import numpy as np
[ ]: import pandas as pad
[ ]: import seaborn as sns
[ ]: from sklearn.datasets import load_wine
[ ]: from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score, classification_report
[ ]: wine = load_wine()
X = wine.data
y = wine.target
[ ]: wine
[ ]: {'data': array([[1.423e+01, 1.710e+00, 2.430e+00, …, 1.040e+00, 3.920e+00,
1.065e+03],
[1.320e+01, 1.780e+00, 2.140e+00, …, 1.050e+00, 3.400e+00,
1.050e+03],
[1.316e+01, 2.360e+00, 2.670e+00, …, 1.030e+00, 3.170e+00,
1.185e+03],
…,
[1.327e+01, 4.280e+00, 2.260e+00, …, 5.900e-01, 1.560e+00,
8.350e+02],
[1.317e+01, 2.590e+00, 2.370e+00, …, 6.000e-01, 1.620e+00,
8.400e+02],
[1.413e+01, 4.100e+00, 2.740e+00, …, 6.100e-01, 1.600e+00,
5.600e+02]]),
'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2]),
'frame': None,
'target_names': array(['class_0', 'class_1', 'class_2'], dtype='<U7'),
'DESCR': '.. _wine_dataset:\n\nWine recognition
dataset\n------------------------\n\n**Data Set Characteristics:**\n\n
:Number of Instances: 178\n :Number of Attributes: 13 numeric, predictive
attributes and the class\n :Attribute Information:\n \t\t- Alcohol\n \t\tMalic acid\n \t\t- Ash\n\t\t- Alcalinity of ash \n \t\t- Magnesium\n\t\t- Total
phenols\n \t\t- Flavanoids\n \t\t- Nonflavanoid phenols\n \t\tProanthocyanins\n\t\t- Color intensity\n \t\t- Hue\n \t\t- OD280/OD315 of
diluted wines\n \t\t- Proline\n\n - class:\n - class_0\n
- class_1\n - class_2\n\t\t\n :Summary Statistics:\n \n
============================= ==== ===== ======= =====\n
Min Max Mean SD\n ============================= ==== ===== =======
=====\n Alcohol: 11.0 14.8 13.0 0.8\n Malic
Acid: 0.74 5.80 2.34 1.12\n Ash:
1.36 3.23 2.36 0.27\n Alcalinity of Ash: 10.6 30.0 19.5
3.3\n Magnesium: 70.0 162.0 99.7 14.3\n Total
Phenols: 0.98 3.88 2.29 0.63\n Flavanoids:
0.34 5.08 2.03 1.00\n Nonflavanoid Phenols: 0.13 0.66 0.36
0.12\n Proanthocyanins: 0.41 3.58 1.59 0.57\n Colour
Intensity: 1.3 13.0 5.1 2.3\n Hue:
0.48 1.71 0.96 0.23\n OD280/OD315 of diluted wines: 1.27 4.00 2.61
0.71\n Proline: 278 1680 746 315\n
============================= ==== ===== ======= =====\n\n :Missing Attribute
Values: None\n :Class Distribution: class_0 (59), class_1 (71), class_2
(48)\n :Creator: R.A. Fisher\n :Donor: Michael Marshall
(MARSHALL%PLU@io.arc.nasa.gov)\n :Date: July, 1988\n\nThis is a copy of UCI
ML Wine recognition datasets.\nhttps://archive.ics.uci.edu/ml/machine-learningdatabases/wine/wine.data\n\nThe data is the results of a chemical analysis of
wines grown in the same\nregion in Italy by three different cultivators. There
are thirteen different\nmeasurements taken for different constituents found in
the three types of\nwine.\n\nOriginal Owners: \n\nForina, M. et al, PARVUS -
\nAn Extendible Package for Data Exploration, Classification and Correlation.
\nInstitute of Pharmaceutical and Food Analysis and Technologies,\nVia Brigata
Salerno, 16147 Genoa, Italy.\n\nCitation:\n\nLichman, M. (2013). UCI Machine
Learning Repository\n[https://archive.ics.uci.edu/ml]. Irvine, CA: University of
California,\nSchool of Information and Computer Science. \n\n.. topic::
References\n\n (1) S. Aeberhard, D. Coomans and O. de Vel, \n Comparison of
Classifiers in High Dimensional Settings, \n Tech. Rep. no. 92-02, (1992),
Dept. of Computer Science and Dept. of \n Mathematics and Statistics, James
Cook University of North Queensland. \n (Also submitted to Technometrics). \n\n
The data was used with many others for comparing various \n classifiers. The
classes are separable, though only RDA \n has achieved 100% correct
2
classification. \n (RDA : 100%, QDA 99.4%, LDA 98.9%, 1NN 96.1% (z-transformed
data)) \n (All results using the leave-one-out technique) \n\n (2) S.
Aeberhard, D. Coomans and O. de Vel, \n "THE CLASSIFICATION PERFORMANCE OF RDA"
\n Tech. Rep. no. 92-01, (1992), Dept. of Computer Science and Dept. of \n
Mathematics and Statistics, James Cook University of North Queensland. \n (Also
submitted to Journal of Chemometrics).\n',
'feature_names': ['alcohol',
'malic_acid',
'ash',
'alcalinity_of_ash',
'magnesium',
'total_phenols',
'flavanoids',
'nonflavanoid_phenols',
'proanthocyanins',
'color_intensity',
'hue',
'od280/od315_of_diluted_wines',
'proline']}
[ ]: X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3,␣
↪random_state=42)
[ ]: clf = GaussianNB()
[ ]: clf.fit(X_train, y_train)
[ ]: GaussianNB()
[ ]: y_pred = clf.predict(X_test)
[ ]: accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Accuracy: 1.0
