Skip to content

Update TXTfpbsupervised.py #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ningboyuan wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update TXTfpbsupervised.py #7

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions TXTfpbsupervised/TXTfpbsupervised.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,14 +10,14 @@
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer

from sklearn.cross_validation import StratifiedKFold
from sklearn.cross_validation import cross_val_score
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score

# svm
from sklearn.linear_model import SGDClassifier

# grid search
from sklearn.grid_search import GridSearchCV
from sklearn.model_selection import GridSearchCV
from pprint import pprint
from time import time

Expand Down Expand Up @@ -115,18 +115,18 @@ def indexer(index1, index2):
return [index1[i] for i in index2]


def cver(y, x, folds, seed):
def cver(y, x, splits, seed):
"""Stratified k-fold crossvalidation with upsampling."""
skf = StratifiedKFold(y, n_folds = folds, shuffle = True,
random_state = seed)
kf = KFold(n_splits = splits, shuffle = True,
random_state = seed)

ind = np.array(list(range(0, len(x))))

ind_train, ind_test = [], []
x_train, x_test = [], []
y_train, y_test = [], []

for train_set, test_set in skf:
for train_set, test_set in kf.split(x):
x_train.append(x[train_set])
x_test.append(x[test_set])
y_train.append(y[train_set])
Expand Down Expand Up @@ -209,7 +209,7 @@ def cv_pred(x, y, custom_cv, piper, unique_y = True):

# setup
seed = 123
folds = 5
splits = 5

# CountVectorizer
stop_words = (None, 'english')
Expand All @@ -231,12 +231,12 @@ def cv_pred(x, y, custom_cv, piper, unique_y = True):
lem = df["lemma"]
sco = df["sentiment"]

custom_cv = cver(sco, lem, folds, seed)
custom_cv = cver(sco, lem, splits, seed)

piper = Pipeline([("vect", CountVectorizer(tokenizer = tokenize)),
("tfidf", TfidfTransformer()),
("clf", SGDClassifier(shuffle = True,
n_iter = 80,
max_iter = 80,
random_state = seed)),
])

Expand Down