cleanup of feature eng

feature_engineering.py

@@ -1,6 +1,7 @@
 
 ################ Dicts with encodings ################
-cleanup_catergories = {"sex": {"female": 1, "male": 0}, "embarked": {"S": 0, "C": 1, "Q": 2}, "Cabin": {"N": 0, "C": 1, "E": 2, "G": 3, "D":4, "A": 5, "B": 6, "F": 7, "T": 8}}
+# cabin_dict= "Cabin": {"N": 0, "C": 1, "E": 2, "G": 3, "D":4, "A": 5, "B": 6, "F": 7, "T": 8}
+cleanup_catergories = {"sex": {"female": 1, "male": 0}, "embarked": {"S": 0, "C": 1, "Q": 2}}
 
 sex_dict = {"female": 1, "male": 0}
 embarked_dict = {"S": 0, "C": 1, "Q": 2}
@@ -85,10 +86,10 @@ def feat_eng(df):
     # pd.cut(df['SibSp'], [0,1,2,7], right=False)
 
     # Cabin into categories based on first letter(deck of boat)
-    df["Cabin"] = df["Cabin"].str.slice(0,1)
+    # df["Cabin"] = df["Cabin"].str.slice(0,1)
 
     # Make a separate category of all te NANs
-    df["Cabin"] = df["Cabin"].fillna("N")
+    # df["Cabin"] = df["Cabin"].fillna("N")
 
     # Fixes for hopsworks...
     df.columns = df.columns.str.lower()