def main():
# import wind data
import pandas as pd
df_wine = pd.read_csv('wine.data',header=None)
df_wine.columns=['Class label','Alcohol','Malic acid','Ash','Alcalinity of ash','Magnesium','Total phenols','Flavanoids'
,'Nonflavanoid phenols','Proanthocynins','Color intensity','Hue','OD280/OD315 of diluted wines',
'Proline']
df_wine = df_wine[df_wine['Class label'] !=1] # drop 1 class
y = df_wine['Class label'].values
X = df_wine[['Alcohol','OD280/OD315 of diluted wines']].values
# encode the data and split
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
le = LabelEncoder()
y = le.fit_transform(y)
y[y==0] = -1
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=1,stratify=y)
ada = Adaboost(N_classifiers=500,max_depth=1,learning_rate=.95,random_state=2)
ada.train(X_train,y_train)
#ada.predict(X_test)
import matplotlib.pyplot as plt
from Perceptron import plot_decision_regions
plt.figure()
plot_decision_regions(X,y,classifier=ada)
plt.title('Adaboost')
plt.xlabel('Alcohol')
plt.ylabel('OD280/OD315 of diluted wines')
plt.show()
def main():
# import data
from sklearn import datasets
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
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=1,
stratify=y)
nb = NaiveBayes()
nb.fit(X_train, y_train)
# plot decision regions
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from Perceptron import plot_decision_regions
#plt.figure()
plot_decision_regions(X, y, classifier=nb)
plt.title('Naive Bayes')
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.show()
def main():
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from Perceptron import plot_decision_regions
df = pd.read_csv('iris.data')
df.tail()
# extract setosa and versicolor
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', 0, 1)
# extract sepal length and petal length
X = df.iloc[0:100, [0, 2]].values
# standardize the features
X_std = np.copy(X)
X_std[:, 0] = (X[:, 0] - X[:, 0].mean()) / X[:, 0].std()
X_std[:, 1] = (X[:, 1] - X[:, 1].mean()) / X[:, 1].std()
# instantiate the logistic regression classifier
lda = LDA()
lda.fit(X_std, y)
# plot the decision regions
plt.figure()
plot_decision_regions(X_std, y, classifier=lda)
plt.title(lda.__class__.__name__)
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.show()
def main():
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from Perceptron import plot_decision_regions
df = pd.read_csv('iris.data')
df.tail()
# extract setosa and versicolor
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', -1, 1)
# extract sepal length and petal length
X = df.iloc[0:100, [0, 2]].values
# standardize the features
X_std = np.copy(X)
X_std[:, 0] = (X[:, 0] - X[:, 0].mean()) / X[:, 0].std()
X_std[:, 1] = (X[:, 1] - X[:, 1].mean()) / X[:, 1].std()
# instantiate the PEGASOS classifier
pegasos = PEGASOS(0.1, m=20, Ni=40, random_state=1)
pegasos.fit(X_std, y)
#print(pegasos.theta)
# plot the decision regions
plt.figure()
plot_decision_regions(X_std, y, classifier=pegasos)
plt.title(pegasos.__class__.__name__)
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.show()
def main():
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
df = pd.read_csv('iris.data')
df.tail()
# extract setosa and versicolor
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', 0, 1)
# extract sepal length and petal length
X = df.iloc[0:100, [0, 2]].values
# standardize the features
X_std = np.copy(X)
X_std[:, 0] = (X[:, 0] - X[:, 0].mean()) / X[:, 0].std()
X_std[:, 1] = (X[:, 1] - X[:, 1].mean()) / X[:, 1].std()
# instantiate the logistic regression classifier
lrc = LogisticRegression(n_iter=70, eta=0.8)
lrc.fit(X_std, y)
# visualize the results
plt.figure()
plt.plot(lrc.errors)
plt.xlabel('# of epochs')
plt.ylabel('training error')
plt.show()
# plot the decision regions
plt.figure()
plot_decision_regions(X_std, y, classifier=lrc)
plt.title('Batched Logistic Regression')
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.show()
def main():
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from Perceptron import plot_decision_regions
# import data
from sklearn import datasets
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
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=1,
stratify=y)
# test = BT_node((X,y),metric='entropy')
# test.update()
# test.info()
#
# test.lchild.update()
# test.lchild.info()
# instantiate the Decision Tree classifier
dc = Decision_Tree(impurity_fun='entropy', max_depth=3)
dc.fit(X_train, y_train, np.ones(y_train.shape) / len(y_train))
# plot the decision regions
plt.figure()
plot_decision_regions(X, y, classifier=dc)
plt.title('Decision Tree')
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.show()
ax[1].set_xlabel('Epochs')
ax[1].set_ylabel('Sum-squared-error')
ax[1].set_title('Adaline - Learning rate 0.0001')
# plt.savefig('images/02_11.png', dpi=300)
plt.show()
## データに対して標準化を行う
X_std = np.copy(X)
X_std[:, 0] = (X[:, 0] - X[:, 0].mean()) / X[:, 0].std()
X_std[:, 1] = (X[:, 1] - X[:, 1].mean()) / X[:, 1].std()
ada = AdalineGD(n_iter=15, eta=0.01)
ada.fit(X_std, y)
plot_decision_regions(X_std, y, classifier=ada)
plt.title('Adaline - Gradient Descent')
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
plt.plot(range(1, len(ada.cost_) + 1), ada.cost_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')
plt.tight_layout()
plt.show()
