Update utils.py

utils.py

@@ -11,30 +11,15 @@ import matplotlib.pyplot as plt
 explainer_filename = "explainer.bz2"
 
 feature_names = ['PROPERTY: Calculated Density (g/cm$^3$)',
-       'PROPERTY: Calculated Young modulus (GPa)', 'Microstructure B2',
-       'Microstructure B2+BCC', 'Microstructure B2+L12',
-       'Microstructure B2+Laves+Sec.', 'Microstructure B2+Sec.',
-       'Microstructure BCC', 'Microstructure BCC+B2',
-       'Microstructure BCC+B2+FCC', 'Microstructure BCC+B2+FCC+Sec.',
-       'Microstructure BCC+B2+L12', 'Microstructure BCC+B2+Laves',
-       'Microstructure BCC+B2+Sec.', 'Microstructure BCC+BCC',
-       'Microstructure BCC+BCC+HCP', 'Microstructure BCC+BCC+Laves',
-       'Microstructure BCC+BCC+Laves(C14)',
-       'Microstructure BCC+BCC+Laves(C15)', 'Microstructure BCC+FCC',
-       'Microstructure BCC+HCP', 'Microstructure BCC+Laves',
-       'Microstructure BCC+Laves(C14)', 'Microstructure BCC+Laves(C15)',
-       'Microstructure BCC+Laves+Sec.', 'Microstructure BCC+Sec.',
-       'Microstructure FCC', 'Microstructure FCC+B2',
-       'Microstructure FCC+B2+Sec.', 'Microstructure FCC+BCC',
-       'Microstructure FCC+BCC+B2', 'Microstructure FCC+BCC+B2+Sec.',
-       'Microstructure FCC+BCC+BCC', 'Microstructure FCC+BCC+Sec.',
-       'Microstructure FCC+FCC', 'Microstructure FCC+HCP',
-       'Microstructure FCC+HCP+Sec.', 'Microstructure FCC+L12',
-       'Microstructure FCC+L12+B2', 'Microstructure FCC+L12+Sec.',
-       'Microstructure FCC+Laves', 'Microstructure FCC+Laves(C14)',
-       'Microstructure FCC+Laves+Sec.', 'Microstructure FCC+Sec.',
-       'Microstructure L12+B2', 'Microstructure Laves(C14)+Sec.',
-       'Microstructure OTHER', 'Preprocessing method ANNEAL',
+       'PROPERTY: Calculated Young modulus (GPa)', 'PROPERTY: Metal Al',
+       'PROPERTY: Metal Co', 'PROPERTY: Metal Fe', 'PROPERTY: Metal Ni',
+       'PROPERTY: Metal Si', 'PROPERTY: Metal Cr', 'PROPERTY: Metal Nb',
+       'PROPERTY: Metal Ti', 'PROPERTY: Metal Mn', 'PROPERTY: Metal V',
+       'PROPERTY: Metal Mo', 'PROPERTY: Metal Cu', 'PROPERTY: Metal Ta',
+       'PROPERTY: Metal Zr', 'PROPERTY: Metal Hf', 'PROPERTY: Metal W',
+       'PROPERTY: Metal Zn', 'PROPERTY: Metal Sn', 'PROPERTY: Metal Re',
+       'PROPERTY: Metal C', 'PROPERTY: Metal Pd', 'PROPERTY: Metal Sc',
+       'PROPERTY: Metal Y', 'Preprocessing method ANNEAL',
        'Preprocessing method CAST', 'Preprocessing method OTHER',
        'Preprocessing method POWDER', 'Preprocessing method WROUGHT',
        'BCC/FCC/other BCC', 'BCC/FCC/other FCC', 'BCC/FCC/other OTHER',
@@ -138,7 +123,7 @@ def turn_into_one_hot(X, mapping_dict):
     one_hot = X
     num_classes_one_hot = {'Num classes microstructure': 45, 'Num classes preprocessing': 5,
                            'Num classes single/multiphase': 3, 'Num classes bcc/fcc/other': 3}
-    one_hot["Microstructure One Hot"] = X["PROPERTY: Microstructure"].apply(to_categorical_num_classes_microstructure, num_classes_one_hot=num_classes_one_hot)
+    #one_hot["Microstructure One Hot"] = X["PROPERTY: Microstructure"].apply(to_categorical_num_classes_microstructure, num_classes_one_hot=num_classes_one_hot)
     one_hot["Processing Method One Hot"] = X["PROPERTY: Processing method"].apply(to_categorical_num_classes_processing,
         num_classes_one_hot=num_classes_one_hot)
     one_hot["BCC/FCC/other One Hot"] = X["PROPERTY: BCC/FCC/other"].apply(to_categorical_bcc_fcc_other,
@@ -146,17 +131,18 @@ def turn_into_one_hot(X, mapping_dict):
     one_hot["Single/Multiphase One Hot"] = X["PROPERTY: Single/Multiphase"].apply(to_categorical_single_multiphase,
         num_classes_one_hot=num_classes_one_hot)
 
-    flatten_microstructure = one_hot["Microstructure One Hot"].apply(pd.Series)
+    #flatten_microstructure = one_hot["Microstructure One Hot"].apply(pd.Series)
     flatten_processing = one_hot["Processing Method One Hot"].apply(pd.Series)
     flatten_bcc_fcc_other = one_hot["BCC/FCC/other One Hot"].apply(pd.Series)
     flatten_single_multiphase = one_hot["Single/Multiphase One Hot"].apply(pd.Series)
 
-    one_hot.drop(columns=["Microstructure One Hot", "Processing Method One Hot", "BCC/FCC/other One Hot",
-                          "Single/Multiphase One Hot"])
+    one_hot.drop(columns=[#"Microstructure One Hot",
+        "Processing Method One Hot", "BCC/FCC/other One Hot",
+        "Single/Multiphase One Hot"])
 
-    for column in flatten_microstructure.columns:
-        one_hot["Microstructure " + str(
-            list(mapping_dict["PROPERTY: Microstructure"].keys())[int(column)])] = flatten_microstructure[int(column)]
+    #for column in flatten_microstructure.columns:
+       # one_hot["Microstructure " + str(
+         #   list(mapping_dict["PROPERTY: Microstructure"].keys())[int(column)])] = flatten_microstructure[int(column)]
     for column in flatten_processing.columns:
         one_hot["Preprocessing method " + str(list(mapping_dict["PROPERTY: Processing method"].keys())[int(column)])] = flatten_processing[column]
     for column in flatten_bcc_fcc_other.columns:
@@ -164,6 +150,7 @@ def turn_into_one_hot(X, mapping_dict):
     for column in flatten_single_multiphase.columns:
         one_hot["Single/Multiphase " + str(list(mapping_dict["PROPERTY: Single/Multiphase"].keys())[int(column)])] = flatten_single_multiphase[column]
     
-    one_hot = one_hot.drop(columns=["PROPERTY: Microstructure", "Microstructure One Hot", "BCC/FCC/other One Hot", "Single/Multiphase One Hot",
-                                    "Processing Method One Hot", "PROPERTY: Processing method", "PROPERTY: BCC/FCC/other", "PROPERTY: Single/Multiphase"])
+    one_hot = one_hot.drop(columns=[#"PROPERTY: Microstructure", "Microstructure One Hot",
+        "BCC/FCC/other One Hot", "Single/Multiphase One Hot",
+        "Processing Method One Hot", "PROPERTY: Processing method", "PROPERTY: BCC/FCC/other", "PROPERTY: Single/Multiphase"])
     return one_hot