Python-сообщество

 import pandas as pd
from sklearn.neighbors import KNeighborsRegressor
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.svm import SVR
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_error, mean_squared_error, median_absolute_error, r2_score
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
#Обучение Полиноминальной регрессии
def learnPolynomialFeatures (dataset, X_,Y_):
    X = dataset[X_].values
    y = dataset[Y_].values
    regr = LinearRegression()
    # create quadratic features
    quadratic = PolynomialFeatures(degree=2)
    cubic = PolynomialFeatures(degree=3)
    X_quad = quadratic.fit_transform(X)
    X_cubic = cubic.fit_transform(X)
    # fit features
    X_fit = np.arange(X.min(), X.max(), 1)[:, np.newaxis]
    regr = regr.fit(X, y)
    y_lin_fit = regr.predict(X_fit)
    linear_r2 = r2_score(y, regr.predict(X))
    regr = regr.fit(X_quad, y)
    y_quad_fit = regr.predict(quadratic.fit_transform(X_fit))
    quadratic_r2 = r2_score(y, regr.predict(X_quad))
    regr = regr.fit(X_cubic, y)
    y_cubic_fit = regr.predict(cubic.fit_transform(X_fit))
    cubic_r2 = r2_score(y, regr.predict(X_cubic))
    
    return X, X_fit, y_lin_fit, linear_r2, y_quad_fit, quadratic_r2, y_cubic_fit, cubic_r2, y
# plot results Polynom Regression
def PlotPolynomRelationPredict (X, X_fit, y_lin_fit, linear_r2, y_quad_fit, quadratic_r2, y_cubic_fit, cubic_r2, y):
    
    plt.scatter(X, y, label='training points', color='lightgray')
    plt.plot(X_fit, y_lin_fit, 
             label='linear (d=1), $R^2={:.2f}$'.format(linear_r2), 
             color='blue', 
             lw=2, 
             linestyle=':')
    plt.plot(X_fit, y_quad_fit, 
             label='quadratic (d=2), $R^2={:.2f}$'.format(quadratic_r2),
             color='red', 
             lw=2,
             linestyle='-')
    plt.plot(X_fit, y_cubic_fit, 
             label='cubic (d=3), $R^2={:.2f}$'.format(cubic_r2),
             color='green', 
             lw=2, 
             linestyle='--')
    plt.xlabel('% lower status of the population [LSTAT]')
    plt.ylabel('Price in $1000\'s [MEDV]')
    plt.legend(loc='upper right')
dataset = pd.read_csv('J:/Exemple_Regression/ENB2012_data.csv', sep=',')
X = dataset[['X1','X2','X3','X4','X5','X6','X7','X8']].values
y = dataset['Y1'].values
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=0)
#Обучение Полиноминальной регрессии
X, X_fit, y_lin_fit, linear_r2, y_quad_fit, quadratic_r2, y_cubic_fit, cubic_r2, y=learnPolynomialFeatures (dataset, ['X1','X2','X3','X4','X5','X6','X7','X8'],'Y1')
PlotPolynomRelationPredict (X, X_fit, y_lin_fit, linear_r2, y_quad_fit, quadratic_r2, y_cubic_fit, cubic_r2, y)

 X_fit = np.arange(X.min(), X.max(), 1)[:, np.newaxis]

 X_fit = np.arange(X.min(), X.max(), 1)[:, np.newaxis]

 X = dataset[['X1','X2','X3','X4','X5','X6','X7','X8']].values
y = dataset['Y1'].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
X, X_fit, y_lin_fit, linear_r2, y_quad_fit, quadratic_r2, y_cubic_fit, cubic_r2, y=learnPolynomialFeatures (X_train, y_train,X_test,y_test)

 #Обучение Полиноминальной регрессии
def learnPolynomialFeatures (X_train, y_train,X_test,y_test):
    regr = LinearRegression()
    # create quadratic features
    quadratic = PolynomialFeatures(degree=2)
    cubic = PolynomialFeatures(degree=3)
    X_quad = quadratic.fit_transform(X_train)
    X_cubic = cubic.fit_transform(X_train)
    # fit features
    #X_fit = np.arange(X.min(), X.max(), 1)[:, np.newaxis]
    regr = regr.fit(X_train, y_train)
    y_lin_fit = regr.predict(X_test)
    linear_r2 = r2_score(y_train, regr.predict(X_train))
    regr = regr.fit(X_quad, y_train)
    y_quad_fit = regr.predict(quadratic.fit_transform(X_test))
    quadratic_r2 = r2_score(y_train, regr.predict(X_quad))
    regr = regr.fit(X_cubic, y_train)
    y_cubic_fit = regr.predict(cubic.fit_transform(X_test))
    cubic_r2 = r2_score(y_train, regr.predict(X_cubic))
    
    return X_train, X_test, y_lin_fit, linear_r2, y_quad_fit, quadratic_r2, y_cubic_fit, cubic_r2, y_train
X = dataset[['X1','X2','X3','X4','X5','X6','X7','X8']].values
y = dataset['Y1'].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
X, X_fit, y_lin_fit, linear_r2, y_quad_fit, quadratic_r2, y_cubic_fit, cubic_r2, y=learnPolynomialFeatures (X_train, y_train,X_test,y_test)

 return X_train, X_test, y_lin_fit, linear_r2, y_quad_fit, quadratic_r2, y_cubic_fit, cubic_r2, y_train

 X = dataset[['X1','X2','X3','X4','X5','X6','X7','X8']].values

 #Обучение модели
def TrainingLineModel (X_train, y_train):
    model_line =LinearRegression()
    model_line.fit(X_train, y_train)
    linear_r2 = r2_score(y_train, model_line.predict(X_train))
    return model_line, linear_r2
#Обучение Полиноминальной регрессии
def TrainingPolynomialRegression (X_train, y_train, degree_):
    
    regr=LinearRegression()
    # create features
    func_degree = PolynomialFeatures(degree=degree_)
    model_regr_fit = regr.fit(func_degree.fit_transform(X_train), y_train)
    degree_r2 = r2_score(y_train, PredictionModel(model_regr_fit, X_train, degree_))
    
    return model_regr_fit, degree_r2
#Предсказание модели
def PredictionModel(model_fit, X_try, degree_):
    
    if degree_>1:
      func_degree = PolynomialFeatures(degree=degree_)  
      y_degree_fit = model_fit.predict(func_degree.fit_transform(X_try))
      return y_degree_fit
    else:
        y_line_fit = model_fit.predict(X_try)
        return y_line_fit
dataset = pd.read_csv('F:Exemple_Regression/ENB2012_data.csv', sep=',')
#Разбивка данных на обучающие и тестовые
X = dataset[['X1','X2','X3','X4','X5','X6','X7','X8']].values
y = dataset['Y1'].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
#Обучение линейной модели
model_line, linear_r2=TrainingLineModel (X_train, y_train)
#Обучение полиноминальных моделей
model_quad, quad_r2=TrainingPolynomialRegression (X_train, y_train, 2)
model_cubic, cubic_r2=TrainingPolynomialRegression (X_train, y_train, 3)
#Предсказание моделей
y_line_predict = PredictionModel(model_line, X_test, 1)
y_quad_predict = PredictionModel(model_quad, X_test, 2)
y_cubic_predict = PredictionModel(model_cubic, X_test, 3)
PlotPolynomRelationPredict (X, X_test, y_line_predict, linear_r2, y_quad_predict, quad_r2, y_cubic_predict, cubic_r2, y)

  X = dataset[0:7].values 

 regr=LinearRegression()

 'X1':'X8'