183 lines
6.5 KiB
Python
183 lines
6.5 KiB
Python
|
import pandas
|
||
|
|
from flask import Flask, render_template
|
||
|
|
from matplotlib import pyplot as plt
|
||
|
|
from numpy import vectorize
|
||
|
|
from sklearn.linear_model import LinearRegression
|
||
|
|
from sklearn.metrics import mean_absolute_error, accuracy_score
|
||
|
|
from sklearn.model_selection import train_test_split
|
||
|
|
|
||
|
|
app = Flask(__name__)
|
||
|
|
|
||
|
|
|
||
|
|
@app.route("/")
|
||
|
|
def home():
|
||
|
|
return "<html>" \
|
||
|
|
"<h1>Жукова Алина ПИбд-41</h1>" \
|
||
|
|
"<h1>Лабораторная работа №5</h1>" \
|
||
|
|
"<table>" \
|
||
|
|
"<td>" \
|
||
|
|
"<form Action='http://127.0.0.1:5000/k4_1_task_5' Method=get>" \
|
||
|
|
"<input type=submit value='Регрессия'>" \
|
||
|
|
"</form>" \
|
||
|
|
"</td>" \
|
||
|
|
"</table>" \
|
||
|
|
"</html>"
|
||
|
|
|
||
|
|
# Регрессия
|
||
|
|
# 10 вариант - Линейная регрессия
|
||
|
|
@app.route("/k4_1_task_5", methods=['GET'])
|
||
|
|
def k4_1_task_5():
|
||
|
|
data = pandas.read_csv('Data_chess_games.csv')
|
||
|
|
data = data.loc[data['created_at'] - data['last_move_at'] != 0]
|
||
|
|
data = data.drop_duplicates()
|
||
|
|
data = data.sample(n=5000, replace=True, random_state=1)
|
||
|
|
|
||
|
|
# отбор нужных столбцов
|
||
|
|
corr = data[['white_rating', 'black_rating', 'moves', 'opening_eco', 'opening_name', 'winner']]
|
||
|
|
def SplitPr(stroke):
|
||
|
|
return len(stroke.split(" "))
|
||
|
|
corr['len'] = corr['moves'].apply(SplitPr)
|
||
|
|
corr = corr.loc[corr['len'] >= 10]
|
||
|
|
|
||
|
|
number_element = 0
|
||
|
|
def SelectElemToStolb(elem):
|
||
|
|
return elem.split(" ")[number_element]
|
||
|
|
|
||
|
|
def ScoreXod(elem):
|
||
|
|
if(elem == "O-O" or elem == "O-O-O"):
|
||
|
|
return 50
|
||
|
|
if(elem.__contains__("x")):
|
||
|
|
return 20
|
||
|
|
if (elem.__contains__("+")):
|
||
|
|
return 50
|
||
|
|
return 10
|
||
|
|
|
||
|
|
def EcoToScore(elem):
|
||
|
|
score_eco = 0
|
||
|
|
if(str(elem).startswith("A")):
|
||
|
|
score_eco = 100
|
||
|
|
if (str(elem).startswith("B")):
|
||
|
|
score_eco = 200
|
||
|
|
if (str(elem).startswith("C")):
|
||
|
|
score_eco = 300
|
||
|
|
if (str(elem).startswith("D")):
|
||
|
|
score_eco = 400
|
||
|
|
if (str(elem).startswith("E")):
|
||
|
|
score_eco = 500
|
||
|
|
score_eco += int(str(elem)[1:])
|
||
|
|
return score_eco
|
||
|
|
|
||
|
|
# 0 - white || 1 - black
|
||
|
|
gamer_ind = 0
|
||
|
|
def ScoreAllXods(elem):
|
||
|
|
score = 0
|
||
|
|
xods = elem.split(" ")
|
||
|
|
ind_temp = 0
|
||
|
|
for xod in xods:
|
||
|
|
if(ind_temp % 2 == gamer_ind % 2):
|
||
|
|
score += ScoreXod(xod)
|
||
|
|
ind_temp += 1
|
||
|
|
|
||
|
|
return score
|
||
|
|
|
||
|
|
corr['score_eco'] = corr['opening_eco'].apply(EcoToScore)
|
||
|
|
|
||
|
|
|
||
|
|
# Ходы
|
||
|
|
corr['w_score_all'] = corr['moves'].apply(ScoreAllXods)
|
||
|
|
gamer_ind = 1
|
||
|
|
corr['b_score_all'] = corr['moves'].apply(ScoreAllXods)
|
||
|
|
|
||
|
|
def WinnerSelect(elem):
|
||
|
|
if(elem == "white"):
|
||
|
|
return 1
|
||
|
|
if(elem == "black"):
|
||
|
|
return -1
|
||
|
|
return 0
|
||
|
|
corr['winner'] = corr['winner'].apply(WinnerSelect)
|
||
|
|
|
||
|
|
y = corr[['winner']]
|
||
|
|
|
||
|
|
# Нормирование к 1
|
||
|
|
max_zn = corr['white_rating'].max()
|
||
|
|
min_zn = corr['white_rating'].min()
|
||
|
|
def normirovanie(elem):
|
||
|
|
return ((elem - min_zn) / (max_zn - min_zn))
|
||
|
|
corr['white_rating'] = corr['white_rating'].apply(normirovanie)
|
||
|
|
|
||
|
|
max_zn = corr['black_rating'].max()
|
||
|
|
min_zn = corr['black_rating'].min()
|
||
|
|
corr['black_rating'] = corr['black_rating'].apply(normirovanie)
|
||
|
|
|
||
|
|
corr_st = corr
|
||
|
|
corr = corr[['white_rating', 'black_rating', 'b_score_all', 'w_score_all', 'score_eco']]
|
||
|
|
|
||
|
|
|
||
|
|
X_train, X_test, y_train, y_test = train_test_split(corr, y, test_size=.05, random_state=42)
|
||
|
|
|
||
|
|
linear = LinearRegression()
|
||
|
|
linear.fit(X_train, y_train)
|
||
|
|
def FunkPorog(elem):
|
||
|
|
if(elem >= 0.5):
|
||
|
|
return 1
|
||
|
|
if(elem > -0.5):
|
||
|
|
return 0
|
||
|
|
if(elem <= -0.5):
|
||
|
|
return -1
|
||
|
|
prediction = linear.predict(X_test)
|
||
|
|
n_predict_vect = vectorize(FunkPorog)
|
||
|
|
|
||
|
|
# Средняя ошибка
|
||
|
|
accuracy_mean_abs_error = mean_absolute_error(prediction, y_test)
|
||
|
|
|
||
|
|
# Предсказание исхода партии, в целых числах
|
||
|
|
predict_acc_score = n_predict_vect(prediction)
|
||
|
|
accuracy_acc_score = accuracy_score(predict_acc_score, y_test)
|
||
|
|
|
||
|
|
|
||
|
|
white_win = corr_st.loc[corr_st['winner'] == 1]
|
||
|
|
white_score = (white_win['w_score_all'])
|
||
|
|
black_score = (white_win['b_score_all'])
|
||
|
|
white_win_x = white_score - black_score + white_win['score_eco']
|
||
|
|
white_win_y = white_win['winner'] + (white_win['black_rating'] - white_win['white_rating'])
|
||
|
|
|
||
|
|
black_win = corr_st.loc[corr_st['winner'] == -1]
|
||
|
|
|
||
|
|
white_score = (black_win['w_score_all'])
|
||
|
|
black_score = (black_win['b_score_all'])
|
||
|
|
black_win_x = white_score - black_score + black_win['score_eco']
|
||
|
|
black_win_y = black_win['winner'] + (black_win['black_rating'] - black_win['white_rating'])
|
||
|
|
|
||
|
|
no_win = corr_st.loc[corr_st['winner'] == 0]
|
||
|
|
|
||
|
|
white_score = (no_win['w_score_all'])
|
||
|
|
black_score = (no_win['b_score_all'])
|
||
|
|
no_win_x = white_score - black_score + no_win['score_eco']
|
||
|
|
no_win_y = no_win['winner'] + (no_win['black_rating'] - no_win['white_rating'])
|
||
|
|
|
||
|
|
white_win = white_win[['white_rating', 'black_rating', 'b_score_all', 'w_score_all', 'score_eco']]
|
||
|
|
black_win = black_win[['white_rating', 'black_rating', 'b_score_all', 'w_score_all', 'score_eco']]
|
||
|
|
no_win = no_win[['white_rating', 'black_rating', 'b_score_all', 'w_score_all', 'score_eco']]
|
||
|
|
|
||
|
|
plt.subplot(1, 2, 1)
|
||
|
|
plt.scatter(white_win_x, (corr_st.loc[corr_st['winner'] == 1])['winner'], alpha=0.6, s=25, c='red')
|
||
|
|
plt.scatter(black_win_x, (corr_st.loc[corr_st['winner'] == -1])['winner'], alpha=0.6, s=25, c='blue')
|
||
|
|
plt.scatter(no_win_x, (corr_st.loc[corr_st['winner'] == 0])['winner'], alpha=0.6, s=25, c='green')
|
||
|
|
plt.scatter(white_win_x, white_win_y, alpha=0.2, s=25, c='pink')
|
||
|
|
plt.scatter(black_win_x, black_win_y, alpha=0.2, s=25, c='cyan')
|
||
|
|
plt.scatter(no_win_x, no_win_y, alpha=0.2, s=25, c='yellow')
|
||
|
|
|
||
|
|
plt.savefig('static\k4_1_5_regression.png')
|
||
|
|
|
||
|
|
return "<html>" \
|
||
|
|
"<h1>Регрессия</h1>" \
|
||
|
|
"<h2>Вариант 10. Задание 5 - Линейная регрессия</h2>" \
|
||
|
|
"<h2> Точность модели:</h2>" \
|
||
|
|
"<h2> Отклонение по абсолютной ошибке: " + str(accuracy_mean_abs_error) + "</h2>" \
|
||
|
|
"<h2> Отклонение по исходу партии в целых числах: " + str(accuracy_acc_score) + "</h2>" \
|
||
|
|
"<div align='center'>" + render_template(
|
||
|
|
'4_1_l6_figure1.html') + "</div>" \
|
||
|
|
"</html>"
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
app.run(debug=True)
|