HW2: SIDEQUEST -- Classification

In [7]:
import sklearn
from sklearn import datasets
In [8]:
wine = datasets.load_wine()
In [9]:
wine.feature_names
Out[9]:
['alcohol',
 'malic_acid',
 'ash',
 'alcalinity_of_ash',
 'magnesium',
 'total_phenols',
 'flavanoids',
 'nonflavanoid_phenols',
 'proanthocyanins',
 'color_intensity',
 'hue',
 'od280/od315_of_diluted_wines',
 'proline']
In [10]:
type(wine)
Out[10]:
sklearn.utils.Bunch
In [12]:
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(wine.data, wine.target, test_size=0.3, random_state = 109)
In [23]:
wine.data[1]
Out[23]:
array([1.32e+01, 1.78e+00, 2.14e+00, 1.12e+01, 1.00e+02, 2.65e+00,
       2.76e+00, 2.60e-01, 1.28e+00, 4.38e+00, 1.05e+00, 3.40e+00,
       1.05e+03])
In [14]:
wine.target
Out[14]:
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, 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])
In [16]:
from sklearn.naive_bayes import GaussianNB
In [17]:
gnb = GaussianNB()
In [18]:
gnb.fit(x_train, y_train)
Out[18]:
GaussianNB(priors=None, var_smoothing=1e-09)
In [19]:
y_pred = gnb.predict(x_test)
In [20]:
from sklearn import metrics
In [21]:
print("Accuracy:", metrics.accuracy_score(y_test, y_pred))

Accuracy: 0.9074074074074074
In [ ]: