': 0.25}, '3141': {'314': 0.75, '31': 0.5, '3': 0.25}, '3142': {'314': 0.75, '31': 0.5, '3': 0.25}, '3143': {'314': 0.75, '31': 0.5, '3': 0.25}, '3151': {'315': 0.75, '31': 0.5, '3': 0.25}, '3152': {'315': 0.75, '31': 0.5, '3': 0.25}, '3153': {'315': 0.75, '31': 0.5, '3': 0.25}, '3154': {'315': 0.75, '31': 0.5, '3': 0.25}, '3155': {'315': 0.75, '31': 0.5, '3': 0.25}, '3211': {'321': 0.75, '32': 0.5, '3': 0.25}, '3212': {'321': 0.75, '32': 0.5, '3': 0.25}, '3213': {'321': 0.75, '32': 0.5, '3': 0.25}, '3214': {'321': 0.75, '32': 0.5, '3': 0.25}, '3221': {'322': 0.75, '32': 0.5, '3': 0.25}, '3222': {'322': 0.75, '32': 0.5, '3': 0.25}, '3230': {'323': 0.75, '32': 0.5, '3': 0.25}, '3240': {'324': 0.75, '32': 0.5, '3': 0.25}, '3251': {'325': 0.75, '32': 0.5, '3': 0.25}, '3252': {'325': 0.75, '32': 0.5, '3': 0.25}, '3253': {'325': 0.75, '32': 0.5, '3': 0.25}, '3254': {'325': 0.75, '32': 0.5, '3': 0.25}, '3255': {'325': 0.75, '32': 0.5, '3': 0.25}, '3256': {'325': 0.75, '32': 0.5, '3': 0.25}, '3257': {'325': 0.75, '32': 0.5, '3': 0.25}, '3258': {'325': 0.75, '32': 0.5, '3': 0.25}, '3259': {'325': 0.75, '32': 0.5, '3': 0.25}, '3311': {'331': 0.75, '33': 0.5, '3': 0.25}, '3312': {'331': 0.75, '33': 0.5, '3': 0.25}, '3313': {'331': 0.75, '33': 0.5, '3': 0.25}, '3314': {'331': 0.75, '33': 0.5, '3': 0.25}, '3315': {'331': 0.75, '33': 0.5, '3': 0.25}, '3321': {'332': 0.75, '33': 0.5, '3': 0.25}, '3322': {'332': 0.75, '33': 0.5, '3': 0.25}, '3323': {'332': 0.75, '33': 0.5, '3': 0.25}, '3324': {'332': 0.75, '33': 0.5, '3': 0.25}, '3331': {'333': 0.75, '33': 0.5, '3': 0.25}, '3332': {'333': 0.75, '33': 0.5, '3': 0.25}, '3333': {'333': 0.75, '33': 0.5, '3': 0.25}, '3334': {'333': 0.75, '33': 0.5, '3': 0.25}, '3339': {'333': 0.75, '33': 0.5, '3': 0.25}, '3341': {'334': 0.75, '33': 0.5, '3': 0.25}, '3342': {'334': 0.75, '33': 0.5, '3': 0.25}, '3343': {'334': 0.75, '33': 0.5, '3': 0.25}, '3344': {'334': 0.75, '33': 0.5, '3': 0.25}, '3351': {'335': 0.75, '33': 0.5, '3': 0.25}, '3352': {'335': 0.75, '33': 0.5, '3': 0.25}, '3353': {'335': 0.75, '33': 0.5, '3': 0.25}, '3354': {'335': 0.75, '33': 0.5, '3': 0.25}, '3355': {'335': 0.75, '33': 0.5, '3': 0.25}, '3359': {'335': 0.75, '33': 0.5, '3': 0.25}, '3411': {'341': 0.75, '34': 0.5, '3': 0.25}, '3412': {'341': 0.75, '34': 0.5, '3': 0.25}, '3413': {'341': 0.75, '34': 0.5, '3': 0.25}, '3421': {'342': 0.75, '34': 0.5, '3': 0.25}, '3422': {'342': 0.75, '34': 0.5, '3': 0.25}, '3423': {'342': 0.75, '34': 0.5, '3': 0.25}, '3431': {'343': 0.75, '34': 0.5, '3': 0.25}, '3432': {'343': 0.75, '34': 0.5, '3': 0.25}, '3433': {'343': 0.75, '34': 0.5, '3': 0.25}, '3434': {'343': 0.75, '34': 0.5, '3': 0.25}, '3435': {'343': 0.75, '34': 0.5, '3': 0.25}, '3511': {'351': 0.75, '35': 0.5, '3': 0.25}, '3512': {'351': 0.75, '35': 0.5, '3': 0.25}, '3513': {'351': 0.75, '35': 0.5, '3': 0.25}, '3514': {'351': 0.75, '35': 0.5, '3': 0.25}, '3521': {'352': 0.75, '35': 0.5, '3': 0.25}, '3522': {'352': 0.75, '35': 0.5, '3': 0.25}, '4110': {'411': 0.75, '41': 0.5, '4': 0.25}, '4120': {'412': 0.75, '41': 0.5, '4': 0.25}, '4131': {'413': 0.75, '41': 0.5, '4': 0.25}, '4132': {'413': 0.75, '41': 0.5, '4': 0.25}, '4211': {'421': 0.75, '42': 0.5, '4': 0.25}, '4212': {'421': 0.75, '42': 0.5, '4': 0.25}, '4213': {'421': 0.75, '42': 0.5, '4': 0.25}, '4214': {'421': 0.75, '42': 0.5, '4': 0.25}, '4221': {'422': 0.75, '42': 0.5, '4': 0.25}, '4222': {'422': 0.75, '42': 0.5, '4': 0.25}, '4223': {'422': 0.75, '42': 0.5, '4': 0.25}, '4224': {'422': 0.75, '42': 0.5, '4': 0.25}, '4225': {'422': 0.75, '42': 0.5, '4': 0.25}, '4226': {'422': 0.75, '42': 0.5, '4': 0.25}, '4227': {'422': 0.75, '42': 0.5, '4': 0.25}, '4229': {'422': 0.75, '42': 0.5, '4': 0.25}, '4311': {'431': 0.75, '43': 0.5, '4': 0.25}, '4312': {'431': 0.75, '43': 0.5, '4': 0.25}, '4313': {'431': 0.75, '43': 0.5, '4': 0.25}, '4321': {'432': 0.75, '43': 0.5, '4': 0.25}, '4322': {'432': 0.75, '43': 0.5, '4': 0.25}, '4323': {'432': 0.75, '43': 0.5, '4': 0.25}, '4411': {'441': 0.75, '44': 0.5, '4': 0.25}, '4412': {'441': 0.75, '44': 0.5, '4': 0.25}, '4413': {'441': 0.75, '44': 0.5, '4': 0.25}, '4414': {'441': 0.75, '44': 0.5, '4': 0.25}, '4415': {'441': 0.75, '44': 0.5, '4': 0.25}, '4416': {'441': 0.75, '44': 0.5, '4': 0.25}, '4419': {'441': 0.75, '44': 0.5, '4': 0.25}, '5111': {'511': 0.75, '51': 0.5, '5': 0.25}, '5112': {'511': 0.75, '51': 0.5, '5': 0.25}, '5113': {'511': 0.75, '51': 0.5, '5': 0.25}, '5120': {'512': 0.75, '51': 0.5, '5': 0.25}, '5131': {'513': 0.75, '51': 0.5, '5': 0.25}, '5132': {'513': 0.75, '51': 0.5, '5': 0.25}, '5141': {'514': 0.75, '51': 0.5, '5': 0.25}, '5142': {'514': 0.75, '51': 0.5, '5': 0.25}, '5151': {'515': 0.75, '51': 0.5, '5': 0.25}, '5152': {'515': 0.75, '51': 0.5, '5': 0.25}, '5153': {'515': 0.75, '51': 0.5, '5': 0.25}, '5161': {'516': 0.75, '51': 0.5, '5': 0.25}, '5162': {'516': 0.75, '51': 0.5, '5': 0.25}, '5163': {'516': 0.75, '51': 0.5, '5': 0.25}, '5164': {'516': 0.75, '51': 0.5, '5': 0.25}, '5165': {'516': 0.75, '51': 0.5, '5': 0.25}, '5169': {'516': 0.75, '51': 0.5, '5': 0.25}, '5211': {'521': 0.75, '52': 0.5, '5': 0.25}, '5212': {'521': 0.75, '52': 0.5, '5': 0.25}, '5221': {'522': 0.75, '52': 0.5, '5': 0.25}, '5222': {'522': 0.75, '52': 0.5, '5': 0.25}, '5223': {'522': 0.75, '52': 0.5, '5': 0.25}, '5230': {'523': 0.75, '52': 0.5, '5': 0.25}, '5241': {'524': 0.75, '52': 0.5, '5': 0.25}, '5242': {'524': 0.75, '52': 0.5, '5': 0.25}, '5243': {'524': 0.75, '52': 0.5, '5': 0.25}, '5244': {'524': 0.75, '52': 0.5, '5': 0.25}, '5245': {'524': 0.75, '52': 0.5, '5': 0.25}, '5246': {'524': 0.75, '52': 0.5, '5': 0.25}, '5249': {'524': 0.75, '52': 0.5, '5': 0.25}, '5311': {'531': 0.75, '53': 0.5, '5': 0.25}, '5312': {'531': 0.75, '53': 0.5, '5': 0.25}, '5321': {'532': 0.75, '53': 0.5, '5': 0.25}, '5322': {'532': 0.75, '53': 0.5, '5': 0.25}, '5329': {'532': 0.75, '53': 0.5, '5': 0.25}, '5411': {'541': 0.75, '54': 0.5, '5': 0.25}, '5412': {'541': 0.75, '54': 0.5, '5': 0.25}, '5413': {'541': 0.75, '54': 0.5, '5': 0.25}, '5414': {'541': 0.75, '54': 0.5, '5': 0.25}, '5419': {'541': 0.75, '54': 0.5, '5': 0.25}, '6111': {'611': 0.75, '61': 0.5, '6': 0.25}, '6112': {'611': 0.75, '61': 0.5, '6': 0.25}, '6113': {'611': 0.75, '61': 0.5, '6': 0.25}, '6114': {'611': 0.75, '61': 0.5, '6': 0.25}, '6121': {'612': 0.75, '61': 0.5, '6': 0.25}, '6122': {'612': 0.75, '61': 0.5, '6': 0.25}, '6123': {'612': 0.75, '61': 0.5, '6': 0.25}, '6129': {'612': 0.75, '61': 0.5, '6': 0.25}, '6130': {'613': 0.75, '61': 0.5, '6': 0.25}, '6210': {'621': 0.75, '62': 0.5, '6': 0.25}, '6221': {'622': 0.75, '62': 0.5, '6': 0.25}, '6222': {'622': 0.75, '62': 0.5, '6': 0.25}, '6223': {'622': 0.75, '62': 0.5, '6': 0.25}, '6224': {'622': 0.75, '62': 0.5, '6': 0.25}, '6310': {'631': 0.75, '63': 0.5, '6': 0.25}, '6320': {'632': 0.75, '63': 0.5, '6': 0.25}, '6330': {'633': 0.75, '63': 0.5, '6': 0.25}, '6340': {'634': 0.75, '63': 0.5, '6': 0.25}, '7111': {'711': 0.75, '71': 0.5, '7': 0.25}, '7112': {'711': 0.75, '71': 0.5, '7': 0.25}, '7113': {'711': 0.75, '71': 0.5, '7': 0.25}, '7114': {'711': 0.75, '71': 0.5, '7': 0.25}, '7115': {'711': 0.75, '71': 0.5, '7': 0.25}, '7119': {'711': 0.75, '71': 0.5, '7': 0.25}, '7121': {'712': 0.75, '71': 0.5, '7': 0.25}, '7122': {'712': 0.75, '71': 0.5, '7': 0.25}, '7123': {'712': 0.75, '71': 0.5, '7': 0.25}, '7124': {'712': 0.75, '71': 0.5, '7': 0.25}, '7125': {'712': 0.75, '71': 0.5, '7': 0.25}, '7126': {'712': 0.75, '71': 0.5, '7': 0.25}, '7127': {'712': 0.75, '71': 0.5, '7': 0.25}, '7131': {'713': 0.75, '71': 0.5, '7': 0.25}, '7132': {'713': 0.75, '71': 0.5, '7': 0.25}, '7133': {'713': 0.75, '71': 0.5, '7': 0.25}, '7211': {'721': 0.75, '72': 0.5, '7': 0.25}, '7212': {'721': 0.75, '72': 0.5, '7': 0.25}, '7213': {'721': 0.75, '72': 0.5, '7': 0.25}, '7214': {'721': 0.75, '72': 0.5, '7': 0.25}, '7215': {'721': 0.75, '72': 0.5, '7': 0.25}, '7221': {'722': 0.75, '72': 0.5, '7': 0.25}, '7222': {'722': 0.75, '72': 0.5, '7': 0.25}, '7223': {'722': 0.75, '72': 0.5, '7': 0.25}, '7224': {'722': 0.75, '72': 0.5, '7': 0.25}, '7231': {'723': 0.75, '72': 0.5, '7': 0.25}, '7232': {'723': 0.75, '72': 0.5, '7': 0.25}, '7233': {'723': 0.75, '72': 0.5, '7': 0.25}, '7234': {'723': 0.75, '72': 0.5, '7': 0.25}, '7311': {'731': 0.75, '73': 0.5, '7': 0.25}, '7312': {'731': 0.75, '73': 0.5, '7': 0.25}, '7313': {'731': 0.75, '73': 0.5, '7': 0.25}, '7314': {'731': 0.75, '73': 0.5, '7': 0.25}, '7315': {'731': 0.75, '73': 0.5, '7': 0.25}, '7316': {'731': 0.75, '73': 0.5, '7': 0.25}, '7317': {'731': 0.75, '73': 0.5, '7': 0.25}, '7318': {'731': 0.75, '73': 0.5, '7': 0.25}, '7319': {'731': 0.75, '73': 0.5, '7': 0.25}, '7321': {'732': 0.75, '73': 0.5, '7': 0.25}, '7322': {'732': 0.75, '73': 0.5, '7': 0.25}, '7323': {'732': 0.75, '73': 0.5, '7': 0.25}, '7411': {'741': 0.75, '74': 0.5, '7': 0.25}, '7412': {'741': 0.75, '74': 0.5, '7': 0.25}, '7413': {'741': 0.75, '74': 0.5, '7': 0.25}, '7421': {'742': 0.75, '74': 0.5, '7': 0.25}, '7422': {'742': 0.75, '74': 0.5, '7': 0.25}, '7511': {'751': 0.75, '75': 0.5, '7': 0.25}, '7512': {'751': 0.75, '75': 0.5, '7': 0.25}, '7513': {'751': 0.75, '75': 0.5, '7': 0.25}, '7514': {'751': 0.75, '75': 0.5, '7': 0.25}, '7515': {'751': 0.75, '75': 0.5, '7': 0.25}, '7516': {'751': 0.75, '75': 0.5, '7': 0.25}, '7521': {'752': 0.75, '75': 0.5, '7': 0.25}, '7522': {'752': 0.75, '75': 0.5, '7': 0.25}, '7523': {'752': 0.75, '75': 0.5, '7': 0.25}, '7531': {'753': 0.75, '75': 0.5, '7': 0.25}, '7532': {'753': 0.75, '75': 0.5, '7': 0.25}, '7533': {'753': 0.75, '75': 0.5, '7': 0.25}, '7534': {'753': 0.75, '75': 0.5, '7': 0.25}, '7535': {'753': 0.75, '75': 0.5, '7': 0.25}, '7536': {'753': 0.75, '75': 0.5, '7': 0.25}, '7541': {'754': 0.75, '75': 0.5, '7': 0.25}, '7542': {'754': 0.75, '75': 0.5, '7': 0.25}, '7543': {'754': 0.75, '75': 0.5, '7': 0.25}, '7544': {'754': 0.75, '75': 0.5, '7': 0.25}, '7549': {'754': 0.75, '75': 0.5, '7': 0.25}, '8111': {'811': 0.75, '81': 0.5, '8': 0.25}, '8112': {'811': 0.75, '81': 0.5, '8': 0.25}, '8113': {'811': 0.75, '81': 0.5, '8': 0.25}, '8114': {'811': 0.75, '81': 0.5, '8': 0.25}, '8121': {'812': 0.75, '81': 0.5, '8': 0.25}, '8122': {'812': 0.75, '81': 0.5, '8': 0.25}, '8131': {'813': 0.75, '81': 0.5, '8': 0.25}, '8132': {'813': 0.75, '81': 0.5, '8': 0.25}, '8141': {'814': 0.75, '81': 0.5, '8': 0.25}, '8142': {'814': 0.75, '81': 0.5, '8': 0.25}, '8143': {'814': 0.75, '81': 0.5, '8': 0.25}, '8151': {'815': 0.75, '81': 0.5, '8': 0.25}, '8152': {'815': 0.75, '81': 0.5, '8': 0.25}, '8153': {'815': 0.75, '81': 0.5, '8': 0.25}, '8154': {'815': 0.75, '81': 0.5, '8': 0.25}, '8155': {'815': 0.75, '81': 0.5, '8': 0.25}, '8156': {'815': 0.75, '81': 0.5, '8': 0.25}, '8157': {'815': 0.75, '81': 0.5, '8': 0.25}, '8159': {'815': 0.75, '81': 0.5, '8': 0.25}, '8160': {'816': 0.75, '81': 0.5, '8': 0.25}, '8171': {'817': 0.75, '81': 0.5, '8': 0.25}, '8172': {'817': 0.75, '81': 0.5, '8': 0.25}, '8181': {'818': 0.75, '81': 0.5, '8': 0.25}, '8182': {'818': 0.75, '81': 0.5, '8': 0.25}, '8183': {'818': 0.75, '81': 0.5, '8': 0.25}, '8189': {'818': 0.75, '81': 0.5, '8': 0.25}, '8211': {'821': 0.75, '82': 0.5, '8': 0.25}, '8212': {'821': 0.75, '82': 0.5, '8': 0.25}, '8219': {'821': 0.75, '82': 0.5, '8': 0.25}, '8311': {'831': 0.75, '83': 0.5, '8': 0.25}, '8312': {'831': 0.75, '83': 0.5, '8': 0.25}, '8321': {'832': 0.75, '83': 0.5, '8': 0.25}, '8322': {'832': 0.75, '83': 0.5, '8': 0.25}, '8331': {'833': 0.75, '83': 0.5, '8': 0.25}, '8332': {'833': 0.75, '83': 0.5, '8': 0.25}, '8341': {'834': 0.75, '83': 0.5, '8': 0.25}, '8342': {'834': 0.75, '83': 0.5, '8': 0.25}, '8343': {'834': 0.75, '83': 0.5, '8': 0.25}, '8344': {'834': 0.75, '83': 0.5, '8': 0.25}, '8350': {'835': 0.75, '83': 0.5, '8': 0.25}, '9111': {'911': 0.75, '91': 0.5, '9': 0.25}, '9112': {'911': 0.75, '91': 0.5, '9': 0.25}, '9121': {'912': 0.75, '91': 0.5, '9': 0.25}, '9122': {'912': 0.75, '91': 0.5, '9': 0.25}, '9123': {'912': 0.75, '91': 0.5, '9': 0.25}, '9129': {'912': 0.75, '91': 0.5, '9': 0.25}, '9211': {'921': 0.75, '92': 0.5, '9': 0.25}, '9212': {'921': 0.75, '92': 0.5, '9': 0.25}, '9213': {'921': 0.75, '92': 0.5, '9': 0.25}, '9214': {'921': 0.75, '92': 0.5, '9': 0.25}, '9215': {'921': 0.75, '92': 0.5, '9': 0.25}, '9216': {'921': 0.75, '92': 0.5, '9': 0.25}, '9311': {'931': 0.75, '93': 0.5, '9': 0.25}, '9312': {'931': 0.75, '93': 0.5, '9': 0.25}, '9313': {'931': 0.75, '93': 0.5, '9': 0.25}, '9321': {'932': 0.75, '93': 0.5, '9': 0.25}, '9329': {'932': 0.75, '93': 0.5, '9': 0.25}, '9331': {'933': 0.75, '93': 0.5, '9': 0.25}, '9332': {'933': 0.75, '93': 0.5, '9': 0.25}, '9333': {'933': 0.75, '93': 0.5, '9': 0.25}, '9334': {'933': 0.75, '93': 0.5, '9': 0.25}, '9411': {'941': 0.75, '94': 0.5, '9': 0.25}, '9412': {'941': 0.75, '94': 0.5, '9': 0.25}, '9510': {'951': 0.75, '95': 0.5, '9': 0.25}, '9520': {'952': 0.75, '95': 0.5, '9': 0.25}, '9611': {'961': 0.75, '96': 0.5, '9': 0.25}, '9612': {'961': 0.75, '96': 0.5, '9': 0.25}, '9613': {'961': 0.75, '96': 0.5, '9': 0.25}, '9621': {'962': 0.75, '96': 0.5, '9': 0.25}, '9622': {'962': 0.75, '96': 0.5, '9': 0.25}, '9623': {'962': 0.75, '96': 0.5, '9': 0.25}, '9624': {'962': 0.75, '96': 0.5, '9': 0.25}, '9629': {'962': 0.75, '96': 0.5, '9': 0.25}, '0110': {'011': 0.75, '01': 0.5, '0': 0.25}, '0210': {'021': 0.75, '02': 0.5, '0': 0.25}, '0310': {'031': 0.75, '03': 0.5, '0': 0.25}}\n",
-      "Accuracy: 0.8611914401388086\n",
-      "Hierarchical Precision: 0.989010989010989, Hierarchical Recall: 0.9836065573770492, Hierarchical F-measure: 0.9863013698630136\n",
-      "Evaluation results saved to isco_results.txt\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import os\n",
     "from datasets import load_dataset\n",
@@ -203,6 +190,10 @@
     "    \"ICILS/multilingual_parental_occupations\", split=\"test\", token=hf_token\n",
     ")\n",
     "\n",
+    "validation_data = load_dataset(\n",
+    "    \"ICILS/multilingual_parental_occupations\", split=\"validation\", token=hf_token\n",
+    ")\n",
+    "\n",
     "# Initialize the pipeline\n",
     "pipe = pipeline(\"text-classification\", model=\"ICILS/XLM-R-ISCO\", token=hf_token)\n",
     "\n",
@@ -211,6 +202,32 @@
     "    # ISCO_CODE_TITLE is a string like \"7412 Electrical Mechanics and Fitters\" so we need to extract the first part for the evaluation.\n",
     "    return isco_code_title.split()[0]\n",
     "\n",
+    "# Initialize the hierarchical accuracy measure\n",
+    "hierarchical_accuracy = evaluate.load(\"danieldux/isco_hierarchical_accuracy\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.8611914401388086, Hierarchical Precision: 0.989010989010989, Hierarchical Recall: 0.9836065573770492, Hierarchical F-measure: 0.9863013698630136\n",
+      "Evaluation results saved to isco_test_results.json\n"
+     ]
+    }
+   ],
+   "source": [
     "# Evaluate the model\n",
     "predictions = []\n",
     "references = []\n",
@@ -219,25 +236,1051 @@
     "    # Predict\n",
     "    prediction = pipe(\n",
     "        example[\"JOB_DUTIES\"]\n",
-    "    )  # Use the correct key \"JOB_DUTIES\" for the text data\n",
+    "    )  # Use the key \"JOB_DUTIES\" for the text data\n",
     "    predicted_label = extract_isco_code(prediction[0][\"label\"])\n",
     "    predictions.append(predicted_label)\n",
     "\n",
     "    # Reference\n",
-    "    reference_label = example[\"ISCO\"]  # Use the correct key \"ISCO\" for the ISCO code\n",
+    "    reference_label = example[\"ISCO\"]  # Use the key \"ISCO\" for the ISCO code\n",
     "    references.append(reference_label)\n",
     "\n",
-    "# Initialize the hierarchical accuracy measure\n",
-    "hierarchical_accuracy = evaluate.load(\"danieldux/isco_hierarchical_accuracy\")\n",
+    "# Compute the hierarchical accuracy\n",
+    "test_results = hierarchical_accuracy.compute(predictions=predictions, references=references)\n",
+    "\n",
+    "# Save the results to a JSON file\n",
+    "with open(\"isco_test_results.json\", \"w\") as f:\n",
+    "    json.dump(test_results, f)\n",
+    "\n",
+    "print(\"Evaluation results saved to isco_test_results.json\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Validation set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 78,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.8576800694243564, Hierarchical Precision: 0.9757462686567164, Hierarchical Recall: 0.9812382739212008, Hierarchical F-measure: 0.9784845650140319\n",
+      "Evaluation results saved to isco_validation_results.json\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Evaluate the model\n",
+    "predictions = []\n",
+    "references = []\n",
+    "for example in validation_data:\n",
+    "\n",
+    "    # Predict\n",
+    "    prediction = pipe(\n",
+    "        example[\"JOB_DUTIES\"]\n",
+    "    )  # Use the key \"JOB_DUTIES\" for the text data\n",
+    "    predicted_label = extract_isco_code(prediction[0][\"label\"])\n",
+    "    predictions.append(predicted_label)\n",
+    "\n",
+    "    # Reference\n",
+    "    reference_label = example[\"ISCO\"]  # Use the key \"ISCO\" for the ISCO code\n",
+    "    references.append(reference_label)\n",
     "\n",
     "# Compute the hierarchical accuracy\n",
-    "results = hierarchical_accuracy.compute(predictions=predictions, references=references)\n",
+    "validation_results = hierarchical_accuracy.compute(predictions=predictions, references=references)\n",
     "\n",
     "# Save the results to a JSON file\n",
-    "with open(\"isco_results.json\", \"w\") as f:\n",
-    "    json.dump(results, f)\n",
+    "with open(\"isco_validation_results.json\", \"w\") as f:\n",
+    "    json.dump(validation_results, f)\n",
+    "\n",
+    "print(\"Evaluation results saved to isco_validation_results.json\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Inter rater agreement"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "# icils_isco_int_ml = \"/datasets/isco-data/processed/2018/icils_2018_isco_ml.parquet\"\n",
+    "icils_isco_int_ml = \"gs://isco-data-asia-southeast1/processed/2018/icils_2018_isco_ml.parquet\"\n",
+    "\n",
+    "icils_df = pd.read_parquet(icils_isco_int_ml)[['JOB', 'DUTIES', 'ISCO', 'ISCO_REL', 'LANGUAGE']]\n",
+    "\n",
+    "# Create a new pandas dataframe with samples that have ISCO_REL values\n",
+    "isco_rel_df = icils_df[icils_df['ISCO'].notna()].copy()\n",
+    "\n",
+    "# remove rows with None values in ISCO_REL\n",
+    "isco_rel_df = isco_rel_df[isco_rel_df['ISCO_REL'].notna()]\n",
+    "\n",
+    "# Group the DataFrame by LANGUAGE column\n",
+    "grouped_df = isco_rel_df.groupby('LANGUAGE')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<pandas.core.groupby.generic.DataFrameGroupBy object at 0x7f2c318dd350>"
+      ]
+     },
+     "execution_count": 79,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "grouped_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.7149425287356321, Hierarchical Precision: 0.9314641744548287, Hierarchical Recall: 0.8898809523809523, Hierarchical F-measure: 0.9101978691019786\n",
+      "Language: da\n",
+      "Result: {'accuracy': 0.7149425287356321, 'hierarchical_precision': 0.9314641744548287, 'hierarchical_recall': 0.8898809523809523, 'hierarchical_fmeasure': 0.9101978691019786}\n",
+      "\n",
+      "Accuracy: 0.9075297225891678, Hierarchical Precision: 0.9578651685393258, Hierarchical Recall: 0.9742857142857143, Hierarchical F-measure: 0.9660056657223796\n",
+      "Language: en\n",
+      "Result: {'accuracy': 0.9075297225891678, 'hierarchical_precision': 0.9578651685393258, 'hierarchical_recall': 0.9742857142857143, 'hierarchical_fmeasure': 0.9660056657223796}\n",
+      "\n",
+      "Accuracy: 0.8794080604534005, Hierarchical Precision: 0.9774590163934426, Hierarchical Recall: 0.9655870445344129, Hierarchical F-measure: 0.9714867617107942\n",
+      "Language: es\n",
+      "Result: {'accuracy': 0.8794080604534005, 'hierarchical_precision': 0.9774590163934426, 'hierarchical_recall': 0.9655870445344129, 'hierarchical_fmeasure': 0.9714867617107942}\n",
+      "\n",
+      "Accuracy: 0.9286376274328082, Hierarchical Precision: 0.9591836734693877, Hierarchical Recall: 0.9733727810650887, Hierarchical F-measure: 0.9662261380323054\n",
+      "Language: fi\n",
+      "Result: {'accuracy': 0.9286376274328082, 'hierarchical_precision': 0.9591836734693877, 'hierarchical_recall': 0.9733727810650887, 'hierarchical_fmeasure': 0.9662261380323054}\n",
+      "\n",
+      "Accuracy: 0.5772994129158513, Hierarchical Precision: 0.8571428571428571, Hierarchical Recall: 0.8808864265927978, Hierarchical F-measure: 0.8688524590163934\n",
+      "Language: fr\n",
+      "Result: {'accuracy': 0.5772994129158513, 'hierarchical_precision': 0.8571428571428571, 'hierarchical_recall': 0.8808864265927978, 'hierarchical_fmeasure': 0.8688524590163934}\n",
+      "\n",
+      "Accuracy: 0.9332579185520362, Hierarchical Precision: 0.9616613418530351, Hierarchical Recall: 0.9525316455696202, Hierarchical F-measure: 0.9570747217806042\n",
+      "Language: it\n",
+      "Result: {'accuracy': 0.9332579185520362, 'hierarchical_precision': 0.9616613418530351, 'hierarchical_recall': 0.9525316455696202, 'hierarchical_fmeasure': 0.9570747217806042}\n",
+      "\n",
+      "Accuracy: 0.9313346228239845, Hierarchical Precision: 0.9816849816849816, Hierarchical Recall: 0.9710144927536232, Hierarchical F-measure: 0.97632058287796\n",
+      "Language: kk\n",
+      "Result: {'accuracy': 0.9313346228239845, 'hierarchical_precision': 0.9816849816849816, 'hierarchical_recall': 0.9710144927536232, 'hierarchical_fmeasure': 0.97632058287796}\n",
+      "\n",
+      "Accuracy: 0.9369047619047619, Hierarchical Precision: 0.9726962457337884, Hierarchical Recall: 0.9827586206896551, Hierarchical F-measure: 0.9777015437392795\n",
+      "Language: ko\n",
+      "Result: {'accuracy': 0.9369047619047619, 'hierarchical_precision': 0.9726962457337884, 'hierarchical_recall': 0.9827586206896551, 'hierarchical_fmeasure': 0.9777015437392795}\n",
+      "\n",
+      "Accuracy: 0.8936170212765957, Hierarchical Precision: 0.9591836734693877, Hierarchical Recall: 0.9563953488372093, Hierarchical F-measure: 0.957787481804949\n",
+      "Language: pt\n",
+      "Result: {'accuracy': 0.8936170212765957, 'hierarchical_precision': 0.9591836734693877, 'hierarchical_recall': 0.9563953488372093, 'hierarchical_fmeasure': 0.957787481804949}\n",
+      "\n",
+      "Accuracy: 0.9259259259259259, Hierarchical Precision: 0.971875, Hierarchical Recall: 0.9658385093167702, Hierarchical F-measure: 0.9688473520249222\n",
+      "Language: ru\n",
+      "Result: {'accuracy': 0.9259259259259259, 'hierarchical_precision': 0.971875, 'hierarchical_recall': 0.9658385093167702, 'hierarchical_fmeasure': 0.9688473520249222}\n",
+      "\n",
+      "Accuracy: 0.9726027397260274, Hierarchical Precision: 0.9927007299270073, Hierarchical Recall: 1.0, Hierarchical F-measure: 0.9963369963369962\n",
+      "Language: sv\n",
+      "Result: {'accuracy': 0.9726027397260274, 'hierarchical_precision': 0.9927007299270073, 'hierarchical_recall': 1.0, 'hierarchical_fmeasure': 0.9963369963369962}\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_29614/1496722815.py:17: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
+      "  results_df = pd.concat([results_df, group_result_df], ignore_index=True)\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "results_df = pd.DataFrame(columns=['Language', 'Accuracy', 'Hierarchical Precision', 'Hierarchical Recall', 'Hierarchical F1'])\n",
+    "\n",
+    "# Iterate over each group\n",
+    "for language, group in grouped_df:\n",
+    "    references = group['ISCO'].tolist()\n",
+    "    predictions = group['ISCO_REL'].tolist()\n",
+    "    \n",
+    "    # Apply the compute function\n",
+    "    rel_result = hierarchical_accuracy.compute(references=references, predictions=predictions)\n",
+    "    \n",
+    "    # Create a new DataFrame with the result for the current group\n",
+    "    group_result_df = pd.DataFrame({'Language': [language], 'Accuracy': [rel_result['accuracy']], 'Hierarchical Precision': [rel_result['hierarchical_precision']], 'Hierarchical Recall': [rel_result['hierarchical_recall']], 'Hierarchical F1': [rel_result['hierarchical_fmeasure']]})\n",
+    "    \n",
+    "    # Concatenate the group_result_df with the results_df\n",
+    "    results_df = pd.concat([results_df, group_result_df], ignore_index=True)\n",
+    "    \n",
+    "    # Print the result\n",
+    "    print(f\"Language: {language}\")\n",
+    "    # print(f\"References: {references}\")\n",
+    "    # print(f\"Predictions: {predictions}\")\n",
+    "    print(f\"Result: {rel_result}\")\n",
+    "    print()\n",
+    "\n",
+    "average_accuracy = results_df['Accuracy'].mean()\n",
+    "average_hierarchical_precision = results_df['Hierarchical Precision'].mean()\n",
+    "average_hierarchical_recall = results_df['Hierarchical Recall'].mean()\n",
+    "average_hierarchical_f1 = results_df['Hierarchical F1'].mean()\n",
+    "\n",
+    "average_row = ['Average', average_accuracy, average_hierarchical_precision, average_hierarchical_recall, average_hierarchical_f1]\n",
+    "results_df.loc[len(results_df)] = average_row\n",
+    "\n",
+    "\n",
+    "results_df.to_csv('language_results.csv', index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>JOB</th>\n",
+       "      <th>DUTIES</th>\n",
+       "      <th>ISCO</th>\n",
+       "      <th>ISCO_REL</th>\n",
+       "      <th>LANGUAGE</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>acopio</td>\n",
+       "      <td>recibe tarros con leche y despues hecha la lec...</td>\n",
+       "      <td>9333</td>\n",
+       "      <td>9333</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>yo vivo con mi abuela y abuelo mi abuela  o tr...</td>\n",
+       "      <td>mi mama trabaja en limpiar las casas</td>\n",
+       "      <td>9111</td>\n",
+       "      <td>9111</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>dueña de casa</td>\n",
+       "      <td>mantiene el orden de la casa</td>\n",
+       "      <td>9701</td>\n",
+       "      <td>9701</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>señora de casa</td>\n",
+       "      <td>trabaja en la lecheria con las bacas y terneros</td>\n",
+       "      <td>9701</td>\n",
+       "      <td>9701</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>trabajadora agricolar</td>\n",
+       "      <td>aplicar liquidos ala plantas</td>\n",
+       "      <td>9211</td>\n",
+       "      <td>9211</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>113962</th>\n",
+       "      <td>Фотограф</td>\n",
+       "      <td>Рассылал снимки в журналы, получал за это гоно...</td>\n",
+       "      <td>3431</td>\n",
+       "      <td>3431</td>\n",
+       "      <td>ru</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>114114</th>\n",
+       "      <td>Магазин</td>\n",
+       "      <td>У него есть всой магазин где он работает.</td>\n",
+       "      <td>5221</td>\n",
+       "      <td>5221</td>\n",
+       "      <td>ru</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>114295</th>\n",
+       "      <td>цирк</td>\n",
+       "      <td>держал перши</td>\n",
+       "      <td>2659</td>\n",
+       "      <td>2659</td>\n",
+       "      <td>ru</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>114317</th>\n",
+       "      <td>Человек-молкула</td>\n",
+       "      <td>Супер-герой</td>\n",
+       "      <td>9705</td>\n",
+       "      <td>9705</td>\n",
+       "      <td>ru</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>114371</th>\n",
+       "      <td>Строительство заборов</td>\n",
+       "      <td>Ставит заборы дачникам и не только</td>\n",
+       "      <td>7111</td>\n",
+       "      <td>7111</td>\n",
+       "      <td>ru</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>13055 rows × 5 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                      JOB  \\\n",
+       "0                                                  acopio   \n",
+       "5       yo vivo con mi abuela y abuelo mi abuela  o tr...   \n",
+       "9                                           dueña de casa   \n",
+       "10                                         señora de casa   \n",
+       "11                                  trabajadora agricolar   \n",
+       "...                                                   ...   \n",
+       "113962                                           Фотограф   \n",
+       "114114                                            Магазин   \n",
+       "114295                                               цирк   \n",
+       "114317                                    Человек-молкула   \n",
+       "114371                              Строительство заборов   \n",
+       "\n",
+       "                                                   DUTIES  ISCO ISCO_REL  \\\n",
+       "0       recibe tarros con leche y despues hecha la lec...  9333     9333   \n",
+       "5                    mi mama trabaja en limpiar las casas  9111     9111   \n",
+       "9                            mantiene el orden de la casa  9701     9701   \n",
+       "10        trabaja en la lecheria con las bacas y terneros  9701     9701   \n",
+       "11                           aplicar liquidos ala plantas  9211     9211   \n",
+       "...                                                   ...   ...      ...   \n",
+       "113962  Рассылал снимки в журналы, получал за это гоно...  3431     3431   \n",
+       "114114          У него есть всой магазин где он работает.  5221     5221   \n",
+       "114295                                       держал перши  2659     2659   \n",
+       "114317                                        Супер-герой  9705     9705   \n",
+       "114371                 Ставит заборы дачникам и не только  7111     7111   \n",
+       "\n",
+       "       LANGUAGE  \n",
+       "0            es  \n",
+       "5            es  \n",
+       "9            es  \n",
+       "10           es  \n",
+       "11           es  \n",
+       "...         ...  \n",
+       "113962       ru  \n",
+       "114114       ru  \n",
+       "114295       ru  \n",
+       "114317       ru  \n",
+       "114371       ru  \n",
+       "\n",
+       "[13055 rows x 5 columns]"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# create a dataframe with samples where ISCO and ISCO_REL the same\n",
+    "isco_rel_df_same = isco_rel_df[isco_rel_df['ISCO'] == isco_rel_df['ISCO_REL']]\n",
+    "\n",
+    "isco_rel_df_same"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>JOB</th>\n",
+       "      <th>DUTIES</th>\n",
+       "      <th>ISCO</th>\n",
+       "      <th>ISCO_REL</th>\n",
+       "      <th>LANGUAGE</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Asistente judirica</td>\n",
+       "      <td>gestionar casos de fiscalia</td>\n",
+       "      <td>3342</td>\n",
+       "      <td>3411</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>lechera</td>\n",
+       "      <td>saca leche</td>\n",
+       "      <td>9212</td>\n",
+       "      <td>9211</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>Mi madre es dueña de casa</td>\n",
+       "      <td>Realiza todos los quehaceres del hogar, y trab...</td>\n",
+       "      <td>9111</td>\n",
+       "      <td>9701</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34</th>\n",
+       "      <td>algricultura</td>\n",
+       "      <td>algricultura</td>\n",
+       "      <td>9705</td>\n",
+       "      <td>9211</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38</th>\n",
+       "      <td>en la agricultura</td>\n",
+       "      <td>produce alimentos de vegetacion</td>\n",
+       "      <td>633</td>\n",
+       "      <td>9211</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111656</th>\n",
+       "      <td>gerente de ventas</td>\n",
+       "      <td>ropa</td>\n",
+       "      <td>5222</td>\n",
+       "      <td>1221</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111700</th>\n",
+       "      <td>policia jubilado</td>\n",
+       "      <td>capitan</td>\n",
+       "      <td>5412</td>\n",
+       "      <td>9703</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>111792</th>\n",
+       "      <td>Vendiendo comida</td>\n",
+       "      <td>Mi padrastro vende comida</td>\n",
+       "      <td>5223</td>\n",
+       "      <td>5212</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>112817</th>\n",
+       "      <td>Собственник  ювелирного магазина</td>\n",
+       "      <td>Продавал ювелирные изделия</td>\n",
+       "      <td>7313</td>\n",
+       "      <td>5221</td>\n",
+       "      <td>ru</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>113081</th>\n",
+       "      <td>Предприниматель</td>\n",
+       "      <td>Вещи продовал (продукты)</td>\n",
+       "      <td>5221</td>\n",
+       "      <td>112</td>\n",
+       "      <td>ru</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1958 rows × 5 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                     JOB  \\\n",
+       "4                     Asistente judirica   \n",
+       "8                                lechera   \n",
+       "14             Mi madre es dueña de casa   \n",
+       "34                          algricultura   \n",
+       "38                     en la agricultura   \n",
+       "...                                  ...   \n",
+       "111656                 gerente de ventas   \n",
+       "111700                  policia jubilado   \n",
+       "111792                  Vendiendo comida   \n",
+       "112817  Собственник  ювелирного магазина   \n",
+       "113081                   Предприниматель   \n",
+       "\n",
+       "                                                   DUTIES  ISCO ISCO_REL  \\\n",
+       "4                             gestionar casos de fiscalia  3342     3411   \n",
+       "8                                              saca leche  9212     9211   \n",
+       "14      Realiza todos los quehaceres del hogar, y trab...  9111     9701   \n",
+       "34                                           algricultura  9705     9211   \n",
+       "38                        produce alimentos de vegetacion   633     9211   \n",
+       "...                                                   ...   ...      ...   \n",
+       "111656                                               ropa  5222     1221   \n",
+       "111700                                            capitan  5412     9703   \n",
+       "111792                          Mi padrastro vende comida  5223     5212   \n",
+       "112817                         Продавал ювелирные изделия  7313     5221   \n",
+       "113081                           Вещи продовал (продукты)  5221      112   \n",
+       "\n",
+       "       LANGUAGE  \n",
+       "4            es  \n",
+       "8            es  \n",
+       "14           es  \n",
+       "34           es  \n",
+       "38           es  \n",
+       "...         ...  \n",
+       "111656       es  \n",
+       "111700       es  \n",
+       "111792       es  \n",
+       "112817       ru  \n",
+       "113081       ru  \n",
+       "\n",
+       "[1958 rows x 5 columns]"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# create a dataframe with samples where ISCO and ISCO_REL are different\n",
+    "isco_rel_df_diff = isco_rel_df[isco_rel_df['ISCO'] != isco_rel_df['ISCO_REL']]\n",
+    "\n",
+    "isco_rel_df_diff"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Make a list of all values in ISCO and ISCO_REL columns\n",
+    "coder1 = list(isco_rel_df['ISCO'])\n",
+    "coder2 = list(isco_rel_df['ISCO_REL'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.8695796975954173, Hierarchical Precision: 0.9876106194690265, Hierarchical Recall: 0.9911190053285968, Hierarchical F-measure: 0.9893617021276595\n",
+      "Evaluation results saved to isco_rel_results.json\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Compute the hierarchical accuracy\n",
+    "reliability_results = hierarchical_accuracy.compute(predictions=coder2, references=coder1)\n",
+    "\n",
+    "# Save the results to a JSON file\n",
+    "with open(\"isco_rel_results.json\", \"w\") as f:\n",
+    "    json.dump(reliability_results, f)\n",
+    "\n",
+    "print(\"Evaluation results saved to isco_rel_results.json\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Giskard model testing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from scipy.special import softmax\n",
+    "from datasets import load_dataset\n",
+    "from transformers import AutoModelForSequenceClassification, AutoTokenizer\n",
+    "\n",
+    "from giskard import Dataset, Model, scan, testing, GiskardClient, Suite"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>IDSTUD</th>\n",
+       "      <th>JOB_DUTIES</th>\n",
+       "      <th>ISCO</th>\n",
+       "      <th>ISCO_REL</th>\n",
+       "      <th>ISCO_TITLE</th>\n",
+       "      <th>ISCO_CODE_TITLE</th>\n",
+       "      <th>COUNTRY</th>\n",
+       "      <th>LANGUAGE</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>10670109</td>\n",
+       "      <td>forældre 1:   Han arbejder som med-chef sammen...</td>\n",
+       "      <td>7412</td>\n",
+       "      <td>None</td>\n",
+       "      <td>Electrical Mechanics and Fitters</td>\n",
+       "      <td>7412 Electrical Mechanics and Fitters</td>\n",
+       "      <td>DNK</td>\n",
+       "      <td>da</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>10130106</td>\n",
+       "      <td>asistente de parbulo y basica. ayudaba en la e...</td>\n",
+       "      <td>5312</td>\n",
+       "      <td>5312</td>\n",
+       "      <td>Teachers' Aides</td>\n",
+       "      <td>5312 Teachers' Aides</td>\n",
+       "      <td>CHL</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>10740120</td>\n",
+       "      <td>trabajaba en el campo como capatas. aveces cui...</td>\n",
+       "      <td>6121</td>\n",
+       "      <td>None</td>\n",
+       "      <td>Livestock and Dairy Producers</td>\n",
+       "      <td>6121 Livestock and Dairy Producers</td>\n",
+       "      <td>URY</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>10170109</td>\n",
+       "      <td>gas abastible. vende gas abastible</td>\n",
+       "      <td>9621</td>\n",
+       "      <td>5243</td>\n",
+       "      <td>Messengers, Package Deliverers and Luggage Por...</td>\n",
+       "      <td>9621 Messengers, Package Deliverers and Luggag...</td>\n",
+       "      <td>CHL</td>\n",
+       "      <td>es</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>11480109</td>\n",
+       "      <td>jordbruk. sår potatis tar upp potatis plogar h...</td>\n",
+       "      <td>6111</td>\n",
+       "      <td>6111</td>\n",
+       "      <td>Field Crop and Vegetable Growers</td>\n",
+       "      <td>6111 Field Crop and Vegetable Growers</td>\n",
+       "      <td>FIN</td>\n",
+       "      <td>sv</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>495</th>\n",
+       "      <td>11780107</td>\n",
+       "      <td>acountent mannager|she mannages calls for jobs...</td>\n",
+       "      <td>1211</td>\n",
+       "      <td>9998</td>\n",
+       "      <td>Finance Managers</td>\n",
+       "      <td>1211 Finance Managers</td>\n",
+       "      <td>AUS</td>\n",
+       "      <td>en</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>496</th>\n",
+       "      <td>10850104</td>\n",
+       "      <td>geometra/muratore. proggetta case e le restaura</td>\n",
+       "      <td>3112</td>\n",
+       "      <td>3112</td>\n",
+       "      <td>Civil Engineering Technicians</td>\n",
+       "      <td>3112 Civil Engineering Technicians</td>\n",
+       "      <td>ITA</td>\n",
+       "      <td>it</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>497</th>\n",
+       "      <td>11460111</td>\n",
+       "      <td>fa parte della misericordia. Trasporta i malat...</td>\n",
+       "      <td>3258</td>\n",
+       "      <td>3258</td>\n",
+       "      <td>Ambulance Workers</td>\n",
+       "      <td>3258 Ambulance Workers</td>\n",
+       "      <td>ITA</td>\n",
+       "      <td>it</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>498</th>\n",
+       "      <td>10340111</td>\n",
+       "      <td>사회복지사. 회사에서 복지원 관리</td>\n",
+       "      <td>2635</td>\n",
+       "      <td>2635</td>\n",
+       "      <td>Social Work and Counselling Professionals</td>\n",
+       "      <td>2635 Social Work and Counselling Professionals</td>\n",
+       "      <td>KOR</td>\n",
+       "      <td>ko</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>499</th>\n",
+       "      <td>10370105</td>\n",
+       "      <td>자영업. 가게를 운영하신다.</td>\n",
+       "      <td>5221</td>\n",
+       "      <td>None</td>\n",
+       "      <td>Shopkeepers</td>\n",
+       "      <td>5221 Shopkeepers</td>\n",
+       "      <td>KOR</td>\n",
+       "      <td>ko</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>500 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       IDSTUD                                         JOB_DUTIES  ISCO  \\\n",
+       "0    10670109  forældre 1:   Han arbejder som med-chef sammen...  7412   \n",
+       "1    10130106  asistente de parbulo y basica. ayudaba en la e...  5312   \n",
+       "2    10740120  trabajaba en el campo como capatas. aveces cui...  6121   \n",
+       "3    10170109                 gas abastible. vende gas abastible  9621   \n",
+       "4    11480109  jordbruk. sår potatis tar upp potatis plogar h...  6111   \n",
+       "..        ...                                                ...   ...   \n",
+       "495  11780107  acountent mannager|she mannages calls for jobs...  1211   \n",
+       "496  10850104    geometra/muratore. proggetta case e le restaura  3112   \n",
+       "497  11460111  fa parte della misericordia. Trasporta i malat...  3258   \n",
+       "498  10340111                                 사회복지사. 회사에서 복지원 관리  2635   \n",
+       "499  10370105                                    자영업. 가게를 운영하신다.  5221   \n",
+       "\n",
+       "    ISCO_REL                                         ISCO_TITLE  \\\n",
+       "0       None                   Electrical Mechanics and Fitters   \n",
+       "1       5312                                    Teachers' Aides   \n",
+       "2       None                      Livestock and Dairy Producers   \n",
+       "3       5243  Messengers, Package Deliverers and Luggage Por...   \n",
+       "4       6111                   Field Crop and Vegetable Growers   \n",
+       "..       ...                                                ...   \n",
+       "495     9998                                   Finance Managers   \n",
+       "496     3112                      Civil Engineering Technicians   \n",
+       "497     3258                                  Ambulance Workers   \n",
+       "498     2635          Social Work and Counselling Professionals   \n",
+       "499     None                                        Shopkeepers   \n",
+       "\n",
+       "                                       ISCO_CODE_TITLE COUNTRY LANGUAGE  \n",
+       "0                7412 Electrical Mechanics and Fitters     DNK       da  \n",
+       "1                                 5312 Teachers' Aides     CHL       es  \n",
+       "2                   6121 Livestock and Dairy Producers     URY       es  \n",
+       "3    9621 Messengers, Package Deliverers and Luggag...     CHL       es  \n",
+       "4                6111 Field Crop and Vegetable Growers     FIN       sv  \n",
+       "..                                                 ...     ...      ...  \n",
+       "495                              1211 Finance Managers     AUS       en  \n",
+       "496                 3112 Civil Engineering Technicians     ITA       it  \n",
+       "497                             3258 Ambulance Workers     ITA       it  \n",
+       "498     2635 Social Work and Counselling Professionals     KOR       ko  \n",
+       "499                                   5221 Shopkeepers     KOR       ko  \n",
+       "\n",
+       "[500 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "MODEL_NAME = \"ICILS/XLM-R-ISCO\"\n",
+    "# DATASET_CONFIG = {\"path\": \"tweet_eval\", \"name\": \"sentiment\", \"split\": \"validation\"}\n",
+    "TEXT_COLUMN = \"JOB_DUTIES\"\n",
+    "TARGET_COLUMN = \"ISCO_CODE_TITLE\"\n",
+    "\n",
+    "tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)\n",
+    "model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)\n",
+    "\n",
+    "label2id: dict = model.config.label2id\n",
+    "id2label: dict = model.config.id2label\n",
+    "# LABEL_MAPPING = id2label.items()\n",
+    "\n",
+    "# raw_data = load_dataset(**DATASET_CONFIG).to_pandas().iloc[:500]\n",
+    "raw_data = load_dataset(\"ICILS/multilingual_parental_occupations\", split=\"test\").to_pandas().iloc[:500]\n",
+    "# raw_data = raw_data.replace({\"ISCO_CODE_TITLE\": LABEL_MAPPING})\n",
+    "raw_data[\"ISCO\"] = raw_data[\"ISCO\"].astype(str)\n",
+    "raw_data[\"ISCO_REL\"] = raw_data[\"ISCO_REL\"].astype(str)\n",
+    "\n",
+    "raw_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2024-03-15 01:07:06,923 pid:166193 MainThread giskard.datasets.base INFO     Your 'pandas.DataFrame' is successfully wrapped by Giskard's 'Dataset' wrapper class.\n",
+      "2024-03-15 01:07:06,925 pid:166193 MainThread giskard.models.automodel INFO     Your 'prediction_function' is successfully wrapped by Giskard's 'PredictionFunctionModel' wrapper class.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/dux/miniconda3/envs/autogenstudio/lib/python3.11/site-packages/giskard/datasets/base/__init__.py:466: UserWarning: The column ISCO is declared as numeric but has 'object' as data type. To avoid potential future issues, make sure to cast this column to the correct data type.\n",
+      "  warning(\n"
+     ]
+    }
+   ],
+   "source": [
+    "giskard_dataset = Dataset(\n",
+    "    df=raw_data,  # A pandas.DataFrame that contains the raw data (before all the pre-processing steps) and the actual ground truth variable (target).\n",
+    "    target=TARGET_COLUMN,  # Ground truth variable.\n",
+    "    name=\"ISCO-08 Parental Occupation Corpus\",  # Optional.\n",
+    ")\n",
+    "\n",
+    "def prediction_function(df: pd.DataFrame) -> np.ndarray:\n",
+    "    encoded_input = tokenizer(list(df[TEXT_COLUMN]), padding=True, return_tensors=\"pt\")\n",
+    "    output = model(**encoded_input)\n",
+    "    return softmax(output[\"logits\"].detach().numpy(), axis=1)\n",
+    "\n",
+    "\n",
+    "giskard_model = Model(\n",
+    "    model=prediction_function,  # A prediction function that encapsulates all the data pre-processing steps and that\n",
+    "    model_type=\"classification\",  # Either regression, classification or text_generation.\n",
+    "    name=\"XLM-R ISCO\",  # Optional\n",
+    "    classification_labels=list(label2id.keys()),  # Their order MUST be identical to the prediction_function's\n",
+    "    feature_names=[TEXT_COLUMN],  # Default: all columns of your dataset\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2024-03-15 01:07:10,228 pid:166193 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'JOB_DUTIES': 'object'} to {'JOB_DUTIES': 'object'}\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2024-03-15 01:07:12,838 pid:166193 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (10, 8) executed in 0:00:02.617399\n",
+      "2024-03-15 01:07:12,848 pid:166193 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'JOB_DUTIES': 'object'} to {'JOB_DUTIES': 'object'}\n",
+      "2024-03-15 01:07:13,007 pid:166193 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (1, 8) executed in 0:00:00.166843\n",
+      "2024-03-15 01:07:13,015 pid:166193 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'JOB_DUTIES': 'object'} to {'JOB_DUTIES': 'object'}\n",
+      "2024-03-15 01:07:13,017 pid:166193 MainThread giskard.utils.logging_utils INFO     Predicted dataset with shape (10, 8) executed in 0:00:00.009517\n",
+      "2024-03-15 01:07:13,029 pid:166193 MainThread giskard.datasets.base INFO     Casting dataframe columns from {'JOB_DUTIES': 'object'} to {'JOB_DUTIES': 'object'}\n"
+     ]
+    },
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
+      "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
+      "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
+      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
+     ]
+    }
+   ],
+   "source": [
+    "results = scan(giskard_model, giskard_dataset)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'results' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[7], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m display(\u001b[43mresults\u001b[49m)\n\u001b[1;32m      3\u001b[0m \u001b[38;5;66;03m# Save it to a file\u001b[39;00m\n\u001b[1;32m      4\u001b[0m results\u001b[38;5;241m.\u001b[39mto_html(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mscan_report.html\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'results' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "display(results)\n",
+    "\n",
+    "# Save it to a file\n",
+    "results.to_html(\"scan_report.html\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "GiskardError",
+     "evalue": "No details or messages available.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mGiskardError\u001b[0m                              Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[2], line 10\u001b[0m\n\u001b[1;32m      7\u001b[0m project_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mxlmr_isco\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m      9\u001b[0m \u001b[38;5;66;03m# Create a giskard client to communicate with Giskard\u001b[39;00m\n\u001b[0;32m---> 10\u001b[0m client \u001b[38;5;241m=\u001b[39m \u001b[43mGiskardClient\u001b[49m\u001b[43m(\u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/autogenstudio/lib/python3.11/site-packages/giskard/client/giskard_client.py:153\u001b[0m, in \u001b[0;36mGiskardClient.__init__\u001b[0;34m(self, url, key, hf_token)\u001b[0m\n\u001b[1;32m    150\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m hf_token:\n\u001b[1;32m    151\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_session\u001b[38;5;241m.\u001b[39mcookies[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mspaces-jwt\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m hf_token\n\u001b[0;32m--> 153\u001b[0m server_settings: ServerInfo \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_server_info\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    155\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m server_settings\u001b[38;5;241m.\u001b[39mserverVersion \u001b[38;5;241m!=\u001b[39m giskard\u001b[38;5;241m.\u001b[39m__version__:\n\u001b[1;32m    156\u001b[0m     warning(\n\u001b[1;32m    157\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYour giskard client version (\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mgiskard\u001b[38;5;241m.\u001b[39m__version__\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m) does not match the hub version \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    158\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m(\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mserver_settings\u001b[38;5;241m.\u001b[39mserverVersion\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m). \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    159\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPlease upgrade your client to the latest version. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    160\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpip install \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgiskard[hub]>=2.0.0b\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m -U\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m    161\u001b[0m     )\n",
+      "File \u001b[0;32m~/miniconda3/envs/autogenstudio/lib/python3.11/site-packages/giskard/client/giskard_client.py:417\u001b[0m, in \u001b[0;36mGiskardClient.get_server_info\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    416\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget_server_info\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ServerInfo:\n\u001b[0;32m--> 417\u001b[0m     resp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_session\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/public-api/ml-worker-connect\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m    418\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    419\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m ServerInfo\u001b[38;5;241m.\u001b[39mparse_obj(resp\u001b[38;5;241m.\u001b[39mjson())\n",
+      "File \u001b[0;32m~/miniconda3/envs/autogenstudio/lib/python3.11/site-packages/requests/sessions.py:602\u001b[0m, in \u001b[0;36mSession.get\u001b[0;34m(self, url, **kwargs)\u001b[0m\n\u001b[1;32m    594\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124;03m\"\"\"Sends a GET request. Returns :class:`Response` object.\u001b[39;00m\n\u001b[1;32m    595\u001b[0m \n\u001b[1;32m    596\u001b[0m \u001b[38;5;124;03m:param url: URL for the new :class:`Request` object.\u001b[39;00m\n\u001b[1;32m    597\u001b[0m \u001b[38;5;124;03m:param \\*\\*kwargs: Optional arguments that ``request`` takes.\u001b[39;00m\n\u001b[1;32m    598\u001b[0m \u001b[38;5;124;03m:rtype: requests.Response\u001b[39;00m\n\u001b[1;32m    599\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    601\u001b[0m kwargs\u001b[38;5;241m.\u001b[39msetdefault(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mallow_redirects\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m--> 602\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mGET\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/autogenstudio/lib/python3.11/site-packages/requests_toolbelt/sessions.py:76\u001b[0m, in \u001b[0;36mBaseUrlSession.request\u001b[0;34m(self, method, url, *args, **kwargs)\u001b[0m\n\u001b[1;32m     74\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Send the request after generating the complete URL.\"\"\"\u001b[39;00m\n\u001b[1;32m     75\u001b[0m url \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcreate_url(url)\n\u001b[0;32m---> 76\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mBaseUrlSession\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     77\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m     78\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/autogenstudio/lib/python3.11/site-packages/requests/sessions.py:589\u001b[0m, in \u001b[0;36mSession.request\u001b[0;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[1;32m    584\u001b[0m send_kwargs \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    585\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtimeout\u001b[39m\u001b[38;5;124m\"\u001b[39m: timeout,\n\u001b[1;32m    586\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mallow_redirects\u001b[39m\u001b[38;5;124m\"\u001b[39m: allow_redirects,\n\u001b[1;32m    587\u001b[0m }\n\u001b[1;32m    588\u001b[0m send_kwargs\u001b[38;5;241m.\u001b[39mupdate(settings)\n\u001b[0;32m--> 589\u001b[0m resp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43msend_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    591\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m resp\n",
+      "File \u001b[0;32m~/miniconda3/envs/autogenstudio/lib/python3.11/site-packages/requests/sessions.py:703\u001b[0m, in \u001b[0;36mSession.send\u001b[0;34m(self, request, **kwargs)\u001b[0m\n\u001b[1;32m    700\u001b[0m start \u001b[38;5;241m=\u001b[39m preferred_clock()\n\u001b[1;32m    702\u001b[0m \u001b[38;5;66;03m# Send the request\u001b[39;00m\n\u001b[0;32m--> 703\u001b[0m r \u001b[38;5;241m=\u001b[39m \u001b[43madapter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    705\u001b[0m \u001b[38;5;66;03m# Total elapsed time of the request (approximately)\u001b[39;00m\n\u001b[1;32m    706\u001b[0m elapsed \u001b[38;5;241m=\u001b[39m preferred_clock() \u001b[38;5;241m-\u001b[39m start\n",
+      "File \u001b[0;32m~/miniconda3/envs/autogenstudio/lib/python3.11/site-packages/requests/adapters.py:538\u001b[0m, in \u001b[0;36mHTTPAdapter.send\u001b[0;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[1;32m    535\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    536\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m\n\u001b[0;32m--> 538\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbuild_response\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mresp\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/autogenstudio/lib/python3.11/site-packages/giskard/client/giskard_client.py:107\u001b[0m, in \u001b[0;36mErrorHandlingAdapter.build_response\u001b[0;34m(self, req, resp)\u001b[0m\n\u001b[1;32m    105\u001b[0m resp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28msuper\u001b[39m(ErrorHandlingAdapter, \u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39mbuild_response(req, resp)\n\u001b[1;32m    106\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m _get_status(resp) \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m400\u001b[39m:\n\u001b[0;32m--> 107\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m explain_error(resp)\n\u001b[1;32m    109\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m resp\n",
+      "\u001b[0;31mGiskardError\u001b[0m: No details or messages available."
+     ]
+    }
+   ],
+   "source": [
+    "import giskard\n",
+    "from datasets import load_dataset\n",
+    "\n",
+    "dataset = load_dataset(\"ICILS/multilingual_parental_occupations\", split=\"test\")\n",
+    "\n",
+    "# Replace this with your own data & model creation.\n",
+    "# df = giskard.demo.titanic_df()\n",
+    "df = dataset\n",
+    "demo_data_preprocessing_function, demo_sklearn_model = giskard.demo.titanic_pipeline()\n",
+    "\n",
+    "# Wrap your Pandas DataFrame\n",
+    "giskard_dataset = giskard.Dataset(df=df,\n",
+    "                                  target=\"ISCO_CODE_TITLE\",\n",
+    "                                  name=\"ISCO-08 Parental Occupation Corpus\",\n",
+    "                                  cat_columns=['LANGUAGE', 'COUNTRY'])\n",
+    "\n",
+    "# Wrap your model\n",
+    "def prediction_function(df):\n",
+    "    preprocessed_df = demo_data_preprocessing_function(df)\n",
+    "    return demo_sklearn_model.predict_proba(preprocessed_df)\n",
+    "\n",
+    "giskard_model = giskard.Model(model=prediction_function,\n",
+    "                              model_type=\"classification\",\n",
+    "                              name=\"Titanic model\",\n",
+    "                              classification_labels=demo_sklearn_model.classes_,\n",
+    "                              feature_names=['PassengerId', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked'])\n",
+    "\n",
+    "# Then apply the scan\n",
+    "results = giskard.scan(giskard_model, giskard_dataset)\n",
+    "\n",
+    "\n",
+    "# Create a Giskard client\n",
+    "client = giskard.GiskardClient(\n",
+    "    url=\"https://danieldux-giskard.hf.space\",  # URL of your Giskard instance\n",
+    "    key=\"<Generate your API Key on the Giskard Hub settings page first>\")\n",
+    "\n",
     "\n",
-    "print(\"Evaluation results saved to isco_results.json\")"
+    "# Upload an automatically created test suite to the current project ✉️\n",
+    "results.generate_test_suite(\"Test suite created by scan\").upload(client, \"xlmr_isco\")\n"
    ]
   }
  ],