def dfBystop(stop, graph, allStations):
'''Return dataframe with timelines for stations near input station and
smoothed timelines'''
mapFromId, mapToId = distances.getMappings(graph)
subgraph = networkx.ego_graph(graph, stop, radius=5,
undirected=True, distance='weight')
columnNames = [mapFromId[node] for node in subgraph.nodes()]
for station in subgraph.nodes():
if station in allStations:
filtered = filtfilt(b, a, allStations[station].interpolate().fillna(method='backfill'))
stationDf = pd.DataFrame({station: allStations[station],
(station + '_filtered'): filtered})
try:
tmpDf = pd.concat([tmpDf, stationDf], axis=1)
except NameError:
tmpDf = stationDf
return tmpDf
for station in subgraph.nodes():
if station in allStations:
filtered = filtfilt(b, a, allStations[station].interpolate().fillna(method='backfill'))
stationDf = pd.DataFrame({station: allStations[station],
(station + '_filtered'): filtered})
try:
tmpDf = pd.concat([tmpDf, stationDf], axis=1)
except NameError:
tmpDf = stationDf
return tmpDf
if __name__ == "__main__":
fulldata = util.pickle_load('data/fulldata_NOnearest_9-22.pkl')
graph = util.pickle_load('subwaydata/NYCsubway_network_graph.pkl')
mapFromId, mapToId = distances.getMappings(graph)
allStations = processHistoricalData(fulldata, graph)
station = mapToId['W 4 St']
stationDf = dfBystop(station, graph, allStations)
result = fitAR(stationDf, station, makePlot=True, order=(1, 1, 0),
showTest=True)
stationDf = dfBystop(station, graph, allStations)
result = fitGP(stationDf, station, showTest=True)
# run GP for all stations and write to dB
test_scores = {}
for station in graph.nodes():
if station in allStations:
stationDf = dfBystop(station, graph, allStations)