You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
295 lines
13 KiB
295 lines
13 KiB
import re
|
|
import pandas as pd
|
|
import numpy as np
|
|
import seaborn as sns
|
|
import matplotlib.pyplot as plt
|
|
from sklearn.tree import export_graphviz
|
|
from sklearn.tree import plot_tree
|
|
from sklearn.pipeline import Pipeline
|
|
from sklearn.ensemble import RandomForestClassifier
|
|
from sklearn.metrics import accuracy_score
|
|
from sklearn.metrics import classification_report
|
|
from sklearn.metrics import confusion_matrix
|
|
from sklearn.model_selection import cross_val_score
|
|
from sklearn.preprocessing import OrdinalEncoder, LabelEncoder
|
|
from sklearn.compose import make_column_transformer
|
|
from sklearn.impute import SimpleImputer
|
|
pd.options.display.max_columns = None
|
|
pd.options.display.max_rows = None
|
|
import sklearn
|
|
|
|
def displayNumberOfNaNValues(df):
|
|
# Create an empty list to store tuples of column index and number of NaN values
|
|
na = []
|
|
# Loop through each column in the DataFrame
|
|
for index, col in enumerate(df):
|
|
# Count the number of NaN values in each column and append the index and count to 'na'
|
|
na.append((index, df[col].isna().sum()))
|
|
# Make a copy of 'na' and sort it based on the count of NaN values in descending order
|
|
na.sort(key=lambda x: x[1], reverse=True)
|
|
# Iterate through the sorted list of columns
|
|
for i in range(len(df.columns)):
|
|
# Check if the count of NaN values for the current column is not zero
|
|
if na[i][1] != 0:
|
|
# Print the column name, count of NaN values, and "NaN"
|
|
print(df.columns[na[i][0]], ":", na[i][1], "NaN")
|
|
# Calculate and print the total number of features with NaN values
|
|
print('Number of features with NaN values:', len([x[1] for x in na if x[1] > 0]))
|
|
print("Total NaN in dataframe :" , df.isna().sum().sum())
|
|
|
|
|
|
df = pd.read_csv('archive/data.csv')
|
|
|
|
# Before April 2001, there were almost no rules in UFC (no judges, no time limits, no rounds, etc.).
|
|
#It's up to this precise date that UFC started to implement a set of rules known as
|
|
#"Unified Rules of Mixed Martial Arts".
|
|
#Therefore, we delete all fights before this major update in UFC's rules history.
|
|
|
|
# Using this old data would not be representative of current fights, especially since this
|
|
#sport has become one of the most regulated due to its mixity and complexity.
|
|
|
|
limit_date = '2001-04-01'
|
|
df = df[(df['date'] > limit_date)]
|
|
|
|
# Display NaN values
|
|
displayNumberOfNaNValues(df)
|
|
|
|
# Define the list of important features to impute
|
|
imp_features = ['R_Weight_lbs', 'R_Height_cms', 'B_Height_cms', 'R_age', 'B_age', 'R_Reach_cms', 'B_Reach_cms']
|
|
|
|
# Initialize a SimpleImputer to impute missing values with median
|
|
imp_median = SimpleImputer(missing_values=np.nan, strategy='median')
|
|
|
|
# Iterate over each feature to impute missing values
|
|
for feature in imp_features:
|
|
# Fit and transform the feature using median imputation
|
|
imp_feature = imp_median.fit_transform(df[feature].values.reshape(-1,1))
|
|
# Assign the imputed values back to the DataFrame
|
|
df[feature] = imp_feature
|
|
|
|
# Impute missing values for 'R_Stance' using most frequent strategy
|
|
imp_stance_R = SimpleImputer(missing_values=np.nan, strategy='most_frequent')
|
|
imp_R_stance = imp_stance_R.fit_transform(df['R_Stance'].values.reshape(-1,1))
|
|
|
|
# Impute missing values for 'B_Stance' using most frequent strategy
|
|
imp_stance_B = SimpleImputer(missing_values=np.nan, strategy='most_frequent')
|
|
imp_B_stance = imp_stance_B.fit_transform(df['B_Stance'].values.reshape(-1,1))
|
|
|
|
# Create DataFrames for imputed stances
|
|
df['R_Stance'] = pd.DataFrame(imp_R_stance, columns=['R_Stance'])
|
|
df['B_Stance'] = pd.DataFrame(imp_B_stance, columns=['B_Stance'])
|
|
|
|
# drop B_avg_BODY_att values in the dataframe
|
|
# List of features with NaN values to drop
|
|
#na_features = ['B_avg_BODY_att', 'R_avg_BODY_att']
|
|
|
|
# Drop rows with NaN values in specified features
|
|
#df.dropna(subset=na_features, inplace=True)
|
|
|
|
# Drop columns 'Referee' and 'location' from the DataFrame
|
|
# The value of references and location has a low impact in battles, which makes it irrelevant to keep
|
|
df.drop(['Referee', 'location'], axis=1, inplace=True)
|
|
|
|
# Drop column 'B_draw' and 'R_draw' and 'Draw' fight and 'Catch Weight' fight
|
|
df.drop(['B_draw', 'R_draw'], axis=1, inplace=True)
|
|
df = df[df['Winner'] != 'Draw']
|
|
df = df[df['weight_class'] != 'Catch Weight']
|
|
|
|
# Remove column when data type is not float or int
|
|
dfWithoutString = df.select_dtypes(include=['float64', 'int64'])
|
|
|
|
plt.figure(figsize=(50, 40))
|
|
corr_matrix = dfWithoutString.corr(method='pearson').abs()
|
|
sns.heatmap(corr_matrix, annot=True)
|
|
|
|
# Show the correlation matrix of the dataframe
|
|
# Very laggy feature
|
|
|
|
# plt.show()
|
|
|
|
# i = index of the fighter's fight, 0 means the last fight, -1 means first fight
|
|
def select_fight_row(df, name, i):
|
|
df_temp = df[(df['R_fighter'] == name) | (df['B_fighter'] == name)] # filter df on fighter's name
|
|
df_temp.reset_index(drop=True, inplace=True) # as we created a new temporary dataframe, we have to reset indexes
|
|
idx = max(df_temp.index) # get the index of the oldest fight
|
|
if i > idx: # if we are looking for a fight that didn't exist, we return nothing
|
|
return
|
|
arr = df_temp.iloc[i,:].values
|
|
return arr
|
|
|
|
# we get the last fight of Khabib :'(
|
|
print(select_fight_row(df, 'Khabib Nurmagomedov', 0))
|
|
|
|
|
|
# get all active UFC fighters (according to the limit_date parameter)
|
|
def list_fighters(df, limit_date):
|
|
# Filter the DataFrame to include only fights occurring after the specified limit date
|
|
df_temp = df[df['date'] > limit_date]
|
|
# Create a set of all fighters from the red corner ('R_fighter') in the filtered DataFrame
|
|
set_R = set(df_temp['R_fighter'])
|
|
# Create a set of all fighters from the blue corner ('B_fighter') in the filtered DataFrame
|
|
set_B = set(df_temp['B_fighter'])
|
|
# Combine the sets of fighters from the red and blue corners to get all unique fighters
|
|
fighters = list(set_R.union(set_B))
|
|
# Print the number of unique fighters included in the list
|
|
# print("Number of fighters: " + str(len(fighters)))
|
|
# Return the list of unique fighters
|
|
return fighters
|
|
|
|
# Last year when data fight was not full and correct
|
|
fighters = list_fighters(df,'2015-01-01')
|
|
|
|
def build_df(df, fighters, i):
|
|
arr = [select_fight_row(df, fighters[f], i) for f in range(len(fighters)) if select_fight_row(df, fighters[f], i) is not None]
|
|
cols = [col for col in df]
|
|
df_fights = pd.DataFrame(data=arr, columns=cols)
|
|
df_fights.drop_duplicates(inplace=True)
|
|
df_fights['title_bout'] = df_fights['title_bout'].map({True: 1, False: 0})
|
|
df_fights.drop(['R_fighter', 'B_fighter', 'date'], axis=1, inplace=True)
|
|
return df_fights
|
|
|
|
def build_df_all_but_last(df, fighters):
|
|
cols = [col for col in df]
|
|
df_fights=pd.DataFrame(columns=cols)
|
|
for f in range(len(fighters)):
|
|
i=0
|
|
while True:
|
|
fight_row = select_fight_row(df, fighters[f], i)
|
|
if fight_row is None:
|
|
if not df_fights.empty:
|
|
df_fights = df_fights.iloc[:-1]
|
|
break
|
|
fight_row = list(fight_row)
|
|
dfTemp = pd.DataFrame(data=[fight_row], columns=cols)
|
|
df_fights = df_fights.dropna(axis=1, how='all')
|
|
df_fights = pd.concat([df_fights, dfTemp], ignore_index=True)
|
|
i=i+1
|
|
df_fights.drop_duplicates(inplace=True)
|
|
df_fights = df_fights[~df_fights.apply(lambda row: 'Open Stance' in row.values, axis=1)].reset_index(drop=True)
|
|
df_fights['title_bout'] = df_fights['title_bout'].map({True: 1, False: 0})
|
|
df_fights.drop(['R_fighter', 'B_fighter', 'date'], axis=1, inplace=True)
|
|
|
|
return df_fights
|
|
|
|
|
|
df_train = build_df_all_but_last(df, fighters)
|
|
df_test = build_df(df, fighters,0)
|
|
|
|
preprocessor = make_column_transformer((OrdinalEncoder(), ['weight_class', 'B_Stance', 'R_Stance']), remainder='passthrough')
|
|
|
|
# If the winner is from the Red corner, Winner label will be encoded as 1, otherwise it will be 0 (Blue corner)
|
|
label_encoder = LabelEncoder()
|
|
y_train = label_encoder.fit_transform(df_train['Winner'])
|
|
y_test = label_encoder.transform(df_test['Winner'])
|
|
|
|
X_train, X_test = df_train.drop(['Winner'], axis=1), df_test.drop(['Winner'], axis=1)
|
|
|
|
# Random Forest composed of 100 decision trees. We optimized parameters using cross-validation and GridSearch tool paired together
|
|
random_forest = RandomForestClassifier(n_estimators=100,
|
|
criterion='entropy',
|
|
max_depth=10,
|
|
min_samples_split=2,
|
|
min_samples_leaf=1,
|
|
random_state=0)
|
|
|
|
model = Pipeline([('encoding', preprocessor), ('random_forest', random_forest)])
|
|
model.fit(X_train, y_train)
|
|
|
|
# We use cross-validation with 5-folds to have a more precise accuracy (reduce variation)
|
|
accuracies = cross_val_score(estimator=model, X=X_train, y=y_train, cv=5)
|
|
print('Accuracy mean : ', accuracies.mean())
|
|
print('Accuracy standard deviation : ', accuracies.std())
|
|
|
|
y_pred = model.predict(X_test)
|
|
print('Testing accuracy : ', accuracy_score(y_test, y_pred), '\n')
|
|
|
|
target_names = ["Blue","Red"]
|
|
print(classification_report(y_test, y_pred, labels=[0,1], target_names=target_names))
|
|
|
|
# cm = confusion_matrix(y_test, y_pred)
|
|
# ax = plt.subplot()
|
|
# sns.heatmap(cm, annot = True, ax = ax, fmt = "d")
|
|
# ax.set_xlabel('Actual')
|
|
# ax.set_ylabel('Predicted')
|
|
# ax.set_title("Confusion Matrix")
|
|
# ax.xaxis.set_ticklabels(['Blue', 'Red'])
|
|
# ax.yaxis.set_ticklabels(['Blue', 'Red'])
|
|
# plt.show()
|
|
|
|
feature_names = [col for col in X_train]
|
|
feature_importances = model['random_forest'].feature_importances_
|
|
indices = np.argsort(feature_importances)[::-1]
|
|
n = 30 # maximum feature importances displayed
|
|
idx = indices[0:n]
|
|
std = np.std([tree.feature_importances_ for tree in model['random_forest'].estimators_], axis=0)
|
|
|
|
#for f in range(n):
|
|
# print("%d. feature %s (%f)" % (f + 1, feature_names[idx[f]], feature_importances[idx[f]]))
|
|
|
|
# plt.figure(figsize=(30, 8))
|
|
# plt.title("Feature importances")
|
|
# plt.bar(range(n), feature_importances[idx], color="r", yerr=std[idx], align="center")
|
|
# plt.xticks(range(n), [feature_names[id] for id in idx], rotation = 45)
|
|
# plt.xlim([-1, n])
|
|
# plt.show()
|
|
|
|
# Sélectionnez un arbre de votre modèle
|
|
tree_estimator = model['random_forest'].estimators_[10]
|
|
|
|
# Tracez l'arbre
|
|
# plt.figure(figsize=(1, 1))
|
|
# plot_tree(tree_estimator, feature_names=df_train.columns, filled=True, rounded=True, fontsize=10)
|
|
# plt.savefig('tree.png', dpi=600) # Enregistrez l'image au format PNG
|
|
# plt.show()
|
|
|
|
def predict(df, pipeline, blue_fighter, red_fighter, weightclass, rounds, title_bout=False):
|
|
try:
|
|
#We build two dataframes, one for each figther
|
|
f1 = df[(df['R_fighter'] == blue_fighter) | (df['B_fighter'] == blue_fighter)].copy()
|
|
f1.reset_index(drop=True, inplace=True)
|
|
f1 = f1[:1]
|
|
f2 = df[(df['R_fighter'] == red_fighter) | (df['B_fighter'] == red_fighter)].copy()
|
|
f2.reset_index(drop=True, inplace=True)
|
|
f2 = f2[:1]
|
|
|
|
# if the fighter was red/blue corner on his last fight, we filter columns to only keep his statistics (and not the other fighter)
|
|
# then we rename columns according to the color of the corner in the parameters using re.sub()
|
|
if (f1.loc[0, ['R_fighter']].values[0]) == blue_fighter:
|
|
result1 = f1.filter(regex='^R', axis=1).copy() #here we keep the red corner stats
|
|
result1.rename(columns = lambda x: re.sub('^R','B', x), inplace=True) #we rename it with "B_" prefix because he's in the blue_corner
|
|
else:
|
|
result1 = f1.filter(regex='^B', axis=1).copy()
|
|
if (f2.loc[0, ['R_fighter']].values[0]) == red_fighter:
|
|
result2 = f2.filter(regex='^R', axis=1).copy()
|
|
else:
|
|
result2 = f2.filter(regex='^B', axis=1).copy()
|
|
result2.rename(columns = lambda x: re.sub('^B','R', x), inplace=True)
|
|
|
|
fight = pd.concat([result1, result2], axis = 1) # we concatenate the red and blue fighter dataframes (in columns)
|
|
fight.drop(['R_fighter','B_fighter'], axis = 1, inplace = True) # we remove fighter names
|
|
fight.insert(0, 'title_bout', title_bout) # we add tittle_bout, weight class and number of rounds data to the dataframe
|
|
fight.insert(1, 'weight_class', weightclass)
|
|
fight.insert(2, 'no_of_rounds', rounds)
|
|
fight['title_bout'] = fight['title_bout'].map({True: 1, False: 0})
|
|
|
|
pred = pipeline.predict(fight)
|
|
proba = pipeline.predict_proba(fight)
|
|
if (pred == 1.0):
|
|
print("The predicted winner is", red_fighter, 'with a probability of', round(proba[0][1] * 100, 2), "%")
|
|
else:
|
|
print("The predicted winner is", blue_fighter, 'with a probability of ', round(proba[0][0] * 100, 2), "%")
|
|
return proba
|
|
except:
|
|
print("One of fighter doesn't exist in the dataframe")
|
|
return
|
|
|
|
|
|
predict(df, model, 'Kamaru Usman', 'Colby Covington', 'Welterweight', 3, True)
|
|
predict(df, model, 'Leon Edwards', 'Belal Muhammad', 'Welterweight', 3, True)
|
|
predict(df, model, 'Conor McGregor', 'Khabib Nurmagomedov', 'Lightweight', 5, True)
|
|
predict(df, model, 'Conor McGregor', 'Tai Tuivasa', 'Heavyweight', 5, True)
|
|
|
|
predict(df,model,'Charles Oliveira','Conor McGregor','Lightweight',5,True)
|
|
predict(df,model,'Charles Oliveira','Khabib Nurmagomedov','Lightweight',5,True)
|
|
predict(df, model, 'Leon Edwards', 'Kamaru Usman', 'Welterweight', 5, True)
|