lambda x: re_spaces.sub(" ", re_attags.sub(" ", " " + x + " "))[1:-1])
df = df.drop_duplicates(subset=['text'])
df.index = df['id'] = range(df.shape[0])
non_alphanums = re.compile('[^A-Za-z]+')
def normalize_text(text):
return non_alphanums.sub(' ', text).lower().strip()
df['text_normalized'] = df['text'].map(lambda x: normalize_text(x))
df['textblob_score'] = df['text_normalized'].map(
lambda x: textblob.TextBlob(x).polarity)
import wordbag_regressor
print("Train wordbag regressor")
wb_regressor = wordbag_regressor.WordbagRegressor(
"../models/wordbag_model.pkl.gz", tripadvisor_dir)
#wb_regressor= wordbag_regressor.WordbagRegressor("../models/wordbag_model.pkl.gz")
df['wordbag_score'] = wb_regressor.predict(df['text'].values)
import wordhash_regressor
print("Train wordhash regressor")
wh_regressor = wordhash_regressor.WordhashRegressor(
"../models/wordhash_model.pkl.gz", tripadvisor_dir)
#wh_regressor= wordhash_regressor.WordhashRegressor("../models/wordhash_model.pkl.gz")
df['wordhash_score'] = wh_regressor.predict(df['text'].values)
import wordseq_regressor
print("Train wordseq regressor")
ws_regressor = wordseq_regressor.WordseqRegressor(
"../models/wordseq_model.pkl.gz", tripadvisor_dir)
#ws_regressor = wordseq_regressor.WordseqRegressor("../models/wordseq_model.pkl.gz")
df = df.drop_duplicates(subset=['text'])
df.index = df['id'] = range(df.shape[0])
non_alphanums = re.compile('[^A-Za-z]+')
def normalize_text(text):
return non_alphanums.sub(' ', text).lower().strip()
df['text_normalized'] = df['text'].map(lambda x: normalize_text(x))
df['textblob_score'] = df['text_normalized'].map(
lambda x: textblob.TextBlob(x).polarity)
import wordbag_regressor
print("Train wordbag regressor")
#wb_regressor= wordbag_regressor.WordbagRegressor("../models/wordbag_model.pkl.gz", tripadvisor_dir)
wb_regressor = wordbag_regressor.WordbagRegressor(
"../models/wordbag_model.pkl.gz")
df['wordbag_score'] = wb_regressor.predict(df['text'].values)
import wordhash_regressor
print("Train wordhash regressor")
wh_regressor = wordhash_regressor.WordhashRegressor(
"../models/wordhash_model.pkl.gz", tripadvisor_dir)
#wh_regressor= wordhash_regressor.WordhashRegressor("../models/wordhash_model.pkl.gz")
df['wordhash_score'] = wh_regressor.predict(df['text'].values)
import wordseq_regressor
print("Train wordseq regressor")
ws_regressor = wordseq_regressor.WordseqRegressor(
"../models/wordseq_model.pkl.gz", tripadvisor_dir)
#ws_regressor = wordseq_regressor.WordseqRegressor("../models/wordseq_model.pkl.gz")
df['wordseq_score'] = ws_regressor.predict_batch(df['text'].values)