def loadTrain():
print("Loading 20 newsgroups training set...")
news_train = load_mlcomp('20news-18828', 'train')
print(news_train.DESCR)
print("%d documents" % len(news_train.filenames))
print("%d categories" % len(news_train.target_names))
return news_train
def loadTrain():
print("Loading 20 newsgroups training set...")
news_train = load_mlcomp('20news-18828', 'train')
print(news_train.DESCR)
print("%d documents" % len(news_train.filenames))
print("%d categories" % len(news_train.target_names))
return news_train
def loadTest():
print("Loading 20 newsgroups test set...")
news_test = load_mlcomp('20news-18828', 'test')
t0 = time()
print("done in %fs" % (time() - t0))
print("%d documents" % len(news_test.filenames))
print("%d categories" % len(news_test.target_names))
return news_test
def loadTest():
print("Loading 20 newsgroups test set...")
news_test = load_mlcomp('20news-18828', 'test')
t0 = time()
print("done in %fs" % (time() - t0))
print("%d documents" % len(news_test.filenames))
print("%d categories" % len(news_test.target_names))
return news_test
def load_data(self):
"""Load the news_train file to see how it's structured"""
# Load the training set
print("Loading 20 newsgroups training set... ")
self.news_train = load_mlcomp('20news-18828',
'train',
mlcomp_root=MLCOMP)
print(self.news_train.DESCR)
print("%d documents" % len(self.news_train.filenames))
print("%d categories" % len(self.news_train.target_names))
return self.news_train
def load_texts(dataset_type='train', groups=None):
"""
load datasets to bytes list
:return:train_dataset_bunch.data bytes list
"""
if groups == 'small':
groups = ['comp.graphics', 'comp.os.ms-windows.misc'] # 仅用于小数据测试时用, #1368
elif groups == 'medium':
groups = ['comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware', 'comp.sys.ma c.hardware',
'comp.windows.x', 'sci.space'] # 中量数据时用 #3414
train_dataset_bunch = datasets.load_mlcomp('20news-18828', dataset_type, mlcomp_root='./datasets',
categories=groups) # 13180
return train_dataset_bunch.data
def load_texts(dataset_type='train', groups=None):
"""
load datasets to bytes list
:return:train_dataset_bunch.data bytes list
"""
if groups == 'small':
groups = ['comp.graphics', 'comp.os.ms-windows.misc'] # 仅用于小数据测试时用, #1368
elif groups == 'medium':
groups = ['comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware', 'comp.sys.ma c.hardware',
'comp.windows.x', 'sci.space'] # 中量数据时用 #3414
train_dataset_bunch = datasets.load_mlcomp('20news-18828', dataset_type, mlcomp_root='./datasets',
categories=groups) # 13180
return train_dataset_bunch.data
def load_texts(dataset_type='train', groups='small'):
"""
load datasets to bytes list
:return:train_dataset_bunch.items bytes list
"""
if groups == 'small':
groups = ['comp.graphics', 'rec.motorcycles', 'talk.politics.guns'] # 仅用于小数据测试时用, #1368
elif groups == 'medium':
groups = ['comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware', 'comp.sys.ma c.hardware',
'comp.windows.X', 'sci.space'] # 中量数据时用 #3414
train_dataset_bunch = datasets.load_mlcomp('20news-18828', dataset_type, mlcomp_root='../datasets',
categories=groups) # 13180
texts = preprocess_texts(train_dataset_bunch.data) # bunch.items list of text bytes
return texts
def extract_test_features(self):
print("Loading 20 newsgroups test set... ")
self.news_test = load_mlcomp('20news-18828',
'test',
mlcomp_root=MLCOMP)
t0 = time()
print("done in %fs" % (time() - t0))
print("Predicting the labels of the test set...")
print("%d documents" % len(self.news_test.filenames))
print("%d categories" % len(self.news_test.target_names))
print("Extracting features from the dataset using the same vectorizer")
t0 = time()
# Read in test data
test_input_strings = (open(f, encoding='latin-1').read()
for f in self.news_test.filenames)
self.X_test = self.vectorizer.transform(test_input_strings)
self.y_test = self.news_test.target
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % self.X_test.shape)
return
if not os.path.exists(DATA_DIR):
print("""\
It seems that you have not yet downloaded the MLCOMP data set.
Please do so and place it into %s."""%DATA_DIR)
sys.exit(1)
#
# groups = [
# 'comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware',
# 'comp.sys.ma c.hardware', 'comp.windows.x', 'sci.space']
# dataset = sklearn.datasets.load_mlcomp("20news-18828", "train",
# mlcomp_root=DATA_DIR,
# categories=groups)
# Load the training set
print("Loading 20 newsgroups training set... ")
news_train = load_mlcomp('20news-18828', 'train',mlcomp_root=DATA_DIR)
print(news_train.DESCR)
print("%d documents" % len(news_train.filenames))
print("%d categories" % len(news_train.target_names))
print("Extracting features from the dataset using a sparse vectorizer")
t0 = time()
vectorizer = TfidfVectorizer(encoding='latin1')
X_train = vectorizer.fit_transform((open(f).read()
for f in news_train.filenames))
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X_train.shape)
assert sp.issparse(X_train)
y_train = news_train.target
print("Loading 20 newsgroups test set... ")
#posts = load_data_from_dir("Building_ML_Systems_with_Python/chapter_03_Codes/data/toy", "\n")
#X_train = vectorizer.fit_transform(posts)
#n_samples, n_features = X_train.shape
#print n_samples
#post = "how does machine learning work?"
#post_vec, found_post, distance = get_similar_posts(X_train, post, posts)
#
#print "\n"
#print "The most similar post to '%s' is: '%s' with distance= %.2f" % (post, found_post, distance)
MLCOMP_DIR = "Building_ML_Systems_with_Python/chapter_03_Codes/data"
categories = [
'comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware',
'comp.sys.mac.hardware', 'comp.windows.x', 'sci.space']
train_data = datasets.load_mlcomp("20news-18828", "train",
mlcomp_root=MLCOMP_DIR,
categories=categories)
test_data = datasets.load_mlcomp("20news-18828", "test",
mlcomp_root=MLCOMP_DIR,
categories=categories)
print("Number of training data posts:", len(train_data.filenames))
print("Number of test data posts:", len(test_data.filenames))
vectorizer = StemmedTfIdfCountVectorizer(min_df=10, max_df=0.5, stop_words='english', decode_error='ignore')
X_train = vectorizer.fit_transform(train_data.data)
X_test = vectorizer.transform(test_data.data)
num_train_samples, num_train_features = X_train.shape
num_test_samples, num_test_features = X_test.shape
labels = train_data.target
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.naive_bayes import MultinomialNB
print(__doc__)
# if 'MLCOMP_DATASETS_HOME' not in os.environ:
# print("MLCOMP_DATASETS_HOME not set; please follow the above instructions")
# sys.exit(0)
#/ updated by Ivy
MLCOMP_DIR = r"E:\ctvit\lab\Code\Pycharm Project\cctv_news_content"
# Load the training set
print("Loading 20 newsgroups training set... ")
news_train = load_mlcomp('20news-18828', mlcomp_root=MLCOMP_DIR)
# news_train = load_mlcomp('20news-18828', 'train')
print(news_train.DESCR)
print("%d documents" % len(news_train.filenames))
print("%d categories" % len(news_train.target_names))
print("Extracting features from the dataset using a sparse vectorizer")
t0 = time()
vectorizer = TfidfVectorizer(encoding='latin1')
X_train = vectorizer.fit_transform(
(open(f).read() for f in news_train.filenames))
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X_train.shape)
assert sp.issparse(X_train)
y_train = news_train.target
┃┫┫ ┃┫┫
┗┻┛ ┗┻┛
"""
import pdb
from sklearn import datasets
from sklearn.cluster import KMeans
from RelatedPosts import StemmedTfidfVectorizer, norm_euclidDist
"""
loading datasets into train_dataset_bunch
"""
MLCOMP_DIR = r'./datasets'
groups = ['comp.graphics', 'comp.os.ms-windows.misc'] #仅用于小数据测试时用
# groups = ['comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware', 'comp.sys.ma c.hardware', 'comp.windows.x', 'sci.space'] # 中量数据时用
train_dataset_bunch = datasets.load_mlcomp(name_or_id='20news-18828', set_='train', mlcomp_root=MLCOMP_DIR,categories=groups) #<class 'sklearn.datasets.base.Bunch'>
# print(type(train_dataset_bunch.items)) #list
# print(type(train_dataset_bunch.items[0])) #bytes
# print(len(train_dataset_bunch.filenames)) # #posts=3414
"""
fit_transform dataset.items into train_dataset_mats
"""
Vectorizer = StemmedTfidfVectorizer
vectorizer = Vectorizer(decode_error='ignore', stop_words='english', min_df=10, max_df=0.5)
# scipy.sparse.csr.csr_matrix
train_dataset_mats = vectorizer.fit_transform(train_dataset_bunch.data)
num_samples, num_features = train_dataset_mats.shape
print("#samples:%d, #features:%d" % (num_samples, num_features))
from flask import Flask
from flask import render_template
from flask import request
import dill
from unicode import convertunicode
from sklearn.datasets import load_mlcomp
MLCOMPDIR = r'NewsData'
trainNews = load_mlcomp('NewsData', 'train', mlcomp_root=MLCOMPDIR)
app = Flask(__name__)
@app.route('/')
def index():
return render_template('index.html')
@app.route('/classify', methods=['GET', 'POST'])
def classify():
if request.method == 'POST':
result = request.form
newsText = result.get('inputText')
newsText = [newsText]
tfidf = dill.load(open("tfidf.pkl", 'rb'))
tfidf.fit_transform(newsText)
model = dill.load(open("model.pkl", 'rb'))
from sklearn import tree
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
#from sklearn.naive_bayes import MultinomialNB
print(__doc__)
#if 'MLCOMP_DATASETS_HOME' not in os.environ:
# print("DATASETS_HOME not set; please follow the above instructions")
# sys.exit(0)
#Load the training set
dataset_name = '20w_nospec_may'
print("Loading twitter training set... ")
twitter_train = load_mlcomp(dataset_name, 'train')
print(twitter_train.DESCR)
print("%d documents" % len(twitter_train.filenames))
print("%d categories" % len(twitter_train.target_names))
print("Extracting features from the dataset using a sparse vectorizer")
t0 = time()
vectorizer = TfidfVectorizer(encoding='latin1')
X_train = vectorizer.fit_transform((open(f).read() for f in twitter_train.filenames))
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X_train.shape)
assert sp.issparse(X_train)
y_train = twitter_train.target
import sklearn
import nltk
import scipy as sp
from sklearn.datasets import load_mlcomp
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_selection import SelectKBest, chi2
from sklearn.pipeline import Pipeline
from sklearn import metrics
from sklearn.naive_bayes import MultinomialNB, BernoulliNB
from sklearn.svm import SVC
MLCOMPDIR = r'LOCATION OF CORPUS'
trainNews = load_mlcomp('16NepaliNews', 'train', mlcomp_root=MLCOMPDIR)
testNews = load_mlcomp('16NepaliNews', 'test', mlcomp_root=MLCOMPDIR)
''' Nepali Stop Words '''
# The stop words file is copied into the stopwords directory of nltk.data\corpora folder
stopWords = set(nltk.corpus.stopwords.words('nepali'))
''' Testing and Training Data '''
xTrain = trainNews.data
xTest = testNews.data
yTrain = trainNews.target
yTest = testNews.target
''' Vectorizer '''
tfidfVectorizer = TfidfVectorizer(tokenizer=lambda x: x.split(" "),
sublinear_tf=True,
encoding='utf-8',
decode_error='ignore',
def testBaseLine(self):
#return # disable slow test for now
logger.info("Running 20NG NB baseline...")
logger.info("Calculating TF-IDF on 20ng data set...")
news_train = load_mlcomp('20news-18828', 'train')
news_test = load_mlcomp('20news-18828', 'test')
target_names = news_test.target_names
vectorizer = TfidfVectorizer(encoding='latin1')
X_train = vectorizer.fit_transform(
(open(f).read() for f in news_train.filenames))
y_train = news_train.target
X_test = vectorizer.transform(
(open(f).read() for f in news_test.filenames))
y_test = news_test.target
del news_train, news_test
logger.info("Running MultinomialNB...")
clf = MultinomialNB().fit(X_train, y_train)
print(
classification_report(y_test,
clf.predict(X_test),
target_names=target_names))
del clf
logger.info("Running pybrain...")
from pybrain.datasets import ClassificationDataSet
from pybrain.utilities import percentError
from pybrain.tools.shortcuts import buildNetwork
from pybrain.supervised.trainers import BackpropTrainer
from pybrain.structure.modules import SoftmaxLayer
from pybrain.tools.xml.networkwriter import NetworkWriter
from pybrain.tools.xml.networkreader import NetworkReader
trndata = ClassificationDataSet(len(vectorizer.get_feature_names()),
1,
nb_classes=len(target_names),
class_labels=target_names)
for i, x in enumerate(X_train):
#print x, y_train[i]
trndata.addSample(x.toarray(), y_train[i])
trndata._convertToOneOfMany()
del X_train, y_train
tstdata = ClassificationDataSet(len(vectorizer.get_feature_names()),
1,
nb_classes=len(target_names),
class_labels=target_names)
for i, x in enumerate(X_test):
tstdata.addSample(x.toarray(), y_test[i])
tstdata._convertToOneOfMany()
del X_test, y_test
logger.info("Building network...")
fnn = buildNetwork(trndata.indim,
100,
trndata.outdim,
outclass=SoftmaxLayer)
trainer = BackpropTrainer(fnn,
dataset=trndata,
momentum=0.1,
learningrate=0.01,
verbose=True,
weightdecay=0.01)
logger.info("Training pybrain for 50 epochs...")
trainer.trainEpochs(50)
pred = fnn.activateOnDataset(tstdata)
pred = np.argmax(pred, axis=1) # argmax gives the class
print(classification_report(y_test, pred, target_names=target_names))
#coding:utf-8
'''
Created on 2015年7月5日
@author: Administrator
'''
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.datasets import load_mlcomp
import nltk.stem
MLCOMP_DIR = r'data'
data = load_mlcomp('20news-18828', mlcomp_root=MLCOMP_DIR)
#print (data.filenames)
#print len(data.filenames)
#print len(data.target_names)
groups = ['comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware', 'comp.sys.ma c.hardware', 'comp.windows.x', 'sci.space']
train_data = load_mlcomp('20news-18828', 'train',mlcomp_root=MLCOMP_DIR,categories=groups)
test_data = load_mlcomp('20news-18828', 'test',mlcomp_root=MLCOMP_DIR)
#print len(test_data.filenames)
english_stemmer = nltk.stem.SnowballStemmer('english')
class StemmedTfidfVectorizer(TfidfVectorizer):
def bulid_analyzer(self):
analyzer = super(TfidfVectorizer,self).bulid_analyzer()
return lambda doc: (english_stemmer.stem(w) for w in analyzer(doc))
vectorizer = StemmedTfidfVectorizer(min_df=10, max_df=0.5,stop_words='english',decode_error='ignore')
vectorized = vectorizer.fit_transform(data)
from sklearn.datasets import load_mlcomp
from sklearn.feature_extraction.text import Vectorizer
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.naive_bayes import MultinomialNB
if 'MLCOMP_DATASETS_HOME' not in os.environ:
print "MLCOMP_DATASETS_HOME not set; please follow the above instructions"
sys.exit(0)
# Load the training set
print "Loading 20 newsgroups training set... "
news_train = load_mlcomp('20news-18828', 'train')
print news_train.DESCR
print "%d documents" % len(news_train.filenames)
print "%d categories" % len(news_train.target_names)
print "Extracting features from the dataset using a sparse vectorizer"
t0 = time()
vectorizer = Vectorizer()
X_train = vectorizer.fit_transform((open(f).read()
for f in news_train.filenames))
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_train.shape
assert sp.issparse(X_train)
y_train = news_train.target
print "Loading 20 newsgroups test set... "
english_stemmer = SnowballStemmer('english')
vectorizer = StemmedTfidfVectorizer(min_df=10,
stop_words='english',
decode_error='ignore')
MLCOMP_DIR = os.path.join(os.getcwd())
print(MLCOMP_DIR)
groups = [
'comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardhware',
'comp.sys.mac.hardware', 'comp.windows.x', 'sci.space'
]
#data = load_mlcomp("20news-18828",mlcomp_root=MLCOMP_DIR)
#train_data = fetch_20newsgroups(subset='train')
#test_data = fetch_20newsgroups(subset='test')
test_data = load_mlcomp("20news-18828", "test", mlcomp_root=MLCOMP_DIR)
train_data = load_mlcomp("20news-18828", "train", mlcomp_root=MLCOMP_DIR)
vectorized = vectorizer.fit_transform(train_data.data)
num_samples, num_features = vectorized.shape
print(num_samples, num_features)
num_clusters = 50
km = KMeans(n_clusters=num_clusters, init='random', n_init=1, verbose=1)
km.fit(vectorized)
new_post = "Disk drive problems. Hi, I have a problem with my hard disk. After 1 year it is working only sporadically now. I tried to format it, but now it doesn't boot any more. Any ideas? Thanks."
new_post_vec = vectorizer.transform([new_post])
new_post_label = km.predict(new_post_vec)[0]
print(new_post_label)
similar_indices = (km.labels_ == new_post_label).nonzero()[0]
similar = []
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
#from sklearn.naive_bayes import MultinomialNB
print(__doc__)
if 'MLCOMP_DATASETS_HOME' not in os.environ:
print("DATASETS_HOME not set; please follow the above instructions")
sys.exit(0)
# Load the training set
dataset_name = 'hashtagging-tweets'
print("Loading twitter training set... ")
twitter_train = load_mlcomp(dataset_name, 'train')
print(twitter_train.DESCR)
print("%d documents" % len(twitter_train.filenames))
print("%d categories" % len(twitter_train.target_names))
print("Extracting features from the dataset using a sparse vectorizer")
t0 = time()
vectorizer = TfidfVectorizer(encoding='latin1')
X_train = vectorizer.fit_transform((open(f).read()
for f in twitter_train.filenames))
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X_train.shape)
assert sp.issparse(X_train)
y_train = twitter_train.target
##################################################
def testBaseLine(self):
#return # disable slow test for now
logger.info("Running 20NG NB baseline...")
logger.info("Calculating TF-IDF on 20ng data set...")
news_train = load_mlcomp('20news-18828', 'train')
news_test = load_mlcomp('20news-18828', 'test')
target_names = news_test.target_names
vectorizer = TfidfVectorizer(encoding='latin1')
X_train = vectorizer.fit_transform((open(f).read()
for f in news_train.filenames))
y_train = news_train.target
X_test = vectorizer.transform((open(f).read()
for f in news_test.filenames))
y_test = news_test.target
del news_train, news_test
logger.info("Running MultinomialNB...")
clf = MultinomialNB().fit(X_train, y_train)
print(classification_report(y_test, clf.predict(X_test),
target_names=target_names))
del clf
logger.info("Running pybrain...")
from pybrain.datasets import ClassificationDataSet
from pybrain.utilities import percentError
from pybrain.tools.shortcuts import buildNetwork
from pybrain.supervised.trainers import BackpropTrainer
from pybrain.structure.modules import SoftmaxLayer
from pybrain.tools.xml.networkwriter import NetworkWriter
from pybrain.tools.xml.networkreader import NetworkReader
trndata = ClassificationDataSet(len(vectorizer.get_feature_names()), 1,
nb_classes = len(target_names),
class_labels = target_names)
for i, x in enumerate(X_train):
#print x, y_train[i]
trndata.addSample(x.toarray(), y_train[i])
trndata._convertToOneOfMany( )
del X_train, y_train
tstdata = ClassificationDataSet(len(vectorizer.get_feature_names()), 1,
nb_classes = len(target_names),
class_labels = target_names)
for i, x in enumerate(X_test):
tstdata.addSample(x.toarray(), y_test[i])
tstdata._convertToOneOfMany( )
del X_test, y_test
logger.info("Building network...")
fnn = buildNetwork(trndata.indim, 100, trndata.outdim, outclass=SoftmaxLayer)
trainer = BackpropTrainer(fnn, dataset=trndata, momentum=0.1, learningrate=0.01,
verbose=True, weightdecay=0.01)
logger.info("Training pybrain for 50 epochs...")
trainer.trainEpochs(50)
pred = fnn.activateOnDataset(tstdata)
pred = np.argmax(pred, axis=1) # argmax gives the class
print(classification_report(y_test, pred,
target_names=target_names))
import dill
import nltk
import scipy as sp
from sklearn.datasets import load_mlcomp
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.pipeline import Pipeline
from sklearn import metrics
from sklearn.naive_bayes import MultinomialNB, BernoulliNB
MLCOMPDIR = r'16NepaliNews/16NepaliNews'
trainNews = load_mlcomp('NepaliData', 'train', mlcomp_root=MLCOMPDIR)
testNews = load_mlcomp('NepaliData', 'test', mlcomp_root=MLCOMPDIR)
stopWords = set(nltk.corpus.stopwords.words('nepali'))
''' Testing and Training Data '''
xTrain = trainNews.data
xTest = testNews.data
yTrain = trainNews.target
yTest = testNews.target
tfidfVectorizer = TfidfVectorizer(tokenizer=lambda x: x.split(" "),
sublinear_tf=True,
encoding='utf-8',
decode_error='ignore',
stop_words=stopWords)
vectorised = tfidfVectorizer.fit_transform(xTrain)
with open('tfidf.pkl', 'wb') as f:
#coding:utf-8
'''
Created on 2015年7月5日
@author: Administrator
'''
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.datasets import load_mlcomp
import nltk.stem
MLCOMP_DIR = r'data'
data = load_mlcomp('20news-18828', mlcomp_root=MLCOMP_DIR)
#print (data.filenames)
#print len(data.filenames)
#print len(data.target_names)
groups = [
'comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware',
'comp.sys.ma c.hardware', 'comp.windows.x', 'sci.space'
]
train_data = load_mlcomp('20news-18828',
'train',
mlcomp_root=MLCOMP_DIR,
categories=groups)
test_data = load_mlcomp('20news-18828', 'test', mlcomp_root=MLCOMP_DIR)
#print len(test_data.filenames)
english_stemmer = nltk.stem.SnowballStemmer('english')
from sklearn.datasets import load_mlcomp
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.naive_bayes import MultinomialNB
if "MLCOMP_DATASETS_HOME" not in os.environ:
print "MLCOMP_DATASETS_HOME not set; please follow the above instructions"
sys.exit(0)
# Load the training set
print "Loading 20 newsgroups training set... "
news_train = load_mlcomp("20news-18828", "train")
print news_train.DESCR
print "%d documents" % len(news_train.filenames)
print "%d categories" % len(news_train.target_names)
print "Extracting features from the dataset using a sparse vectorizer"
t0 = time()
vectorizer = TfidfVectorizer(charset="latin1")
X_train = vectorizer.fit_transform((open(f).read() for f in news_train.filenames))
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_train.shape
assert sp.issparse(X_train)
y_train = news_train.target
print "Loading 20 newsgroups test set... "
news_test = load_mlcomp("20news-18828", "test")
#X_train = vectorizer.fit_transform(posts)
#n_samples, n_features = X_train.shape
#print n_samples
#post = "how does machine learning work?"
#post_vec, found_post, distance = get_similar_posts(X_train, post, posts)
#
#print "\n"
#print "The most similar post to '%s' is: '%s' with distance= %.2f" % (post, found_post, distance)
MLCOMP_DIR = "Building_ML_Systems_with_Python/chapter_03_Codes/data"
categories = [
'comp.graphics', 'comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware',
'comp.sys.mac.hardware', 'comp.windows.x', 'sci.space'
]
train_data = datasets.load_mlcomp("20news-18828",
"train",
mlcomp_root=MLCOMP_DIR,
categories=categories)
test_data = datasets.load_mlcomp("20news-18828",
"test",
mlcomp_root=MLCOMP_DIR,
categories=categories)
print("Number of training data posts:", len(train_data.filenames))
print("Number of test data posts:", len(test_data.filenames))
vectorizer = StemmedTfIdfCountVectorizer(min_df=10,
max_df=0.5,
stop_words='english',
decode_error='ignore')
X_train = vectorizer.fit_transform(train_data.data)
X_test = vectorizer.transform(test_data.data)
from sklearn.datasets import load_mlcomp
from aiml.learnig.my_stemmer import StemmedTfidfVectorizer
from sklearn.cluster import KMeans
from aiml.learnig.utils import dis_raw
MLCOMP_ROOT = '/home/ring/datasets/mlcomp'
groups = ['comp.graphics', 'comp.os.ms-windows.misc',
'comp.sys.ibm.pc.hardware', 'comp.sys.ma c.hardware', 'comp.windows.x', 'sci.space']
train_data = load_mlcomp('20news-18828', mlcomp_root=MLCOMP_ROOT, set_='train', categories=groups)
#test_data = load_mlcomp('20news-18828', mlcomp_root=MLCOMP_ROOT, set_='test')
vectorizer = StemmedTfidfVectorizer(min_df=10, max_df=0.5, stop_words='english', decode_error='ignore')
vectorized = vectorizer.fit_transform(train_data.data)
num_samples, num_features = vectorized.shape
print("#samples: %d, #features: %d" % (num_samples, num_features))
new_posts = """Disk drive problems. Hi, I have a problem with my hard disk.
After 1 year it is working only sporadically now.
I tried to format it, but now it doesn't boot any more.
Any ideas? Thanks."""
new_posts_vec = vectorizer.transform([new_posts])
# K-Means聚类
num_clusters = train_data.target.max() + 1
km = KMeans(n_clusters=num_clusters, n_init=1, init='random', verbose=1)
km.fit(vectorized)
print('#K-Means total matched %i' % len(train_data.target == km.labels_))
# 分类预测
new_post_label = km.predict(new_posts_vec)
# 获取相同类别文章的下标
metadata = 'relig'
elif (entry == 4):
path = path + 'T\\ti'
metadata = 'ti'
elif (entry == 5):
path = path + 'C\\course'
metadata = 'course'
else:
print('Tente um número entre 1 - 4')
print('1-age, 2-gender, 3-relig, 4-ti, 5-course')
exit(0)
print("Loading database")
age_train = load_mlcomp(metadata, metadata)
print(age_train.DESCR)
print("%d documents" % len(age_train.filenames))
print("%d categories" % len(age_train.target_names))
I = {}
T = {}
i = 0
for f in age_train.filenames:
I[i] = open(f, encoding='utf-8').read()
i = i + 1
i = 0
for f in age_train.target:
T[i] = f
i = i + 1
data = datasets.load_iris() print "Features: ", len(data["data"][0]) print "Instances: ", len(data["data"]) print len(set(data["target"])) # data = datasets.load_linnerud() # import pdb # pdb.set_trace() # print "Features: ", len(data["data"][0]) # print "Instances: ", len(data["data"]) # print len(set(data["target"])) data = datasets.load_mlcomp() print "Features: ", len(data["data"][0]) print "Instances: ", len(data["data"]) import pdb pdb.set_trace() data = datasets.load_sample_image() print "Features: ", len(data["data"][0]) print "Instances: ", len(data["data"]) print len(set(data["target"])) data = datasets.load_sample_images() print "Features: ", len(data["data"][0]) print "Instances: ", len(data["data"]) print len(set(data["target"]))
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.naive_bayes import MultinomialNB
print(__doc__)
if 'MLCOMP_DATASETS_HOME' not in os.environ:
print("MLCOMP_DATASETS_HOME not set; please follow the above instructions")
sys.exit(0)
# Load the training set
print("Loading 20 newsgroups training set... ")
news_train = load_mlcomp('20news-18828', 'train')
print(news_train.DESCR)
print("%d documents" % len(news_train.filenames))
print("%d categories" % len(news_train.target_names))
print("Extracting features from the dataset using a sparse vectorizer")
t0 = time()
vectorizer = TfidfVectorizer(charset='latin1')
X_train = vectorizer.fit_transform((open(f).read()
for f in news_train.filenames))
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X_train.shape)
assert sp.issparse(X_train)
y_train = news_train.target
print("Loading 20 newsgroups test set... ")
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
#from sklearn.naive_bayes import MultinomialNB
print(__doc__)
if 'MLCOMP_DATASETS_HOME' not in os.environ:
print("DATASETS_HOME not set; please follow the above instructions")
sys.exit(0)
# Load the training set
dataset_name = 'hashtagging-tweets'
print("Loading twitter training set... ")
twitter_train = load_mlcomp(dataset_name, 'train')
print(twitter_train.DESCR)
print("%d documents" % len(twitter_train.filenames))
print("%d categories" % len(twitter_train.target_names))
print("Extracting features from the dataset using a sparse vectorizer")
t0 = time()
vectorizer = TfidfVectorizer(encoding='latin1')
X_train = vectorizer.fit_transform(
(open(f).read() for f in twitter_train.filenames))
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X_train.shape)
assert sp.issparse(X_train)
y_train = twitter_train.target
##################################################
