import utils.utils as u
import utils.stats as stat
import utils.preprocessor_methods as pr
import storage.data as d
from numpy import *
from pylab import *
from sklearn.metrics import precision_recall_fscore_support
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(message)s')
d.set_file_names()
docs_test, y_test, docs_train, y_train, docs_train_subjectivity, y_train_subjectivity, docs_train_polarity, y_train_polarity = d.get_data()
"""
MaxEnt:
{
'vect__ngram_range': (1, 1),
'vect__smooth_idf': True,
'vect__max_df': 0.5,
'vect__sublinear_tf': True,
'vect__preprocessor': <function placeholders at 0x9be31b4>,
'clf__penalty': 'l1',
'clf__C': 1.0,
'vect__use_idf': True
}
"""
c1_vect_options = {
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import utils.utils as u
import utils.stats as s
import storage.data as d
from pylab import arange, savefig
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(message)s')
d.set_file_names()
docs_test, y_test, docs_train, y_train, docs_train_subjectivity, y_train_subjectivity, docs_train_polarity, y_train_polarity = d.get_data(
)
# labels = ['NB', 'SVM', 'MaxEnt', 'Combined (Foo -> Bar)', 'Combined (Foo -> Bar)', 'Combined (Foo -> Bar)', 'Combined (Foo -> Bar)', 'Combined (Foo -> Bar)', 'Combined (Foo -> Bar)', 'Boosting']
# values = [0.549392, 0.34543453, 0.23432999, 0.654213, 0.3213495, 0.65343, 0.53999211, 0.34543453, 0.23432999, 0.654213]
labels = []
values = []
def test(clf):
global labels, values
y_predict = clf.predict(docs_test)
score = u.score(y_test, y_predict)
labels.append(str(clf))
import sys
import logging
from models import *
import storage.data as d
import storage.prediction_exporter as pe
import utils.stats as s
import utils.preprocessor_methods as pr
logging.basicConfig(level=logging.DEBUG, format="%(asctime)s %(message)s")
docs_test, y_test, docs_train, y_train, docs_train_subjectivity, y_train_subjectivity, docs_train_polarity, y_train_polarity = (
d.get_data()
)
pe.set_base_from_dataset(d.get_full_test_set())
vect_options = {
"ngram_range": (1, 1),
"sublinear_tf": True,
"preprocessor": pr.remove_noise,
"use_idf": False,
"stop_words": None,
}
default_options = {"C": 1.0}
clf = SVM(docs_train, y_train, default_options=default_options, vect_options=vect_options)
if len(sys.argv) > 1: