def fit(self , X , y):
X_train , X_test , y_train , y_test = train_test_split(X , y , test_size = self.test_size ,
random_state = self.random_state);
# m行n列なのでnが返ってくる。つまり特徴量の次元
dim = X_train.shape[1];
self.indices_ = tuple(range(dim));
self.subsets_ = [self.indices_];
score = self._calc_score(X_train , y_train , X_test , y_test , self.indices_);
self.scores_ = [score];
while dim > self.k_features:
scores = [];
subsets = [];
# indices_からrの組み合わせのいてれーた
for p in combinations(self.indices_ , r=dim-1):
score = self._calc_score(X_train , y_train , X_test , y_test , p);
scores.append(score);
subsets.append(p);
best = np.argmax(scores);
self.indices_ = subsets[best];
self.subsets_.append(self.indices_);
dim -= 1;
self.scores_.append(scores[best]);
self.k_score_ = self.scores_[-1];
def fit(self, X, y):
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=self.test_size,
random_state=self.random_state)
dim = X_train.shape[1]
self.indices_ = tuple(range(dim))
self.subsets_ = [self.indices_]
score = self._calc_score(X_train, y_train,
X_test, y_test, self.indices_)
self.scores_ = [score]
while dim > self.k_features:
scores = []
subsets = []
for p in combinations(self.indices_, r=dim - 1):
score = self._calc_score(X_train, y_train,
X_test, y_test, p)
scores.append(score)
subsets.append(p)
best = np.argmax(scores)
self.indices_ = subsets[best]
self.subsets_.append(self.indices_)
dim -= 1
self.scores_.append(scores[best])
self.k_score_ = self.scores_[-1]
return self
def fit(self, X, y):
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=self.test_size,
random_state=self.random_state)
dim = X_train.shape[1]
self.indices_ = tuple(range(dim))
self.subsets_ = [self.indices_]
score = self._calc_score(X_train, y_train,
X_test, y_test, self.indices_)
self.scores_ = [score]
while dim > self.k_features:
scores = []
subsets = []
for p in combinations(self.indices_, r=dim - 1):
score = self._calc_score(X_train, y_train,
X_test, y_test, p)
scores.append(score)
subsets.append(p)
best = np.argmax(scores)
self.indices_ = subsets[best]
self.subsets_.append(self.indices_)
dim -= 1
self.scores_.append(scores[best])
self.k_score_ = self.scores_[-1]
return self
def divide_data(self, test_size=0.3, random_state=1):
from distutils.version import LooseVersion as Version
from sklearn import __version__ as sklearn_version
if Version(sklearn_version) < '0.18':
from sklearn.grid_search import train_test_split
else:
from sklearn.model_selection import train_test_split
self._X_train, self._X_test, self._y_train, self._y_test = train_test_split(self._X, self._y, test_size=test_size, random_state=random_state)
self.standarize()
def load_iris(test_size=0.3, random_state=0):
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=test_size, random_state=random_state)
sc = StandardScaler()
sc.fit(X_train)
# 平均0, 分散1に標準化
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
X_combined_std = np.vstack((X_train_std, X_test_std)) # 縦に連結
y_combined = np.hstack((y_train, y_test)) # 横に連結
return [
X_combined_std, X_train_std, X_train, X_test_std, X_test, y_combined,
y_train, y_test
]
df_wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash',
'Alcalinity of ash', 'Magnesium', 'Total phenols',
'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins',
'Color intensity', 'Hue', 'OD280/OD315 of diluted wines',
'Proline']
print('Class labels', np.unique(df_wine['Class label']))
print('\nWine data excerpt:\n\n', df_wine.head())
X, y = df_wine.iloc[:, 1:].values, df_wine.iloc[:, 0].values
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.3, random_state=0)
#############################################################################
print(50 * '=')
print('Section: Bringing features onto the same scale')
print(50 * '-')
mms = MinMaxScaler()
X_train_norm = mms.fit_transform(X_train)
X_test_norm = mms.transform(X_test)
stdsc = StandardScaler()
X_train_std = stdsc.fit_transform(X_train)
X_test_std = stdsc.transform(X_test)
from sklearn.grid_search import train_test_split
else:
from sklearn.model_selection import train_test_split
#############################################################################
print(50 * '=')
print('Section: First steps with scikit-learn')
print(50 * '-')
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
print('Class labels:', np.unique(y))
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
#############################################################################
print(50 * '=')
print('Section: Training a perceptron via scikit-learn')
print(50 * '-')
ppn = Perceptron(n_iter=40, eta0=0.1, random_state=0)
ppn.fit(X_train_std, y_train)
print('Y array shape', y_test.shape)
activity = 7#ラベルの個数
features = 35
featureReductionComponent=15
#※事前にデータセットのラベルが右端に入力されていること
bunkatu=5#k分割の分割数
AccuracyPCA, AccuracySTD =0, 0
a = np.loadtxt('Feature/Features.csv', delimiter=',', dtype='float')
X=a[:,0:features]
y=a[:,features:features+1]
#ラベルをintに変換し、配列を1次元に変換(必須)
y=np.array(y, dtype=int)
y=y.reshape(-1,)
X_train,X_test,y_train,y_test= train_test_split(X, y, test_size=0.2, stratify=y)
#※X_train,X_testはスケーリングしていないため、必ずStandardScaler()にかける事が必要
print(X_train.shape[0],X_train.shape[1])
print(X_test.shape[0],X_test.shape[1])
#############################################################################
sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)
X_test_std = sc.transform(X_test)
#print (X_train_std)
#############################################################################
print(50 * '=')
print('Section: Total and explained variance')
'machine-learning-databases/wine/wine.data',
header=None)
df_wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash',
'Alcalinity of ash', 'Magnesium', 'Total phenols',
'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins',
'Color intensity', 'Hue',
'OD280/OD315 of diluted wines', 'Proline']
print('Wine data excerpt:\n\n:', df_wine.head())
X, y = df_wine.iloc[:, 1:].values, df_wine.iloc[:, 0].values
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.3, random_state=0)
sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)
X_test_std = sc.transform(X_test)
cov_mat = np.cov(X_train_std.T)
eigen_vals, eigen_vecs = np.linalg.eig(cov_mat)
print('\nEigenvalues \n%s' % eigen_vals)
#############################################################################
print(50 * '=')
print('Section: Total and explained variance')
print(50 * '-')
if Version(sklearn_version) < '0.18':
from sklearn.grid_search import train_test_split
else:
from sklearn.model_selection import train_test_split
#############################################################################
print(50 * '=')
print('Section: First steps with scikit-learn')
print(50 * '-')
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
print('Class labels:', np.unique(y))
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.3, random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
#############################################################################
print(50 * '=')
print('Section: Training a perceptron via scikit-learn')
print(50 * '-')
ppn = Perceptron(n_iter=40, eta0=0.1, random_state=0)
ppn.fit(X_train_std, y_train)
print('Y array shape', y_test.shape)
print('Breast Cancer dataset excerpt:\n\n')
print(df.head())
print("Breast Cancer dataset dimensions: \n\n")
print(df.shape)
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
y_enc = le.transform(["M", "B"])
print("Label encoding example, le.transform(['M', 'B'])")
print(le.transform(["M", "B"]))
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.20, random_state=1)
print(50 * "=")
print("Section: Combining transformers and estimators in a pipeline")
print(50 * "-")
pipe_lr = Pipeline([("scl", StandardScaler()), ("pca", PCA(n_components=2)),
("clf", LogisticRegression(random_state=1))])
pipe_lr.fit(X_train, y_train)
print("Test Accuracy: %.3f" % pipe_lr.score(X_test, y_test))
y_pred = pipe_lr.predict(X_test)
print(50 * "=")
print("Section: K-fold cross-validation")
print(50 * "-")
print('Breast Cancer dataset excerpt:\n\n')
print(df.head())
print('Breast Cancer dataset dimensions:\n\n')
print(df.shape)
X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
y_enc = le.transform(['M', 'B'])
print("Label encoding example, le.transform(['M', 'B'])")
print(le.transform(['M', 'B']))
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.20, random_state=1)
#############################################################################
print(50 * '=')
print('Section: Combining transformers and estimators in a pipeline')
print(50 * '-')
pipe_lr = Pipeline([('scl', StandardScaler()),
('pca', PCA(n_components=2)),
('clf', LogisticRegression(random_state=1))])
pipe_lr.fit(X_train, y_train)
print('Test Accuracy: %.3f' % pipe_lr.score(X_test, y_test))
y_pred = pipe_lr.predict(X_test)
def do(self):
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
print('Etykiety klas:', np.unique(y))
if Version(sklearn_version) < '0.18':
from sklearn.grid_search import train_test_split
else:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
ppn = Perceptron(n_iter_no_change=40, eta0=0.1, random_state=0)
ppn.fit(X_train_std, y_train)
y_test.shape
y_pred = ppn.predict(X_test_std)
print('Nieprawidłowo sklasyfikowane próbki: %d' %
(y_test != y_pred).sum())
print('Dokładność: %.2f' % accuracy_score(y_test, y_pred))
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
# plot_decision_regions(X=X_combined_std, y=y_combined,
# classifier=ppn, test_idx=range(105, 150))
# plt.xlabel('Długość płatka [standaryzowana]')
# plt.ylabel('Szerokość płatka [standaryzowana]')
# plt.legend(loc='upper left')
# plt.tight_layout()
#plt.savefig('./rysunki/03_01.png', dpi=300)
#plt.show()
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression(C=100.0, random_state=0)
lr.fit(X_train_std, y_train)
# plot_decision_regions(X_combined_std, y_combined,
# classifier=lr, test_idx=range(105, 150))
# plt.xlabel('Długość płatka [standaryzowana]')
# plt.ylabel('Szerokość płatka [standaryzowana]')
# plt.legend(loc='upper left')
# plt.tight_layout()
# #plt.savefig('./rysunki/03_05.png', dpi=300)
# plt.show()
from sklearn.svm import SVC
svm = SVC(kernel='linear', C=1.0, random_state=0)
svm.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std,
y_combined,
classifier=svm,
test_idx=range(105, 150))
plt.xlabel('Długość płatka [standaryzowana]')
plt.ylabel('Szerokość płatka [standaryzowana]')
plt.legend(loc='upper left')
plt.tight_layout()
#plt.savefig('./rysunki/03_10.png', dpi=300)
plt.show()
pass