def KNN_parameter(path):
print "Classifier: K Nearest Neighbors"
print "KFOLD parameter test"
# preprocess
main.reorganize_dataset(path)
main.remove_incompatible_files(path)
# load data
files = sklearn.datasets.load_files(path, shuffle=True)
# refine emails - delete unwanted text form them
util.refine_all_emails(files.data)
# feature Extractoin
# BOW
BOW = util.bagOfWords(files.data)
# TFIDF
tfidf_transformer = sklearn.feature_extraction.text.TfidfTransformer(
use_idf=False).fit(BOW)
TFIDF = tfidf_transformer.transform(BOW)
# k in kfold
n_cross_val = 5
# calculate results
i, uniform_results, weighted_results = KFOLD_KNN_parameter_test(
TFIDF, files.target, n_cross_val=n_cross_val, n_neighbors=5)
# plot
plot_results(i, [uniform_results, weighted_results],
['uniform', 'weighted'])
def NB(path):
print ("Classifier: Naive Bayes")
print ("Train-Test Split")
# preprocess
main.reorganize_dataset(path)
main.remove_incompatible_files(path)
# load data
files = sklearn.datasets.load_files(path, shuffle = True)
# refine emails - delete unwanted text form them
util.refine_all_emails(files.data)
# feature Extractoin
# BOW
BOW = util.bagOfWords(files.data)
# TF
tf_transformer = sklearn.feature_extraction.text.TfidfTransformer(use_idf=False).fit(BOW)
TF = tf_transformer.transform(BOW)
# TFIDF
tfidf_transformer = sklearn.feature_extraction.text.TfidfTransformer(use_idf=False).fit(BOW)
TFIDF = tfidf_transformer.transform(BOW)
# build classifier
clf = sklearn.naive_bayes.MultinomialNB()
# calculate results
i, BOW_results = split_test_classifier(clf, BOW, files.target)
i, TF_results = split_test_classifier(clf, TF, files.target)
i, TFIDF_results = split_test_classifier(clf, TFIDF, files.target)
# plot
plot_results(i, [BOW_results, TF_results, TFIDF_results], ['BOW', 'TF', 'TFIDF'])
def KNN_parameter(path):
print ("Classifier: K Nearest Neighbors")
print ("KFOLD parameter test")
# preprocess
main.reorganize_dataset(path)
main.remove_incompatible_files(path)
# load data
files = sklearn.datasets.load_files(path, shuffle = True)
# refine emails - delete unwanted text form them
util.refine_all_emails(files.data)
# feature Extractoin
# BOW
BOW = util.bagOfWords(files.data)
# TFIDF
tfidf_transformer = sklearn.feature_extraction.text.TfidfTransformer(use_idf=False).fit(BOW)
TFIDF = tfidf_transformer.transform(BOW)
# k in kfold
n_cross_val = 5
# calculate results
i, uniform_results, weighted_results = KFOLD_KNN_parameter_test(TFIDF, files.target, n_cross_val = n_cross_val, n_neighbors = 5)
# plot
plot_results(i, [uniform_results, weighted_results], ['uniform', 'weighted'])
def KNN(path):
print "Classifier: K Nearest Neighbors"
print "Train-Test Split"
# preprocess
main.reorganize_dataset(path)
main.remove_incompatible_files(path)
# load data
files = sklearn.datasets.load_files(path, shuffle=True)
# refine emails - delete unwanted text form them
util.refine_all_emails(files.data)
# feature Extractoin
# BOW
BOW = util.bagOfWords(files.data)
# TF
tf_transformer = sklearn.feature_extraction.text.TfidfTransformer(
use_idf=False).fit(BOW)
TF = tf_transformer.transform(BOW)
# TFIDF
tfidf_transformer = sklearn.feature_extraction.text.TfidfTransformer(
use_idf=False).fit(BOW)
TFIDF = tfidf_transformer.transform(BOW)
# build classifier
n_neighbors = 5
# weights = 'uniform'
weights = 'distance'
clf = sklearn.neighbors.KNeighborsClassifier(n_neighbors, weights=weights)
# calculate results
i, BOW_results = split_test_classifier(clf, BOW, files.target)
i, TF_results = split_test_classifier(clf, TF, files.target)
i, TFIDF_results = split_test_classifier(clf, TFIDF, files.target)
# plot
plot_results(i, [BOW_results, TF_results, TFIDF_results],
['BOW', 'TF', 'TFIDF'])
def SVM(path):
print "Classifier: Support Vector Machine"
print "Train-Test Split"
# preprocess
main.reorganize_dataset(path)
main.remove_incompatible_files(path)
# load data
files = sklearn.datasets.load_files(path, shuffle=True)
# refine emails - delete unwanted text form them
util.refine_all_emails(files.data)
# feature Extractoin
# BOW
BOW = util.bagOfWords(files.data)
# TF
tf_transformer = sklearn.feature_extraction.text.TfidfTransformer(
use_idf=False).fit(BOW)
TF = tf_transformer.transform(BOW)
# TFIDF
tfidf_transformer = sklearn.feature_extraction.text.TfidfTransformer(
use_idf=False).fit(BOW)
TFIDF = tfidf_transformer.transform(BOW)
# build classifier
clf = sklearn.svm.LinearSVC()
# calculate results
i, BOW_results = split_test_classifier(clf, BOW, files.target)
i, TF_results = split_test_classifier(clf, TF, files.target)
i, TFIDF_results = split_test_classifier(clf, TFIDF, files.target)
# plot
plot_results(i, [BOW_results, TF_results, TFIDF_results],
['BOW', 'TF', 'TFIDF'])
def KNN(path): print "Classifier: K Nearest Neighbors" print "Train-Test Split" # preprocess main.reorganize_dataset(path) main.remove_incompatible_files(path) # load data files = sklearn.datasets.load_files(path, shuffle = True) # refine emails - delete unwanted text form them util.refine_all_emails(files.data) # feature Extractoin # BOW BOW = util.bagOfWords(files.data) # TF tf_transformer = sklearn.feature_extraction.text.TfidfTransformer(use_idf=False).fit(BOW) TF = tf_transformer.transform(BOW) # TFIDF tfidf_transformer = sklearn.feature_extraction.text.TfidfTransformer(use_idf=False).fit(BOW) TFIDF = tfidf_transformer.transform(BOW) # build classifier n_neighbors = 5 # weights = 'uniform' weights = 'distance' clf = sklearn.neighbors.KNeighborsClassifier(n_neighbors, weights=weights) # calculate results i, BOW_results = split_test_classifier(clf, BOW, files.target) i, TF_results = split_test_classifier(clf, TF, files.target) i, TFIDF_results = split_test_classifier(clf, TFIDF, files.target) # plot plot_results(i, [BOW_results, TF_results, TFIDF_results], ['BOW', 'TF', 'TFIDF'])