def evaluate(category, clf, datamanager, data=(None, None)):
"""Run evaluation of a classifier, for one category.
If data isn't set explicitly, the test set is
used by default.
"""
log_file = os.path.join(datamanager.PATHS["LOGS"], "evaluation",
class_name(clf), category)
log_file = os.path.join(log_file, str(datetime.now()) + ".log")
vcd = VisualConceptDetection(None, datamanager, log_file=log_file)
clf = vcd.load_object("Classifier", category, clf)
vcd.classifier = clf
if (data[0] is None) or (data[1] is None):
return vcd.evaluate_test_set(category)
else:
return vcd.evaluate(X_test=data[0], y_test=data[1])
def setUp(self):
self.datamanager = MyTestDataManager()
clf = AdaBoostClassifier(n_estimators=14)
clf.base_estimator.max_depth = 10
self.vcd = VisualConceptDetection(clf, self.datamanager)
import sys
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.svm import LinearSVC, SVC
from vcd import VisualConceptDetection
import os
import time
from util import svm
from datamanagers.CaltechManager import CaltechManager
import numpy as np
import pylab as pl
from runGridSearch import GridSearch
if __name__ == "__main__":
category = "airplanes"
total = time.time()
clf = RandomForestClassifier(n_estimators=2000)
# clf = AdaBoostClassifier(n_estimators = 2000)
# clf.base_estimator.max_depth = 4
# clf = LinearSVC(C=100)
# clf = SVC(C=10)
dm = CaltechManager()
vcd = VisualConceptDetection(classifier=clf, datamanager=dm)
vcd.run(category)
print "Total execution time: %f minutes" % ((time.time() - total) / 60.0)
if __name__ == "__main__":
# ada = AdaBoostClassifier()
# ada.n_estimators = 50
# ada.base_estimator.max_depth = 1
random_forest = RandomForestClassifier(n_estimators=100)
category = "trilobite"
dataset = "all"
datamanager = CaltechManager()
datamanager.PATHS["RESULTS"] = os.path.join(
datamanager.PATHS["BASE"], "results_trilobite_rf_testing")
# vcd = VisualConceptDetection(ada, datamanager)
vcd = VisualConceptDetection(random_forest, datamanager)
clf = vcd.load_object("Classifier", category)
feature_importances = clf.feature_importances_
sample_matrix = vcd.datamanager.build_sample_matrix(dataset, category)
class_vector = vcd.datamanager.build_class_vector(dataset, category)
pred = clf.predict_proba(sample_matrix)
vis = EnsembleVisualization(datamanager)
del clf
image_titles = [
vis.get_image_title(prediction, real)
for prediction, real in izip(pred, class_vector)
]
del class_vector
def get_svm_importances(coef):
"""Normalize the SVM weights."""
factor = 1.0 / np.linalg.norm(coef)
return (coef * factor).ravel()
if __name__ == "__main__":
svm = LinearSVC(C=0.1)
category = "Faces"
dataset = "all"
datamanager = CaltechManager()
datamanager.PATHS["RESULTS"] = os.path.join(
datamanager.PATHS["BASE"], "results_Faces_LinearSVC_normalized")
vcd = VisualConceptDetection(svm, datamanager)
clf = vcd.load_object("Classifier", category)
importances = get_svm_importances(clf.coef_)
sample_matrix = vcd.datamanager.build_sample_matrix(dataset, category)
class_vector = vcd.datamanager.build_class_vector(dataset, category)
pred = clf.decision_function(sample_matrix)
del clf
image_titles = [
get_image_title(prediction, real)
for prediction, real in izip(pred, class_vector)
]
del class_vector
del sample_matrix
