'''Author: Shawon Ashraf'''
import corpus.corpus as ec
from collections import Counter
import matplotlib.pyplot as plt
if __name__ == "__main__":
path_to_gold = '../data/isear/isear-val.csv'
path_to_pred = '../data/isear/isear-val-prediction.csv'
path_to_train = '../data/isear/isear-train.csv'
path_to_test = '../data/isear/isear-test.csv'
c = ec.Corpus(path_to_train, path_to_test, path_to_gold, path_to_pred)
print("===========================")
print("Statistics for training data")
print("============================")
print()
train_data = c.train_data
train_labels = [emo.label for emo in train_data]
train_counts = Counter(train_labels)
for k in train_counts.keys():
print(f"{k} => {train_counts[k]}")
print(f"total = {sum(train_counts.values())}")
print()
print("===========================")
print("Statistics for testing data")
from corpus import corpus
import sys
if __name__ == '__main__':
c = corpus.Corpus('test', sys.argv[1])
f = c.frequency('f1', [200500, 200600, 200700], ['terrorist'], 'Filtered')
f.frequency_from_file(sys.argv[2])
e = f.take_freq()
e.display()
e.write_to_json('/Users/ben/Desktop/graph_data')
parser.add_argument("-y", action="store", help="year ranges")
parser.add_argument("-n", action="store", help="frequency record name")
parser.add_argument("-d",
action="store",
help="publication date key name for volumes",
default="Date")
parser.add_argument("-txt", action="store", help="output text filepath")
return parser.parse_args()
if __name__ == '__main__':
args = setup_parser()
corp = corpus.Corpus('corp', args.i)
freq = corp.frequency('freq', [int(y) for y in args.y.split(",")], args.t,
args.d)
freq1 = freq.take_freq(args.k.split(","), args.n)
freq1.write_to_json("{}_global.json".format(args.o))
freq1.write("{}_global.txt".format(args.txt))
avg = freq.take_average_freq(args.k.split(","), args.n)
avg.write_to_json("{}_avg.json".format(args.o))
avg.write("{}_avg.txt".format(args.txt))
var = freq.take_variance(args.k.split(","), args.n)
var.write_to_json("{}_var.json".format(args.o))
var.write("{}_var.txt".format(args.txt))
parser.add_argument("-t",
action="store",
help="text field to analyze",
default="Filtered")
parser.add_argument("-d",
action="store",
help="publication date key name for volumes",
default="Year Published")
parser.add_argument("-y", action="store", help="year range")
return parser.parse_args()
if __name__ == '__main__':
args = setup_parser()
if args.y:
r = args.y.split(",")
y_min = int(r[0])
y_max = int(r[1])
else:
y_min = -1 * sys.maxsize
y_max = sys.maxsize
corp = corpus.Corpus("corp", args.i)
sub = corp.build_sub_corpus('sub', args.o, args.k.split(','), args.t,
args.d, int(args.l), [y_min, y_max])