import pandas as pd
from numpy import *
import numpy as np
from sklearn.neural_network import MLPClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import learning_curve
from sklearn.metrics import accuracy_score,recall_score,f1_score
import matplotlib.pyplot as plt
from sklearn.metrics import mean_absolute_error
from sklearn import svm
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.utils.np_utils import to_categorical
from random import sample
import csv
from sklearn.metrics import mean_squared_error
from sklearn.metrics import median_absolute_error
from tensorflow import keras
from sklearn.metrics import classification_report
from sklearn.metrics import precision_recall_curve, average_precision_score
from sklearn.model_selection import ShuffleSplit
from sklearn.linear_model import Lasso
from sklearn.metrics import confusion_matrix
from sklearn.metrics import mean_squared_error
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import cross_val_score
from keras.layers import Embedding
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")
df = pd.read_csv('tr_data_after2.csv',encoding="utf_8_sig")
home_team = df["home_team"]
away_team = df["away_team"]
home_times = df["home_times"]
away_times = df["away_times"]
home_win = df["home_win"]
away_win = df["away_win"]
home_goals = df["home_goals"]
away_goals = df["away_goals"]
home_r_win = df["home_r_win"]
away_r_win = df["away_r_win"]
home_Ave_goal = df["home_Ave_goal"]
away_Ave_goal = df["away_Ave_goal"]
result = df["result"]
team_merge = pd.concat([home_team,away_team,home_times,away_times,home_win,away_win,home_goals,away_goals,home_r_win,away_r_win,home_Ave_goal,away_Ave_goal,result], axis=1).drop(['home_team','away_team'],axis=1)
# Min-Max处理
play_score_temp = team_merge.iloc[:, :-1]
# play_score_normal = (play_score_temp - play_score_temp.min()) / (play_score_temp.max() - play_score_temp.min())
# 标准分数处理
play_score_normal = (play_score_temp - play_score_temp.mean()) / (play_score_temp.std())
play_score_normal = pd.concat([play_score_normal, team_merge.iloc[:, -1]], axis=1)
# print(play_score_normal)
# 获取csv数据的长度（条数）
with open('tr_data_after2.csv', 'r',encoding="utf_8_sig") as f:
line=len(f.readlines())
tr_index=sample(range(0,line-1),int(line*0.7))
te_index=[i for i in range(0,line-1) if i not in tr_index]
tr_x = play_score_normal.iloc[tr_index, :-1] # 训练特征
tr_y = play_score_normal.iloc[tr_index, -1] # 训练目标
te_x = play_score_normal.iloc[te_index, :-1] # 测试特征
te_y = play_score_normal.iloc[te_index, -1] # 测试目标
df2 = pd.read_csv('data.csv',encoding="utf_8_sig")
country = df2["country"]
times = df2["times"]
win = df2["win"]
goals = df2["goals"]
rate = df2["rate of winning"]
Average = df2["Average goal"]
frames=[country,times,win,goals,rate,Average]
country_all = pd.concat(frames, axis=1).dropna(axis=0, how='any', thresh=None, subset=None, inplace=False)
num_data = country_all.iloc[:,[1,2,3,4,5]]
# 测试对象Min-Max处理
# country_all_MM = (num_data - num_data.min()) / (num_data.max() - num_data.min())
# 标准分数标准化
country_all_MM = (num_data - num_data.mean()) / (num_data.std())
country_all_MM = pd.concat([country, country_all_MM], axis=1)
# country_all_MM.to_csv("tr_data_z.csv",encoding="utf_8_sig")
play_score_normal.reset_index(drop = True)
play_score_normal.to_csv("play_score_normal.csv",encoding="utf_8_sig")
model=MLPClassifier(hidden_layer_sizes=10,max_iter=1000).fit(tr_x,tr_y)
print("神经网络:")
print("训练集准确度:{:.3f}".format(model.score(tr_x,tr_y)))
print("测试集准确度:{:.3f}".format(model.score(te_x,te_y)))
y_pred = model.predict(te_x)
print("平均绝对误差:",mean_absolute_error(te_y, y_pred))
# 准确率，召回率，F-score评价
print("ACC",accuracy_score(te_y,y_pred))
print("REC",recall_score(te_y,y_pred,average="micro"))
print("F-score",f1_score(te_y,y_pred,average="micro"))
print("逻辑回归:")
logreg = LogisticRegression(C=1,solver='liblinear',multi_class ='auto')
logreg.fit(tr_x, tr_y)
score = logreg.score(tr_x, tr_y)
score2 = logreg.score(te_x, te_y)
print("训练集准确度:{:.3f}".format(logreg.score(tr_x,tr_y)))
print("测试集准确度:{:.3f}".format(logreg.score(te_x,te_y)))
y_pred = logreg.predict(te_x)
print("平均绝对误差:",mean_absolute_error(te_y, y_pred))
print("ACC",accuracy_score(te_y,y_pred))
print("REC",recall_score(te_y,y_pred,average="micro"))
print("F-score",f1_score(te_y,y_pred,average="micro"))
print("决策树:")
tree=DecisionTreeClassifier(max_depth=50,random_state=0)
tree.fit(tr_x,tr_y)
y_pred = tree.predict(te_x)
print("训练集准确度:{:.3f}".format(tree.score(tr_x,tr_y)))
print("测试集准确度:{:.3f}".format(tree.score(te_x,te_y)))
print("平均绝对误差:",mean_absolute_error(te_y, y_pred))
print("ACC",accuracy_score(te_y,y_pred))
print("REC",recall_score(te_y,y_pred,average="micro"))
print("F-score",f1_score(te_y,y_pred,average="micro"))
print("随机森林:")
rf=RandomForestClassifier(max_depth=20,n_estimators=1000,random_state=0)
rf.fit(tr_x,tr_y)
print("训练集准确度:{:.3f}".format(rf.score(tr_x,tr_y)))
print("测试集准确度:{:.3f}".format(rf.score(te_x,te_y)))
y_pred = rf.predict(te_x)
print("平均绝对误差:",mean_absolute_error(te_y, y_pred))
print("ACC",accuracy_score(te_y,y_pred))
print("REC",recall_score(te_y,y_pred,average="micro"))
print("F-score",f1_score(te_y,y_pred,average="micro"))
print("SVM支持向量机:")
clf = svm.SVC(C=0.1, kernel='linear', decision_function_shape='ovr')
clf.fit(tr_x, tr_y.ravel())
y_pred = clf.predict(te_x)
print("训练集准确度:{:.3f}".format(clf.score(tr_x,tr_y)))
print("测试集准确度:{:.3f}".format(clf.score(te_x,te_y)))
print("平均绝对误差:",mean_absolute_error(te_y, y_pred))
print("ACC",accuracy_score(te_y,y_pred))
print("REC",recall_score(te_y,y_pred,average="micro"))
print("F-score",f1_score(te_y,y_pred,average="micro"))
# 学习曲线函数
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
plt.figure()
plt.title(title)
if ylim is not None:
plt.ylim(*ylim)
plt.xlabel("game num")
plt.ylabel("score")
train_sizes, train_scores, test_scores = learning_curve(
estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
train_scores_mean = np.mean(train_scores, axis=1)
train_scores_std = np.std(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
test_scores_std = np.std(test_scores, axis=1)
plt.grid()
plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
train_scores_mean + train_scores_std, alpha=0.1,
color="r")
plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
test_scores_mean + test_scores_std, alpha=0.1, color="g")
plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
label="Training score")
plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
label="Cross-validation score")
plt.legend(loc="best")
return plt
cv = ShuffleSplit(n_splits=line, test_size=0.2, random_state=0)
plot_learning_curve(logreg, "logreg", tr_x, tr_y, ylim=None, cv=cv, n_jobs=1)
plot_learning_curve(tree, "tree", tr_x, tr_y, ylim=None, cv=None, n_jobs=1)
plot_learning_curve(rf, "rf", tr_x, tr_y, ylim=None, cv=None, n_jobs=1)
plot_learning_curve(model, "model", tr_x, tr_y, ylim=None, cv=None, n_jobs=1)
plot_learni
源代码+csv.zip （28个子文件） 
源代码+csv 
2res.csv 59B fifa_ch.csv 28KB competition.py 461B tr_data_M.csv 8KB 2018.csv 2KB progress.csv 189B tr_data_eng.csv 77KB data_eng.csv 3KB tr_data_date.csv 81KB tr_data_after2.csv 57KB results.csv 2.82MB 16res.csv 254B tr_data.csv 72KB data.csv 4KB data.py 2KB tr_data_z.csv 9KB sjwl.py 16KB 8res.csv 149B fifa.csv 26KB 4res.csv 92B NO16.csv 205B soup.py 2KB group.py 1KB fifa.py 858B res.csv 3KB country.csv 1KB tr_data_after.csv 95KB play_score_normal.csv 139KB资源评论
