forked from udacity/ud120-projects
-
Notifications
You must be signed in to change notification settings - Fork 0
/
find_signature.py
52 lines (36 loc) · 1.95 KB
/
find_signature.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
#!/usr/bin/python
import pickle
import numpy
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, "r"))
authors = pickle.load( open(authors_file, "r") )
### test_size is the percentage of events assigned to the test set (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 = vectorizer.fit_transform(features_train)
features_test = vectorizer.transform(features_test).toarray()
### 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].toarray()
labels_train = labels_train[:150]
### your code goes here
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
clf = DecisionTreeClassifier()
clf.fit(features_train, labels_train)
pred = clf.predict(features_test)
print "training points:", len(features_train)
print "accuracy_score: ", accuracy_score(labels_test, pred)
print "Importance of most important word:", clf.feature_importances_[clf.feature_importances_ > 0.2]
print "Location of most important word:", clf.feature_importances_.argmax()
print "Most important word:", vectorizer.get_feature_names()[clf.feature_importances_.argmax()]