24 lines
567 B
Python
24 lines
567 B
Python
|
import pandas as pd
|
||
|
|
|
||
|
|
from config import DATA_SIZE
|
||
|
|
|
||
|
|
|
||
|
|
def load_dataset():
|
||
|
|
data = pd.read_csv('true_car_listings.csv')[:DATA_SIZE]
|
||
|
|
|
||
|
|
names = ['Year', 'Mileage', 'City', 'State', 'Vin', 'Make', 'Model']
|
||
|
|
convert_to_num(data, 'City')
|
||
|
|
convert_to_num(data, 'State')
|
||
|
|
convert_to_num(data, 'Vin')
|
||
|
|
convert_to_num(data, 'Make')
|
||
|
|
convert_to_num(data, 'Model')
|
||
|
|
Y = data['Price']
|
||
|
|
X = data[names]
|
||
|
|
|
||
|
|
return X, Y, names
|
||
|
|
|
||
|
|
|
||
|
|
def convert_to_num(data, col):
|
||
|
|
unique_numbers = list(set(data[col]))
|
||
|
|
data[col] = data[col].apply(unique_numbers.index)
|