from numpy import mean

from numpy import var

from numpy import std

import pandas as pd

from scipy.stats import pearsonr

print('Mean: %.3f' % mean(mylist))

print('Variance: %.3f' % var(mylist))

print('Standard Deviation: %.3f' % std(mylist))

sr = pd.read_csv('winequality-red.csv')

print(f'\nThe type is: {type(sr)}')

print(sr.head(10))

header = list(sr.columns)

print("List of column names:", header)

data1 = sr['quality']

data2 = sr['alcohol']

data3 = sr['sulphates']

data4 = sr['chlorides']

print('Pearsons correlation between quality and alcohol is: %.3f' % corr)

print('Pearsons correlation between quality and sulphates is: %.3f' % corr)

print('Pearsons correlation between quality and chlorides is: %.3f' % corr)

print('---------------------')

print('xxxxxxxxxxxxxxxxxxxxx')

print('---------------------')

print(correlation_matrix)

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sb

import warnings

warnings.filterwarnings('ignore')

df = pd.read_csv('winequalityN.csv')

print("1- df.head >>> ")

print(df.head())

print("")

print("2- df.info >>> ")

print(df.info())

print("")

print("3- df.describe().T >>> ")

print(df.describe().T)

print("")

print("4- df.isnull().sum() >>> ")

print(df.isnull().sum())

print("")

for col in df.columns:

if df[col].isnull().sum() > 0:

print("5- df.isnull().sum().sum() >>> ")

print(df.isnull().sum().sum())

print("")

plt.bar(df['quality'], df['alcohol'])

plt.xlabel('quality')

plt.ylabel('alcohol')

for col in df.columns:

if df[col].dtype == 'object':

try:

df[col] = pd.to_numeric(df[col], errors='coerce') # Convert to numeric, replace non-convertibles with NaN

except:

pass # Skip columns that cannot be converted

sb.heatmap(df.corr() > 0.7, annot=True, cbar=False)

if __name__ == "__main__":

print()

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split #train_test_split, it is part of scikit-learn

from sklearn.preprocessing import MinMaxScaler

from sklearn import metrics

from sklearn.svm import SVC

from xgboost import XGBClassifier #XGBClassifier is part of XGBoost

from sklearn.linear_model import LogisticRegression

import warnings

warnings.filterwarnings('ignore')

df = pd.read_csv('winequalityN.csv')

print("1a- df.head >>> ")

print(df.head())

print("")

df['best quality'] = [1 if x > 5 else 0 for x in df.quality]

df.replace({'white': 1, 'red': 0}, inplace=True)

features = df.drop(['quality', 'best quality'], axis=1)

target = df['best quality']

from sklearn.impute import SimpleImputer # SimpleImputer it is part of scikit-learn

imputer = SimpleImputer(strategy='mean') # Or another strategy like 'median'

print("2a- Model Development - xtrain.shape, xtest.shape >>> ")

print(xtrain.shape, xtest.shape)

print("")

norm = MinMaxScaler()

models = [LogisticRegression(), XGBClassifier(), SVC(kernel='rbf')]

print("3a- Normalising the data >>> ")

for i in range(3):

#print(f'{models[i]} : ')

print('<<< for i = >>>', i)

print("<<< Models >>> ", f'{models[i]} : ')

print('<<< Training Accuracy : ', metrics.roc_auc_score(ytrain, models[i].predict(xtrain)))

print('<<< Validation Accuracy : ', metrics.roc_auc_score(

print()

from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay

import matplotlib.pyplot as plt

disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=models[1].classes_) # Assuming your model has a 'classes_' attribute

if __name__ == "__main__":

print()