import geopandas as gpd
import json
import datetime
from shapely.geometry import Point

%matplotlib inline
import matplotlib.pylab as pylab
pylab.rcParams['figure.figsize'] = 16, 12 

with open("LocationHistory.json", 'r') as fh:
    data = json.loads(fh.read())

locations = data['locations']
print len(locations)

# first pass, gather activity types
act_types = set()
for loc in locations:
    try:
        activities = loc['activitys'][0]['activities']
        assert len(activities) >= 1
        for act in activities:
            act_type = act['type']
            act_types.add(act_type)
    except:
        pass    
    
act_types = sorted(list(act_types))
print act_types

def generate_locations(locations):
    for loc in locations:
        loc['lon'] = loc['longitudeE7'] * 0.0000001
        loc['lat'] = loc['latitudeE7'] * 0.0000001
        #loc['wkt'] = 'POINT({0} {1})'.format(loc['lon'], loc['lat'])
        loc['geometry'] = Point(loc['lon'], loc['lat'])
        loc['timestampSec'] = int(loc['timestampMs']) * 0.001  # ms to s
        loc['datetime'] = datetime.datetime.fromtimestamp(loc['timestampSec']).strftime('%Y-%m-%d %H:%M:%S')
        for typ in act_types:
            loc[typ] = 0
        
        maxprob = 0
        bestguess = ""
        try:
            activities = loc['activitys'][0]['activities']
            assert len(activities) >= 1

            # Look at confidence estimate for each activity
            for act in activities:
                conf = act['confidence']
                act_type = act['type']
                if conf > maxprob:
                    maxprob = conf
                    bestguess = act_type 
                loc[act_type] = conf
        except:
            pass

        loc['likelyActivity'] = bestguess

        # Get rid of extraneous columns
        try:
            del loc['activitys']
        except KeyError:
            pass
        try:
            del loc['latitudeE7']
            del loc['longitudeE7']
            del loc['timestampMs']
        except KeyError:
            pass
        
        yield loc

            
      
#test = pd.DataFrame(generate_locations(locations))
alldf = gpd.GeoDataFrame(generate_locations(locations), 
                        crs={'proj':'longlat', 'ellps':'WGS84', 'datum':'WGS84', 'no_defs':True})
alldf.head(3)

df = alldf[alldf['accuracy'] < 50]
print len(df)

hits = df.sindex.intersection((-122.7147, 45.51435, -122.6708, 45.54110), objects=True)
dfsub = gpd.GeoDataFrame([df.ix[hit.object] for hit in hits])
len(dfsub)

dfsub.plot()

!rm location_history.*

df.to_file('location_history.shp')