Ejemplo n.º 1
0
tag_groups = mfv.autogen_tag_groups()
machines = ['win7x32','win7x64']

#seperate by machine
for machine in machines : 
    for tags in tag_groups :
        #group name auto generated by tags and machine
        group_name = "{0}_{1}_{2}_{3}_{4}".format(tags[0][1],tags[1][1],tags[2][1],tags[3][1],machine)
        
        print "Creating automated stats for {0}".format(group_name) 
    
        task_ids = None
        hashes = None
        
        #get subset
        subset_vectors = mfv.select_vectors(tags, [machine], task_ids, hashes)    
        subset_vectors = mfv.normalize_vectors(subset_vectors, max_values_vector)
    
        #get superset - keep only fileytpe tags and machine
        superset_vectors = mfv.select_vectors([tags[1]],[machine],None,None)
        superset_vectors = mfv.normalize_vectors(superset_vectors, max_values_vector)
    
        #find archetype vector and extract feature keys
        archetype, archetype_stddev = mfv.get_archetype(subset_vectors, superset_vectors)
        feature_keys = []
        for key, value in archetype.features.iteritems() :
            feature_keys.append(key)
        
        #find groups stats and plot archetype features for group     
        mfv.stats_summary(subset_vectors,superset_vectors)
        title = "Scatter Plot of Family {0}".format(group_name)
test_task_id = int(sys.argv[1])

#retrieve features from the database
cmd = "SELECT label,mean_features,stddev_features,max_value_features FROM archetypes"

cursor.execute(cmd)
results = cursor.fetchall()

for result in results :
    #parse data from results    
    archetype_label = result[0]
    mean_features = json.loads(result[1])
    stddev_features = json.loads(result[2])
    max_value_features = json.loads(result[3])

    #add features to FeatureVectors
    mean_vector = mfv.FeatureVector(None,None,None,mean_features)
    stddev_vector = mfv.FeatureVector(None,None,None,stddev_features)
    max_values_vector = mfv.FeatureVector(None,None,None,max_value_features)

    #retrieve and normalize the test_vector
    test_vector = mfv.select_vectors(None,None,[test_task_id],None)[0]
    test_vectors = mfv.normalize_vectors([test_vector],max_values_vector)

    #add labels to vectors
    mean_vector.label = archetype_label+"_mean"
    stddev_vector.label = archetype_label+"_stddev"

    title = "Comparison of Task {0} to Archetype : {1}".format(test_task_id,archetype_label)
    filename = "comparisions/{0}/{1}".format(test_task_id, archetype_label)
    print mfv.plotly_scatter(test_vectors, mean_vector, stddev_vector, None, filename, title)
Ejemplo n.º 3
0
#retrieve features from the database
cmd = "SELECT label,mean_features,stddev_features,max_value_features FROM archetypes"

cursor.execute(cmd)
results = cursor.fetchall()

for result in results:
    #parse data from results
    archetype_label = result[0]
    mean_features = json.loads(result[1])
    stddev_features = json.loads(result[2])
    max_value_features = json.loads(result[3])

    #add features to FeatureVectors
    mean_vector = mfv.FeatureVector(None, None, None, mean_features)
    stddev_vector = mfv.FeatureVector(None, None, None, stddev_features)
    max_values_vector = mfv.FeatureVector(None, None, None, max_value_features)

    #retrieve and normalize the test_vector
    test_vector = mfv.select_vectors(None, None, [test_task_id], None)[0]
    test_vectors = mfv.normalize_vectors([test_vector], max_values_vector)

    #add labels to vectors
    mean_vector.label = archetype_label + "_mean"
    stddev_vector.label = archetype_label + "_stddev"

    title = "Comparison of Task {0} to Archetype : {1}".format(
        test_task_id, archetype_label)
    filename = "comparisions/{0}/{1}".format(test_task_id, archetype_label)
    print mfv.plotly_scatter(test_vectors, mean_vector, stddev_vector, None,
                             filename, title)