"""
import numpy as np
import pickle
from import_data import load_pickle
from features import simple_features, feature_array
folders = [
'MM09', 'MM10', 'MM11', 'MM12', 'MM14', 'MM15', 'MM16', 'MM18', 'MM19',
'MM20', 'MM21'
]
path = "C:/Users\SB00745777\OneDrive - Ulster University\KaraOne\Data/"
for f in folders:
new_path = path + f
data = load_pickle(new_path, "window_data.p")
labels = load_data(new_path, "labels", "labels")
feature_vector = []
for tr in data:
wdw_mn, wdw_absmn, wdw_sm, wdw_sd, wdw_md, wdw_vr, wdw_mx, wdw_absmx, wdw_mnm, wdw_absmin, wdw_mxmn, wdw_mnmx = (
[] for i in range(12))
for wdw in tr:
ch_mn, ch_absmn, ch_sm, ch_sd, ch_md, ch_vr, ch_mx, ch_absmx, ch_mnm, ch_absmin, ch_mxmn, ch_mnmx = (
[] for i in range(12))
for ch in wdw:
mn, absmn, sd, sm, md, vr, mx, absmx, mnm, absmin, mxmn, mnmx = simple_features(
ch)
ch_mn.append(mn)
ch_absmn.append(absmn)
ch_sm.append(sm)
import pandas as pd
import time as time
# from neural_network_classifier import run_neural_network
# from xgboost_classifier import run_xgboost
from import_data import load_pickle
from feature_extraction import extract_features
# from svm_classifier import run_svm
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from neural_network_classifier import magic
train1_df = load_pickle('data/train1.pkl')
test1_df = load_pickle('data/test1.pkl')
train2_df = load_pickle('data/train2.pkl')
test2_df = load_pickle('data/test2.pkl')
# charf_tr1 = extract_features(train1_df, chars=True)
# wordf_tr1 = extract_features(train1_df, words=True)
# posf_tr1 = extract_features(train1_df, pos_tags = True)
# posf_ts1 = extract_features(test1_df, pos_tags=True)
# print("svm w/ countvectorizer on n-gram chars")
tr1_char_1 = extract_features(
train1_df,
TfidfVectorizer(analyzer="char", ngram_range=(1, 1), binary=False))
tr1_char_2 = extract_features(
train1_df,
TfidfVectorizer(analyzer="char", ngram_range=(2, 2), binary=False))
tr1_char_3 = extract_features(
train1_df,
import numpy as np
from sklearn.svm import SVC
from sklearn.model_selection import StratifiedKFold, cross_val_score
from import_data import load_pickle
from feature_extraction import extract_features
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.preprocessing import LabelEncoder
train1_df = load_pickle('data/train1.pkl')
count_tr1_char_2 = extract_features(
train1_df,
TfidfVectorizer(analyzer="word", ngram_range=(3, 3), binary=False))
def run_svm(df):
# casting X as list
X = df["text"].tolist()
# labelencoding and casting y as list
enc = LabelEncoder()
y = df["author"].tolist()
y = enc.fit_transform(y).tolist()
clf = SVC(gamma="auto", kernel="linear")
score = cross_val_score(clf, X, y, cv=5)
return [score, score.mean(), score.std()]
print(run_svm(count_tr1_char_2))
from sklearn.multiclass import OneVsRestClassifier
folders = [
'MM09', 'MM10', 'MM11', 'MM12', 'MM14', 'MM15', 'MM16', 'MM18', 'MM19',
'MM20', 'MM21'
] #folder names
path = "C:/Users\cfcoo\OneDrive - Ulster University\KaraOne\Data/"
classes = [
'/uw/', '/tiy/', '/iy/', '/m/', '/n/', '/piy/', '/diy/', 'gnaw', 'pat',
'knew', 'pot'
] #class labels
classifier_scores = pd.DataFrame() #DataFrame for saving CV scores
for f in folders:
new_path = path + f
data = load_pickle(new_path, "td_df.p")
features = data.Features.tolist()
features = np.array(features)
targets = np.array(data.Targets)
class_names = order_class_labels(
classes,
targets) #orders class_names in the order they first appear in dataset
X_Train, X_Test, y_train, y_test = train_test_split(features,
targets,
test_size=0.2,
random_state=42)
clf = SVC(kernel='linear', class_weight='balanced')
pca = PCA(svd_solver='randomized', whiten=True)