Rolynominal regression + Lasso regression (다항 회귀)

 Ref. : https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.PolynomialFeatures.html

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.preprocessing import PolynomialFeatures

from sklearn.linear_model import Lasso

from sklearn.model_selection import train_test_split

from sklearn.metrics import r2_score, mean_squared_error

# Data load

df = pd.read_csv('./data/xxx.csv')

# Target data separation

y = df['y']

X = df.drop('y', axis = 1)

# Split train : test data set = 7:3 and set random seed

X_train, X_test, y_train, y_test = train_test_split(X,

                                                    y,

                                                    test_size = 0.3,

                                                    random_state = 42)

# Define a model structure for a polynomial variable

poly = PolynomialFeatures(degree = 2, include_bias = False)

# Train polynomial variable

poly.fit(X_train)

# Show feature names

poly.get_feature_names_out()

# poly.get_feature_names()

pd.options.display.max_columns = 200

# Change the data frame to the polynomial variables

poly_X_train = pd.DataFrame(poly.transform(X_train),

                            columns = poly.get_feature_names_out())

# poly_X_train = pd.DataFrame(poly.transform(X_train),

#                             columns = poly.get_feature_names())

# Change the test data to the polynomial variables

poly_X_test = poly.transform(X_test)

# Define a model structure

ls = Lasso() # To reduce some low coefficients

# Train model

ls.fit(poly_X_train, y_train)

# Model prediction

ls_pred = ls.predict(poly_X_test)

# Confirm coefficient

ls.coef_

# Error metric

print("Lasso-r2 score:", r2_score(y_test, ls_pred))

print("Lasso-RMSE:", np.sqrt(mean_squared_error(y_test, ls_pred)))

# Plot

plt.figure(figsize=(20, 20))

plt.barh(poly.get_feature_names_out(), ls.coef_)

Ridge regression

Linear least squares with l2 regularization.

Ref.: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.linear_model import Ridge

from sklearn.model_selection import train_test_split

from sklearn.metrics import r2_score, mean_squared_error

# Data load

df = pd.read_csv('./data/xxx.csv')

# Target data separation

y = df['y']

X = df.drop('y', axis = 1)

# Split train : test data set = 7:3 and set random seed

X_train, X_test, y_train, y_test = train_test_split(X,

                                                    y,

                                                    test_size = 0.3,

                                                    random_state = 42)

# Define model structure

rg = Ridge(alpha = 0.1)

# Train model

rg.fit(X_train, y_train)

# Model prediction

rg_pred = rg.predict(X_test)

# Confirm coefficient

rg.coef_

# Error metric

print("Ridge-r2 score:", r2_score(y_test, rg_pred))

print("Ridge-RMSE:", np.sqrt(mean_squared_error(y_test, rg_pred)))

# Plot

plt.bar(X_train.columns, rg.coef_)

Linear regression (기본 선형회귀 모델)

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

from sklearn.metrics import r2_score, mean_squared_error

# Data load

df = pd.read_csv('./data/xxx.csv')

# Target data separation

y = df['y']

X = df.drop('y', axis = 1)

# Split train : test data set = 7:3 and set random seed

X_train, X_test, y_train, y_test = train_test_split(X,

                                                    y,

                                                    test_size = 0.3,

                                                    random_state = 42)

# Define model structure

lr = LinearRegression()

# Train model

lr.fit(X_train, y_train)

# Model prediction

lr_pred = lr.predict(X_test)

# Confirm coefficient

lr.coef_

# Error metric

print("r2 score:", r2_score(y_test, lr_pred))

print("RMSE:", np.sqrt(mean_squared_error(y_test, lr_pred)))

# Plot

plt.scatter(lr_pred, y_test)

 

응봉근린공원 한남테니스장

 주소: 서울 용산구 다산로 8-11 외1필지