def test_map(self):
usMap = Map()
usMap.plotPoints([-105.16, -117.16, -77.00], [40.02, 32.73, 38.55],
color=GeneralMethods.getRandomColor())
usMap.plotPoints([-114.21, -88.10], [48.25, 17.29],
color=GeneralMethods.getRandomColor())
plt.show()
def runMRJob(mrJobClass,
outputFileName,
inputFileList,
mrJobClassParams = {},
args='-r hadoop'.split(),
**kwargs):
mrJob = mrJobClass(args=args, **mrJobClassParams)
GeneralMethods.runCommand('rm -rf %s'%outputFileName)
for l in mrJob.runJob(inputFileList=inputFileList, **kwargs): FileIO.writeToFileAsJson(l[1], outputFileName)
def runMRJobWithOutPutToHDFS(mrJobClass,
outputFileName,
inputFileList,
mrJobClassParams = {},
args='-r hadoop'.split(),
**kwargs):
mrJob = mrJobClass(args=args, **mrJobClassParams)
GeneralMethods.runCommand('hadoop fs -rm -r %s'%outputFileName)
mrJob.runJobWithOutPutToHDFS(outputFileName, inputFileList=inputFileList, **kwargs)
def plot_graph_clusters_on_world_map(graph,
s=0,
lw=0,
alpha=0.6,
bkcolor='#CFCFCF',
*args,
**kwargs):
no_of_clusters, tuples_of_location_and_cluster_id = clusterUsingAffinityPropagation(
graph)
map_from_location_to_cluster_id = dict(tuples_of_location_and_cluster_id)
map_from_cluster_id_to_cluster_color = dict([
(i, GeneralMethods.getRandomColor()) for i in range(no_of_clusters)
])
points, colors = zip(*map(
lambda location: (getLocationFromLid(location.replace(
'_', ' ')), map_from_cluster_id_to_cluster_color[
map_from_location_to_cluster_id[location]]), graph.nodes()))
_, m = plotPointsOnWorldMap(points,
c=colors,
s=s,
lw=lw,
returnBaseMapObject=True,
*args,
**kwargs)
for u, v, data in graph.edges(data=True):
if map_from_location_to_cluster_id[
u] == map_from_location_to_cluster_id[v]:
color, u, v, w = map_from_cluster_id_to_cluster_color[
map_from_location_to_cluster_id[u]], getLocationFromLid(
u.replace('_', ' ')), getLocationFromLid(
v.replace('_', ' ')), data['w']
m.drawgreatcircle(u[1], u[0], v[1], v[0], color=color, alpha=alpha)
return (no_of_clusters, tuples_of_location_and_cluster_id)
def getFrequentItemsets(self, maxdepth=0):
self.read_data()
self.prune_items()
self.eclat_mine(self.data)
itemIdToItemMap = GeneralMethods.reverseDict(self.itemToItemIdMap)
return [([itemIdToItemMap[itemId]
for itemId in itemset[0]], itemset[1])
for itemset in self.frequentItemsets]
def test_approximateToNearest5Minutes(self):
self.assertEqual(
datetime(2011, 7, 5, 15, 10),
GeneralMethods.approximateToNearest5Minutes(
datetime(2011, 7, 5, 15, 13, 34)))
self.assertEqual(
datetime(2011, 7, 5, 15, 15),
GeneralMethods.approximateToNearest5Minutes(
datetime(2011, 7, 5, 15, 15)))
self.assertEqual(
datetime(2011, 7, 5, 15, 10),
GeneralMethods.approximateToNearest5Minutes(
datetime(2011, 7, 5, 15, 13, 11, 30)))
self.assertEqual(
datetime(2011, 7, 5, 15, 35),
GeneralMethods.approximateToNearest5Minutes(
datetime(2011, 7, 5, 15, 35, 01)))
def plot_graph_clusters_on_world_map(graph, s=0, lw=0, alpha=0.6, bkcolor='#CFCFCF', *args, **kwargs):
from graphs import clusterUsingAffinityPropagation
no_of_clusters, tuples_of_location_and_cluster_id = clusterUsingAffinityPropagation(graph)
map_from_location_to_cluster_id = dict(tuples_of_location_and_cluster_id)
map_from_cluster_id_to_cluster_color = dict([(i, GeneralMethods.getRandomColor()) for i in range(no_of_clusters)])
points, colors = zip(*map(lambda location: (getLocationFromLid(location.replace('_', ' ')), map_from_cluster_id_to_cluster_color[map_from_location_to_cluster_id[location]]), graph.nodes()))
_, m = plotPointsOnWorldMap(points, c=colors, s=s, lw=lw, returnBaseMapObject=True, *args, **kwargs)
for u, v, data in graph.edges(data=True):
if map_from_location_to_cluster_id[u]==map_from_location_to_cluster_id[v]:
color, u, v, w = map_from_cluster_id_to_cluster_color[map_from_location_to_cluster_id[u]], getLocationFromLid(u.replace('_', ' ')), getLocationFromLid(v.replace('_', ' ')), data['w']
m.drawgreatcircle(u[1], u[0], v[1], v[0], color=color, alpha=alpha)
return (no_of_clusters, tuples_of_location_and_cluster_id)
def test_reverseDict(self):
self.assertEqual({
1: 'a',
2: 'b'
}, GeneralMethods.reverseDict({
'a': 1,
'b': 2
}))
self.assertRaises(Exception, GeneralMethods.reverseDict, {
'a': 1,
'b': 1
})
def write_file_from_hdfs_to_local_file(hdfs_file, f_local):
f_temp_output = '/tmp/%s'%(''.join(random.choice(string.ascii_uppercase + string.digits) for x in range(10)))
GeneralMethods.runCommand('hadoop fs -cat %s/part* > %s'%(hdfs_file, f_temp_output))
GeneralMethods.runCommand('rm -rf %s'%f_local)
for data in file(f_temp_output): FileIO.writeToFile(data.strip().split('\t')[1], f_local)
GeneralMethods.runCommand('rm -rf %s'%f_temp_output)
def plotNorm(maxYValue, mu, sigma, color=None, **kwargs):
s = np.random.normal(mu, sigma, 1000)
count, bins = np.histogram(s, 1000, normed=True)
if not color:
color = GeneralMethods.getRandomColor()
plt.fill_between(
bins,
((1 / (sigma * np.sqrt(2 * np.pi)) * np.exp(-(bins - mu) ** 2 / (2 * sigma ** 2))) / 4) * maxYValue,
linewidth=1,
color=color,
alpha=0.3,
)
plt.plot(
bins,
((1 / (sigma * np.sqrt(2 * np.pi)) * np.exp(-(bins - mu) ** 2 / (2 * sigma ** 2))) / 4) * maxYValue,
linewidth=3,
color=color,
**kwargs
)
def plotNorm(maxYValue, mu, sigma, color=None, **kwargs):
s = np.random.normal(mu, sigma, 1000)
count, bins = np.histogram(s, 1000, normed=True)
if not color: color = GeneralMethods.getRandomColor()
plt.fill_between(
bins,
((1 / (sigma * np.sqrt(2 * np.pi)) * np.exp(-(bins - mu)**2 /
(2 * sigma**2))) / 4) *
maxYValue,
linewidth=1,
color=color,
alpha=0.3)
plt.plot(bins,
((1 /
(sigma * np.sqrt(2 * np.pi)) * np.exp(-(bins - mu)**2 /
(2 * sigma**2))) / 4) *
maxYValue,
linewidth=3,
color=color,
**kwargs)
def test_approximateToNearest5Minutes(self):
self.assertEqual(datetime(2011,7,5,15,10), GeneralMethods.approximateToNearest5Minutes(datetime(2011,7,5,15,13,34)))
self.assertEqual(datetime(2011,7,5,15,15), GeneralMethods.approximateToNearest5Minutes(datetime(2011,7,5,15,15)))
self.assertEqual(datetime(2011,7,5,15,10), GeneralMethods.approximateToNearest5Minutes(datetime(2011,7,5,15,13,11,30)))
self.assertEqual(datetime(2011,7,5,15,35), GeneralMethods.approximateToNearest5Minutes(datetime(2011,7,5,15,35,01)))
def __isValidObject(self):
return self.twoWayMap.getMap(
TwoWayMap.MAP_REVERSE) == GeneralMethods.reverseDict(
self.twoWayMap.getMap(TwoWayMap.MAP_FORWARD))
def drawKMLsForPoints(pointsIterator, outputKMLFile, color=None):
kml = KML()
if not color: color = GeneralMethods.getRandomColor()
kml.addLocationPoints(pointsIterator, color=color)
kml.write(outputKMLFile)
def drawKMLsForPoints(pointsIterator, outputKMLFile, color=None):
kml = KML()
if not color: color = GeneralMethods.getRandomColor()
kml.addLocationPoints(pointsIterator, color=color)
kml.write(outputKMLFile)
def tearDown(self):
GeneralMethods.remove_file(self.f1)
GeneralMethods.remove_file(self.f2)
GeneralMethods.remove_file('pig_tests.pig')
def getFrequentItemsets(self, maxdepth=0):
self.read_data()
self.prune_items()
self.eclat_mine(self.data)
itemIdToItemMap = GeneralMethods.reverseDict(self.itemToItemIdMap)
return [([itemIdToItemMap[itemId] for itemId in itemset[0]], itemset[1]) for itemset in self.frequentItemsets]
def test_reverseDict(self):
self.assertEqual({1:'a', 2:'b'}, GeneralMethods.reverseDict({'a':1, 'b':2}))
self.assertRaises(Exception, GeneralMethods.reverseDict, {'a':1, 'b':1})
def test_map(self):
usMap = Map()
usMap.plotPoints([-105.16, -117.16, -77.00], [40.02, 32.73, 38.55], color=GeneralMethods.getRandomColor())
usMap.plotPoints([-114.21, -88.10], [48.25, 17.29], color=GeneralMethods.getRandomColor())
plt.show()
def test_getValueDistribution(self):
map = {'a': [1, 2, 3], 'b': [3], 'c': [4]}
self.assertEqual({
1: 2,
3: 1
}, GeneralMethods.getValueDistribution(map.itervalues(), len))
def test_run(self):
pig = Pig([self.f1, self.f2], [('A', '32'), ('B', 'sdfd')])
pig.run()
GeneralMethods.runCommand('cat %s'%pig.output_pig_script)
def test_getValueDistribution(self):
map = {'a': [1,2,3], 'b': [3], 'c': [4]}
self.assertEqual({1: 2, 3: 1}, GeneralMethods.getValueDistribution(map.itervalues(), len))
def __isValidObject(self): return self.twoWayMap.getMap(TwoWayMap.MAP_REVERSE)==GeneralMethods.reverseDict(self.twoWayMap.getMap(TwoWayMap.MAP_FORWARD)) def test_basicOperation(self):
def addLocationPoints(self, points, color=None):
if not color: color = GeneralMethods.getRandomColor()
for point in (list(reversed(point)) for point in points):
pnt = self.kml.newpoint(coords=[point])
pnt.iconstyle.icon.href = 'http://maps.google.com/mapfiles/kml/shapes/shaded_dot.png'
pnt.iconstyle.color = 'ff' + color[1:]
def runMRJob(mrJobClass, outputFileName, inputFileList, args='-r hadoop'.split(), **kwargs):
mrJob = mrJobClass(args=args)
GeneralMethods.runCommand('rm -rf %s'%outputFileName)
for l in mrJob.runJob(inputFileList=inputFileList, **kwargs): FileIO.writeToFileAsJson(l[1], outputFileName)
def addLocationPoints(self, points, color=None):
if not color: color=GeneralMethods.getRandomColor()
for point in (list(reversed(point)) for point in points):
pnt = self.kml.newpoint(coords=[point])
pnt.iconstyle.icon.href = 'http://maps.google.com/mapfiles/kml/shapes/shaded_dot.png'
pnt.iconstyle.color = 'ff'+color[1:]
