Skip to content

Update email_preprocess.py #262

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

Update email_preprocess.py #262

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
15 changes: 7 additions & 8 deletions tools/email_preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,9 @@
#!/usr/bin/python

import pickle
import cPickle
import numpy

from sklearn import cross_validation
from sklearn import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_selection import SelectPercentile, f_classif

Expand All @@ -29,17 +28,17 @@ def preprocess(words_file = "../tools/word_data.pkl", authors_file="../tools/ema

### the words (features) and authors (labels), already largely preprocessed
### this preprocessing will be repeated in the text learning mini-project
authors_file_handler = open(authors_file, "r")
authors_file_handler = open(authors_file, "rb")
authors = pickle.load(authors_file_handler)
authors_file_handler.close()

words_file_handler = open(words_file, "r")
word_data = cPickle.load(words_file_handler)
words_file_handler = open(words_file, "rb")
word_data = pickle.load(words_file_handler)
words_file_handler.close()

### test_size is the percentage of events assigned to the test set
### (remainder go into training)
features_train, features_test, labels_train, labels_test = cross_validation.train_test_split(word_data, authors, test_size=0.1, random_state=42)
features_train, features_test, labels_train, labels_test = train_test_split(word_data, authors, test_size=0.1, random_state=42)



Expand All @@ -59,7 +58,7 @@ def preprocess(words_file = "../tools/word_data.pkl", authors_file="../tools/ema
features_test_transformed = selector.transform(features_test_transformed).toarray()

### info on the data
print "no. of Chris training emails:", sum(labels_train)
print "no. of Sara training emails:", len(labels_train)-sum(labels_train)
print("no. of Chris training emails:", sum(labels_train))
print("no. of Sara training emails:", len(labels_train)-sum(labels_train))

return features_train_transformed, features_test_transformed, labels_train, labels_test