def main(argv):
# Constants for the analyzer and the classifier
dataset = 'commit_comments-dump.2015-01-29.json'
group = 'id'
model_file = 'model.pickle'
# Create the analyzer
analyzer = Analyzer(group)
# Create the classifier
algorithm_class = RandomForestRegressor
algorithm_parameters = {
'n_estimators': 100,
'n_jobs': 2,
'min_samples_split': 10
}
classifier = Classifier(group, model_file)
classifier.create_model(train=True,
class_name=algorithm_class,
parameters=algorithm_parameters)
# Compare analyzer output with classifier output and identify differences
unrecognized_negative = {}
unrecognized_positive = {}
predictions = classifier.predict()
line = 0 # Dataset line
i = 0 # Prediction ID (+1)
file = open(dataset, 'rb')
for data in Utilities.read_json(file, 'id', group):
line = line + 1
if line % 1000 == 0:
print(line)
if not classifier.filter(data):
continue
i = i + 1
message = data['message']
score = analyzer.analyze(message)[0]
if score == 0:
continue
diff = predictions[i - 1] - score
if abs(diff) < 1.0:
continue
target = unrecognized_negative if diff < 0 else unrecognized_positive
target[line] = diff
result = sorted(unrecognized_positive.items(), key=lambda x: x[1])
for item in result:
print("{}: {}: {}".format(item[0], item[1],
linecache.getline(dataset, item[0])[:-1]))
def main(argv):
folds = int(argv[0]) if len(argv) > 0 else 5
filter = argv[1].lower() if len(argv) > 1 else ""
# Fields to check whether the filter, if given, appears in.
filter_fields = ['name', 'class_name', 'module']
# Read the manifest containing algorithm descriptions.
with open('algorithms.json', 'r') as manifest:
algorithms = json.load(manifest)
# Load previous results
try:
with open('experiment_results.json', 'r') as file:
results = json.load(file)
except:
results = {}
for algorithm in algorithms:
# Skip running the algorithm if it is disabled or the filter name does
# not appear in any of the fields.
if 'disabled' in algorithm and algorithm['disabled']:
continue
if filter and all(
[filter not in algorithm[k].lower() for k in filter_fields]):
continue
# Convert manifest entries to classifier class and parameters
class_name = Utilities.get_class(algorithm['module'],
algorithm['class_name'])
dense = algorithm['dense'] if 'dense' in algorithm else False
# Create all possible combinations of parameters.
parameter_combinations = itertools.product(
*algorithm['parameters'].values())
single_parameters = [
param for param, values in algorithm['parameters'].iteritems()
if len(values) == 1
]
string_parameters = [
param for param, values in algorithm['parameters'].iteritems()
if isinstance(values[0], (str, unicode))
]
for combination in parameter_combinations:
classifier = Classifier('id')
# Turn the selected parameter combination back into a dictionary
parameters = dict(zip(algorithm['parameters'].keys(), combination))
# Create the model according to the parameters
classifier.create_model(train=False,
class_name=class_name,
parameters=parameters,
dense=dense)
Utilities.print_algorithm(algorithm['name'], parameters)
parameter_string = Utilities.get_parameter_string(
parameters, single_parameters + string_parameters)
# Run cross-validation and print results
result = classifier.output_cross_validate(folds)
print('')
name = algorithm['name']
for param in string_parameters:
name += ", %s=%s" % (param, parameters[param])
# Write the result measurements into the results dictionary.
if name not in results:
results[name] = OrderedDict()
results[name].update({
parameter_string: {
'average': result.mean(),
'standard_deviation': result.std()
}
})
# Write intermediate results (back) into a pretty-printed JSON file
with open('experiment_results.json', 'w') as file:
json.dump(results, file, indent=4, separators=(',', ': '))
def main(argv):
folds = int(argv[0]) if len(argv) > 0 else 5
filter = argv[1].lower() if len(argv) > 1 else ""
# Fields to check whether the filter, if given, appears in.
filter_fields = ['name', 'class_name', 'module']
# Read the manifest containing algorithm descriptions.
with open('algorithms.json', 'r') as manifest:
algorithms = json.load(manifest)
# Load previous results
try:
with open('experiment_results.json', 'r') as file:
results = json.load(file)
except:
results = {}
for algorithm in algorithms:
# Skip running the algorithm if it is disabled or the filter name does
# not appear in any of the fields.
if 'disabled' in algorithm and algorithm['disabled']:
continue
if filter and all([filter not in algorithm[k].lower() for k in filter_fields]):
continue
# Convert manifest entries to classifier class and parameters
class_name = Utilities.get_class(algorithm['module'], algorithm['class_name'])
dense = algorithm['dense'] if 'dense' in algorithm else False
# Create all possible combinations of parameters.
parameter_combinations = itertools.product(*algorithm['parameters'].values())
single_parameters = [param for param,values in algorithm['parameters'].iteritems() if len(values) == 1]
string_parameters = [param for param,values in algorithm['parameters'].iteritems() if isinstance(values[0],(str,unicode))]
for combination in parameter_combinations:
classifier = Classifier('id')
# Turn the selected parameter combination back into a dictionary
parameters = dict(zip(algorithm['parameters'].keys(), combination))
# Create the model according to the parameters
classifier.create_model(train=False, class_name=class_name, parameters=parameters, dense=dense)
Utilities.print_algorithm(algorithm['name'], parameters)
parameter_string = Utilities.get_parameter_string(parameters, single_parameters + string_parameters)
# Run cross-validation and print results
result = classifier.output_cross_validate(folds)
print('')
name = algorithm['name']
for param in string_parameters:
name += ", %s=%s" % (param,parameters[param])
# Write the result measurements into the results dictionary.
if name not in results:
results[name] = OrderedDict()
results[name].update({
parameter_string: {
'average': result.mean(),
'standard_deviation': result.std()
}
})
# Write intermediate results (back) into a pretty-printed JSON file
with open('experiment_results.json', 'w') as file:
json.dump(results, file, indent=4, separators=(',', ': '))