def computeDensity(df, focusPoints, level=1):
"""
Computes the predicted density for a list of focus points for a level
---
df: Output dataframe from bayes step
['TIMESTAMP', 'Z', MU', 'VAR']
where 'MU' and 'VAR' both contains series of 3-tuples
focusPoints: list of focus points
[(a, b), (c, d), (e, f)] where a through f are floats
level: integer 0 or 1 representing floor2 or floor18
---
Returns: dict {timestamp: densityDistribution}
Note: to query, just densityDistribution.query(point)
"""
print 'COMPUTING PREDICTED DENSITY'
print 'Reference points = ' + str(focusPoints)
print 'mazeName = ' + str(getMazeName(level))
return computedensities.compute(getMazeName(level), focusPoints, df, quiet=True)
def computeDensity(df, focusPoints, level=1):
"""
Computes the predicted density for a list of focus points for a level
---
df: Output dataframe from bayes step
['TIMESTAMP', 'Z', MU', 'VAR']
where 'MU' and 'VAR' both contains series of 3-tuples
focusPoints: list of focus points
[(a, b), (c, d), (e, f)] where a through f are floats
level: integer 0 or 1 representing floor2 or floor18
---
Returns: dict {timestamp: densityDistribution}
Note: to query, just densityDistribution.query(point)
"""
print 'COMPUTING PREDICTED DENSITY'
print 'Reference points = ' + str(focusPoints)
print 'mazeName = ' + str(getMazeName(level))
return computedensities.compute(getMazeName(level),
focusPoints,
df,
quiet=True)
return result_df
def predictGPonFile(fileName):
df = pd.read_csv(fileName+'_A.csv', converters={"SHORTEST_PATHS": ast.literal_eval})
testTimes = pd.read_csv(fileName+'_B.csv')
result_df = predictGP(df, testTimes)
result_df.to_csv(fileName+'_OUT.csv')
if __name__ == '__main__':
if len(sys.argv) > 1:
predictGPonFile(sys.argv[1])
quit()
df = pd.read_csv('testGP.csv')
testTimes = pd.read_csv('test_times.csv')
df['SHORTEST_PATHS'] = df['SHORTEST_PATHS'].str.split(',')
result = predictGP(df, testTimes)
import computedensities
densityDistribution = computedensities.compute('floor18map',
[(8,8), (89,60), (55,5)],
result)
print densityDistribution
#userID = df['USER'][0]
#result = predictGP(df[df['USER'] == userID])
#print result
def predictGPonFile(fileName):
df = pd.read_csv(fileName + '_A.csv',
converters={"SHORTEST_PATHS": ast.literal_eval})
testTimes = pd.read_csv(fileName + '_B.csv')
result_df = predictGP(df, testTimes)
result_df.to_csv(fileName + '_OUT.csv')
if __name__ == '__main__':
if len(sys.argv) > 1:
predictGPonFile(sys.argv[1])
quit()
df = pd.read_csv('testGP.csv')
testTimes = pd.read_csv('test_times.csv')
df['SHORTEST_PATHS'] = df['SHORTEST_PATHS'].str.split(',')
result = predictGP(df, testTimes)
import computedensities
densityDistribution = computedensities.compute('floor18map', [(8, 8),
(89, 60),
(55, 5)],
result)
print densityDistribution
#userID = df['USER'][0]
#result = predictGP(df[df['USER'] == userID])
#print result
