https://github.com/udacity/ud120-projects

email_preprocess.py

#!/usr/bin/python

import pickle
import cPickle
import numpy

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


def preprocess(words_file = "../tools/word_data.pkl", authors_file="../tools/email_authors.pkl"):
    """ 
        this function takes a pre-made list of email texts (by default word_data.pkl)
        and the corresponding authors (by default email_authors.pkl) and performs
        a number of preprocessing steps:
            -- splits into training/testing sets (10% testing)
            -- vectorizes into tfidf matrix
            -- selects/keeps most helpful features

        after this, the feaures and labels are put into numpy arrays, which play nice with sklearn functions

        4 objects are returned:
            -- training/testing features
            -- training/testing labels

    """

    ### 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 = 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.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)

    #print "Features test, ", features_test

    ### text vectorization--go from strings to lists of numbers
    vectorizer = TfidfVectorizer(sublinear_tf=True, max_df=0.5,
                                 stop_words='english')
    #features_train_transformed = vectorizer.fit_transform(features_train)
    #features_test_transformed  = vectorizer.transform(features_test)
    features_train_vectorized = vectorizer.fit_transform(features_train)
    features_test_vectorized = vectorizer.transform(features_test)


    ### feature selection, because text is super high dimensional and 
    ### can be really computationally chewy as a result
    #selector = SelectPercentile(f_classif, percentile=10)
    #selector.fit(features_train_transformed, labels_train)
    #features_train_transformed = selector.transform(features_train_transformed).toarray()
    #features_test_transformed  = selector.transform(features_test_transformed).toarray()
    selector = SelectPercentile(f_classif, percentile=5)
    selector.fit(features_train_vectorized, labels_train)
    features_train_transformed = selector.transform(features_train_vectorized).toarray()
    features_test_transformed  = selector.transform(features_test_vectorized).toarray()

    #print "Label trains, ", labels_train
    flattened_feature = features_train_transformed.ravel()
    z_f = [f for f in flattened_feature if f == 0]
    print "Zero feat, ", len(z_f)
    print "features, ", len(flattened_feature)

    print "Number of features: ", len(flattened_feature) - len(z_f)

    ### 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)
    
    return features_train_transformed, features_test_transformed, labels_train, labels_test


preprocess()

Interesting Resources to look at

http://stackoverflow.com/questions/21338090/how-can-i-store-and-print-the-top-20-feature-names-and-scores