146 lines
6.2 KiB
Python
146 lines
6.2 KiB
Python
import pandas as pd
|
||
import joblib
|
||
import json
|
||
from typing import List, Dict
|
||
from schemas.schemas import LaptopCreate, LaptopResponse, PredictPriceResponse
|
||
|
||
class LaptopService:
|
||
def __init__(self, model_path: str, feature_columns_path: str, poly_path: str, scaler_path: str):
|
||
try:
|
||
self.model = joblib.load(model_path)
|
||
except FileNotFoundError:
|
||
raise Exception(f"Model file not found at {model_path}")
|
||
except Exception as e:
|
||
raise Exception(f"Error loading model: {str(e)}")
|
||
|
||
try:
|
||
self.feature_columns = joblib.load(feature_columns_path)
|
||
except FileNotFoundError:
|
||
raise Exception(f"Feature columns file not found at {feature_columns_path}")
|
||
except Exception as e:
|
||
raise Exception(f"Error loading feature columns: {str(e)}")
|
||
|
||
try:
|
||
self.poly_transformer = joblib.load(poly_path)
|
||
self.scaler = joblib.load(scaler_path)
|
||
except FileNotFoundError:
|
||
raise Exception("Polynomial transformer or scaler file not found.")
|
||
except Exception as e:
|
||
raise Exception(f"Error loading polynomial transformer or scaler: {str(e)}")
|
||
|
||
def predict_price(self, data: Dict[str, any]) -> PredictPriceResponse:
|
||
# Преобразование данных в DataFrame
|
||
input_df = pd.DataFrame([data])
|
||
|
||
print("До One-Hot Encoding:")
|
||
print(input_df.head())
|
||
print("Колонки:", input_df.columns)
|
||
|
||
# Применение One-Hot Encoding к категориальным признакам
|
||
input_df = pd.get_dummies(input_df, columns=['processor', 'os', 'resolution', 'gpu', 'matrix_type'], drop_first=False)
|
||
|
||
print("После One-Hot Encoding:")
|
||
print(input_df.head())
|
||
print("Колонки:", input_df.columns)
|
||
|
||
# Добавление отсутствующих признаков
|
||
for col in self.feature_columns:
|
||
if col not in input_df.columns and col != 'price':
|
||
input_df[col] = 0
|
||
|
||
# Упорядочивание колонок
|
||
input_df = input_df[self.feature_columns]
|
||
|
||
# Преобразование с использованием PolynomialFeatures
|
||
input_poly = self.poly_transformer.transform(input_df)
|
||
|
||
# Масштабирование данных
|
||
input_scaled = self.scaler.transform(input_poly)
|
||
|
||
# Предсказание цены
|
||
predicted_price = self.model.predict(input_scaled)[0]
|
||
|
||
return PredictPriceResponse(predicted_price=round(predicted_price, 2))
|
||
|
||
def get_unique_data(self):
|
||
# Указываем путь к файлу
|
||
file_path = 'services/ml/scripts/modelBuilders/columns/unique_values_laptop.json'
|
||
|
||
# Открываем и читаем данные из файла
|
||
with open(file_path, 'r', encoding='utf-8') as file:
|
||
data = json.load(file) # Загружаем данные из JSON
|
||
|
||
# Возвращаем данные, которые будут переданы в ответ
|
||
return data
|
||
|
||
|
||
class TVService:
|
||
def __init__(self, model_path: str, feature_columns_path: str, poly_path: str, scaler_path: str):
|
||
try:
|
||
self.model = joblib.load(model_path)
|
||
except FileNotFoundError:
|
||
raise Exception(f"Model file not found at {model_path}")
|
||
except Exception as e:
|
||
raise Exception(f"Error loading model: {str(e)}")
|
||
|
||
try:
|
||
self.feature_columns = joblib.load(feature_columns_path)
|
||
except FileNotFoundError:
|
||
raise Exception(f"Feature columns file not found at {feature_columns_path}")
|
||
except Exception as e:
|
||
raise Exception(f"Error loading feature columns: {str(e)}")
|
||
|
||
try:
|
||
self.poly_transformer = joblib.load(poly_path)
|
||
self.scaler = joblib.load(scaler_path)
|
||
except FileNotFoundError:
|
||
raise Exception("Polynomial transformer or scaler file not found.")
|
||
except Exception as e:
|
||
raise Exception(f"Error loading polynomial transformer or scaler: {str(e)}")
|
||
|
||
def predict_price(self, data: Dict[str, any]) -> PredictPriceResponse:
|
||
input_df = pd.DataFrame([data])
|
||
|
||
print("До One-Hot Encoding:")
|
||
print(input_df.head())
|
||
print("Колонки:", input_df.columns)
|
||
|
||
# Применение One-Hot Encoding
|
||
input_df = pd.get_dummies(input_df,
|
||
columns=['display', 'tuners', 'features', 'os', 'color', 'power_of_volume'],
|
||
drop_first=False)
|
||
|
||
# Преобразование булевых значений в числовые
|
||
input_df = input_df.astype(int)
|
||
|
||
print("После One-Hot Encoding:")
|
||
print(input_df.head())
|
||
print("Колонки:", input_df.columns)
|
||
|
||
# Добавление отсутствующих признаков
|
||
missing_columns = [col for col in self.feature_columns if col not in input_df.columns and col != 'price']
|
||
missing_df = pd.DataFrame(0, index=input_df.index, columns=missing_columns)
|
||
input_df = pd.concat([input_df, missing_df], axis=1)
|
||
|
||
# Упорядочение столбцов
|
||
input_df = input_df.reindex(columns=self.feature_columns, fill_value=0)
|
||
|
||
# Полиномиальные и масштабированные данные
|
||
input_poly = self.poly_transformer.transform(input_df)
|
||
input_scaled = self.scaler.transform(input_poly)
|
||
|
||
# Предсказание
|
||
predicted_price = self.model.predict(input_scaled)[0]
|
||
return PredictPriceResponse(predicted_price=round(predicted_price, 2))
|
||
|
||
def get_unique_data(self):
|
||
# Указываем путь к файлу
|
||
file_path = 'services/ml/scripts/modelBuilders/columns/unique_values_tv.json'
|
||
|
||
# Открываем и читаем данные из файла
|
||
with open(file_path, 'r', encoding='utf-8') as file:
|
||
data = json.load(file) # Загружаем данные из JSON
|
||
|
||
# Возвращаем данные, которые будут переданы в ответ
|
||
return data
|