def baseline(person, debug=1, mcnemar=False):
rep_data = load_json("representatives")[person]
rep_party = (rep_data["current_role"])["party"]
path = "all_no_summary_linear_"
# using data from all_no_summary_linear experiment coz data for all reps is generated
data_set_test = json.loads(
open("data_set/" + path + "test/" + str(person)).read()
) # Ugly but short way to open test data
test_data_points = data_set_test["data"]
data_points = test_data_points # not concatenating train and test datasets
dataset_length = len(data_points)
numerrors = 0
numfalseyes = 0
numfalseno = 0
stats = {}
badpredict = []
for point in data_points:
bill_number = (point["bill"])["number"]
sponsor_party = ((point["bill"])["sponsor_role"])["party"]
# print sponsor_party
voteobj = point["vote_obj"]
vote = svm.getVoteOutcome(voteobj["option"])
# predict vote based on sponsor_party
predictedVote = 0
if rep_party == sponsor_party:
predictedVote = 1
# evaluate performance
if vote == 0:
if predictedVote == 1:
if mcnemar:
badpredict.append(bill_number)
numerrors = numerrors + 1
numfalseyes = numfalseyes + 1
else:
if predictedVote == 0:
if mcnemar:
badpredict.append(bill_number)
numerrors = numerrors + 1
numfalseno = numfalseno + 1
errorrate = float(numerrors) / float(dataset_length) * 100
accuracy = float(100) - errorrate
print
print "====================================="
print " " + name
print "====================================="
print
if debug >= 2:
print "Number of errors: " + str(numerrors)
if debug >= 1:
print "Error Percentage: " + str(errorrate)
if debug >= 1:
print "Accuracy: " + str(accuracy)
if debug >= 2:
print "Number of false predictions of a yes vote: " + str(numfalseyes)
if debug >= 2:
print "Number of false predictions of a no vote: " + str(numfalseno)
stats["Total Errors"] = numerrors
stats["Accuracy"] = accuracy
stats["Error Rate"] = errorrate
stats["Total False Positives"] = numfalseyes
stats["Total False Negatives"] = numfalseno
stats["Dataset Size"] = str(dataset_length)
if mcnemar:
stats["WrongPredictions"] = badpredict
return stats
import gen_feature_data
import svm
import config
from gen_feature_data import load_json
'''
Generic experiment with no summary features.
'''
name = "summary"
rep_id = '400404'
rep_data = load_json('representatives')[rep_id]
config.features_to_ignore = []
config.force_preprocess = True
config.use_sparse_data = True
print
print '====================================='
print ' '+name
print '====================================='
print
# Generate our feature vectors
# TODO(john): Cache this before we start to massive tests to save time
gen_feature_data.genExperimentData(rep_id, experiment_name=name)
# Train the SVM and print results
# TODO(john): Return results in such a way that we can analyze multiple reps