from sklearn.linear_model import PassiveAggressiveRegressor
from sklearn.datasets import make_regression
from importation_pandas import importcsv
from sklearn.model_selection import train_test_split
setX, setY = importcsv()
X_train, X_test, y_train, y_test = train_test_split(setX, setY, test_size=0.01, random_state=42)
regr = PassiveAggressiveRegressor(max_iter=100, random_state=0,tol=1e-3)
regr.fit(X_train, y_train)
#PassiveAggressiveRegressor(C=1.0, average=False, early_stopping=False,epsilon=0.1, fit_intercept=True, loss='epsilon_insensitive', max_iter=100, n_iter_no_change=5, random_state=0,shuffle=True, tol=0.001, validation_fraction=0.1,verbose=0, warm_start=False)
print(regr.score(X_test, y_test))
regr.densify()
pred = regr.predict(X_test)
result=[]
for k in range(len(pred)):
if pred[k]<0.1:
value = 0
else:
value =1
if value == y_test[k]:
result.append('O')
else:
暂时未知
对于算法的具体过程还不是很清楚，所以暂时作为一个黑箱吧
'''
rg = PassiveAggressiveRegressor(C=1.0,
fit_intercept=True,
n_iter=5,
shuffle=True,
verbose=0,
loss='epsilon_insensitive',
epsilon=0.1,
random_state=None,
warm_start=False)
rg.fit(X_train, Y_train)
rg.partial_fit(X_train, Y_train) # 增量学习
Y_pre = rg.predict(X_test)
rg.score(X_test, Y_test)
rg.coef_
rg.intercept_
'''
C 正则化项系数
fit_intercept 是否计算截距
n_iter 迭代次数
shuffle 是否洗牌
verbose 哈
loss 损失函数
epsilon 阈值
random_state 随机器
warm_start=False 新的迭代开始后，是否用上一次的最后结果作为初始化
'''
from sklearn.linear_model import PassiveAggressiveClassifier, PassiveAggressiveRegressor
pac = PassiveAggressiveClassifier()
pac2 = PassiveAggressiveClassifier()
par = PassiveAggressiveRegressor()
par2 = PassiveAggressiveRegressor()
# Now fit
pac.fit(train_bow, train_ratings)
par.fit(train_bow, train_ratings)
pac2.fit(train_bigram, train_ratings)
par2.fit(train_bigram, train_ratings)
# Record and desplay results
pac_bow_train = pac.score(train_bow, train_ratings)
pac_bow_test = pac.score(test_bow, test_ratings)
pac_bigram_train = pac2.score(train_bigram, train_ratings)
pac_bigram_test = pac2.score(test_bigram, test_ratings)
par_bow_train = par.score(train_bow, train_ratings)
par_bow_test = par.score(test_bow, test_ratings)
par_bigram_train = par2.score(train_bigram, train_ratings)
par_bigram_test = par2.score(test_bigram, test_ratings)
# pac = par = pac2 = par2 = 1
del pac, par, pac2, par2
# Results
print('Passive Aggressive Classifier')
print('BOW Results: ' + per(pac_bow_train) + ' training accuracy, ' +
per(pac_bow_test) + ' testing accuracy')
print('Bigram Results: ' + per(pac_bigram_train) + ' training accuracy, ' +
per(pac_bigram_test) + ' testing accuracy')
print('Passive Aggressive Regressor')
print('BOW Results: ' + per(par_bow_train) + ' training accuracy, ' +
per(par_bow_test) + ' testing accuracy')
print('Bigram Results: ' + per(par_bigram_test) + ' training accuracy, ' +
#Perceptron Model
from sklearn.linear_model import PassiveAggressiveRegressor
regr = PassiveAggressiveRegressor(random_state=0,
C=1.0,
average=False,
epsilon=0.1,
fit_intercept=True,
loss='epsilon_insensitive',
max_iter=None,
n_iter=None,
shuffle=True,
tol=None,
verbose=0,
warm_start=False)
regr.fit(X, y)
print(regr.score(x_train, y_train)) #Train Error: 32.86
#PassiveAggressiveRegressor()
predictions = regr.predict(x_test)
for i, prediction in enumerate(predictions):
print 'Predicted: %s' % (prediction)
############################################################################################################
#Support Vector Machine Regression
from sklearn import svm
clf1 = svm.SVR(C=1.0,
cache_size=200,
coef0=0.0,
degree=8,
epsilon=0.1,
gamma='auto',
