Predict for TV

2024-12-02 21:27:11 +04:00
parent c6ad3a213a
commit ee01e85053
9 changed files with 283 additions and 39 deletions
--- a/controllers/controller.py
+++ b/controllers/controller.py
@@ -1,18 +1,24 @@
 from fastapi import APIRouter, HTTPException
-from schemas.schemas import LaptopCreate, LaptopResponse, PredictPriceResponse
-from services.service import LaptopService
+from schemas.schemas import LaptopCreate, TVCreate, PredictPriceResponse
+from services.service import LaptopService, TVService
 import os

 router = APIRouter()

 # Инициализация сервиса
-MODEL_PATH = os.getenv("MODEL_PATH", "services/ml/laptop_price_model.pkl")
-FEATURE_COLUMNS_PATH = os.getenv("FEATURE_COLUMNS_PATH", "services/ml/feature_columns.pkl")
-POLY_PATH = os.getenv("POLY_PATH", "services/ml/poly_transformer.pkl")
-SCALER_PATH = os.getenv("SCALER_PATH", "services/ml/scaler.pkl")
+MODEL_PATH = os.getenv("MODEL_PATH", "services/ml/laptopML/laptop_price_model.pkl")
+FEATURE_COLUMNS_PATH = os.getenv("FEATURE_COLUMNS_PATH", "services/ml/laptopML/feature_columns.pkl")
+POLY_PATH = os.getenv("POLY_PATH", "services/ml/laptopML/poly_transformer.pkl")
+SCALER_PATH = os.getenv("SCALER_PATH", "services/ml/laptopML/scaler.pkl")
 laptop_service = LaptopService(model_path=MODEL_PATH, feature_columns_path=FEATURE_COLUMNS_PATH, poly_path=POLY_PATH, scaler_path=SCALER_PATH)

-@router.post("/predict_price/", response_model=PredictPriceResponse, summary="Predict laptop price", description="Predict the price of a laptop based on its specifications.", response_description="The predicted price of the laptop.")
+MODEL_PATH = os.getenv("MODEL_PATH", "services/ml/tvML/tv_price_model.pkl")
+FEATURE_COLUMNS_PATH = os.getenv("FEATURE_COLUMNS_PATH", "services/ml/tvML/feature_columns_tv.pkl")
+POLY_PATH = os.getenv("POLY_PATH", "services/ml/tvML/poly_transformer.pkl")
+SCALER_PATH = os.getenv("SCALER_PATH", "services/ml/tvML/scaler.pkl")
+tv_service = TVService(model_path=MODEL_PATH, feature_columns_path=FEATURE_COLUMNS_PATH, poly_path=POLY_PATH, scaler_path=SCALER_PATH)
+
+@router.post("/predict_price/laptop/", response_model=PredictPriceResponse, summary="Predict laptop price", description="Predict the price of a laptop based on its specifications.", response_description="The predicted price of the laptop.")
 def predict_price(data: LaptopCreate):
    """
    Predict the price of a laptop given its specifications.
@@ -27,3 +33,10 @@ def predict_price(data: LaptopCreate):
        return laptop_service.predict_price(data.dict())
    except Exception as e:
        raise HTTPException(status_code=400, detail=str(e))
+
+@router.post("/predict_price/tv/", response_model=PredictPriceResponse, summary="Predict TV price", description="Predict the price of a TV based on its specifications.", response_description="The predicted price of the TV.")
+def predict_price(data: TVCreate):
+    try:
+        return tv_service.predict_price(data.dict())
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=str(e))
--- a/models/models.py
+++ b/models/models.py
@@ -17,3 +17,15 @@ class Laptop(Base):
    battery_size = Column(Integer)
    release_year = Column(Integer)
    display_type = Column(String, index=True)
+
+class TV(Base):
+    __tablename__ = "tvs"
+
+    id = Column(Integer, primary_key=True, index=True)
+    display = Column(String, index=True)
+    tuners = Column(String)
+    features = Column(String)
+    os = Column(String)
+    power_of_volume = Column(String)
+    screen_sizes: int
+    color = Column(String)
--- a/schemas/schemas.py
+++ b/schemas/schemas.py
@@ -14,6 +14,15 @@ class LaptopCreate(BaseModel):
    release_year: int
    display_type: str

+class TVCreate(BaseModel):
+    display: str
+    tuners: str
+    features: str
+    os: str
+    power_of_volume: str
+    screen_sizes: int
+    color: str
+
 class LaptopResponse(BaseModel):
    id: int
    brand: str
@@ -31,5 +40,15 @@ class LaptopResponse(BaseModel):
    class Config:
        orm_mode = True

+class TVResponse(BaseModel):
+    id: int
+    display: str
+    tuners: str
+    features: str
+    os: str
+    power_of_volume: str
+    screen_sizes: int
+    color: str
+
 class PredictPriceResponse(BaseModel):
    predicted_price: float
--- a/services/ml/feature_importances.py
+++ b/services/ml/feature_importances.py
@@ -1,26 +0,0 @@
-import matplotlib.pyplot as plt
-import joblib
-import numpy as np
-
-from services.ml.modelBuilder import X_train
-
-# Загрузка модели и признаков
-model_rf = joblib.load('laptop_price_model.pkl')
-feature_columns = joblib.load('feature_columns.pkl')
-
-# Получение важности признаков
-importances = model_rf.feature_importances_
-indices = np.argsort(importances)[::-1]
-
-# Вывод наиболее важных признаков
-print("Важность признаков:")
-for f in range(X_train.shape[1]):
-    print(f"{f + 1}. {feature_columns[indices[f]]} ({importances[indices[f]]})")
-
-# Визуализация важности признаков
-plt.figure(figsize=(12, 8))
-plt.title("Важность признаков (Random Forest)")
-plt.bar(range(X_train.shape[1]), importances[indices], align='center')
-plt.xticks(range(X_train.shape[1]), [feature_columns[i] for i in indices], rotation=90)
-plt.tight_layout()
-plt.show()
--- a/services/ml/scripts/dataGenerators/generate_synthetic_data_laptop.py
+++ b/services/ml/scripts/dataGenerators/generate_synthetic_data_laptop.py
@@ -174,5 +174,5 @@ print("\nСтатистика по ценам:")
 print(synthetic_df['price'].describe())

 # Сохранение в CSV
-synthetic_df.to_csv('synthetic_laptops.csv', index=False)
+synthetic_df.to_csv('../../../../datasets/synthetic_laptops.csv', index=False)
 print("\nСинтетические данные сохранены в 'synthetic_laptops.csv'.")
--- a/services/ml/scripts/dataGenerators/generate_synthetic_data_tv.py
+++ b/services/ml/scripts/dataGenerators/generate_synthetic_data_tv.py
@@ -0,0 +1,107 @@
+import pandas as pd
+import numpy as np
+import random
+from datetime import datetime
+
+# Установка случайного зерна для воспроизводимости
+np.random.seed(42)
+random.seed(42)
+
+# Определение возможных значений для категориальных признаков
+displays = ['LED', 'OLED', 'QLED', 'LCD', 'Plasma']
+screen_sizes = [32, 40, 43, 50, 55, 65, 75, 85]  # в дюймах
+tuners = ['DVB-T2', 'DVB-C', 'DVB-S2', 'ATSC', 'ISDB-T']
+features = ['Smart TV', 'HDR', '3D', 'Voice Control', 'Bluetooth', 'WiFi', 'Ambient Mode']
+oss = ['WebOS', 'Android TV', 'Tizen', 'Roku', 'Fire TV']
+power_of_volume = ['10W', '20W', '30W', '40W', '50W']  # мощность динамиков
+colors = ['Black', 'Silver', 'White', 'Gray', 'Metallic']
+
+# Функции для генерации признаков
+def generate_display():
+    return random.choice(displays)
+
+def generate_screen_size():
+    return random.choice(screen_sizes)
+
+def generate_tuners():
+    return random.choice(tuners)
+
+def generate_features():
+    return ', '.join(random.sample(features, random.randint(1, 4)))  # случайный набор фич
+
+def generate_os():
+    return random.choice(oss)
+
+def generate_power_of_volume():
+    return random.choice(power_of_volume)
+
+def generate_color():
+    return random.choice(colors)
+
+# Функция для расчёта цены
+def calculate_price(display, screen_size, tuners, features, os, power_of_volume, color):
+    base_price = 20000  # базовая цена
+
+    # Тип дисплея
+    display_premium = {'LED': 0, 'OLED': 40000, 'QLED': 30000, 'LCD': 10000, 'Plasma': 15000}
+    base_price += display_premium.get(display, 0)
+
+    # Размер экрана
+    base_price += (screen_size - 32) * 1000
+
+    # Функции
+    base_price += len(features.split(', ')) * 5000
+
+    # ОС
+    os_premium = {'WebOS': 10000, 'Android TV': 15000, 'Tizen': 12000, 'Roku': 8000, 'Fire TV': 7000}
+    base_price += os_premium.get(os, 5000)
+
+    # Мощность звука
+    power_value = int(power_of_volume.rstrip('W'))
+    base_price += power_value * 500
+
+
+    # Добавление случайного шума
+    noise = np.random.normal(0, 3000)
+    final_price = base_price + noise
+
+    return max(round(final_price, 2), 5000)
+
+# Функция для генерации синтетических данных
+def generate_synthetic_data(num_samples=100000):
+    data = []
+    for _ in range(num_samples):
+        display= generate_display()
+        screen_size = generate_screen_size()
+        tuners = generate_tuners()
+        features = generate_features()
+        os = generate_os()
+        power_of_volume = generate_power_of_volume()
+        color = generate_color()
+
+        price = calculate_price(
+            display, screen_size, tuners, features, os, power_of_volume, color
+        )
+
+        data.append({
+            'display': display,
+            'screen_size': screen_size,
+            'tuners': tuners,
+            'features': features,
+            'os': os,
+            'power_of_volume': power_of_volume,
+            'color': color,
+            'price': price
+        })
+    return pd.DataFrame(data)
+
+print("Генерация синтетических данных для телевизоров...")
+synthetic_df = generate_synthetic_data(num_samples=100000)
+
+# Просмотр первых строк
+print("\nПример данных после генерации:")
+print(synthetic_df.head())
+
+# Сохранение в CSV
+synthetic_df.to_csv('../../../../datasets/synthetic_tvs.csv', index=False)
+print("\nСинтетические данные сохранены в 'synthetic_tvs.csv'.")
--- a/services/ml/scripts/modelBuilders/modelBuilderLaptop.py
+++ b/services/ml/scripts/modelBuilders/modelBuilderLaptop.py
@@ -8,7 +8,7 @@ import joblib
 import numpy as np

 # Шаг 1: Загрузка данных
-df = pd.read_csv('../../datasets/synthetic_laptops.csv')
+df = pd.read_csv('../../../../datasets/synthetic_laptops.csv')

 # Шаг 2: Проверка и очистка имен столбцов
 df.columns = df.columns.str.strip().str.lower()
@@ -84,10 +84,10 @@ print(f"Random Forest - MAE: {mae}, RMSE: {rmse}, R²: {r2}")

 # Шаг 13: Сохранение модели
 feature_columns = X.columns.tolist()
-joblib.dump(feature_columns, 'feature_columns.pkl')
-joblib.dump(best_model, 'laptop_price_model.pkl')
-joblib.dump(poly, 'poly_transformer.pkl')
-joblib.dump(scaler, 'scaler.pkl')
+joblib.dump(feature_columns, '../../laptopML/feature_columns.pkl')
+joblib.dump(best_model, '../../laptopML/laptop_price_model.pkl')
+joblib.dump(poly, '../../laptopML/poly_transformer.pkl')
+joblib.dump(scaler, '../../laptopML/scaler.pkl')
 print("Модель, трансформер и скейлер сохранены.")

 # Шаг 14: Важность признаков
--- a/services/ml/scripts/modelBuilders/modelBuilderTV.py
+++ b/services/ml/scripts/modelBuilders/modelBuilderTV.py
@@ -0,0 +1,73 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
+from sklearn.preprocessing import PolynomialFeatures, StandardScaler
+import matplotlib.pyplot as plt
+import joblib
+import numpy as np
+
+# Загрузка данных
+df = pd.read_csv('../../../../datasets/synthetic_tvs.csv')
+
+# Проверка и очистка данных
+required_columns = ['display', 'tuners', 'features', 'os', 'power_of_volume', 'color', 'screen_size', 'price']
+missing_columns = [col for col in required_columns if col not in df.columns]
+if missing_columns:
+    raise Exception(f"Отсутствуют столбцы: {missing_columns}")
+
+df = df.dropna(subset=required_columns)
+
+# Преобразование категориальных переменных
+categorical_features = ['display', 'tuners', 'features', 'os', 'power_of_volume','color']
+df = pd.get_dummies(df, columns=categorical_features, drop_first=True)
+
+# Разделение на X и y
+X = df.drop('price', axis=1)
+y = df['price']
+
+# Полиномиальные признаки
+poly = PolynomialFeatures(degree=1, interaction_only=True, include_bias=False)
+X_poly = poly.fit_transform(X)
+
+# Масштабирование
+scaler = StandardScaler()
+X_poly_scaled = scaler.fit_transform(X_poly)
+
+# Разделение на обучающую и тестовую выборки
+X_train, X_test, y_train, y_test = train_test_split(X_poly_scaled, y, test_size=0.5, random_state=42)
+
+# Настройка Random Forest
+param_grid = {
+    'n_estimators': [100, 200],
+    'max_depth': [10, 20],
+    'max_features': ['sqrt', 'log2', 0.5],
+    'min_samples_split': [5, 10],
+    'min_samples_leaf': [2, 4]
+}
+
+grid_search = GridSearchCV(RandomForestRegressor(random_state=42), param_grid, cv=3, scoring='neg_mean_absolute_error')
+grid_search.fit(X_train, y_train)
+best_model = grid_search.best_estimator_
+
+# Вывод важности признаков
+feature_importances = best_model.feature_importances_
+feature_names = poly.get_feature_names_out(X.columns)
+
+# Построение графика важности признаков
+sorted_indices = np.argsort(feature_importances)[::-1]
+plt.figure(figsize=(10, 8))
+plt.barh([feature_names[i] for i in sorted_indices[:20]], feature_importances[sorted_indices[:20]])
+plt.xlabel('Importance')
+plt.ylabel('Feature')
+plt.title('Top 20 Feature Importances')
+plt.gca().invert_yaxis()
+plt.show()
+
+# Сохранение модели
+feature_columns = X.columns.tolist()
+joblib.dump(feature_columns, '../../tvML/feature_columns.pkl')
+joblib.dump(best_model, '../../tvML/tv_price_model.pkl')
+joblib.dump(poly, '../../tvML/poly_transformer.pkl')
+joblib.dump(scaler, '../../tvML/scaler.pkl')
+print("Модель для телевизоров сохранена.")
--- a/services/service.py
+++ b/services/service.py
@@ -52,3 +52,49 @@ class LaptopService:
        predicted_price = self.model.predict(input_scaled)[0]

        return PredictPriceResponse(predicted_price=round(predicted_price, 2))
+
+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])
+
+        # Применение One-Hot Encoding
+        input_df = pd.get_dummies(input_df, columns=['display', 'tuners', 'features', 'os', 'color'], drop_first=True)
+
+        # Добавление отсутствующих признаков
+        for col in self.feature_columns:
+            if col not in input_df.columns and col != 'price':
+                input_df[col] = 0
+
+        input_df = input_df[self.feature_columns]
+
+        # 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))
+