saving work

my_data5.py

@@ -15,6 +15,7 @@ from sklearn.neural_network import MLPClassifier
 from sklearn.pipeline import Pipeline
 from xgboost import XGBClassifier
 from sklearn.preprocessing import StandardScaler
+from sklearn.preprocessing import MinMaxScaler
 from sklearn.model_selection import train_test_split
 import os
 from sklearn.metrics import accuracy_score, confusion_matrix, precision_score, recall_score, roc_auc_score, roc_curve, f1_score
@@ -23,15 +24,30 @@ import pandas as pd
 homedir = os.path.expanduser("~")
 os.chdir(homedir + "/git/ML_AI_training/test_data")
 
-# this needs to be merged_df2 or merged_df3?
 #gene 'pncA'
-drug = 'pyrazinamide'
+#drug = 'pyrazinamide'
 
-my_df = pd.read_csv("pnca_merged_df3.csv")
+#==============
+# directories
+#==============
+datadir = homedir + '/git/Data/'
+indir = datadir + drug + '/input/'
+outdir = datadir + drug + '/output/'
 
+#=======
+# input
+#=======
+# this needs to be merged_df2 or merged_df3?
+infile_ml1 = outdir + gene.lower() + '_merged_df3.csv' 
+#infile_ml2 = outdir + gene.lower() + '_merged_df2.csv'
+
+my_df = pd.read_csv(infile_ml1)
 my_df.dtypes
 my_df_cols = my_df.columns
 
+gene_baiscL = ['pnca']
+geneL_naL   = ['gid', 'rpob']
+geneL_ppi2L = ['alr', 'embb', 'katg', 'rpob']
 #%%============================================================================
 # GET Y
 # Y = my_df.loc[:,drug] #has NA
@@ -116,7 +132,7 @@ def modelPipeline(X_train, X_test, y_train, y_test):
     for clf_name, clf in clfs:
 
         pipeline = Pipeline(steps=[
-                                   ('scaler', StandardScaler()),
+                                   ('scaler', MinMaxScaler()),
                                    ('classifier', clf)
                                    ]
                             )