def import_files(dataset_name):
"""
This function is used to import both the training and the testing datasets
:param dataset_name: The name of the dataset
:return: The dictionaries for each users in the dataset
"""
try:
string_train = import_data.import_train_data(dataset_name)
data_dict_train = convert_data_to_array.convert_to_array(string_train)
except:
print "You have given wrong dataset name or the dataset is in wrong directory, please check"
exit(1)
string_train = import_data.import_test_data(dataset_name)
data_dict_test = convert_data_to_array.convert_to_array(string_train)
return data_dict_test, data_dict_train
import numpy as np
from sklearn import svm
from import_data import import_train_data, import_test_data
from feature_map import feature_map_part1_1
train_raw_digit_dataset = import_train_data("digitdata/trainingimages",
"digitdata/traininglabels")
test_raw_digit_dataset = import_test_data("digitdata/testimages",
"digitdata/testlabels")
def run_part1_digit_ec4():
print("Importing data...")
(_, traindata, _,
trainlabel) = feature_map_part1_1(train_raw_digit_dataset, {
' ': 0,
'#': 1,
'+': 1
}, (28, 28), 10)
(_, testdata, _, testlabel) = feature_map_part1_1(test_raw_digit_dataset, {
' ': 0,
'#': 1,
'+': 1
}, (28, 28), 10)
clf = svm.SVC()
print("Training...")
clf.fit(traindata, trainlabel)
print("Testing")
preds_test = clf.predict(testdata)
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import ticker
from import_data import import_train_data, import_test_data
from naive_bayes import train, test, evaluation, output_result, run
from feature_map import feature_map_part2_2
train_audio_dataset = import_train_data("mfccdata/training_data.txt",
"mfccdata/training_labels.txt")
test_audio_dataset = import_test_data("mfccdata/testing_data.txt",
"mfccdata/testing_labels.txt")
def run_part22_audio(k):
print("================MFC - BINARY FEATURE================")
print("Importing data...")
train_dataset = feature_map_part2_2(train_audio_dataset, {
' ': 1,
'%': 0
}, (30, 13), 5)
test_dataset = feature_map_part2_2(test_audio_dataset, {
' ': 1,
'%': 0
}, (30, 13), 5)
run(k, train_dataset, test_dataset)
print("===================================================\n")
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import ticker
from import_data import import_train_data, import_test_data
from naive_bayes import train, test, evaluation, output_result, run
from feature_map import feature_map_part1_1, feature_map_part1_2
train_raw_digit_dataset = import_train_data("digitdata/trainingimages",
"digitdata/traininglabels")
test_raw_digit_dataset = import_test_data("digitdata/testimages",
"digitdata/testlabels")
train_raw_face_dataset = import_train_data("facedata/facedatatrain",
"facedata/facedatatrainlabels")
test_raw_face_dataset = import_test_data("facedata/facedatatest",
"facedata/facedatatestlabels")
# Returns the n largest indices from a numpy array
def largest_indices(ary, n):
flat = ary.flatten()
indices = np.argpartition(flat, -n)[-n:]
indices = indices[np.argsort(-flat[indices])]
return np.unravel_index(indices, ary.shape)
def run_part1_digit_1(k):
print("================DIGIT - BINARY FEATURE================")
print("Importing data...")
train_dataset = feature_map_part1_1(train_raw_digit_dataset, {
' ': 0,
'#': 1,
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import ticker
from import_data import import_train_data, import_test_data
from naive_bayes import train, test, evaluation, output_result, run
from feature_map import feature_map_part2_extra3
import itertools
(train_yes_data,
train_yes_label) = import_train_data("audiodata/yes_train.txt",
"audiodata/yes_train_label.txt")
(test_yes_data,
test_yes_label) = import_test_data("audiodata/yes_test.txt",
"audiodata/yes_test_label.txt")
(train_no_data,
train_no_label) = import_train_data("audiodata/no_train.txt",
"audiodata/no_train_label.txt")
(test_no_data,
test_no_label) = import_test_data("audiodata/no_test.txt",
"audiodata/no_test_label.txt")
def run_part2_extra3(k):
print("================AUDIO - AVERAGE FEATURE================")
print("Importing data...")
train_audio_dataset = (np.concatenate((train_yes_data, train_no_data)),
np.concatenate((train_yes_label, train_no_label)))
test_audio_dataset = (np.concatenate((test_yes_data, test_no_data)),
np.concatenate((test_yes_label, test_no_label)))