def classify():
for i in range(0, 200):
start = time.time()
if i == 0:
iter_times = 1
else:
iter_times = i * 50
print 'iter_times{0}'.format(str(iter_times))
classifier = Perceptron(n_iter=iter_times, eta0=0.001)
classifier.fit_transform(data, label)
predictions = classifier.predict(test)
reportname = './report/{0}.txt'.format('report_{0}'.format(
str(iter_times)))
report = open(reportname, 'w')
r = classification_report(testLabel, predictions)
fpr, tpr, thresholds = roc_curve(testLabel, predictions, pos_label=2)
report.write(r)
end = time.time()
report.write('time{0}'.format(str(end - start)))
report.close()
from sklearn.linear_model import Perceptron
categories = ['rec.sport.hockey', 'rec.sport.baseball', 'rec.autos']
newsgroups_train = fetch_20newsgroups(subset='train',
categories=categories,
remove=('headers', 'footers', 'quotes'))
newsgroups_test = fetch_20newsgroups(subset='test',
categories=categories,
remove=('headers', 'footers', 'quotes'))
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(newsgroups_train.data)
X_test = vectorizer.transform(newsgroups_test.data)
classifier = Perceptron(n_iter=100, eta0=0.1)
classifier.fit_transform(X_train, newsgroups_train.target)
predictions = classifier.predict(X_test)
print classification_report(newsgroups_test.target, predictions)
################# Example #################
"""
"""
"""
sudo apt-get remove libopenblas-base
openblas (required for video contextualization)
is incompatible with scipy.
"""
import numpy as np
import matplotlib
matplotlib.use('Qt4Agg')
# coding=utf-8
from sklearn.metrics import f1_score, classification_report
from sklearn.linear_model import Perceptron
import numpy as np
import time, os
from sklearn.metrics import roc_curve
from matplotlib import pyplot as plt
import numpy as np
data = np.loadtxt('./data/TrainSamples.csv', delimiter=",")
print data
label = np.loadtxt('./data/TrainLabels.csv', delimiter=",")
print label
test = np.loadtxt('./data/TestSamples1.csv', delimiter=',')
testLabel = np.loadtxt('./data/TestLabels1.csv', delimiter=',')
print 'iter_times{0}'.format(str(1000))
start = time.time()
classifier = Perceptron(n_iter=1000, eta0=0.001)
classifier.fit_transform(data, label)
predictions = classifier.predict(test)
reportname = 'Perceptron.txt'
report = open(reportname, 'w')
r = classification_report(testLabel, predictions)
fpr, tpr, thresholds = roc_curve(testLabel, predictions, pos_label=2)
report.write(r)
end = time.time()
report.write('time{0}'.format(str(end - start)))
report.close()
#df = df._get_numeric_data()
#msk = np.random.rand(len(df)) < 0.8
train = df
train_target = train['Survived']
train = train.drop('Survived', axis=1)
#print train
test = df_test
#test_target = test['Survived']
#test = test.drop('Survived',axis=1)
print len(train)
print len(test)
#print newsgroups_train.filenames
#print newsgroups_test.filenames.shape
#print vectorizer
#print X_train
classifier = Perceptron(n_iter=5000, eta0=0.3)
classifier.fit_transform(train, train_target)
predictions = classifier.predict(test)
#print predictions
#print classification_report(test_target, predictions)
print predictions
np.savetxt('test_final.csv', predictions)
#cm = confusion_matrix(test_target,predictions)
#print cm
#print classifier.score(train,train_target)
plt.xlabel('Proportion of the day spent sleeping')
plt.ylabel('Proportion of the day spent being grumpy')
plt.title('Kittens and Adult Cats')
plt.show()
#Perceptron
categories = ['rec.sport.hockey', 'rec.sport.baseball', 'rec.autos']
newsgroups_train = fetch_20newsgroups(subset='train', categories=categories, remove=('headers', 'footers', 'quotes'))
newsgroups_test = fetch_20newsgroups(subset='test', categories=categories, remove=('headers', 'footers', 'quotes'))
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(newsgroups_train.data)
X_test = vectorizer.transform(newsgroups_test.data)
classifier = Perceptron(n_iter=100, eta0=0.1)
classifier.fit_transform(X_train, newsgroups_train.target)
predictions = classifier.predict(X_test)
print classification_report(newsgroups_test.target, predictions)
"""
Output seen
precision recall f1-score support
0 0.89 0.87 0.88 396
1 0.87 0.78 0.82 397
2 0.79 0.88 0.83 399
avg / total 0.85 0.85 0.85 1192
"""
#plot the output
import matplotlib
#df = df._get_numeric_data()
#msk = np.random.rand(len(df)) < 0.8
train = df
train_target = train['Survived']
train = train.drop('Survived',axis=1)
#print train
test = df_test
#test_target = test['Survived']
#test = test.drop('Survived',axis=1)
print len(train)
print len(test)
#print newsgroups_train.filenames
#print newsgroups_test.filenames.shape
#print vectorizer
#print X_train
classifier = Perceptron(n_iter=5000, eta0=0.3)
classifier.fit_transform(train, train_target )
predictions = classifier.predict(test)
#print predictions
#print classification_report(test_target, predictions)
print predictions
np.savetxt('test_final.csv',predictions)
#cm = confusion_matrix(test_target,predictions)
#print cm
#print classifier.score(train,train_target)
