IN-P3/src/preprocessing.py

59 lines
1.4 KiB
Python

from pandas import DataFrame, read_csv
from sklearn.preprocessing import LabelEncoder, normalize
from sklearn.model_selection import KFold
def construct_dataframes(train, test):
file_list = [train, test]
df_dict = {}
for file in file_list:
df_dict[file] = read_csv(filepath_or_buffer=file)
df_list = list(df_dict.values())
return df_list
def drop_null_values(df_list) -> DataFrame:
for df in df_list:
df.dropna(inplace=True)
df.drop(columns="Tipo_marchas", inplace=True)
return df_list
def trim_column_names(df_list) -> DataFrame:
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):
files = [
"ao"
"asientos"
"ciudad"
"combustible"
"consumo"
"descuento"
"kilometros"
"mano"
"motor_cc"
"nombre"
"potencia"
"potencia"
]
for data in files:
pass
def split_k_sets(df):
k_fold = KFold(shuffle=True, random_state=42)
return k_fold.split(df)
def parse_data(train, test):
df_list = construct_dataframes(train=train, test=test)
processed_df_list = drop_null_values(df_list)
numeric_df_list = trim_column_names(processed_df_list)
return numeric_df_list