update support texts and light gbm model names

dashboard/app.py

@@ -44,8 +44,8 @@ app_ui = ui.page_fluid(
                 ui.markdown("**Ranking**"),
                 ui.input_select(
                     "model_select_rank", "Select ranking model:",
-                    choices = ["Light XGBM 1", "Light XGBM 2", "Light XGBM 3"],
-                    selected = "Light XGBM 3"
+                    choices = ["Light GBM 1", "Light GBM 2", "Light GBM 3"],
+                    selected = "Light GBM 3"
                 ),
                 ui.input_select(
                     "rank_cutoff_select", "Select minimum prediction score (%):",

dashboard/modules/ranking.py

@@ -154,11 +154,11 @@ def rank_campaign(CAMPAIGN_ID, ranker=lgbm_model_3, rank_cutoff=50):
 
 # Rank single lead
 def rank_single_lead(CAMPAIGN_ID, LEAD_ID, rank_cutoff=50, ranker=lgbm_model_3):
-    if ranker == "Light XGBM 1":
+    if ranker == "Light GBM 1":
         ranker = lgbm_model_1
-    elif ranker == "Light XGBM 2":
+    elif ranker == "Light GBM 2":
         ranker = lgbm_model_2
-    elif ranker == "Light XGBM 3":
+    elif ranker == "Light GBM 3":
         ranker = lgbm_model_3
 
     # Selecting single lead data and combine text columns used for ranking

dashboard/modules/support_texts.py

@@ -61,7 +61,7 @@ ranking_intro_3 =                   '''
                                     '''
 
 models_test_ranking_1 =             '''
-                                    The ranking models are based on LightGMB, which is a gradient boosting framework that uses tree based learning algorithms. From this framework, models are created using the LGBMRanker. Here, the objective
+                                    The ranking models are based on LightGBM, which is a gradient boosting framework that uses tree based learning algorithms. From this framework, models are created using the LGBMRanker. Here, the objective
                                     parameter is set to 'lambdarank' and the boosting type parameter is set to 'Gradient Boosting Decision Tree'. The combination of these two parameters mean that the models use a lambdaMART algorithm. The models
                                     available in this dashboard are described below. More information about, for example, the specific training parameters can be found in the source code.
                                     <br>