def get_binary(self):
return Pipeline([
('tfidf', TfidfVectorizer(stop_words=sw.words('dutch'), norm='l2', use_idf=True)),
('feat_select', SelectPercentile(percentile=10)),
('clf', OneVsRestClassifier(SGDClassifier(alpha=0.0001,
average=False,
class_weight=None,
epsilon=0.1,
eta0=0.0,
fit_intercept=True,
l1_ratio=0.15,
learning_rate='optimal',
loss='log',
n_iter=10,
n_jobs=1,
penalty='l2',
power_t=0.5,
random_state=None,
shuffle=True,
verbose=0,
warm_start=False
)))
])
python类SelectPercentile()的实例源码
def get_sgdc(self):
return Pipeline([
('tfidf', TfidfVectorizer(stop_words=sw.words('dutch'), norm='l2', use_idf=True)),
('feat_select', SelectPercentile(percentile=10)),
('clf', SGDClassifier(alpha=0.0001,
average=False,
class_weight=None,
epsilon=0.1,
eta0=0.0,
fit_intercept=True,
l1_ratio=0.15,
learning_rate='optimal',
loss='log',
n_iter=10,
n_jobs=1,
penalty='l2',
power_t=0.5,
random_state=None,
shuffle=True,
verbose=0,
warm_start=False))
])
def select_percentile_selector(data,target):
# Select Model
selector = SelectPercentile(percentile = 75) # Default is 10%
# Fit, Format, and Return
return format_selector(selector, data, target)
# http://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.SelectKBest.html
def select_feat(X,y,percentile=20):
"Select best 20 % of features using Anova F-value - *f_classif* from scikit.learn"
selector = SelectPercentile(f_classif, percentile=percentile)
selector.fit(X, y)
return selector.transform(X)
def get_classification_data(self, division_dummies=True, samples=None, percentile=100):
raw = PlayerCollection.filter_by_class(self.raw)
df = PlayerCollection.raw_to_df(raw)
players, divisions = PlayerCollection.aggregate_df(df)
players, divisions = PlayerCollection.to_matrix(players, divisions)
players, divisions = PlayerCollection.subsample(players, divisions, samples)
X_train, X_test, y_train, y_test = train_test_split(
players, divisions, random_state=42, stratify=divisions)
selector = SelectPercentile(f_classif, percentile=percentile)
selector.fit(X_train, y_train)
X_train = selector.transform(X_train)
X_test = selector.transform(X_test)
if division_dummies:
y_train = pd.get_dummies(y_train).as_matrix()
y_test = pd.get_dummies(y_test).as_matrix()
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)
return X_train, X_test, y_train, y_test
def test_make_pipeline():
t1 = SelectKBest()
t2 = SelectKBest()
t3 = SelectKBest()
t4 = SelectKBest()
t5 = SelectPercentile()
t6 = SelectKBest()
t7 = SelectKBest()
t8 = SelectKBest()
t9 = SelectPercentile()
in_steps = [[t1, None],
[t2, t3],
[t4, t5], # mixed
t6,
[None, t7],
[t8, None, t9], # mixed
None]
pipe = make_pipeline(*in_steps, memory='/path/to/nowhere')
union = make_union(*in_steps)
for est, est_steps in [(pipe, pipe.steps),
(union, union.transformer_list)]:
names, steps = zip(*est_steps)
assert names == ('selectkbest-1', 'selectkbest-2', 'alt-1',
'selectkbest-3', 'selectkbest-4', 'alt-2', 'nonetype')
assert steps == (t1, t2, t4, t6, None, t8, None)
assert len(est._param_grid) == 5
assert est._param_grid[names[0]] == [t1, None]
assert est._param_grid[names[1]] == [t2, t3]
assert est._param_grid[names[2]] == [t4, t5]
assert est._param_grid[names[4]] == [None, t7]
assert est._param_grid[names[5]] == [t8, None, t9]
assert type(pipe) is Pipeline
assert type(union) is FeatureUnion
assert pipe.memory == '/path/to/nowhere'
def __init__(self, filename=None):
super().__init__(filename)
if not filename:
self.clf = Pipeline([
('tfidf', TfidfVectorizer(stop_words=sw.words('dutch'))),
('anova', SelectPercentile(f_classif)),
('clf', MultinomialNB())
])
def variance_threshold_selector(data,target):
# Select Model
selector = VarianceThreshold(0) # Defaults to 0.0, e.g. only remove features with the same value in all samples
# Fit, Format, and Return
return format_selector(selector,data,target)
# http://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.SelectPercentile.html
def __init__(self, clf, params, name):
self.clf = Pipeline([('select', SelectPercentile(score_func=mutual_info_classif, percentile=70)), ('clf', clf)])
params['select__percentile'] = [60, 70, 80, 90]
self.clf = GridSearchCV(self.clf, param_grid=params, scoring='f1_macro')
self.name = name
self.scaler = MinMaxScaler()
def preprocess(X,y):
### test_size is the percentage of events assigned to the test set
### (remainder go into training)
features_train, features_test, labels_train, labels_test = model_selection.train_test_split(X, y, test_size=0.2, 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)
joblib.dump(vectorizer, 'vectorizer_intent.pkl')
### 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)
joblib.dump(selector, 'selector_intent.pkl')
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
def buildVectorizer(classes, examples, parameters):
featureChoice = None
doFeatureSelection = False
tfidf = False
featureSelectPerc = 10
if "featureChoice" in parameters:
featureChoice = parameters["featureChoice"]
if "doFeatureSelection" in parameters and parameters["doFeatureSelection"] == "True":
doFeatureSelection = True
if "featureSelectPerc" in parameters:
featureSelectPerc = int(parameters["featureSelectPerc"])
if "tfidf" in parameters and parameters["tfidf"] == "True":
tfidf = True
print "Starting vectorizer..."
vectorizer = Vectorizer(classes,examples,featureChoice,tfidf)
vectors = vectorizer.getTrainingVectors()
print "Vectors of size:", vectors.shape
if doFeatureSelection:
print "Trimming training vectors..."
from sklearn.feature_selection import SelectKBest,SelectPercentile,chi2
#featureSelector = SelectKBest(chi2, k=100)`:
featureSelector = SelectPercentile(chi2,featureSelectPerc)
vectorsTrimmed = featureSelector.fit_transform(vectors, classes)
vectorsTrimmed = coo_matrix(vectorsTrimmed)
print "Trimmed training vectors of size:", vectorsTrimmed.shape
else:
vectorsTrimmed = vectors
featureSelector = None
return vectorsTrimmed,vectorizer,featureSelector
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)
### 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=1)
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()
### 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
