def get_num_and_data(args):
if not args.num:
print('use test data')
pre = Preprocessing('digits')
pre.load_data(filename='test.csv', name='test')
X_test = torch.tensor(pre.get('test').drop(columns=['0']).values,
device=device,
dtype=dtype)
y_test = torch.tensor(pre.get('test')['0'].values,
device=device,
dtype=dtype)
index = random.randint(0, len(y_test))
print('index {}'.format(index))
num = int(y_test[index].item())
print('real_numer {}'.format(num))
data_to_predict = X_test[index:index + 1, :]
return num, data_to_predict
else:
print('use written images')
num = int(args.num)
im_imp = Image_Importer('digits')
im_imp.load_image_as_grey(num)
print('real_numer {}'.format(num))
data_to_predict = im_imp.get_image_as_256px_array(num)
return num, data_to_predict
import argparse
from models import LogReg
import matplotlib.pyplot as plt
if not __name__ == '__main_':
parser = argparse.ArgumentParser(description='Digits')
parser.add_argument('--s_model', default=True, help='save trained model')
args=parser.parse_args()
n_classes = 10
n_epochs = 200
pre = Preprocessing('digits')
pre.load_data(filename='train.csv', name='train')
X_df = pre.get(name='train').drop(columns=['0'])
y_df = pre.get(name='train')['0']
dtype = torch.float
device = torch.device("cpu")
model_name = 'logreg_digits'
model = LogReg(model_name, 256, n_classes)
learning_rate = 0.0001
batch_size = 32
train_classifier = TrainClassifier(model, X_df, y_df)
from sklearn.model_selection import train_test_split
import torch.nn as nn
import models
from models import LogReg
if not __name__ == '__main_':
parser = argparse.ArgumentParser(description='IMDBData')
parser.add_argument('--n_feat', default=1000, help='number of features')
parser.add_argument('--s_model', default=False, help='save trained model')
args=parser.parse_args()
pre = Preprocessing('IMDB')
n_classes = 2
n_features = int(args.n_feat)
n_epochs = 100
pre.load_data(filename=f'training_data_{n_features}.csv', name='training_data')
X_df = pre.get(name='training_data').drop(columns=['target'])
y_df = pre.get(name='training_data')['target']
model = LogReg('log_reg', n_features, n_classes)
train_classifier = TrainClassifier(model, X_df, y_df)
trained_model, optimizer, criterion, loss_hist, loss_validate_hist = train_classifier.run_train(n_epochs = n_epochs)
pre.save_results(loss_hist, loss_validate_hist, f'log_reg_{100}')
"max_df": 1.0,
"min_df": 0,
"stop_words": [],
# keep defaults
"analyzer": "word",
"tokenizer": None,
"lowcase": False
}
lda_args = {
"n_topics": 2,
"max_iter": 1,
"n_jobs": -1,
# Note: thold is more prior than n_topic_words
# But works slower
"n_topic_words": 4,
"word_thold": None
}
preprocessing_pipeline = Preprocessing()
doc2topic = Docs2Topics(feature_extraction_args, lda_args)
preprocessed_text = preprocessing_pipeline.preprocess_batch([texts])
topics, words_per_topic = doc2topic.fit_get_topics(preprocessed_text)
import pprint
pprint.pprint(topics)
print(words_per_topic)
import time
if not __name__ == '__main_':
parser = argparse.ArgumentParser(description='IMDBData')
parser.add_argument('--n_words', default=100, help='num words')
parser.add_argument('--s_model',
default=False,
help='save transform model')
args = parser.parse_args()
n_words = args.n_words
pre = Preprocessing('imdb')
TRAIN_PATH_POS = 'train/pos/'
TRAIN_PATH_NEG = 'train/neg/'
pre.load_all_texts_from_directory(path=TRAIN_PATH_POS, name='raw_pos')
pre.load_all_texts_from_directory(path=TRAIN_PATH_NEG, name='raw_neg')
texts_list = pd.concat([pre.data['raw_pos'], pre.data['raw_neg']])
print('fit & transform training data')
text_transformer = TextTransformer(num_words=n_words)
train_features = text_transformer.fit_and_transform(texts_list)
train_features['target'] = np.append(np.ones(len(pre.data['raw_pos'])),
np.zeros(len(pre.data['raw_neg'])))
from preprocessing_utils import Preprocessing
from sklearn.model_selection import train_test_split
if not __name__ == '__main_':
pre_train = Preprocessing('digits')
kwarg = {'header': None, 'sep': ' '}
pre_train.load_data(filename='zip.train', name='raw', **kwarg)
pre_train.cleanup(name='raw',
drop_duplicates=True,
dropna={
'axis': 1,
'thresh': 2
})
print(pre_train.get('clean').head())
#classes = ['0_0.0', '0_1.0', '0_2.0', '0_3.0', '0_4.0', '0_5.0', '0_6.0', '0_7.0', '0_8.0', '0_9.0']
X = pre_train.get('clean').drop(columns=[0])
y = pre_train.get('clean')[0]
pre_train.set(name='train', value=pre_train.get('clean'))
pre_train.save(name='train')
pre_test = Preprocessing('digits')
kwarg = {'header': None, 'sep': ' '}
pre_test.load_data(filename='zip.test', name='raw', **kwarg)
pre_test.cleanup(name='raw',