def train_HOMER(trainX_embedded, trainY):
trainX_embedded_sp = sparse.lil_matrix(trainX_embedded)
trainY_sp = sparse.lil_matrix(trainY)
#meka_classpath = download_meka()
model = Meka(
#meka_classifier="meka.classifiers.multilabel.BR", # Binary Relevance
#meka_classifier = "meka.classifiers.multilabel.CC",
meka_classifier = "meka.classifiers.multilabel.MULAN -S HOMER.BalancedClustering.%d.BinaryRelevance" % FLAGS.num_clusters,
#weka_classifier = "weka.classifiers.functions.Logistic",
#weka_classifier = "weka.classifiers.functions.SMO -C 1 -K \"weka.classifiers.functions.supportVector.RBFKernel -C 250007 -G 1\"",
weka_classifier = "weka.classifiers.functions.LibSVM -C %d -G %d" % (FLAGS.C, FLAGS.gamma),
#weka_classifier = "weka.classifiers.functions.LibSVM",
meka_classpath=download_meka(), # obtained via download_meka # for PC
java_command='java' # path to java executable
)
model.fit(trainX_embedded_sp, trainY_sp)
return model
def train_svm(trainX_embedded, trainY, mode=FLAGS.mode):
#trainX_embedded_sp = sparse.lil_matrix(trainX_embedded)
#trainY_sp = sparse.lil_matrix(trainY)
#print(FLAGS.C,FLAGS.gamma)
#meka_classpath = download_meka()
if mode == 'rbf':
model = Meka(
meka_classifier="meka.classifiers.multilabel.BR", # Binary Relevance
#meka_classifier = "meka.classifiers.multilabel.CC",
#meka_classifier = "meka.classifiers.multilabel.MULAN -S HOMER.BalancedClustering.3.BinaryRelevance",
#weka_classifier = "weka.classifiers.functions.Logistic",
#weka_classifier = "weka.classifiers.functions.SMO -C 1 -K \"weka.classifiers.functions.supportVector.RBFKernel -C 250007 -G 1\"",
weka_classifier=
"weka.classifiers.functions.LibSVM -M 5000 -Z -C %f -G %f" %
(FLAGS.C, FLAGS.gamma),
#see https://weka.sourceforge.io/doc.stable/weka/classifiers/functions/LibSVM.html
meka_classpath=
"/exports/eddie/scratch/hdong3/scikit_ml_learn_data/meka/meka-release-1.9.2/lib/", # for eddie server
#meka_classpath=download_meka(), # obtained via download_meka # for PC
java_command='java' # path to java executable
)
elif mode == 'linear':
model = Meka(
meka_classifier="meka.classifiers.multilabel.BR", # Binary Relevance
weka_classifier="weka.classifiers.functions.LibLINEAR -C %f" %
(FLAGS.C),
#see https://weka.sourceforge.io/doc.stable/weka/classifiers/functions/LibLINEAR.html
meka_classpath=
"/exports/eddie/scratch/hdong3/scikit_ml_learn_data/meka/meka-release-1.9.2/lib/", # for eddie server
java_command='java' # path to java executable
)
else:
print('kernal mode unrecognised: using rbf kernel')
model = Meka(
meka_classifier="meka.classifiers.multilabel.BR", # Binary Relevance
weka_classifier=
"weka.classifiers.functions.LibSVM -M 200 -C %f -G %f" %
(FLAGS.C, FLAGS.gamma),
meka_classpath=
"/exports/eddie/scratch/hdong3/scikit_ml_learn_data/meka/meka-release-1.9.2/lib/", # for eddie server
java_command='java' # path to java executable
)
model.fit(trainX_embedded, trainY)
return model
from sklearn.datasets import make_multilabel_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import hamming_loss
from skmultilearn.ext import Meka
X, y = make_multilabel_classification(sparse=True, return_indicator='sparse')
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
"""
meka_classifier = "meka.classifiers.multilabel.PCC",
weka_classifier = "weka.classifiers.functions.Logistic",
"""
meka = Meka(
meka_classifier="meka.classifiers.multilabel.LC",
weka_classifier="weka.classifiers.bayes.NaiveBayes",
meka_classpath="/home/loki/Downloads/meka-release-1.9.3-SNAPSHOT/lib/",
java_command="/usr/bin/java")
try:
meka.fit(X_train, y_train)
except Exception as e:
print(e)
print(e.args[0].decode('utf8'))
predictions = meka.predict(X_test)
hamming_loss(y_test, predictions)
print(predictions)
def class_multi_label(x, Y, model, wekamodelname, value):
# detect is the data classification is a multi-label problem.
num_of_labels = Y.ndim
print("\n\n-----------------------------------------------------------\n")
if (num_of_labels == 1):
print("This is not a multi-label problem!!!!!!")
return model
javapath = "C:\\" "Program Files" "\\Java\\jre1.8.0_251\\bin\\javaw.exe"
myclasspath = download_meka()
print(myclasspath)
try:
while 1:
if (value < 1) or (value > 9):
print("This is a Multi label problem")
print("Please select:")
print("1. For binary relevance")
print("2. For pairwise comparison")
print("3. Calibrated label ranking")
print("4. Chain classifier ")
print("5. PowerSet no pruning ")
print("6. PowerSet with pruning ")
print("7. Random-k Labelsets ")
print("8. Pairwise comparison ")
print("9. Multi Label knn ")
value = input("Please enter a choice:\n")
if value == 1:
print("Applying binary relevance")
#clf=BinaryRelevance(classifier=model,require_dense=[False, True])
if wekamodelname == "nothing":
print("WEKA does not support this classifier")
clf = 0
break
clf = Meka(
meka_classifier="meka.classifiers.multilabel.BR",
weka_classifier=wekamodelname,
meka_classpath=myclasspath,
java_command=javapath # path to java executable
)
break
elif value == 2:
print("Fourclass Pairwise")
if wekamodelname == "nothing":
print("WEKA does not support this classifier")
clf = 0
break
clf = Meka(
meka_classifier="meka.classifiers.multilabel.FW",
weka_classifier=wekamodelname,
meka_classpath=myclasspath,
java_command=javapath # path to java executable
)
break
elif value == 3:
print("Applying calibrated label ranking")
if wekamodelname == "nothing":
print("WEKA does not support this classifier")
clf = 0
break
clf = Meka(
meka_classifier="meka.classifiers.multilabel.MULAN",
weka_classifier=wekamodelname + " -S CLR",
meka_classpath=myclasspath,
java_command=javapath # path to java executable
)
break
elif value == 4:
print("Applying Chain Classifier")
##clf = ClassifierChain(classifier=model,require_dense=[False, True])
if wekamodelname == "nothing":
print("WEKA does not support this classifier")
clf = 0
break
clf = Meka(
meka_classifier="meka.classifiers.multilabel.CC",
weka_classifier=wekamodelname,
meka_classpath=myclasspath,
java_command=javapath # path to java executable
)
break
elif value == 5:
print("Applying powerset NO pruning")
clf = LabelPowerset(classifier=model,
require_dense=[False, True])
break
elif value == 6:
print("Applying powerset with pruning")
if wekamodelname == "nothing":
print("WEKA does not support this classifier")
clf = 0
break
clf = Meka(
meka_classifier="meka.classifiers.multilabel.PS",
weka_classifier=wekamodelname,
meka_classpath=myclasspath,
java_command=javapath # path to java executable
)
break
elif value == 7:
print("Applying Random-k Labelsets")
try:
clf = RakelD(base_classifier=model,
base_classifier_require_dense=[False, True],
labelset_size=4)
except:
print("RakelD exception")
break
elif value == 8:
print("Monte-Carlo Classifier Chains")
if wekamodelname == "nothing":
print("WEKA does not support this classifier")
clf = 0
break
clf = Meka(
meka_classifier="meka.classifiers.multilabel.MCC",
weka_classifier=wekamodelname,
meka_classpath=myclasspath,
java_command=javapath # path to java executable
)
break
elif value == 9:
print("Applying Multilabel k Nearest Neighbours")
try:
clf = MLkNN(k=3)
except:
print("Multilabel k Nearest Neighbours exception")
break
else:
print("Try again!!!!")
except:
print("\nSomething went wrong, but continue\n")
return clf
from sklearn.metrics import hamming_loss
from skmultilearn.ext import Meka
import os
home = os.environ['HOME']
print(home)
# wrd = pd.read_csv('/mnt/d/Documents/uni/The Final Project/TheSuperQuestionTyper/Primary_data/1000word_vector_Q.csv')
# tpc = pd.read_csv('/mnt/d/Documents/uni/The Final Project/TheSuperQuestionTyper/Primary_data/topic_vector_Q.csv')
#
# tpc.drop('tpc41', axis=1, inplace=True)
# tpc.drop('tpc42', axis=1, inplace=True)
# X = wrd.values
# y = tpc.values
X, y = make_multilabel_classification(sparse=True, return_indicator='sparse')
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
meka = Meka(meka_classifier="meka.classifiers.multilabel.LC",
weka_classifier="weka.classifiers.bayes.NaiveBayes",
meka_classpath="/opt/meka-1.9/lib/",
java_command='/usr/bin/java')
meka.fit(X_train, y_train)
print(X_test[15])
try:
predictions = meka.predict(X_test)
hamming_loss(y_test, predictions)
except:
print(meka.error)
def classifier(self):
meka_classifier = "meka.classifiers.multilabel.BR"
weka_classifier = "weka.classifiers.rules.ZeroR"
return Meka(meka_classifier=meka_classifier,
weka_classifier=weka_classifier)
# -*- coding:utf-8 -*-
from sklearn.datasets import make_multilabel_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import hamming_loss
from skmultilearn.ext import Meka
from skmultilearn.adapt import MLkNN
X, y = make_multilabel_classification(sparse=True, return_indicator='sparse')
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
meka = Meka(meka_classifier="meka.classifiers.multilabel.LC",
meka_classpath="F:\\mekalib\\",
java_command="d:\\Program Files\\Java/jdk1.8.0_60\\jre\\bin\\java")
meka.fit(X_train, y_train)
predictions = meka.predict(X_test)
hamming_loss(y_test, predictions)