Upload app.py

app.py

@@ -15,7 +15,6 @@ from matplotlib import pyplot
 import xgboost as xgb
 import lightgbm as lgb
 import catboost as cb
-from catboost import Pool
 from sklearn.ensemble import RandomForestClassifier
 import optuna
 from optuna.samplers import TPESampler
@@ -109,6 +108,7 @@ y1 = x1.pop('OUTCOME')
 categorical_columns1 = list(x1.select_dtypes('object').columns)
 x1 = x1.astype({col: "category" for col in categorical_columns1})
 y1_data_xgb = xgb.DMatrix(x1, label=y1, enable_categorical=True)
+x1_lgb = x1.rename(columns = lambda x:re.sub('[^A-Za-z0-9_]+', '', x))
 y1_data_lgb = lgb.Dataset(x1, label=y1) 
 y1_data_cb = Pool(data=x1, label=y1, cat_features=categorical_columns1)
 x1_rf = x1
@@ -125,7 +125,8 @@ y2 = x2.pop('OUTCOME')
 categorical_columns2 = list(x2.select_dtypes('object').columns)
 x2 = x2.astype({col: "category" for col in categorical_columns2})
 y2_data_xgb = xgb.DMatrix(x2, label=y2, enable_categorical=True)
-y2_data_lgb = lgb.Dataset(x2, label=y2) 
+x2_lgb = x2.rename(columns = lambda x:re.sub('[^A-Za-z0-9_]+', '', x))
+y2_data_lgb = lgb.Dataset(x2_lgb, label=y2) 
 y2_data_cb = Pool(data=x2, label=y2, cat_features=categorical_columns2)
 x2_rf = x2
 categorical_columns2 = list(x2_rf.select_dtypes('category').columns)
@@ -141,6 +142,7 @@ y3 = x3.pop('OUTCOME')
 categorical_columns3 = list(x3.select_dtypes('object').columns)
 x3 = x3.astype({col: "category" for col in categorical_columns3})
 y3_data_xgb = xgb.DMatrix(x3, label=y3, enable_categorical=True)
+x3_lgb = x3.rename(columns = lambda x:re.sub('[^A-Za-z0-9_]+', '', x))
 y3_data_lgb = lgb.Dataset(x3, label=y3) 
 y3_data_cb = Pool(data=x3, label=y3, cat_features=categorical_columns3)
 x3_rf = x3
@@ -157,6 +159,7 @@ y4 = x4.pop('OUTCOME')
 categorical_columns4 = list(x4.select_dtypes('object').columns)
 x4 = x4.astype({col: "category" for col in categorical_columns4})
 y4_data_xgb = xgb.DMatrix(x4, label=y4, enable_categorical=True)
+x4_lgb = x4.rename(columns = lambda x:re.sub('[^A-Za-z0-9_]+', '', x))
 y4_data_lgb = lgb.Dataset(x4, label=y4) 
 y4_data_cb = Pool(data=x4, label=y4, cat_features=categorical_columns4)
 x4_rf = x4
@@ -173,6 +176,7 @@ y5 = x5.pop('OUTCOME')
 categorical_columns5 = list(x5.select_dtypes('object').columns)
 x5 = x5.astype({col: "category" for col in categorical_columns5})
 y5_data_xgb = xgb.DMatrix(x5, label=y5, enable_categorical=True)
+x5_lgb = x5.rename(columns = lambda x:re.sub('[^A-Za-z0-9_]+', '', x))
 y5_data_lgb = lgb.Dataset(x5, label=y5) 
 y5_data_cb = Pool(data=x5, label=y5, cat_features=categorical_columns5)
 x5_rf = x5
@@ -996,4 +1000,4 @@ with gr.Blocks(title = "NTDB-Epidural") as demo:
                     outputs = [plot],
                 )
                 
-demo.launch()   
+demo.launch()