WINEQUALITY_RED

import matplotlib.pyplot as plt
import pandas
from pandas.plotting import scatter_matrix

from sklearn import model_selection
from sklearn.model_selection import train_test_split

from sklearn.naive_bayes import GaussianNB
from sklearn import metrics

url="C:/Users/Martin Njuguna/Documents/winequality-red.csv"
names=['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar', 'chlorides free', 'sulfur dioxide', 'total sulfur dioxide', 'density', 'pH', 'sulphates', 'alcohol', 'quality']
dataset=pandas.read_csv(url,names=names)

print(dataset.shape)
print(dataset.head(5))
print(dataset)
print(dataset.describe())
print(dataset.groupby('quality').size())

dataset.plot(kind='box',subplots=True,layout=(5,5),sharex=False,sharey=False)
plt.show()

dataset.hist()
plt.show()

scatter_matrix(dataset)
plt.show()

array=dataset.values
X=array[:,0:11] #Extract fields
Y=array[:,4] #Extract results

#Split the data into 80%, 20% for training and testing
validation_size=0.20
seed=7
X_train,X_test,Y_train,Y_test=model_selection.train_test_split\
    (X,Y, test_size=validation_size,random_state=seed)

print("X_train",X_train)
print("X_test",X_test)
print("Y_train",Y_train)
print("Y_test",Y_test)

model=GaussianNB()
model=model.fit(X_train,Y_train)

y_predicted =model.predict(X_test)
print(metrics.accuracy_score(Y_test,y_predicted))