find_signature.py

#!/usr/bin/python

import pickle
import numpy
from sklearn.feature_selection import SelectPercentile, f_classif

numpy.random.seed(42)

### The words (features) and authors (labels), already largely processed.
### These files should have been created from the previous (Lesson 10)
### mini-project.
words_file = "../text_learning/your_word_data.pkl"
authors_file = "../text_learning/your_email_authors.pkl"
word_data = pickle.load(open(words_file, "rb"))
authors = pickle.load(open(authors_file, "rb"))

### test_size is the percentage of events assigned to the test set (the
### remainder go into training)
### feature matrices changed to dense representations for compatibility with
### classifier functions in versions 0.15.2 and earlier
from sklearn import cross_validation

features_train, features_test, labels_train, labels_test = cross_validation.train_test_split(word_data, authors,
                                                                                             test_size=0.1,
                                                                                             random_state=42)

from sklearn.feature_extraction.text import TfidfVectorizer

vectorizer = TfidfVectorizer(sublinear_tf=True, max_df=0.5,
                             stop_words='english')
features_train_transformed = vectorizer.fit_transform(features_train).toarray()
features_test_transformed = vectorizer.transform(features_test).toarray()

selector = SelectPercentile(f_classif, percentile=10)
selector.fit(features_train, labels_train)

features_train_transformed = selector.transform(features_train)
features_test_transformed = selector.transform(features_test)

print("CHRIS = {}:,SARA= {}".format(print(sum(labels_train)), len(labels_train) - sum(labels_train)))

### a classic way to overfit is to use a small number
### of data points and a large number of features;
### train on only 150 events to put ourselves in this regime
features_train = features_train[:150]
labels_train = labels_train[:150]

### your code goes here