def main():
data = DataManager.load_data("data/data_banknote_authentication.txt")
# remove break lines
data = np.array([item.strip("\n") for item in data])
data = np.array([item.split(',') for item in data])
data = data.astype(np.float)
# 0 for authentic and 1 for inauthentic
df = pd.DataFrame(data)
df[4] = df[4].astype(int)
authentic = df[df[4] == 0]
inauthentic = df[df[4] == 1]
X = df.iloc[np.r_[0:200, 1100:1300], [0, 3]].values
y = [0 if x < 200 else 1 for x in range(400)]
plt.scatter(X[:200, 0],
X[:200, 1],
color='red',
marker='o',
label='authentic')
plt.scatter(X[200:400, 0],
X[200:400, 1],
color='blue',
marker='x',
label='inauthentic')
plt.xlabel('variance of Wavelet Transformed image')
plt.ylabel('entropy of image')
plt.legend(loc='upper left')
plt.show()
ppn = Perceptron(eta=0.1, n_iter=10)
ppn.fit(X, y)
plot_decision_regions(X, y, clasiifier=ppn)
plt.xlabel('variance of Wavelet Transformed image')
plt.ylabel('entropy of image')
plt.legend(loc='upper left')
plt.show()
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=10, eta=0.01)
ada.fit(X_std, y)
plot_decision_regions(X_std, y, clasiifier=ada)
plt.title('Adaline - gradient descent')
plt.xlabel('variance of Wavelet Transformed image')
plt.ylabel('entropy of image')
plt.legend(loc='upper left')
plt.show()
def test_tashizan(self):
"""test method for adaline
"""
# 初期化
expected = np.array([1.59872116e-16, -1.26256159e-01, 1.10479201e+00])
df = pd.read_csv('../tests/data/iris.data', header=None)
y = df.iloc[0:100, 4].values
y = np.where(y == 'Iris-setosa', -1, 1)
X = df.iloc[0:100, [0, 2]].values
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()
# テスト実行
ad = AdalineGD(n_iter=15, eta=0.01)
ad.fit(X_std, y)
actual = ad.w_
# Assert
np.testing.assert_array_almost_equal(expected, actual, 2)
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
# plot class samples
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0],
y=X[y == cl, 1],
alpha=0.8,
c=cmap(idx),
marker=markers[idx],
label=cl)
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.show()
plt.plot(range(1, len(ada.cost_) + 1), ada.cost_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')
plt.show()
def Test():
# get data
ml_data = Data()
ml_data.init_data()
ml_data.view_initial_data()
# test perceptron
ppn = Perceptron(eta=0.1, n_iter=10)
ppn.fit(ml_data.X, ml_data.y)
plt.plot(range(1, len(ppn.errors_) + 1), ppn.errors_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Number of updates')
plt.show()
plot = ml_data.plot_decision_regions(ml_data.X, ml_data.y, classifier=ppn)
plot.xlabel('sepal length')
plot.ylabel('petal length')
plot.legend(loc='upper left')
plot.show()
# Adaline implementation
fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(10, 4))
ada1 = AdalineGD(n_iter=10, eta=0.1).fit(ml_data.X, ml_data.y)
ax[0].plot(range(1, len(ada1.cost_) + 1), np.log10(ada1.cost_), marker='o')
ax[0].set_xlabel('Epoch')
ax[0].set_ylabel('log(Sum Squared error)')
ax[0].set_title('Adaline - Learning rate 0.01')
ada2 = AdalineGD(n_iter=10, eta=0.0001).fit(ml_data.X, ml_data.y)
ax[1].plot(range(1, len(ada2.cost_) + 1), ada2.cost_, marker='o')
ax[1].set_xlabel('Epoch')
ax[1].set_ylabel('Sum Squared error')
ax[1].set_title('Adaline - Learning rate 0.0001')
plt.show()
# Adaline with feature scaling
ml_data.standard_scaled()
ada = AdalineGD(n_iter=10, eta=0.01)
ada.fit(ml_data.X_std, ml_data.y)
plot = ml_data.plot_decision_regions(ml_data.X_std,
ml_data.y,
classifier=ada)
plot.title('Adaline - Gradinet Descent')
plot.xlabel('sepal length')
plot.ylabel('petal length')
plot.legend(loc='upper left')
plot.tight_layout()
plot.show()
plt.plot(range(1, len(ada.cost_) + 1), ada.cost_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Sum Squared error')
plt.show()
# Adaline with stochastic gradient
ada3 = AdalineGD(n_iter=15, eta=0.01, random_state=1)
ada3.fit(ml_data.X_std, ml_data.y)
plot = ml_data.plot_decision_regions(ml_data.X_std,
ml_data.y,
classifier=ada3)
plot.title('Adaline - Stochastic Gradient Descent')
plot.xlabel('sepal length')
plot.ylabel('petal length')
plot.legend(loc='upper left')
plot.show()
plt.plot(range(1, len(ada3.cost_) + 1), ada3.cost_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Average cost')
plt.show()
#ada1 = AdalineGD(n_iter=10, eta=0.01).fit(x,y)
#ax[0].plot(range(1, len(ada1.cost_)+1),np.log10(ada1.cost_), marker = 'o')
# ax[0].set_xlabel('Epochs')
# ax[0].set_ylabel('log(Sum-squared-error)')
#ax[0].set_title('Adaline - Learning Rate 0.01')
#ada2 = AdalineGD(n_iter=10, eta=0.0001).fit(x,y)
#ax[1].plot(range(1, len(ada2.cost_)+1), ada2.cost_, marker='o')
# ax[1].set_xlabel('Epochs')
# ax[1].set_ylabel('Sum-squared-error')
#ax[1].set_title('Adaline - Learning rate 0.0001')
# standardizing instead
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.show()
plt.plot(range(1, len(ada.cost_) + 1), ada.cost_, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')
plt.show()
# only select the setosa and versicolor species
data = data.loc[(data["Class label"] == "Iris-setosa") |
(data["Class label"] == "Iris-versicolor")]
# convert species labels to integers, -1 for setosa and 1 for versicolor
data["Class label"] = np.where(data["Class label"]=="Iris-setosa", -1, 1)
# split data into feature matrix (only "Sepal length" and "Petal length" are
# used) and target vector
X = data[["Sepal length", "Petal length"]]
y = data["Class label"]
# create a plot of the cost function against the iteration number for learning
# rates of 0.01 and 0.0001
iris_ada1 = AdalineGD(n_iterations=10, eta=0.01)
iris_ada1.fit(X.values, y.values)
iris_ada2 = AdalineGD(n_iterations=10, eta=0.0001)
iris_ada2.fit(X.values, y.values)
fig1, ax = plt.subplots(nrows=1, ncols=2, figsize=(10, 6))
ax[0].plot(range(1, iris_ada1.n_iterations + 1), np.log10(iris_ada1.cost_),
marker="o")
ax[0].set(xlabel="Iterations", ylabel="log(SSE)",
title="Adaline - Learning rate 0.01")
ax[1].plot(range(1, iris_ada2.n_iterations + 1), iris_ada2.cost_,
marker="o")
ax[1].set(xlabel="Iterations", ylabel="SSE",
title="Adaline - Learning rate 0.0001")
import numpy as np
from adaline import AdalineGD
agd = AdalineGD(eta=0.001)
X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9], [0, 1, 1], [7, 8, 8], [7, 7,
7]])
Y = np.array([-1, -1, 1, -1, 1, 1])
agd.fit(X, Y)
print(agd.predict(X))
import numpy as np
from mlxtend.plotting import plot_decision_regions
from adaline import AdalineGD
dataset = pd.read_csv('iris.csv', header=None)
# print (dataset.tail())
output = dataset.iloc[0:100, 4].values
Y = np.where(output == 'Iris-setosa', -1, 1)
X = dataset.iloc[0:100, [0, 2]].values
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()
obj = AdalineGD(epochs=15, learning_rate=0.01)
obj.fit(X_std, Y)
plot_decision_regions(X_std, Y, clf=obj)
plt.title('Adaline - Gradient Descent')
plt.xlabel('sepal length [standardized]')
plt.ylabel('petal length [standardized]')
plt.legend(loc='upper left')
plt.show()
plt.plot(range(1, len(obj.cost_list) + 1), obj.cost_list, marker='o')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')
plt.show()
ada2 = AdalineGD(n_iter=10, eta=0.0001).fit(X, y)
ax[1].plot(range(1, len(ada2.cost_) + 1), ada2.cost_, marker='o')
ax[1].set_xlabel('Epochs')
ax[1].set_ylabel('Sum-squared-error')
ax[1].set_title('Adaline - Learning rate 0.0001')
plt.show()
# データのスケーリング(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()
# 再度学習率(0.01)で実行
ada_gd = AdalineGD(n_iter=15, eta=0.01)
ada_gd.fit(X_std, y)
# 境界領域のプロット
plot_dicision_regions(X_std, y, classifier=ada_gd)
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()
# エポック数とコストの関係
plt.plot(range(1, len(ada_gd.cost_) + 1), ada_gd.cost_, marker='o')
plt.title('Adaline - Learning2 rate 0.01')
plt.xlabel('Epochs')
plt.ylabel('Sum-squared-error')