In [ ]:
from sklearn import tree
# from email_preprocess import preprocess
In [ ]:
if 'features_train' not in locals() or globals():
%run ../dev/environment_setup.ipynb
In [ ]:
def preprocess2 (number):
# words_file = "../data/word_data.pkl"
# authors_file="../data/email_authors.pkl"
### the words (features) and authors (labels), already largely preprocessed
### this preprocessing will be repeated in the text learning mini-project
word_data = pickle.load( open("../data/word_data.pkl", "r"))
authors = pickle.load( open("../data/email_authors.pkl", "r") )
### 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)
### 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)
### feature selection, because text is super high dimensional and
### can be really computationally chewy as a result
selector = SelectPercentile(f_classif, percentile=number)
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()
return features_train_transformed, features_test_transformed, labels_train, labels_test
In [ ]:
features_train, features_test, labels_train, labels_test = preprocess2(1)
In [ ]:
clf = tree.DecisionTreeClassifier(min_samples_split=40)
In [ ]:
train_predict_fulldataset("Train and Predict Data with percentile = 1")
In [ ]:
features_train, features_test, labels_train, labels_test = preprocess2(10)
In [ ]:
train_predict("Train and Predict Data with percentile = 10")