Created
June 4, 2019 13:35
-
-
Save dnabanita7/b3c83c58f154c2ce0cc73950e71f8baa to your computer and use it in GitHub Desktop.
pd.concat can append dataframes but it is showing an error
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import sys | |
import errno | |
import pandas as pd | |
import numpy as np | |
import scipy.sparse as sparse | |
from sklearn.feature_extraction.text import CountVectorizer | |
from sklearn.feature_extraction.text import TfidfTransformer | |
try: | |
import cPickle as pickle | |
except ImportError: | |
import pickle | |
np.set_printoptions(suppress=True) | |
if len(sys.argv) != 3 and len(sys.argv) != 5: | |
sys.stderr.write('Arguments error. Usage:\n') | |
sys.stderr.write('\tpython featurization.py data-dir-path features-dir-path\n') | |
sys.exit(1) | |
train_input = os.path.join(sys.argv[1], 'train.tsv') | |
test_input = os.path.join(sys.argv[1], 'test.tsv') | |
train_output = os.path.join(sys.argv[2], 'train.pkl') | |
test_output = os.path.join(sys.argv[2], 'test.pkl') | |
try: | |
reload(sys) | |
sys.setdefaultencoding('utf-8') | |
except NameError: | |
pass | |
def mkdir_p(path): | |
try: | |
os.makedirs(path) | |
except OSError as exc: # Python >2.5 | |
if exc.errno == errno.EEXIST and os.path.isdir(path): | |
pass | |
else: | |
raise | |
def save_matrix(df, matrix, output): | |
id_matrix = sparse.csr_matrix(df.id.astype(np.int64)).T | |
label_matrix = sparse.csr_matrix(df.label.astype(np.int64)).T | |
result = sparse.hstack([id_matrix, label_matrix, matrix], format='csr') | |
msg = 'The output matrix {} size is {} and data type is {}\n' | |
sys.stderr.write(msg.format(output, result.shape, result.dtype)) | |
with open(output, 'wb') as fd: | |
pickle.dump(result, fd, pickle.HIGHEST_PROTOCOL) | |
pass | |
mkdir_p(sys.argv[2]) | |
# Generate train feature matrix | |
for tp in pd.read_csv( | |
train_input, | |
encoding='utf-8', | |
header=None, | |
sep='\t', | |
names=['id', 'label', 'text'], | |
iterator=True, | |
chunksize=1000 | |
): | |
train_words = np.array(tp.text.str.lower().values.astype('U')) | |
bag_of_words = CountVectorizer(stop_words='english', | |
max_features=5000) | |
bag_of_words.fit(train_words) | |
train_words_binary_matrix = bag_of_words.transform(train_words) | |
tfidf = TfidfTransformer(smooth_idf=False) | |
tfidf.fit(train_words_binary_matrix) | |
tp_tfidf_matrix = tfidf.transform(train_words_binary_matrix) | |
df_train = df_train.append(tp, ignore_index = True) | |
train_words_tfidf_matrix = train_words_tfidf_matrix.append(tp_tfidf_matrix, ignore_index=True) | |
save_matrix(df_train, train_words_tfidf_matrix, train_output) | |
# Generate test feature matrix | |
for tp in pd.read_csv(test_input, | |
encoding='utf-8', | |
header=None, | |
sep='\t', | |
names=['id', 'label', 'text'], | |
iterator=True, | |
chunksize=50): | |
test_words = np.array(tp.text.str.lower().values.astype('U')) | |
test_words_binary_matrix = bag_of_words.transform(test_words) | |
tp_tfidf_matrix = tfidf.transform(test_words_binary_matrix) | |
df_test = df_test.append(tp, ignore_index=True) | |
test_words_tfidf_matrix = test_words_tfidf_matrix.append(tp_tfidf_matrix, ignore_index=True) | |
save_matrix(df_test, test_words_tfidf_matrix, test_output) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment