EvaluationEfficiencyOptimizationWind/davisAPI/prediction.py

import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sqlalchemy import create_engine


def run_prediction_module():
    engine = create_engine('mysql+pymysql://wind:wind@193.124.203.110:3306/wind_towers')

    query = """
    SELECT BarTrend, CRC, DateStamp, DewPoint, HeatIndex, ETDay, HumIn, HumOut,
           Pressure, RainDay, RainMonth, RainRate, RainStorm, RainYear,
           TempIn, TempOut, WindDir, WindSpeed, WindSpeed10Min
    FROM weather_data
    WHERE DateStamp >= '2024-10-14 21:00:00' - INTERVAL 36 HOUR;
    """
    df = pd.read_sql(query, engine)

    df['DateStamp'] = pd.to_datetime(df['DateStamp'])
    df.set_index('DateStamp', inplace=True)
    df.sort_index(inplace=True)

    lags = 3
    shifted_dfs = [df]

    for lag in range(1, lags + 1):
        shifted_df = df.shift(lag).add_suffix(f'_t-{lag}')
        shifted_dfs.append(shifted_df)

    df_with_lags = pd.concat(shifted_dfs, axis=1)

    df_with_lags.dropna(inplace=True)
    df_with_lags = df_with_lags.copy()

    # Преобразуем BarTrend в числовой формат
    le = LabelEncoder()
    df_with_lags['BarTrend_encoded'] = le.fit_transform(df_with_lags['BarTrend'])

    # Выбор только числовых данных
    df_with_lags = df_with_lags.select_dtypes(include=['float64', 'int64'])

    # Словари для хранения моделей и MSE
    models = {}
    mse_scores = {}

    # Обучение моделей для каждого целевого столбца
    for target_column in df.columns:
        if target_column not in df_with_lags.columns:
            continue

        X = df_with_lags.drop(columns=[target_column]).values
        y = df_with_lags[target_column].values

        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, shuffle=False)

        model = RandomForestRegressor()
        model.fit(X_train, y_train)

        y_pred = model.predict(X_test)
        mse = mean_squared_error(y_test, y_pred)
        mse_scores[target_column] = mse
        models[target_column] = model

        quality = "хорошая" if mse < 1.0 else "плохая"
        print(f"MSE для {target_column}: {mse} ({quality})")

    # Обучаем модель для BarTrend_encoded отдельно
    X_bartrend = df_with_lags.drop(columns=['BarTrend_encoded']).values
    y_bartrend = df_with_lags['BarTrend_encoded'].values

    X_train_bartrend, X_test_bartrend, y_train_bartrend, y_test_bartrend = train_test_split(X_bartrend, y_bartrend,
                                                                                            test_size=0.2,
                                                                                            shuffle=False)

    model_bartrend = RandomForestRegressor()
    model_bartrend.fit(X_train_bartrend, y_train_bartrend)

    y_pred_bartrend = model_bartrend.predict(X_test_bartrend)
    mse_bartrend = mean_squared_error(y_test_bartrend, y_pred_bartrend)
    models['BarTrend_encoded'] = model_bartrend
    mse_scores['BarTrend_encoded'] = mse_bartrend

    quality_bartrend = "хорошая" if mse_bartrend < 1.0 else "плохая"
    print(f"MSE для BarTrend: {mse_bartrend} ({quality_bartrend})")

    last_data = X[-1].reshape(1, -1)

    predictions = {}
    for target_column, model in models.items():
        prediction = model.predict(last_data)[0]
        if target_column == 'BarTrend_encoded':
            prediction = le.inverse_transform([int(prediction)])[0]
            predictions['BarTrend'] = prediction
            print(f"Предсказание для BarTrend: {prediction}")
            break
        predictions[target_column] = prediction
        print(f"Предсказание для {target_column}: {prediction}")

    return predictions  # Возвращаем словарь с предсказанными значениями и названиями столбцов