import numpy as np
import pandas as pd
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.model_selection import train_test_split
import statsmodels.formula.api as sm
from sklearn.linear_model import LinearRegression
dataset = pd.read_csv('COM.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 4].values
print("自变量")
print(X)
print("...")
print("因变量")
print(y)
print("...")
labelencoder_X = LabelEncoder()
X[:, 3] = labelencoder_X.fit_transform(X[:, 3])
onehotencoder = OneHotEncoder(categorical_features = [3])
X = onehotencoder.fit_transform(X).toarray()
float_formatter= lambda X:"%.2f" % X
np.set_printoptions(formatter={'float_kind':float_formatter})
print("转换后的X")
print(X)
print("...")
X = X[:, 1:] #删除某一列 就是删除了第0列
print(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
print("/X_train/X_test/y_train/y_test")
regressor = LinearRegression()
regressor.fit(X_train, y_train)
y_pred = regressor.predict(X_test)
print("包含了的预测结果的向量")
print(y_pred)
X_train = np.append(arr = np.ones((40, 1)).astype(int), values = X_train, axis = 1)
Ximo = X_train
regressor_OLS = sm.OLS(endog = y_train, exog = Ximo).fit()
print("第一次的summary")
print(regressor_OLS.summary())
Ximo = X_train [:, [0, 1, 3, 4, 5]]
regressor_OLS = sm.OLS(endog = y_train, exog = Ximo).fit()
print("第二次的summary")
print(regressor_OLS.summary())
Ximo = X_train [:, [0, 3, 4, 5]]
regressor_OLS = sm.OLS(endog = y_train, exog = Ximo).fit()
print("第三次的summary")
print(regressor_OLS.summary())
Ximo = X_train [:, [0, 3, 5]]
regressor_OLS = sm.OLS(endog = y_train, exog = Ximo).fit()
print("第四次的summary")
print(regressor_OLS.summary())
Ximo = X_train [:, [0, 3]]
regressor_OLS = sm.OLS(endog = y_train, exog = Ximo).fit()
print("第五次的summary")
print(regressor_OLS.summary())
