}, {
DataSource.NAME: 'Twitter',
DataSource.PATH: '../../data/SemEval-2014.csv'
}]
srcs = [{
DataSource.NAME: src[DataSource.NAME],
DataSource.PATH: os.path.abspath(src[DataSource.PATH]),
DataSource.TYPE: os.path.splitext(src[DataSource.PATH])[1]
} for src in srcs]
for src in srcs:
print("Name: '%s'\nType: '%s'" %
(src[DataSource.NAME], src[DataSource.TYPE]))
dSrc = DataSource(src)
srcStats = dSrc.getStats()
print("\nUsable data:")
pprint.pprint(srcStats[DataSource.REGULAR])
print("\nUnusable data:")
pprint.pprint(srcStats[DataSource.BROKEN])
print("-----------------")
print("Finished!")
for src in srcs:
srcName = src[DataSource.NAME]
dSrc = DataSource(src)
srcStats = dSrc.getStats()
kws, ocs = [], []
for word in srcStats[DataSource.REGULAR].items():
ocs.append(word[1][DataStats.AMOUNT])
DataSource.PATH:'../scraping/data/sentences_data.txt'
},
{
DataSource.NAME:'Twitter',
DataSource.PATH:'../../data/SemEval-2014.csv'
}
]
srcs = [{DataSource.NAME:src[DataSource.NAME],
DataSource.PATH:os.path.abspath(src[DataSource.PATH]),
DataSource.TYPE:os.path.splitext(src[DataSource.PATH])[1]} for src in srcs]
for src in srcs:
print("Name: '%s'\nType: '%s'" % (src[DataSource.NAME], src[DataSource.TYPE]))
dSrc = DataSource(src)
srcStats = dSrc.getStats()
print("\nUsable data:")
pprint.pprint(srcStats[DataSource.REGULAR])
print("\nUnusable data:")
pprint.pprint(srcStats[DataSource.BROKEN])
print("-----------------")
print("Finished!")
for src in srcs:
srcName = src[DataSource.NAME]
dSrc = DataSource(src)
srcStats = dSrc.getStats()
kws,ocs = [],[]
for word in srcStats[DataSource.REGULAR].items():
ocs.append(word[1][DataStats.AMOUNT])
