Processing GPS Data

import pandas as pd
from gpx_converter import Converter

files = [
    '../backpacking-trips/big-sur-2021-08-20-thru-22/salmon-creek-trailhead-to-spruce-camp-82021-91230am.gpx',
    '../backpacking-trips/big-sur-2021-08-20-thru-22/spruce-camp-to-estrella-camp-82021-112028am.gpx',
    '../backpacking-trips/big-sur-2021-08-20-thru-22/estrella-camp-to-lions-den-camp.gpx',
    '../backpacking-trips/big-sur-2021-08-20-thru-22/lions-den-camp-to-cruikshank-camp.gpx',
    '../backpacking-trips/big-sur-2021-08-20-thru-22/to-north-buckeye-camp.gpx',
    '../backpacking-trips/big-sur-2021-08-20-thru-22/track-82221-81723am.gpx'
]

from haversine import haversine, Unit

loc1=(35.815768,-121.358696)
loc2=(35.815689,-121.358611)
print('{:2.1f} feet'.format(haversine(loc1,loc2,unit=Unit.FEET)))

raw = (Converter(input_file=files[0])
        .gpx_to_dataframe())
raw.info()
raw.head()

raw['time_delta'] = raw['time'].shift(-1)-raw['time']
raw['time_delta_seconds'] = ((raw['time_delta']
                              .fillna(pd.Timedelta(seconds=0))
                              .astype(int)/1000000000)
                             .astype(int))
raw.info()
raw.head()

print('Average time delta between GPS meansurements: {} seconds'.format(raw['time_delta_seconds'].mean()))
raw['time_delta_seconds'].hist(bins=raw['time_delta_seconds'].max());

test = (Converter(input_file=files[0])
        .gpx_to_dataframe())

# Convert GMT to PST and format
test['time'] = test['time'].apply(lambda x: x.tz_convert('US/Pacific'))
test['seconds_delta'] = (((test['time'].shift(-1)-test['time'])
                           .fillna(pd.Timedelta(seconds=0))
                           .astype(int)/1000000000)
                          .astype(int))
test['human_date'] = test['time'].dt.strftime('%Y-%m-%d')
test['human_time'] = test['time'].dt.strftime('%I:%M:%S %p')
test[['time','human_date','human_time','seconds_delta']].head()

# Convert altitude from meters to feet
test['altitude_feet'] = round(test['altitude'] * 3.280839895).astype('int')
test[['time','altitude','altitude_feet']].head()

# Calculate speed and altitude change from one measurement to the next
for i in range(test.shape[0]-1):
    start = test.at[i,   'latitude'], test.at[i,   'longitude']
    end =   test.at[i+1, 'latitude'], test.at[i+1, 'longitude']
    distance = round(haversine(start,
                               end,
                               unit=Unit.FEET),1)
    test.at[i, 'distance_feet'] = distance
    
    altitude_change = test.at[i+1, 'altitude_feet'] - test.at[i, 'altitude_feet']
    test.at[i, 'altitude_change'] = altitude_change
    
test['speed_mph'] = ((test['distance_feet'] / test['seconds_delta']) * (3600/5280)).round(1)
test[['time','distance_feet','seconds_delta','speed_mph','altitude_feet','altitude_change']].head()

print('Average speed: {} mph'.format(round(test['speed_mph'].mean(),2)))
test['speed_mph'].hist(bins=20);

def transform_gpx_data(filename):
    df = (Converter(input_file=filename)
          .gpx_to_dataframe())
    df['time'] = df['time'].apply(lambda x: x.tz_convert('US/Pacific'))
    df['seconds_delta'] = (((df['time'].shift(-1)-df['time'])
                            .fillna(pd.Timedelta(seconds=0))
                            .astype(int)/1000000000)
                           .astype(int))
    df['human_date'] = df['time'].dt.strftime('%Y-%m-%d')
    df['human_time'] = df['time'].dt.strftime('%I:%M:%S %p')
    
    df['altitude_feet'] = round(df['altitude'] * 3.280839895).astype('int')
    
    for i in range(df.shape[0]-1):
        start = df.at[i,   'latitude'], df.at[i,   'longitude']
        end =   df.at[i+1, 'latitude'], df.at[i+1, 'longitude']
        distance = round(haversine(start,
                                   end,
                                   unit=Unit.FEET),1)
        df.at[i, 'distance_feet'] = distance

        altitude_change = df.at[i+1, 'altitude_feet'] - df.at[i, 'altitude_feet']
        df.at[i, 'altitude_change'] = altitude_change
    
    df['speed_mph'] = ((df['distance_feet'] / df['seconds_delta']) * (3600/5280)).round(1)
    
    df = df[['time', 'human_date', 'human_time', 'seconds_delta',
             'latitude', 'longitude', 'altitude', 'altitude_feet',
             'distance_feet', 'speed_mph', 
             'altitude_feet','altitude_change']].copy()
    return df

d = transform_gpx_data(files[0])
pd.DataFrame(d.iloc[:3].T)

d.info()

for file in files:
    print(file)
    d = transform_gpx_data(file)
    string = '''{}, {} - {}
Start: ({}, {}),   End: ({}, {})
{} GPS datapoints
{} duration
{:3.2f} miles @ {:3.1f} avg MPH
{:3.0f}/{:3.0f} feet total/net elevation change'''.format(d['human_date'].min(), 
                                                          d.iloc[0]['human_time'], 
                                                          d.iloc[d.shape[0]-1]['human_time'], 
                                                          d.iloc[0]['latitude'], 
                                                          d.iloc[0]['longitude'],
                                                          d.iloc[d.shape[0]-1]['latitude'], 
                                                          d.iloc[d.shape[0]-1]['longitude'],
                                                          d.shape[0],
                                                          str(d['time'].max()-d['time'].min())[7:12],
                                                          d['distance_feet'].sum()/5280, 
                                                          d['speed_mph'].mean(),
                                                          d['altitude_change'].abs().sum(), 
                                                          d['altitude_change'].sum())
    print(string + '\n')