def Perceptron_Model(X_train, y_train, X_test, y_test, max_iter):
model = Perceptron(max_iter = max_iter)
classifier = model.fit(X_train, y_train)
testing_model = model.predict(X_test)
score = accuracy_score(y_test, testing_model)
cv_scores = cross_val_score(classifier, X_test, y_test, cv = 3)
print(' ')
print('===== Perceptron Model =====')
print('score:', score)
print('cross validation scores:', cv_scores)
# Visualize parameters in a table.
visualize_params(model.get_params())
# Display confusion matrix.
visualize_heatmap(y_test, testing_model, 'Perceptron Model')
return score
print('召回率：', metrics.recall_score(y_test, y_pred_class))
print('错误率：', 1 - (metrics.accuracy_score(y_test, y_pred_class)))
# In[12]:
# 训练感知机模型
from sklearn.linear_model import Perceptron
# n_iter_no_change：可以理解成梯度下降中迭代的次数
# eta0：可以理解成梯度下降中的学习率
# random_state：设置随机种子的，为了每次迭代都有相同的训练集顺序
ppn = Perceptron(n_iter_no_change=40, eta0=0.1, random_state=0)
ppn.fit(X_train, y_train)
# In[13]:
ppn.get_params()
# In[14]:
# 分类测试集，这将返回一个测试结果的数组
y_pred = ppn.predict(X_test)
# 计算模型在测试集上的准确性
metrics.accuracy_score(y_test, y_pred)
# In[15]:
from sklearn import svm
svr = svm.SVR()
svr.fit(X_train, y_train)
import numpy as np
from sklearn.datasets import load_iris
from sklearn.linear_model import Perceptron
iris = load_iris()
X = iris.data[:, (2, 3)] # petal length, petal width
y = (iris.target == 0).astype(np.int)
# Classifier based on Perceptron
model = Perceptron()
model.fit(X, y)
parameters = model.get_params()
for k, v in parameters.items():
print(k, " : ", v)
print(model.score(X, y))
y_pred = model.predict([[2.0, 0.5]])
print(y_pred)
y_pred = model.predict([[3.0, 1.5]])
print(y_pred)
[2,2],
[4,4],
[5,5]])
y = np.array([-1, -1, 1, 1])
w = np.array([0,99, 5])
Example2Perceptron = Perceptron(X,y,plot_data_lines = True, plot_errors = True)
w_ex2 = Example2Perceptron.train(w,epochs = 20)
print(w_ex2)
from sklearn.linear_model import Perceptron
sk_perceptron = Perceptron(tol=1e-5, random_state=0)
sk_perceptron.fit(X,y)
print(sk_perceptron.score(X,y))
print(sk_perceptron.get_params())
print([sk_perceptron.coef_, sk_perceptron.intercept_])
print(sk_perceptron.n_iter_)
sk_bigdata = Perceptron(max_iter = 1000, eta0=0.1, tol=1e-5, random_state=0)
sk_bigdata.fit(X_train, y_train)
print([sk_bigdata.coef_, sk_bigdata.intercept_])
print('Accuracy Training= ',sk_bigdata.score(X_train, y_train)*100)
print('Accuracy Testing= ',sk_bigdata.score(X_test, y_test)*100)
ciplakAyak = X-np.mean(X, axis = 0)
cov = np.dot(ciplakAyak.T,ciplakAyak)/X.shape[0]
print(cov)
cov_numpy = np.cov(X, rowvar = False, ddof = 0)
print(cov_numpy)
import numpy as np from sklearn.linear_model import SGDClassifier, Perceptron r''' 特点： 二分类 特征空间线性可分 ''' X = np.array([(3,3),(4,3),[1,1]]) y = np.array(['b','b','a']) module = Perceptron(n_iter=20,verbose=1) print module.get_params() module.fit(X,y) print module.predict(np.array([(0,0),(2,10),(4,5),(1,1)])) print module.get_params(deep=True)
jinputdata = np.array(jpos + jneg)
jinputlabels = jposlab + jneglab
inputdata = np.array(pos + neg)
inputlabels = poslab + neglab
with open('inputdata.pkl', 'wb') as f:
pickle.dump(inputdata, f)
with open('inputlabels.pkl', 'wb') as f:
pickle.dump(inputlabels, f)
with open('validbound.pkl', 'wb') as f:
pickle.dump(jinputdata, f)
with open('validlab.pkl', 'wb') as f:
pickle.dump(jinputlabels, f)
perceptron = Perceptron()
perceptron.fit(inputdata.reshape(-1, 1), inputlabels)
with open('perceptron-parameters.pkl', 'wb') as f:
pickle.dump(perceptron.get_params(), f)
#
score = perceptron.score(jinputdata.reshape(-1, 1), jinputlabels)
with open('perceptron-score.pkl', 'wb') as f:
pickle.dump(score, f)
with open('inputdata.pkl', 'rb') as f:
inputdata = pickle.load(f)
with open('inputlabels.pkl', 'rb') as f:
inputlabels = pickle.load(f)
perceptron = Perceptron()
perceptron.fit(inputdata.reshape(-1, 1), inputlabels)
file_path = "images_segmentation.pkl"
n_bytes = 2 ** 31
word = keys[n]
wordTest.append(word)
print(wordTest)
####################################################################################################
#Test these words for Sentiment analysis
#Training and testing accuracy is 83.14% and 81.14% respectively.
#Errors in classification at times can be observed
for i in wordTest:
predSent(i)
####################################################################################################
#Parameters of the model
clf.get_params()
#Weights associated with the model
print("Weights assigned by sklearn Perceptron: \n", clf.coef_[0])
####################################################################################################
#Mis classification errors in the test dataset
y_predict = clf.predict(X_test)
cnt = 0
for i in range(len(X_test)):
if y_predict[i] != y_test[i]:
cnt = cnt + 1
print("Total number of misclassification with Perceptron classifier: ", cnt) #221
####################################################################################################
cols = [1] # get rid of index and day, but keep month
dataSet = dataSet.drop(dataSet.columns[cols], axis=1)
dataSet['Month'] = dataSet['Month'].apply(
lambda x: math.floor(x / 4)) # sort month into 1,2,3,4 by season
msk = np.random.rand(len(dataSet)) < 0.8
trainData = dataSet[msk]
testData = dataSet[~msk]
X_train, Y_train = getXandY(trainData)
X_test, Y_test = getXandY(testData)
pla = Perceptron(max_iter=1000, random_state=np.random, warm_start=True)
print(pla.get_params())
for i in range(0, 700):
pla = pla.fit(X_train, Y_train)
score = pla.score(X_test, Y_test)
Y_pred = pla.predict(X_test)
# F1 Measure
Y_test = pd.Series(Y_test)
series = Y_test.value_counts()
null_accuracy = (series[0] / (series[0] + series[1]))
print('Null Acuuracy: ', str(null_accuracy))
cm = confusion_matrix(Y_test, Y_pred)
print(cm)
print('Confusion matrix\n\n', cm)
print('\nTrue Positives(TP) = ', cm[0, 0])
plt.show()
# Waiting to implement
pass
if __name__ == '__main__':
"""
PLA
"""
X, Y = getInputData("classification.txt")
X = np.c_[np.ones(len(X)), np.array(
X
)] # Coordinates vector of points, which is added '1' at first column.
pla = Perceptron()
pla.n_iter = 200
info = pla.get_params()
print(info)
pla = pla.fit(X, Y)
score = pla.score(X, Y)
W = pla.coef_
print('score =', score)
print('W=', W)
plot(X, Y, W[0])
"""
pocket PLA
"""
iterList = []
numList = []
best_score = 0
W = None
X, Y = getInputData1("classification.txt") #Get column 5 as Y
