57 lines
2.9 KiB
Python
57 lines
2.9 KiB
Python
# Importowanie potrzebnych bibliotek
|
|
import pickle
|
|
import csv
|
|
import pandas as pd
|
|
import numpy as np
|
|
from sklearn.linear_model import LinearRegression
|
|
from sklearn.metrics import mean_squared_error
|
|
|
|
# Nazwa pliku z modelem
|
|
filename = "flat_model.pkl"
|
|
|
|
#Ładowanie danych do trenowania
|
|
data = pd.read_table("mieszkania/train.tsv", delimiter='\t', header=None)
|
|
data.rename(columns={0: 'cena', 1: 'stan', 2: 'czynsz', 3: 'x3', 4: 'cenazam', 5: 'link', 6: 'pietro', 7: 'x7', 8: 'metraz', 9: 'rynek', 10: 'liczba pokoi', 11: 'budynek', 12: 'x12', 13: 'x13', 14: 'x14', 15: 'x15', 16: 'x16', 17: 'x17', 18: 'x18', 19: 'x19', 20: 'x20', 21: 'x21', 22: 'x22', 23: 'x23', 24: 'x24', 25: 'x25'}, inplace=True)
|
|
|
|
#Ładowanie danych do ewaluacji
|
|
data_eval = pd.read_table("mieszkania/test.tsv", delimiter='\t', header=None)
|
|
data_eval_expected = pd.read_table("mieszkania/test_expected.tsv", delimiter='\t', header=None)
|
|
data_eval.rename(columns={0: 'stan', 1: 'czynsz', 2: 'x3', 3: 'cenazam', 4: 'link', 5: 'pietro', 6: 'x7', 7: 'metraz', 8: 'rynek', 9: 'liczba pokoi', 10: 'budynek', 11: 'x12', 12: 'x13', 13: 'x14', 14: 'x15', 15: 'x16', 16: 'x17', 17: 'x18', 18: 'x19', 19: 'x20', 20: 'x21', 21: 'x22', 22: 'x23', 23: 'x24', 24: 'x25'}, inplace=True)
|
|
data_eval_expected.rename(columns={0:'cena'}, inplace=True)
|
|
data_eval = pd.concat([data_eval, data_eval_expected], axis=1)
|
|
|
|
#Czyszczenie danych
|
|
data.drop(['x3','cenazam','link','pietro','budynek','x7','x12','x13','x14','x15','x16','x17','x18','x19','x20','x21','x22','x23','x24','x25'], inplace=True, axis=1)
|
|
data['czynsz'] = data['czynsz'].str.extract('(\d+)')
|
|
data['stan'] = data['stan'].map({'do zamieszkania': 2, 'do remontu': 1, 'do wykończenia': 2})
|
|
data['rynek'] = data['rynek'].map({'wtórny': 0, 'pierwotny': 1})
|
|
data.dropna(inplace=True)
|
|
|
|
data_eval.drop(['x3','cenazam','link','pietro','budynek','x7','x12','x13','x14','x15','x16','x17','x18','x19','x20','x21','x22','x23','x24','x25'], inplace=True, axis=1)
|
|
data_eval['czynsz'] = data_eval['czynsz'].str.extract('(\d+)')
|
|
data_eval['stan'] = data_eval['stan'].map({'do zamieszkania': 2, 'do remontu': 1, 'do wykończenia': 2})
|
|
data_eval['rynek'] = data_eval['rynek'].map({'wtórny': 0, 'pierwotny': 1})
|
|
data_eval.dropna(inplace=True)
|
|
|
|
#Wybranie danych do treningu
|
|
cena = data['cena']
|
|
parametry = data[['stan', 'czynsz', 'liczba pokoi', 'metraz', 'rynek']]
|
|
|
|
#Wybranie danych do ewaluacji
|
|
cena_eval = data_eval['cena'].tolist()
|
|
parametry_eval = data_eval[['stan', 'czynsz', 'liczba pokoi', 'metraz', 'rynek']]
|
|
|
|
#Proces trenowania
|
|
model = LinearRegression()
|
|
model.fit(X=parametry, y=cena)
|
|
|
|
#Ewaluacja
|
|
cena_predicted_eval = model.predict(parametry_eval)
|
|
mse = mean_squared_error(cena_eval, cena_predicted_eval)
|
|
|
|
#Zwrócenie metryki mean squared error na zbiorze do ewaluacji
|
|
print(f"Metryka mean squared error {mse}")
|
|
|
|
#Zapisanie modelu
|
|
pickle.dump(model, open(filename, "wb"))
|