from turtle import pd
import numpy as np
df = pd.read_csv('voice.csv')
def linearRegression(homeTeam, awayTeam):
import pandas as pd
from sklearn.tree import DecisionTreeRegressor
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
from math import sqrt
try:
if ('Man United' in homeTeam):
dataset = 'dataset/ManUHome.csv'
elif ('Fulham' in homeTeam):
dataset = 'dataset/FulhamHome.csv'
elif ('Newcastle' in homeTeam):
dataset = 'dataset/NewcastleHome.csv'
elif ('Man City' in homeTeam):
dataset = 'dataset/ManCHome.csv'
elif ('Wolves' in homeTeam):
dataset = 'dataset/WolvesHome.csv'
elif ('Liverpool' in homeTeam):
dataset = 'dataset/LiverpoolHome.csv'
elif ('Southampton' in homeTeam):
dataset = 'dataset/SouthamptonHome.csv'
elif ('Arsenal' in homeTeam):
dataset = 'dataset/ArsenalHome.csv'
elif ('Burnley' in homeTeam):
dataset = 'dataset/BurnleyHome.csv'
elif ('Everton' in homeTeam):
dataset = 'dataset/EvertonHome.csv'
elif ('Leicester' in homeTeam):
dataset = 'dataset/LeicesterHome.csv'
elif ('Tottenham' in homeTeam):
dataset = 'dataset/TottenhamHome.csv'
elif ('West Ham' in homeTeam):
dataset = 'dataset/WestHamHome.csv'
elif ('Chelsea' in homeTeam):
dataset = 'dataset/ChelseaHome.csv'
elif ('Brighton' in homeTeam):
dataset = 'dataset/BrightonHome.csv'
elif ('Crystal Palace' in homeTeam):
dataset = 'dataset/CrystalPalaceHome.csv'
elif ('West Brom' in homeTeam):
dataset = 'dataset/WestBromHome.csv'
elif ('Sheffield United' in homeTeam):
dataset = 'dataset/SheffieldUnitedHome.csv'
elif ('Leeds' in homeTeam):
dataset = 'dataset/LeedsHome.csv'
elif ('Aston Villa' in homeTeam):
dataset = 'dataset/AstonVillaHome.csv'
##Read Data from the Database into pandas
df = pd.read_csv(dataset, sep=',', header=0)
##Declare the Columns You Want to Use as Features
features = ['HTHG', 'HS', 'HST']
##Specify the Prediction Target
target = ['FTHG']
##Clean Data
df = df.dropna()
##Extract Features and Target ('Full time home goals') Values into Separate Dataframes
X = df[features]
y = df[target]
##Typical row from features
print(X.iloc[2])
##Linear Regression: Fit a model to the training set
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.50,
train_size=0.50,
random_state=324)
regressor = LinearRegression()
regressor.fit(X_train, y_train)
##Perform Prediction using Linear Regression Model
y_prediction = regressor.predict(X_test)
print(y_prediction)
# sg.Print('Prediction for Home Team...', do_not_reroute_stdout=False)
##What is the mean of the expected target value in test set ?
# print(y_test.describe())
##Evaluate Linear Regression Accuracy using Root Mean Square Error
RMSE = sqrt(mean_squared_error(y_true=y_test, y_pred=y_prediction))
# formatted_Home_RMSE = "{:.2f}".format(RMSE)
formatted_Home_RMSE = round(RMSE)
# print("\nPredicted amount of goals using Linear Regression for {0}\nin their next game against {2} is: {1}".format(homeTeam, formatted_Home_RMSE,awayTeam))
# print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, y_prediction))
# print('Mean Squared Error:', metrics.mean_squared_error(y_test, y_prediction))
# print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, y_prediction)))
##Decision Tree Regressor - Fit a new regression model to the training set
regressor = DecisionTreeRegressor(max_depth=20)
regressor.fit(X_train, y_train)
##Perform Prediction using Decision Tree Regressor
y_prediction = regressor.predict(X_test)
y_prediction
##Evaluate Decision Tree Regression Accuracy using Root Mean Square Error
RMSE2 = sqrt(mean_squared_error(y_true=y_test, y_pred=y_prediction))
# formatted_Home_RMSE2 = "{:.2f}".format(RMSE2)
formatted_Home_RMSE2 = round(RMSE2)
# print("\nPredicted amount of goals using Decision Tree Regression for {0}\nin their next game against {2} is: {1}".format(homeTeam, formatted_Home_RMSE2,awayTeam))
except:
sg.Popup("No dataset available")
try:
if ('Man United' in awayTeam):
dataset = 'dataset/ManUAway.csv'
elif ('Fulham' in awayTeam):
dataset = 'dataset/FulhamAway.csv'
elif ('Newcastle' in awayTeam):
dataset = 'dataset/NewcastleAway.csv'
elif ('Man City' in awayTeam):
dataset = 'dataset/ManCAway.csv'
elif ('Wolves' in awayTeam):
dataset = 'dataset/WolvesAway.csv'
elif ('Liverpool' in awayTeam):
dataset = 'dataset/LiverpoolAway.csv'
elif ('Southampton' in awayTeam):
dataset = 'dataset/SouthamptonAway.csv'
elif ('Arsenal' in awayTeam):
dataset = 'dataset/ArsenalAway.csv'
elif ('Burnley' in awayTeam):
dataset = 'dataset/BurnleyAway.csv'
elif ('Everton' in awayTeam):
dataset = 'dataset/EvertonAway.csv'
elif ('Leicester' in awayTeam):
dataset = 'dataset/LeicesterAway.csv'
elif ('Tottenham' in awayTeam):
dataset = 'dataset/TottenhamAway.csv'
elif ('West Ham' in awayTeam):
dataset = 'dataset/WestHamAway.csv'
elif ('Chelsea' in awayTeam):
dataset = 'dataset/ChelseaAway.csv'
elif ('Brighton' in awayTeam):
dataset = 'dataset/BrightonAway.csv'
elif ('Crystal Palace' in awayTeam):
dataset = 'dataset/CrystalPalaceAway.csv'
elif ('West Brom' in awayTeam):
dataset = 'dataset/WestBromAway.csv'
elif ('Sheffield United' in awayTeam):
dataset = 'dataset/SheffieldUnitedAway.csv'
elif ('Leeds' in awayTeam):
dataset = 'dataset/LeedsAway.csv'
elif ('Aston Villa' in awayTeam):
dataset = 'dataset/AstonVillaAway.csv'
##Read Data from the Database into pandas
df = pd.read_csv(dataset, sep=',', header=0)
##Declare the Columns You Want to Use as Features
features = ['HTAG', 'AS', 'AST']
##Specify the Prediction Target
target = ['FTAG']
##Clean Data
df = df.dropna()
##Extract Features and Target ('Full time away goals') Values into Separate Dataframes
X = df[features]
y = df[target]
##Typical row from features
# print(X.iloc[2])
##Linear Regression: Fit a model to the training set
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.75,
train_size=0.25,
random_state=324)
regressor = LinearRegression()
regressor.fit(X_train, y_train)
##Perform Prediction using Linear Regression Model
y_prediction = regressor.predict(X_test)
# sg.Print('\nPrediction for Away Team...', do_not_reroute_stdout=False)
##What is the mean of the expected target value in test set ?
# print(y_test.describe())
##Evaluate Linear Regression Accuracy using Root Mean Square Error
RMSE = sqrt(mean_squared_error(y_true=y_test, y_pred=y_prediction))
# formatted_Away_RMSE = "{:.2f}".format(RMSE)
formatted_Away_RMSE = round(RMSE)
# print("\nPredicted amount of goals using Linear Regression for {0}\nin their next game against {2} is: {1}".format(awayTeam, formatted_Away_RMSE,homeTeam))
##Decision Tree Regressor - Fit a new regression model to the training set
regressor = DecisionTreeRegressor(max_depth=20)
regressor.fit(X_train, y_train)
##Perform Prediction using Decision Tree Regressor
y_prediction = regressor.predict(X_test)
y_prediction
##Evaluate Decision Tree Regression Accuracy using Root Mean Square Error
RMSE2 = sqrt(mean_squared_error(y_true=y_test, y_pred=y_prediction))
# formatted_Away_RMSE2 = "{:.2f}".format(RMSE2)
formatted_Away_RMSE2 = round(RMSE2)
# print("\nPredicted amount of goals using Decision Tree Regression for {0}\nin their next game against {2} is: {1}".format(awayTeam, formatted_Away_RMSE2,homeTeam))
except:
sg.Popup("No dataset available")
# formatted_Home_RMSE = round(formatted_Home_RMSE)
# formatted_Away_RMSE = round(formatted_Away_RMSE)
sg.Print("Match Predictions utilizing Machine Learning Algorithms",
do_not_reroute_stdout=False)
print("-------------------------------------------")
print(
"Predicted Match Score using Linear Regression\n {0} : {1} - {2} : {3}"
.format(homeTeam[0], formatted_Home_RMSE, awayTeam[0],
formatted_Away_RMSE))
print("-------------------------------------------")
print(
"Predicted Match Score using Decision Tree Regression\n {0} : {1} - {2} : {3}"
.format(homeTeam[0], formatted_Home_RMSE2, awayTeam[0],
formatted_Away_RMSE2))
# api(homeTeam, awayTeam, formatted_Home_RMSE2, formatted_Away_RMSE2)
predictions = {
'homeTeam': homeTeam[0],
'awayTeam': awayTeam[0],
'homeTeamScore': formatted_Home_RMSE2,
'awayTeamScore': formatted_Away_RMSE2,
}
import json
with open('json/predictions.json', 'w') as f:
json.dump(predictions, f)
from dynamoDB import dataWriter
call(["python", "dynamoDB/dataWriter.py"])
from turtle import pd
import pandas as pd
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn import metrics
PavoDataset = pd.read_csv('dataset.csv')
print(PavoDataset.head(6))
print(PavoDataset.describe())
location = PavoDataset['location3'][:]
print(location.head(6))
X = PavoDataset.drop(['location3', 'location1', 'location2'], axis=1)
X_train, X_test, y_train, y_test = train_test_split(X,
location,
test_size=0.10)
knn = KNeighborsClassifier(n_neighbors=3)
#Train the model using the training sets
knn.fit(X_train, y_train)
P = [[207.4, 182.2, 189.4, 193.0, 193.6]]
asa = knn.predict(P)
print("2) Using K Neighbors Classifier Prediction is " + str(knn.predict(P)))
#some_dict={35: [177.2, 178.0, 183.6, 177.2, 182.6], 89: [188.8, 185.8, 181.0, 190.0, 193.0], 92: [196.0, 196.0, 190.6, 191.2, 194.8], 267: [184.0, 177.2, 173.5, 174.6, 182.2]}
some_dict = {
35: [177.8, 180.0, 182.2, 174.6, 182.8],
def logisticRegression(homeTeam, awayTeam):
import pandas as pd
import numpy as np
from sklearn import preprocessing
import matplotlib.pyplot as plt
plt.rc("font", size=14)
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
import seaborn as sns
try:
if ('Man United' in homeTeam):
dataset = 'dataset/ManUHome.csv'
elif ('Fulham' in homeTeam):
dataset = 'dataset/FulhamHome.csv'
elif ('Newcastle' in homeTeam):
dataset = 'dataset/NewcastleHome.csv'
elif ('Man City' in homeTeam):
dataset = 'dataset/ManCHome.csv'
elif ('Wolves' in homeTeam):
dataset = 'dataset/WolvesHome.csv'
elif ('Liverpool' in homeTeam):
dataset = 'dataset/LiverpoolHome.csv'
elif ('Southampton' in homeTeam):
dataset = 'dataset/SouthamptonHome.csv'
elif ('Arsenal' in homeTeam):
dataset = 'dataset/ArsenalHome.csv'
elif ('Burnley' in homeTeam):
dataset = 'dataset/BurnleyHome.csv'
elif ('Everton' in homeTeam):
dataset = 'dataset/EvertonHome.csv'
elif ('Leicester' in homeTeam):
dataset = 'dataset/LeicesterHome.csv'
elif ('Tottenham' in homeTeam):
dataset = 'dataset/TottenhamHome.csv'
elif ('West Ham' in homeTeam):
dataset = 'dataset/WestHamHome.csv'
elif ('Chelsea' in homeTeam):
dataset = 'dataset/ChelseaHome.csv'
elif ('Brighton' in homeTeam):
dataset = 'dataset/BrightonHome.csv'
elif ('Crystal Palace' in homeTeam):
dataset = 'dataset/CrystalPalaceHome.csv'
elif ('West Brom' in homeTeam):
dataset = 'dataset/WestBromHome.csv'
elif ('Sheffield United' in homeTeam):
dataset = 'dataset/SheffieldUnitedHome.csv'
elif ('Leeds' in homeTeam):
dataset = 'dataset/LeedsHome.csv'
elif ('Aston Villa' in homeTeam):
dataset = 'dataset/AstonVillaHome.csv'
##Read Data from the Database into pandas
df = pd.read_csv(dataset, sep=',', header=0)
##Declare the Columns You Want to Use as Features
features = ['HTHG', 'HS', 'HST']
##Specify the Prediction Target
target = ['FTHG']
##Clean Data
df = df.dropna()
##Extract Features and Target ('Full time home goals') Values into Separate Dataframes
X = df[features]
y = df[target]
##Typical row from features
print(X.iloc[2])
##Logistic Regression: Fit a model to the training set
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.50,
train_size=0.50,
random_state=324)
from sklearn.linear_model import LogisticRegression
from sklearn import metrics
logreg = LogisticRegression()
logreg.fit(X_train, y_train)
##Perform Prediction using Logistic Regression Model
y_prediction = logreg.predict(X_test)
print(y_prediction)
sg.Print('Prediction for Home Team...', do_not_reroute_stdout=False)
print('Accuracy of logistic regression classifier on test set: {:.2f}'.
format(logreg.score(X_test, y_test)))
from sklearn.metrics import confusion_matrix
confusion_matrix = confusion_matrix(y_test, y_prediction)
print(confusion_matrix)
except:
sg.Popup("No dataset available")
def statistics(homeTeam, awayTeam):
import pandas as pd
import matplotlib.pyplot as plt
plt.rc("font", size=14)
try:
if ('Man United' in homeTeam):
dataset = 'dataset/ManUHome.csv'
elif ('Fulham' in homeTeam):
dataset = 'dataset/FulhamHome.csv'
elif ('Newcastle' in homeTeam):
dataset = 'dataset/NewcastleHome.csv'
elif ('Man City' in homeTeam):
dataset = 'dataset/ManCHome.csv'
elif ('Wolves' in homeTeam):
dataset = 'dataset/WolvesHome.csv'
elif ('Liverpool' in homeTeam):
dataset = 'dataset/LiverpoolHome.csv'
elif ('Southampton' in homeTeam):
dataset = 'dataset/SouthamptonHome.csv'
elif ('Arsenal' in homeTeam):
dataset = 'dataset/ArsenalHome.csv'
elif ('Burnley' in homeTeam):
dataset = 'dataset/BurnleyHome.csv'
elif ('Everton' in homeTeam):
dataset = 'dataset/EvertonHome.csv'
elif ('Leicester' in homeTeam):
dataset = 'dataset/LeicesterHome.csv'
elif ('Tottenham' in homeTeam):
dataset = 'dataset/TottenhamHome.csv'
elif ('West Ham' in homeTeam):
dataset = 'dataset/WestHamHome.csv'
elif ('Chelsea' in homeTeam):
dataset = 'dataset/ChelseaHome.csv'
elif ('Brighton' in homeTeam):
dataset = 'dataset/BrightonHome.csv'
elif ('Crystal Palace' in homeTeam):
dataset = 'dataset/CrystalPalaceHome.csv'
elif ('West Brom' in homeTeam):
dataset = 'dataset/WestBromHome.csv'
elif ('Sheffield United' in homeTeam):
dataset = 'dataset/SheffieldUnitedHome.csv'
elif ('Leeds' in homeTeam):
dataset = 'dataset/LeedsHome.csv'
elif ('Aston Villa' in homeTeam):
dataset = 'dataset/AstonVillaHome.csv'
##Read Data from the Database into pandas
df = pd.read_csv(dataset, sep=',', header=0)
##Declare the Columns You Want to Use as Features
features = ['HTHG', 'HS', 'HST']
##Specify the Prediction Target
target = ['FTHG']
##Clean Data
df = df.dropna()
# sns.countplot(x='FTHG', data=data, palette='hls')
# plt.show()
# plt.savefig('count_plot')
# data.groupby('FTHG').mean()
# data.groupby('HS').mean()
# data.groupby('HST').mean()
pd.crosstab(df.FTHG, df.HS).plot(kind='bar')
plt.title('{} home goals vs. shots'.format(homeTeam))
plt.xlabel('Goals')
plt.ylabel('Shots')
plt.savefig('img/goals_vs_shots_home')
plt.show(block=True)
# data.FTHG.hist()
# plt.title('Histogram of Home Goals')
# plt.xlabel('Goals')
# plt.ylabel('Frequency')
# plt.savefig('hist_goals')
except:
sg.Popup("No dataset available")
def predicting(homeTeam, awayTeam):
import pandas as pd
try:
if ('Man United' in homeTeam):
dataset = 'dataset/ManUHome.csv'
elif ('Fulham' in homeTeam):
dataset = 'dataset/FulhamHome.csv'
elif ('Fulham' in awayTeam):
dataset = 'dataset/FulhamAway.csv'
elif ('Man United' in awayTeam):
dataset = 'dataset/ManUAway.csv'
if ('Man United' in homeTeam):
dataset = 'dataset/ManUHome.csv'
elif ('Fulham' in homeTeam):
dataset = 'dataset/FulhamHome.csv'
elif ('Newcastle' in homeTeam):
dataset = 'dataset/NewcastleHome.csv'
elif ('Man City' in homeTeam):
dataset = 'dataset/ManCHome.csv'
elif ('Wolves' in homeTeam):
dataset = 'dataset/WolvesHome.csv'
elif ('Liverpool' in homeTeam):
dataset = 'dataset/LiverpoolHome.csv'
elif ('Southampton' in homeTeam):
dataset = 'dataset/SouthamptonHome.csv'
elif ('Arsenal' in homeTeam):
dataset = 'dataset/ArsenalHome.csv'
elif ('Burnley' in homeTeam):
dataset = 'dataset/BurnleyHome.csv'
elif ('Everton' in homeTeam):
dataset = 'dataset/EvertonHome.csv'
elif ('Leicester' in homeTeam):
dataset = 'dataset/LeicesterHome.csv'
elif ('Tottenham' in homeTeam):
dataset = 'dataset/TottenhamHome.csv'
elif ('West Ham' in homeTeam):
dataset = 'dataset/WestHamHome.csv'
elif ('Chelsea' in homeTeam):
dataset = 'dataset/ChelseaHome.csv'
elif ('Brighton' in homeTeam):
dataset = 'dataset/BrightonHome.csv'
elif ('Crystal Palace' in homeTeam):
dataset = 'dataset/CrystalPalaceHome.csv'
elif ('West Brom' in homeTeam):
dataset = 'dataset/WestBromHome.csv'
elif ('Sheffield United' in homeTeam):
dataset = 'dataset/SheffieldUnitedHome.csv'
elif ('Leeds' in homeTeam):
dataset = 'dataset/LeedsHome.csv'
elif ('Aston Villa' in homeTeam):
dataset = 'dataset/AstonVillaHome.csv'
df1 = pd.read_csv(dataset,
usecols=[
'HomeTeam', 'AwayTeam', 'FTHG', 'FTAG', 'FTR',
'HTR', 'HS', 'AS', 'HST', 'AST', 'B365H',
'B365D', 'B365A'
])
df1.head()
stdoutOrigin = sys.stdout
sys.stdout = open("logs/log.txt", "w")
from statsmodels.stats import proportion
confHome = proportion.proportion_confint((df1['FTR'] == 'H').sum(),
df1['FTR'].count(),
alpha=0.05,
method='wilson')
confAway = proportion.proportion_confint((df1['FTR'] == 'A').sum(),
df1['FTR'].count(),
alpha=0.05,
method='wilson')
confDraw = proportion.proportion_confint((df1['FTR'] == 'D').sum(),
df1['FTR'].count(),
alpha=0.05,
method='wilson')
print(
'The chance of home team to win with %95 confidence interval falls in :{}'
.format(confHome))
print(
'--------------------------------------------------------------------------------'
)
print(
'The chance of away team to win with %95 confidence interval falls in :{}'
.format(confAway))
print(
'--------------------------------------------------------------------------------'
)
print('The chance of a draw with %95 confidence interval falls in :{}'.
format(confDraw))
sys.stdout.close()
sys.stdout = stdoutOrigin
textPrinting('logs/log.txt')
import matplotlib.pyplot as plt
plt.figure(figsize=(6, 8))
plt.pie(df1['FTR'].value_counts(),
labels=['Home Win', 'Home Loss', 'Draw'],
autopct='%1.1f%%',
shadow=True,
startangle=0)
plt.axis('equal')
plt.title('Win Percentage', size=18)
plt.show()
sg.Popup("Complete")
except:
sg.Popup("No Matches")
with open(path, 'r') as file:
allData = []
data = np.loadtxt(file, delimiter=delimiter)
allData.append(data)
allData = np.asarray(allData)
return allData
popt, pcov = curve_fit(gaus, x1, y1, p0=[1, mean, sigma])
a, mu, sigma = popt
delta_a, delta_mu, delta_sigma = np.sqrt(np.diag(pcov))
# R^2
residuals = y1 - gaus(x1, *popt)
ss_res = np.sum(residuals**2)
ss_tot = np.sum((y1 - np.mean(y1))**2)
r_squared = 1 - (ss_res / ss_tot)
def gaus(x, a, x0, sigma):
return a * np.exp(-(x - x0)**2 / (2 * sigma**2))
fit_param = []
## Fig1
df1 = pd.read_csv('gaussien.csv', sep=";", header=1)
x1 = df1.to_numpy().T[0].astype(float)
y1 = df1.to_numpy().T[1].astype(float)
x1_fit = np.linspace(x1[0], x1[-1], 1000)
plt.plot(x1_fit, gaus(x1_fit, *popt), linewidth=0.5, alpha=0.75, color='C0')
import datetime
from datetime import time
from turtle import pd
import pyautogui
import subprocess
subprocess.Popen("/Applications/OBS.app")
position = pyautogui.locateOnScreen("buttons\\recording_button.png")
# Move the cursor to the position of the button
pyautogui.moveTo(position)
# Perform click operation
pyautogui.click()
time.sleep(2)
df = pd.read_csv('timetable.csv')
while True:
time = datetime.now().strftime("%H:%M")
if time not in df.Time.values:
position = pyautogui.locateOnScreen("button\\stoprecording_button.png")
pyautogui.moveTo(position)
break