In [1]:

    

# Necessary imports 
import os
import time
from nbminer.notebook_miner import NotebookMiner
from nbminer.cells.cells import Cell
from nbminer.features.features import Features
from nbminer.stats.summary import Summary
from nbminer.stats.multiple_summary import MultipleSummary
from nbminer.encoders.ast_graph.ast_graph import *
people = os.listdir('../testbed/Final')
notebooks = []
for person in people:
    person = os.path.join('../testbed/Final', person)
    if os.path.isdir(person):
        direc = os.listdir(person)
        notebooks.extend([os.path.join(person, filename) for filename in direc if filename.endswith('.ipynb')])
notebook_objs = [NotebookMiner(file) for file in notebooks[:20]]
notebook_objs_2 = [NotebookMiner(file) for file in notebooks[20:40]]


    

In [2]:

    

from nbminer.pipeline.pipeline import Pipeline
from nbminer.preprocess.get_ast_features import GetASTFeatures
from nbminer.preprocess.get_imports import GetImports
from nbminer.preprocess.resample_by_node import ResampleByNode
from nbminer.results.reconstruction_error.astor_error import AstorError
from nbminer.preprocess.feature_encoding import FeatureEncoding
from nbminer.encoders.cluster.hierarchical_encoder import HierarchicalEncoder
from nbminer.results.similarity.jaccard_similarity import NotebookJaccardSimilarity
a = Features(notebook_objs, 'group_1')
a.add_notebooks(notebook_objs_2, 'group_2')
gastf = GetASTFeatures()
rbn = ResampleByNode()
gi = GetImports()
fe = FeatureEncoding()
he = HierarchicalEncoder()
njs = NotebookJaccardSimilarity()
pipe = Pipeline([gastf, rbn, gi, fe, he, njs])
a = pipe.transform(a)


    

    




<nbminer.preprocess.get_ast_features.GetASTFeatures object at 0x1508d58ef0>
<nbminer.preprocess.resample_by_node.ResampleByNode object at 0x1506f8e9b0>
<nbminer.preprocess.get_imports.GetImports object at 0x1508304f98>
<nbminer.preprocess.feature_encoding.FeatureEncoding object at 0x1508304470>
<nbminer.encoders.cluster.hierarchical_encoder.HierarchicalEncoder object at 0x1508304f60>
<nbminer.results.similarity.jaccard_similarity.NotebookJaccardSimilarity object at 0x15082b1a58>

In [ ]:

    




    

In [3]:

    

njs.average_jaccard_similarity(8)


    

    
Out[3]:





0.27637082686051972

In [8]:

    

import numpy as np
intra, inter = njs.group_average_jaccard_similarity('group_2')
print('Mean within group: ', np.mean(np.array(intra)))
print('STD within group: ', np.std(np.array(intra)))
print('Mean outside group: ', np.mean(np.array(inter)))
print('STD outside group: ', np.std(np.array(inter)))


    

    




Mean within group:  0.220318770273
STD within group:  0.0290303713246
Mean outside group:  0.226463016768
STD outside group:  0.0251643222422

In [ ]: