X_train, X_test, Y_train, Y_test = pp.split_train_test(x_ary=X,
y_ary=Y,
train_size=0.8)
# Feature Scaling
#X = pp.feature_scaling(fit_ary=X, transform_arys=(X))
#Y = pp.feature_scaling(fit_ary=Y, transform_arys=(Y))
# In[] Linear Regression as comparison
from HappyML.regression import SimpleRegressor
import HappyML.model_drawer as md
reg_simple = SimpleRegressor()
Y_simple = reg_simple.fit(x_train=X, y_train=Y).predict(x_test=X)
md.sample_model(sample_data=(X, Y), model_data=(X, Y_simple))
print("R-Squared of Simple Regression:", reg_simple.r_score(x_test=X,
y_test=Y))
# In[] Polynomial Regression
#from sklearn.preprocessing import PolynomialFeatures
#from HappyML.performance import rmse
#import pandas as pd
#
#deg=5
#poly_reg = PolynomialFeatures(degree=deg)
#X_poly = pd.DataFrame(poly_reg.fit_transform(X))
#
#regressor = SimpleRegressor()
#regressor.fit(X_poly, Y)
#Y_predict = regressor.predict(x_test=X_poly)
# In[] Visualize the Training Set
#import matplotlib.pyplot as plt
#
#plt.scatter(X_train, Y_train, color="red")
#plt.plot(X_train, regressor.predict(X_train), color="blue")
#plt.title("Salary vs. Experience")
#plt.xlabel("Experience")
#plt.ylabel("Salary")
#plt.show()
from HappyML import model_drawer as md
sample_data = (X_train, Y_train)
model_data = (X_train, regressor.predict(X_train))
md.sample_model(sample_data=sample_data,
model_data=model_data,
title="訓練集樣本點 vs. 預測模型",
font="DFKai-sb")
md.sample_model(sample_data=(X_test, Y_test),
model_data=(X_test, Y_pred),
title="測試集樣本點 vs. 預測模型",
font="DFKai-sb")
# In[] Test for Linearity of Features
#from HappyML import model_drawer as md
#
#for i in range(X_train.shape[1]):
# md.sample_model(sample_data=(X_train[:, i], Y_train), model_data=None, title="Linearity of Column {}".format(i))
from HappyML.criteria import AssumptionChecker
checker = AssumptionChecker(X_train, X_test, Y_train, Y_test, Y_pred)
regressor[1][0].fit(X_w_train, Y_w_train.iloc[:, 0].to_frame())
regressor[1][1].fit(X_w_train, Y_w_train.iloc[:, 1].to_frame())
print("台灣 6~15 歲學童身高、體重評估系統\n")
gender = eval(input("請輸入您的性別（1.男 2.女）：")) - 1
age = eval(input("請輸入您的年齡（6-15）："))
height = eval(input("請輸入您的身高（cm）："))
weight = eval(input("請輸入您的體重（kg）："))
h_avg = regressor[0][gender].predict(x_test=pd.DataFrame([[age]])).iloc[0, 0]
w_avg = regressor[1][gender].predict(x_test=pd.DataFrame([[age]])).iloc[0, 0]
model_data_h = (X_h_train, regressor[0][gender].predict(X_h_train))
md.sample_model(sample_data=(age, height),
model_data=model_data_h,
title="身高落點分布",
xlabel="年齡",
ylabel="身高",
font="Microsoft JhengHei")
if gender == 0:
print(age, "歲男生平均身高為", "{:.2f}".format(h_avg), "公分，您的身高為", height, "公分")
elif gender == 1:
print(age, "歲女生平均身高為", "{:.2f}".format(h_avg), "公分，您的身高為", height, "公分")
model_data_w = (X_w_train, regressor[1][gender].predict(X_w_train))
md.sample_model(sample_data=(age, weight),
model_data=model_data_w,
title="體重落點分布",
xlabel="年齡",
ylabel="體重",
font="Microsoft JhengHei")
if gender == 0:
import HappyML.preprocessor as pp
dataset = pp.dataset("C:/Users/henry/Desktop/Python Training/Python機器學習/範例原始碼＆「快樂版」函式庫/Ch05 Regression/Position_Salaries.csv")
X, Y = pp.decomposition(dataset, x_columns=[1], y_columns=[2])
X_train, X_test, Y_train, Y_test = pp.split_train_test(x_ary=X, y_ary=Y, train_size=0.8)
# In[]
from HappyML.regression import SimpleRegressor
import HappyML.model_drawer as md
reg_simple = SimpleRegressor()
Y_simple = reg_simple.fit(x_train=X, y_train=Y).predict(X)
md.sample_model(sample_data=(X, Y), model_data=(X, Y_simple))
print("R-Squared of Simple Regression:", reg_simple.r_score(x_test=X, y_test=Y))
# In[]
from sklearn.preprocessing import PolynomialFeatures
deg = 12
poly_reg = PolynomialFeatures(degree=deg)
X_poly = poly_reg.fit_transform(X)
# In[]
import pandas as pd
regressor = SimpleRegressor()
regressor.fit(X_poly, Y)
Y_predict = regressor.predict(x_test=pd.DataFrame(X_poly))