def main(load=True):
indices = ['X', 'Y', 'PdDistrictInt']
train = sfc.get_data('data/trim_1e4.csv', drop_data=True)[indices]
all = sfc.get_data('data/all.csv', drop_data=True)
knn = Juristictions()
if load:
knn.load()
else:
knn.train(train)
knn.save()
data = knn.outside_juristiction(all)
sfc.write_data(data, 'data/outside_pd.csv', comment='Outside juristiction')
return
def main(load=True):
indices = ['X', 'Y', 'PdDistrictInt']
train = sfc.get_data('data/trim_1e4.csv', drop_data=True)[indices]
all = sfc.get_data('data/all.csv', drop_data=True)
knn = Juristictions()
if load:
knn.load()
else:
knn.train(train)
knn.save()
data = knn.outside_juristiction(all)
sfc.write_data(data, 'data/outside_pd.csv', comment='Outside juristiction')
return
def make_dataset(input, output, comment='', verbose=False, size=None):
data = None
# Get the input data
if isinstance(input, str):
if not os.path.exists(input):
input2 = os.path.join('data', input)
if not os.path.exists(input2):
raise IOError('Neither {} nor {} exist'.format(input, input2))
input = input2
data = sfc.get_data(input)
elif isinstance(input, pandas.DataFrame):
data = copy.deepcopy(input)
else:
raise IOError('Cannot deal with a {}'.format(type(input)))
# Shrink to random records
if size is not None and size < len(data):
random.seed(sfc._SEED)
data = data.ix[sorted(random.sample(xrange(len(data)), size))]
data.reset_index(drop=True)
sfc.write_data(data, output, comment=comment)
return
def make_dataset(input, output, comment="", verbose=False, size=None):
data = None
# Get the input data
if isinstance(input, str):
if not os.path.exists(input):
input2 = os.path.join("data", input)
if not os.path.exists(input2):
raise IOError("Neither {} nor {} exist".format(input, input2))
input = input2
data = sfc.get_data(input)
elif isinstance(input, pandas.DataFrame):
data = copy.deepcopy(input)
else:
raise IOError("Cannot deal with a {}".format(type(input)))
# Shrink to random records
if size is not None and size < len(data):
random.seed(sfc._SEED)
data = data.ix[sorted(random.sample(xrange(len(data)), size))]
data.reset_index(drop=True)
sfc.write_data(data, output, comment=comment)
return
def main(load=True):
indices = ['X', 'Y', 'PdDistrictInt']
train = sfc.get_data('data/trim_1e4.csv', drop_data=True)[indices]
all = sfc.get_data('data/all.csv', drop_data=True)
knn = Juristictions()
if load:
knn.load()
else:
knn.train(train)
knn.save()
data = knn.outside_juristiction(all)
sfc.write_data(data, 'data/outside_pd.csv', comment='Outside juristiction')
return
###############################################################################
if __name__ == "__main__":
#main(False)
knn = Juristictions()
knn.load()
#knn.plot(('data/outside_pd.csv', 'Outside PD'), ('data/all.csv', 'all'))
data = sfc.get_data('data/all.csv')
all = knn.add_outside_juristiction(data)
sfc.write_data(all, 'data/all.csv')
###############################################################################
###############################################################################
def main(load=True):
indices = ['X', 'Y', 'PdDistrictInt']
train = sfc.get_data('data/trim_1e4.csv', drop_data=True)[indices]
all = sfc.get_data('data/all.csv', drop_data=True)
knn = Juristictions()
if load:
knn.load()
else:
knn.train(train)
knn.save()
data = knn.outside_juristiction(all)
sfc.write_data(data, 'data/outside_pd.csv', comment='Outside juristiction')
return
###############################################################################
if __name__ == "__main__":
#main(False)
knn = Juristictions()
knn.load()
#knn.plot(('data/outside_pd.csv', 'Outside PD'), ('data/all.csv', 'all'))
data = sfc.get_data('data/all.csv')
all = knn.add_outside_juristiction(data)
sfc.write_data(all, 'data/all.csv')
###############################################################################
