Encode non-numeric columns

src/preprocessing.py

@@ -1,5 +1,5 @@
 from pandas import DataFrame, read_csv
-from sklearn.preprocessing import LabelEncoder, normalize
+from sklearn.preprocessing import LabelEncoder
 from sklearn.model_selection import KFold
 
 
@@ -12,22 +12,29 @@ def construct_dataframes(train, test):
     return df_list
 
 
-def drop_null_values(df_list) -> DataFrame:
+def drop_null_values(df_list):
     for df in df_list:
         df.dropna(inplace=True)
         df.drop(columns="Tipo_marchas", inplace=True)
     return df_list
 
 
+def rename_columns(df_list) -> DataFrame:
+    for df in df_list:
+        df.columns = df.columns.str.lower()
+    return df_list
+
+
 def trim_column_names(df_list) -> DataFrame:
-    columns = ["Consumo", "Motor_CC", "Potencia"]
+    columns = ["consumo", "motor_CC", "potencia"]
     for df in df_list:
         for col in columns:
             df[col] = df[col].str.replace(pat="[^.0-9]", repl="").astype(float)
     return df_list
 
 
-def encode_fields(df_list):
+def encode_columns(df_list):
+    label_encoder = LabelEncoder()
     files = [
         "ao"
         "asientos"
@@ -40,10 +47,12 @@ def encode_fields(df_list):
         "motor_cc"
         "nombre"
         "potencia"
-        "potencia"
     ]
     for data in files:
-        pass
+        for df in df_list:
+            label = label_encoder.fit(read_csv("data/" + data + ".csv", squeeze=True))
+            df[data] = label.transform(df[data])
+    return df_list
 
 
 def split_k_sets(df):
@@ -53,6 +62,8 @@ def split_k_sets(df):
 
 def parse_data(train, test):
     df_list = construct_dataframes(train=train, test=test)
-    processed_df_list = drop_null_values(df_list)
+    renamed_df_list = rename_columns(df_list)
+    processed_df_list = drop_null_values(renamed_df_list)
     numeric_df_list = trim_column_names(processed_df_list)
-    return numeric_df_list
+    encoded_df_list = encode_columns(numeric_df_list)
+    return encoded_df_list