fix l2 norms for officer race, updated models added

block_officer_gender.py

@@ -0,0 +1,147 @@
+import gradio as gr
+
+import config
+import model
+from inference import infer_officer_gender
+
+
+def infer(model_name,
+          current_rank,
+          incident_rank,
+          previous_complaints,
+          complaint_duration_days,
+          days_on_force,
+          officer_gender,
+          fado_type,
+          allegation,
+          ccrb_disposition,
+          penalty_rec,
+          penalty_cat,
+          location_type,
+          contact_outcome,
+          impacted_gender,
+          impacted_race,
+          incident_precinct):
+    # throw error if model name is not selected
+    if not model_name:
+        raise gr.Error("Please select a model")
+
+    return infer_officer_gender(model_name,
+                              current_rank,
+                              incident_rank,
+                              previous_complaints,
+                              complaint_duration_days,
+                              days_on_force,
+                              officer_gender,
+                              fado_type,
+                              allegation,
+                              ccrb_disposition,
+                              penalty_rec,
+                              penalty_cat,
+                              location_type,
+                              contact_outcome,
+                              impacted_gender,
+                              impacted_race,
+                              incident_precinct)
+
+
+with gr.Blocks() as officerGenderDemo:
+    with gr.Row():
+        with gr.Column():
+            current_rank_dropdown = gr.Dropdown(choices=config.features_and_options["CurrentRank"],
+                                                multiselect=False,
+                                                label=config.current_rank_label,
+                                                value=config.features_and_options["CurrentRank"][0])
+            incident_rank_dropdown = gr.Dropdown(choices=config.features_and_options["IncidentRank"],
+                                                 multiselect=False,
+                                                 label=config.incident_rank_label,
+                                                 value=config.features_and_options["IncidentRank"][0])
+            previous_complaints_slider = gr.Slider(minimum=0,
+                                                   maximum=100,
+                                                   step=1,
+                                                   label=config.previous_complaints_label,
+                                                   value=3)
+            complaint_duration_days_slider = gr.Slider(minimum=0,
+                                                       maximum=100,
+                                                       step=1,
+                                                       label=config.complaint_duration_days_label,
+                                                       value=3)
+            days_on_force_slider = gr.Number(label=config.days_on_force_label,
+                                             value=700)
+
+            officer_gender_dropdown = gr.Dropdown(choices=config.features_and_options["OfficerGender"],
+                                                  multiselect=False,
+                                                  interactive=True,
+                                                  label=config.officer_gender_label,
+                                                  value=config.features_and_options["OfficerGender"][0])
+            fado_type_dropdown = gr.Dropdown(choices=config.features_and_options["FADOType"],
+                                             multiselect=False,
+                                             label=config.fado_type_label,
+                                             value=config.features_and_options["FADOType"][0])
+            allegation_dropdown = gr.Dropdown(choices=config.features_and_options["Allegation"],
+                                              multiselect=False,
+                                              label=config.allegation_label,
+                                              value=config.features_and_options["Allegation"][0])
+        with gr.Column():
+            ccrb_disposition_dropdown = gr.Dropdown(choices=config.features_and_options["CCRBDisposition"],
+                                                    multiselect=False,
+                                                    label=config.ccrb_disposition_label,
+                                                    value=config.features_and_options["CCRBDisposition"][0])
+            penalty_rec_dropdown = gr.Dropdown(choices=config.features_and_options["PenaltyRec"],
+                                               multiselect=False,
+                                               label=config.penalty_rec_label,
+                                               value=config.features_and_options["PenaltyRec"][0])
+            penalty_cat_dropdown = gr.Dropdown(choices=config.features_and_options["PenaltyCat"],
+                                               multiselect=False,
+                                               interactive=True,
+                                               label=config.penalty_cat_label,
+                                               value=config.features_and_options["PenaltyCat"][0])
+            location_type_dropdown = gr.Dropdown(choices=config.features_and_options["LocationType"],
+                                                 multiselect=False,
+                                                 label=config.location_type_label,
+                                                 value=config.features_and_options["LocationType"][0])
+            contact_outcome_dropdown = gr.Dropdown(choices=config.features_and_options["ContactOutcome"],
+                                                   multiselect=False,
+                                                   label=config.contact_outcome_label,
+                                                   value=config.features_and_options["ContactOutcome"][0])
+
+            impacted_gender_dropdown = gr.Dropdown(choices=config.features_and_options["ImpactedGender"],
+                                                   multiselect=False,
+                                                   label=config.impacted_gender_label,
+                                                   value=config.features_and_options["ImpactedGender"][0])
+            impacted_race_dropdown = gr.Dropdown(choices=config.features_and_options["ImpactedRace"],
+                                                 multiselect=False,
+                                                 label=config.impacted_race_label,
+                                                 value=config.features_and_options["ImpactedRace"][0])
+            incident_precinct_dropdown = gr.Dropdown(choices=config.features_and_options["IncidentPrecinct"],
+                                                     multiselect=False,
+                                                     label=config.incident_precinct_label,
+                                                     value=config.features_and_options["IncidentPrecinct"][0])
+
+    with gr.Row():
+        with gr.Column():
+            model_dropdown = gr.Dropdown(choices=model.available_models("OfficerRace"),
+                                         multiselect=False,
+                                         label=config.model_label)
+
+    out = gr.Textbox(label="Prediction")
+
+    input_components = [model_dropdown,
+                        current_rank_dropdown,
+                        incident_rank_dropdown,
+                        previous_complaints_slider,
+                        complaint_duration_days_slider,
+                        days_on_force_slider,
+                        officer_gender_dropdown,
+                        fado_type_dropdown,
+                        allegation_dropdown,
+                        ccrb_disposition_dropdown,
+                        penalty_rec_dropdown,
+                        penalty_cat_dropdown,
+                        location_type_dropdown,
+                        contact_outcome_dropdown,
+                        impacted_gender_dropdown,
+                        impacted_race_dropdown,
+                        incident_precinct_dropdown]
+    btn = gr.Button("Predict")
+    btn.click(fn=infer, inputs=input_components, outputs=out)

config.py

@@ -64,9 +64,23 @@ features_and_options = {
 }
 
 # todo update this values
-officer_race_previous_complaints_l2_norm = 100.0
-officer_race_complaint_duration_days_l2_norm = 100.0
-officer_race_days_on_force_l2_norm = 100.0
+# Undersampling
+officer_race_l2_norm = {
+    "undersampling": {
+        "days_on_force": 584626.6887151151,
+        "complaint_duration_days": 51802.459555507594,
+        "previous_complaints": 1638.7052816171674,
+        "current_rank": 566.5465558981009,
+        "incident_rank": 440.99886621169446
+    },
+    "no_undersampling": {
+        "days_on_force": 1601408.5087007,
+        "complaint_duration_days": 132675.77404334222,
+        "previous_complaints": 4305.6496606203345,
+        "current_rank": 1539.0136451636808,
+        "incident_rank": 1196.2131917012118
+    }
+}
 
 # labels
 model_label = "Choose a model"
@@ -88,56 +102,3 @@ contact_outcome_label = "Contact Outcome"
 impacted_gender_label = "Impacted Person's Gender"
 impacted_race_label = "Impacted Person's Race"
 incident_precinct_label = "Incident Precinct"
-
-### input feature order
-# ['CurrentRank', 'IncidentRank', 'DaysOnForce', 'previousComplaints', 'complaintDurationDays',
-# 'OfficerGender_Female', 'OfficerGender_Male', 'OfficerGender_TGNC / Other', 'FADOType_Abuse of Authority',
-# 'FADOType_Bias-Based Policing', 'FADOType_Discourtesy', 'FADOType_Force', 'FADOType_Offensive Language',
-# 'FADOType_Untruthful Statement', 'Allegation_Action', 'Allegation_Beat', 'Allegation_Black',
-# 'Allegation_Chokehold', 'Allegation_Curse', 'Allegation_Demeanor/tone', 'Allegation_Dragged/Pulled',
-# 'Allegation_Entry of Premises', 'Allegation_Failure to provide RTKA card', 'Allegation_Forcible Removal to
-# Hospital', 'Allegation_Frisk', 'Allegation_Frisk and/or search', 'Allegation_Gun Drawn', 'Allegation_Gun pointed',
-# 'Allegation_Hit against inanimate object', 'Allegation_Nasty Words', 'Allegation_Nightstick as club (incl asp &
-# baton)', 'Allegation_Nightstick/Billy/Club', 'Allegation_Other', 'Allegation_Other - Abuse', 'Allegation_Other -
-# Force', 'Allegation_Other- Discourtesy', 'Allegation_Pepper spray', 'Allegation_Person Searched',
-# 'Allegation_Physical force', 'Allegation_Premise Searched', 'Allegation_Premises entered and/or searched',
-# 'Allegation_Property damaged', 'Allegation_Punch/Kick', 'Allegation_Push/Shove', 'Allegation_Question',
-# 'Allegation_Question and/or stop', 'Allegation_Race', 'Allegation_Refusal to obtain medical treatment',
-# 'Allegation_Refusal to process civilian complaint', 'Allegation_Refusal to provide name', 'Allegation_Refusal to
-# provide name/shield number', 'Allegation_Refusal to provide shield number', 'Allegation_Retaliatory summons',
-# 'Allegation_Search (of person)', 'Allegation_Search of Premises', 'Allegation_Seizure of property',
-# 'Allegation_Slap', 'Allegation_Stop', 'Allegation_Strip-searched', 'Allegation_Threat of arrest',
-# 'Allegation_Threat of force', 'Allegation_Threat of force (verbal or physical)', 'Allegation_Threat of summons',
-# 'Allegation_Threat to damage/seize property', 'Allegation_Vehicle search', 'Allegation_Vehicle stop',
-# 'Allegation_Word', 'CCRBDisposition_Alleged Victim Unavailable', 'CCRBDisposition_Alleged Victim Uncooperative',
-# 'CCRBDisposition_Closed - Pending Litigation', 'CCRBDisposition_Complainant Unavailable',
-# 'CCRBDisposition_Complainant Uncooperative', 'CCRBDisposition_Complaint Withdrawn', 'CCRBDisposition_Exonerated',
-# 'CCRBDisposition_Miscellaneous', 'CCRBDisposition_Miscellaneous - Subject Resigned', 'CCRBDisposition_Miscellaneous
-# - Subject Retired', 'CCRBDisposition_Miscellaneous - Subject Terminated', 'CCRBDisposition_Substantiated (
-# Charges)', 'CCRBDisposition_Substantiated (Command Discipline A)', 'CCRBDisposition_Substantiated (Command
-# Discipline B)', 'CCRBDisposition_Substantiated (Command Discipline)', 'CCRBDisposition_Substantiated (Command Lvl
-# Instructions)', 'CCRBDisposition_Substantiated (Formalized Training)', 'CCRBDisposition_Substantiated (
-# Instructions)', 'CCRBDisposition_Substantiated (MOS Unidentified)', 'CCRBDisposition_Substantiated (No
-# Recommendations)', 'CCRBDisposition_Unable to Determine', 'CCRBDisposition_Unfounded',
-# 'CCRBDisposition_Unsubstantiated', 'CCRBDisposition_Victim Unidentified', 'CCRBDisposition_Within NYPD Guidelines',
-# 'CCRBDisposition_Witness Unavailable', 'CCRBDisposition_Witness Uncooperative', 'PenaltyRec_Substantiated (
-# Charges)', 'PenaltyRec_Substantiated (Command Discipline A)', 'PenaltyRec_Substantiated (Command Discipline B)',
-# 'PenaltyRec_Substantiated (Command Discipline)', 'PenaltyRec_Substantiated (Formalized Training)',
-# 'PenaltyRec_Substantiated (Instructions)', 'PenaltyRec_Substantiated (MOS Unidentified)', 'PenaltyRec_Substantiated
-# (No Recommendations)', 'PenaltyRec_Unknown', 'PenaltyCat_Command Discipline', 'PenaltyCat_Loss of vacation',
-# 'PenaltyCat_No discipline', 'PenaltyCat_Pending', 'PenaltyCat_Probation', 'PenaltyCat_Reprimand',
-# 'PenaltyCat_Resigned/Retired', 'PenaltyCat_Suspension', 'PenaltyCat_Termination', 'LocationType_Apartment/house',
-# 'LocationType_Bus', 'LocationType_Commercial building', 'LocationType_Hospital', 'LocationType_NYCHA',
-# 'LocationType_Other', 'LocationType_Park', 'LocationType_Police building', 'LocationType_Police vehicle',
-# 'LocationType_Public space/building', 'LocationType_Residential building', 'LocationType_River or waterway',
-# 'LocationType_School', 'LocationType_Street/highway', 'LocationType_Subway station/train', 'LocationType_Unknown',
-# 'ContactOutcome_Arrest', 'ContactOutcome_No arrest made or summons issued', 'ContactOutcome_Summons',
-# 'ContactOutcome_Unknown', 'ImpactedGender_Female', 'ImpactedGender_Male', 'ImpactedGender_TGNC / Other',
-# 'ImpactedGender_Unknown', 'ImpactedRace_American Indian', 'ImpactedRace_Asian', 'ImpactedRace_Black',
-# 'ImpactedRace_Hispanic', 'ImpactedRace_Other Race', 'ImpactedRace_Refused', 'ImpactedRace_Unknown',
-# 'ImpactedRace_White', 'IncidentPrecinct_Bronx', 'IncidentPrecinct_Brooklyn North', 'IncidentPrecinct_Brooklyn
-# South', 'IncidentPrecinct_Manhattan North', 'IncidentPrecinct_Manhattan South', 'IncidentPrecinct_Queens North',
-# 'IncidentPrecinct_Queens South', 'IncidentPrecinct_Staten Island']
-#
-# Index(['OfficerRace_Asian', 'OfficerRace_Black',
-# 'OfficerRace_Hispanic', 'OfficerRace_White'], dtype='object')

inference.py

@@ -2,7 +2,7 @@ import numpy as np
 
 import config
 from model import load_models
-from preprocessor import process_officer_race
+from preprocessor import process_officer_race, process_officer_gender
 
 
 def predict_officer_race(model_name, X):
@@ -21,7 +21,7 @@ def infer_officer_race(model_name, current_rank, incident_rank, previous_complai
                        days_on_force, officer_gender, fado_type, allegation, ccrb_disposition,
                        penalty_rec, penalty_cat, location_type, contact_outcome, impacted_gender, impacted_race,
                        incident_precinct):
-    input_array = process_officer_race(current_rank, incident_rank, previous_complaints, complaint_duration_days,
+    input_array = process_officer_race(model_name,current_rank, incident_rank, previous_complaints, complaint_duration_days,
                                        days_on_force, officer_gender, fado_type, allegation, ccrb_disposition,
                                        penalty_rec, penalty_cat, location_type, contact_outcome, impacted_gender, impacted_race,
                                        incident_precinct)
@@ -34,7 +34,7 @@ def infer_officer_gender(model_name, current_rank, incident_rank, previous_compl
                        days_on_force, officer_gender, fado_type, allegation, ccrb_disposition,
                        penalty_rec, penalty_cat, location_type, contact_outcome, impacted_gender, impacted_race,
                        incident_precinct):
-    input_array = process_officer_race(current_rank, incident_rank, previous_complaints, complaint_duration_days,
+    input_array = process_officer_gender(current_rank, incident_rank, previous_complaints, complaint_duration_days,
                                        days_on_force, officer_gender, fado_type, allegation, ccrb_disposition,
                                        penalty_rec, penalty_cat, location_type, contact_outcome, impacted_gender, impacted_race,
                                        incident_precinct)

models/OfficerRace/ADA Undersampling/{ada_undersampling__OfficerRace_Asian.pkl → ada_undersampling_OfficerRace_Asian.pkl}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5938b672055afcc013873a2e2fa7b907f4ba9503d9d0d0a506a62d2545df366b
-size 1856036
+oid sha256:9c10588bcab2d11f1a2692421f8b9cc3034184990223d8f936d1b2e6ff76d86c
+size 1912628

models/OfficerRace/ADA Undersampling/{ada_undersampling__OfficerRace_Black.pkl → ada_undersampling_OfficerRace_Black.pkl}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad083343f12c479fb9510467f98181604daa4fb7061f2ada1dca1a070b48626c
-size 3000404
+oid sha256:fd3a4d92badf05908acff487914d60d0b1e4f7d8c4ddd96faa8e978d0e103184
+size 4120436

models/OfficerRace/ADA Undersampling/{ada_undersampling__OfficerRace_Hispanic.pkl → ada_undersampling_OfficerRace_Hispanic.pkl}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b973e31937e42e1bbdac28db5bcced0d342e4f7f2993daf90cad379dd8509ff2
-size 2448164
+oid sha256:5a714d2af5c26e700e39ac8e7913fa801402f5de6ff817567c5f263034df69e1
+size 2582228

models/OfficerRace/ADA Undersampling/{ada_undersampling__OfficerRace_White.pkl → ada_undersampling_OfficerRace_White.pkl}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744428aa96f9c824939054cf643be475e58970e20705e1237f850f9465eadea0
-size 3244916
+oid sha256:f7ac862e8729d1ab0769b24c16a8c70db6a2bfac08f43f2b359f7520985911b3
+size 5265668

models/OfficerRace/Decision Tree Undersampling/dt_undersampling_OfficerRace_Asian.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4386382127471778e9f2b0204b3ee1bbd1527e8a8c8e9d305d64b40e8e56357
+size 832793

models/OfficerRace/Decision Tree Undersampling/dt_undersampling_OfficerRace_Black.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79f0d27fe31d3867c2a97254b9eb2f427d5e54a12f36fcf44ae049a44f033ff
+size 954329

models/OfficerRace/Decision Tree Undersampling/dt_undersampling_OfficerRace_Hispanic.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de17b0b32654d61b5a0b8bc3aa25d1aa777f56bbc963bb866008b085595a1ac
+size 1064633

models/OfficerRace/Decision Tree Undersampling/dt_undersampling_OfficerRace_White.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d2e0eda9284b85febbc247796795ea2d181e14ce965faefc6449b090aba05fe
+size 933161

models/OfficerRace/GB Undersampling/gb_undersampling_OfficerRace_Asian.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:34a707091f94272edf56bedfb24994b0b8d7c9afd1a7d168c0627054f933c8e1
-size 6278571

models/OfficerRace/GB Undersampling/gb_undersampling_OfficerRace_Black.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ce31414991aeaeb5b66137175f368e7b79fa438e3222e8e747f42f22a9dbef38
-size 6598014

models/OfficerRace/GB Undersampling/gb_undersampling_OfficerRace_Hispanic.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6b6bfe15aa59e21b28fcf9c663e8e08ce4b7bd9f3f09a39ae8cf37ef0eebdc0d
-size 6630474

models/OfficerRace/GB Undersampling/gb_undersampling_OfficerRace_White.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6b5c2994e14db4499042a87e7c5e20515e6a29cfcfc51dd7bfc82ea9bf66a9d8
-size 6599854

models/OfficerRace/{Logistic Regression → Logistic Regression Undersampling}/lr_undersampling_OfficerRace_Asian.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f993447cca64f5280ff39a1fd7bf6795a7b82e180ab92d81b1a8782ab05207b7
+oid sha256:4da8179e585bff1b317e3723f2859affa19a438b6d8a2b91dc0a90d2ebe19316
 size 2079

models/OfficerRace/{Logistic Regression → Logistic Regression Undersampling}/lr_undersampling_OfficerRace_Black.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca50af63aae1e30e35ca2cfd9a834121d5d9dd64c34c4eb7322acb6d1cd3fd07
+oid sha256:d40da619b2419b8d61ca40f1a5e4e57828c75ac93ae33e44d5c39ba2cefbae5a
 size 2079

models/OfficerRace/{Logistic Regression → Logistic Regression Undersampling}/lr_undersampling_OfficerRace_Hispanic.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8419d5775699d928ebc525679badd9903d29dc2bc468c6ceb876b7dbf7592ef
+oid sha256:27f06d2feb2a65c6fdd2afdd46d316b93bd0eb0717ef7cf1afd7d649cf4c8a06
 size 2079

models/OfficerRace/{Logistic Regression → Logistic Regression Undersampling}/lr_undersampling_OfficerRace_White.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe720f754746a114a6e507aa6cb3a362d6d8bb5adc6cc3ac5b5265fa153b7c2b
+oid sha256:5f8adbf9f30af073454fb50b522c4461d317781210b117574bdc189d7c70c5bd
 size 2079

preprocessor.py

@@ -48,25 +48,29 @@ rank_to_ordinal = {
 }
 
 
-def transform_rank(current_rank):
-    return np.array((rank_to_ordinal[current_rank], ))
+def transform_incident_rank(l2_norms, incident_rank):
+    return np.array((rank_to_ordinal[incident_rank] / l2_norms["incident_rank"], ))
 
 
-def transform_previous_complaints(previous_complaints):
+def transform_current_rank(l2_norms, current_rank):
+    return np.array((rank_to_ordinal[current_rank] / l2_norms["current_rank"], ))
+
+
+def transform_previous_complaints(l2_norms, previous_complaints):
     x = int(previous_complaints)
-    x = x / config.officer_race_previous_complaints_l2_norm
+    x = x / l2_norms["previous_complaints"]
     return np.array((x, ))
 
 
-def transform_complaint_duration_days(complaint_duration_days):
+def transform_complaint_duration_days(l2_norms, complaint_duration_days):
     x = int(complaint_duration_days)
-    x = x / config.officer_race_complaint_duration_days_l2_norm
+    x = x / l2_norms["complaint_duration_days"]
     return np.array((x, ))
 
 
-def transform_days_on_force(days_on_force):
+def transform_days_on_force(l2_norms, days_on_force):
     x = int(days_on_force)
-    x = x / config.officer_race_days_on_force_l2_norm
+    x = x / l2_norms["days_on_force"]
     return np.array((x, ))
 
 
@@ -77,16 +81,19 @@ def transform_to_ohe(column_name, value):
     return one_hot
 
 
-def process_officer_race(current_rank, incident_rank, previous_complaints, complaint_duration_days,
+def process_officer_race(model_name, current_rank, incident_rank, previous_complaints, complaint_duration_days,
                          days_on_force, officer_gender, fado_type, allegation, ccrb_disposition,
                          penalty_rec, penalty_cat, location_type, contact_outcome,
                          impacted_gender, impacted_race,
                          incident_precinct):
-    current_rank = transform_rank(current_rank)
-    incident_rank = transform_rank(incident_rank)
-    previous_complaints = transform_previous_complaints(previous_complaints)
-    complaint_duration_days = transform_complaint_duration_days(complaint_duration_days)
-    days_on_force = transform_days_on_force(days_on_force)
+    l2_norms = config.officer_race_l2_norm['undersampling' if 'Undersampling' in model_name else 'no_undersampling']
+
+    current_rank = transform_current_rank(l2_norms, current_rank)
+    incident_rank = transform_incident_rank(l2_norms, incident_rank)
+    previous_complaints = transform_previous_complaints(l2_norms, previous_complaints)
+    complaint_duration_days = transform_complaint_duration_days(l2_norms, complaint_duration_days)
+    days_on_force = transform_days_on_force(l2_norms, days_on_force)
+
     officer_gender = transform_to_ohe('OfficerGender', officer_gender)
     fado_type = transform_to_ohe('FADOType', fado_type)
     allegation = transform_to_ohe('Allegation', allegation)