FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
@author: richard lyman
'''
import numpy as np
import ocr_utils
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import train_test_split
y, X, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train = (48,49,50) , columns=(9,17),nChars=500)
def sigmoid(z):
return 1.0 / (1.0 + np.exp(-z))
z = np.arange(-7, 7, 0.1)
phi_z = sigmoid(z)
title='sigmoid'
plt.plot(z, phi_z)
plt.axvline(0.0, color='k')
plt.axhspan(0.0, 1.0, facecolor='1.0', alpha=1.0, ls='dotted')
plt.axhline(y=0.5, ls='dotted', color='k')
plt.yticks([0.0, 0.5, 1.0])
plt.ylim(-0.1, 1.1)
plt.xlabel('z')
plt.ylabel('$\phi (z)$')
def get_params(self, deep=True):
""" Get classifier parameter names for GridSearch"""
if not deep:
return super(MajorityVoteClassifier, self).get_params(deep=False)
else:
out = self.named_classifiers.copy()
for name, step in six.iteritems(self.named_classifiers):
for key, value in six.iteritems(step.get_params(deep=True)):
out['%s__%s' % (name, key)] = value
return out
charsToTrain = (48, 51)
nChars = 500
y, X, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train=charsToTrain,
columns=(9, 17),
nChars=nChars)
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test =\
train_test_split(X, y,
test_size=0.5,
random_state=1)
clf1 = LogisticRegression(penalty='l2', C=0.001, random_state=0)
clf2 = DecisionTreeClassifier(max_depth=1, criterion='entropy', random_state=0)
SOFTWARE.
@author: richard lyman
'''
from sklearn.ensemble import AdaBoostClassifier
import ocr_utils
from sklearn.cross_validation import train_test_split
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
charsToTrain=(48,51)
nChars = 1000
y, X, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train = charsToTrain , columns=(9,17), nChars=nChars)
le = LabelEncoder()
y = le.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=0.40,random_state=1)
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
tree = DecisionTreeClassifier(criterion='entropy',
max_depth=1)
ada = AdaBoostClassifier(base_estimator=tree,
n_estimators=500,
learning_rate=0.1,
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
@author: richard lyman
'''
import numpy as np
import ocr_utils
from sklearn.preprocessing import StandardScaler
y_train, X_train, y_test, X_test, labels = ocr_utils.load_E13B(
chars_to_train=(48, 49, 50),
columns=(9, 17),
test_size=0.3,
nChars=300,
random_state=0)
sc = StandardScaler()
sc.fit(X_train)
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))
y_combined = np.hstack((y_train, y_test))
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=5, p=2, metric='minkowski')
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
@author: richard lyman
'''
import numpy as np
import ocr_utils
import matplotlib.pyplot as plt
y, X, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train=(48, 49, 50),
columns=range(0, 20),
nChars=1000,
random_state=0)
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
from sklearn.preprocessing import StandardScaler
stdsc = StandardScaler()
X_train_std = stdsc.fit_transform(X_train)
X_test_std = stdsc.transform(X_test)
sc = StandardScaler()
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
@author: richard lyman
'''
import numpy as np
import ocr_utils
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.cross_validation import cross_val_score
from sklearn.grid_search import GridSearchCV
from sklearn.svm import SVC
if __name__ == '__main__':
y_train, X_train, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train = (48,51) , test_size=0.3, columns=(9,17), random_state=0)
pipe_svc = Pipeline([('scl', StandardScaler()),
('clf', SVC(random_state=1))])
c_gamma_range = [0.01, 0.1, 1.0, 10.0]
param_grid = [{'clf__C': c_gamma_range,
'clf__kernel': ['linear']},
{'clf__C': c_gamma_range,
'clf__gamma': c_gamma_range,
'clf__kernel': ['rbf'],}]
gs = GridSearchCV(estimator=pipe_svc,
param_grid=param_grid,
from scipy import interp
import matplotlib.pyplot as plt
import numpy as np
import ocr_utils
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.cross_validation import StratifiedKFold
from sklearn.decomposition import PCA
from sklearn.cross_validation import train_test_split
from sklearn.metrics import make_scorer, precision_score, roc_curve, auc
if __name__ == '__main__':
y, X, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train=(48, 51),
columns=(9, 17),
random_state=0)
from sklearn.preprocessing import LabelEncoder
# the ROC is for data with a binary outcome. Change the ASCII characters to 0,1
le = LabelEncoder()
y = le.fit_transform(y)
le.transform((48, 51))
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.20,
random_state=1)
pipe_lr = Pipeline([('scl', StandardScaler()),
('pca', PCA(n_components=2)),
import ocr_utils
import numpy as np
from numpy.random import seed
import matplotlib.pyplot as plt
#############################################################################
# read images and scatter plot
# retrieve 100 sets of target numbers and column sums
# y: the ascii characters 48 and 49 ('0', '1')
# X: the sum of the vertical pixels in the rows in horizontal columns 9 and 17
ascii_characters_to_train = (48, 51)
columnsXY = (9, 17)
nchars = 500
y, X, y_test, X_test, labels = ocr_utils.load_E13B(
chars_to_train=ascii_characters_to_train, columns=columnsXY, nChars=120)
y = np.where(y == ascii_characters_to_train[1], -1, 1)
#############################################################################
# AdalineSGD from Python Machine Learning
class AdalineSGD(object):
"""ADAptive LInear NEuron classifier.
Parameters
------------
eta : float
Learning rate (between 0.0 and 1.0)
n_iter : int
Passes over the training dataset.
# from sklearn.metrics import make_scorer,roc_curve, auc
from scipy import interp
import matplotlib.pyplot as plt
import numpy as np
import ocr_utils
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.cross_validation import StratifiedKFold
from sklearn.decomposition import PCA
from sklearn.cross_validation import train_test_split
from sklearn.metrics import make_scorer,precision_score,roc_curve, auc
if __name__ == '__main__':
y, X, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train = (48,51) , columns=(9,17), random_state=0)
from sklearn.preprocessing import LabelEncoder
# the ROC is for data with a binary outcome. Change the ASCII characters to 0,1
le = LabelEncoder()
y = le.fit_transform(y)
le.transform((48,51))
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=1)
pipe_lr = Pipeline([('scl', StandardScaler()),
('pca', PCA(n_components=2)),
('clf', LogisticRegression(penalty='l2',random_state=0,C=100.0))])
# X_train2 = X_train[:, [4, 14]]
X_train2 = X_train
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
@author: richard lyman
'''
import numpy as np
import ocr_utils
import matplotlib.pyplot as plt
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import train_test_split
y, X, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train=(48, 49, 50),
columns=(9, 17),
nChars=500)
def sigmoid(z):
return 1.0 / (1.0 + np.exp(-z))
z = np.arange(-7, 7, 0.1)
phi_z = sigmoid(z)
title = 'sigmoid'
plt.plot(z, phi_z)
plt.axvline(0.0, color='k')
plt.axhspan(0.0, 1.0, facecolor='1.0', alpha=1.0, ls='dotted')
plt.axhline(y=0.5, ls='dotted', color='k')
plt.yticks([0.0, 0.5, 1.0])
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
@author: richard lyman
'''
import numpy as np
import ocr_utils
import matplotlib.pyplot as plt
y, X, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train = (48,49,50) , columns=range(0,20), nChars=1000, random_state=0)
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.3, random_state=0)
from sklearn.preprocessing import StandardScaler
stdsc = StandardScaler()
X_train_std = stdsc.fit_transform(X_train)
X_test_std = stdsc.transform(X_test)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
@author: richard lyman
'''
import ocr_utils
import numpy as np
#############################################################################
# read images and scatter plot
# retrieve 400 sets of target numbers and column sums
# y: the ascii characters 48 and 49 ('0', '1')
# X: the sum of the vertical pixels in the rows in horizontal columns 9 and 17
ascii_characters_to_train = (48,49)
columnsXY = (9,17)
y, X, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train=ascii_characters_to_train , columns=columnsXY,nChars=256)
# put the ASCII equivalent of the unique characters in y into the legend of the plot
legend=[]
for ys in np.unique(y):
legend.append('{} \'{}\''.format(ys, chr(ys)))
ocr_utils.scatter_plot(X=X,
y=y,
legend_entries=legend,
axis_labels = ['column {} sum'.format(columnsXY[i]) for i in range(len(columnsXY))],
title='E13B sum of columns')
#############################################################################
# read and show character images for '0', and '1'
# select the digits in columnsXY in the E13B font
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. @author: richard lyman ''' import numpy as np import ocr_utils columnsXY = range(0,20) y_train, X_train, y_test, X_test, labels = ocr_utils.load_E13B(chars_to_train = (48,49,50) , columns=columnsXY , test_size=0.3, nChars=1000, random_state=0) from sklearn.preprocessing import StandardScaler stdsc = StandardScaler() X_train_std = stdsc.fit_transform(X_train) X_test_std = stdsc.transform(X_test) sc = StandardScaler() sc.fit(X_train) 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)) y_combined = np.hstack((y_train, y_test)) from sklearn.linear_model import LogisticRegression