导入库
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import sklearn
from sklearn import preprocessing
import seaborn as sns
%matplotlib inline
读取数据
df =pd.read_csv('./EngineeredData_2.csv')
df =df.dropna()
将数据拆分为x和y:
X= df.drop (['Week','Div', 'Date', 'HomeTeam', 'AwayTeam','HTHG', 'HTAG','HTR',
'FTAG', 'FTHG','HGKPP', 'AGKPP', 'FTR'], axis =1)
将y转换为整数:
L = preprocessing.LabelEncoder ()
matchresults = L.fit_transform (list (df['FTR']))
y =list(matchresults)
将数据拆分为训练并进行测试:
from sklearn.model_selection import train_test_split
X_tng,X_tst, y_tng, y_tst =train_test_split (X, y, test_size = 50, shuffle=False)
X_tng.head()
导入类
from sklearn.linear_model import LogisticRegression
实例化模型
logreg = LogisticRegression ()
使模型与数据匹配
logreg.fit (X_tng, y_tng)
预测测试数据y_pred = logreg.predict(X_tst)
acc = logreg. score (X_tst, y_tst)
print (acc)
准确度达到100%是否有意义?
X= df.drop('FTR', axis =1)