Created
November 15, 2015 23:19
-
-
Save cbare/48de7da55b4683793b12 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import json | |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| import synapseclient | |
| from collections import OrderedDict | |
| syn = synapseclient.Synapse() | |
| syn.login() | |
| results = syn.tableQuery('SELECT count(*) FROM syn5299184') | |
| print "Total number of records:", results.asInteger() | |
| ## Get a limited number of records | |
| results = syn.tableQuery('SELECT * FROM syn5299184 LIMIT 20') | |
| file_map = syn.downloadTableColumns(results, ["deviceMotion_walking_outbound.json.items"]) | |
| ## if we download all the data, we'll see that one is missing. This shows us why: | |
| results = syn.tableQuery('SELECT * FROM syn5299184 where "deviceMotion_walking_outbound.json.items" IS NULL') | |
| for result in results: | |
| print result | |
| ## load the json files | |
| data = OrderedDict() | |
| for file_handle, path in file_map.iteritems(): | |
| with open(path) as f: | |
| data[file_handle] = json.loads(f.read()) | |
| ## Each json file is a list of maps whose keys are: | |
| ## * userAcceleration | |
| ## * timestamp | |
| ## * magneticField | |
| ## * gravity | |
| ## * rotationRate | |
| ## * attitude | |
| ## data[data.keys()[0]][0].keys() | |
| ## Here are the data types | |
| names = ['attitude', | |
| 'userAcceleration', | |
| 'rotationRate', | |
| 'gravity', | |
| 'magneticField'] | |
| ## build dataframes for all data types except timestamp, which | |
| ## becomes the index for the others. | |
| records = OrderedDict() | |
| for file_handle, rs in data.iteritems(): | |
| series = OrderedDict() | |
| timestamps = [r['timestamp'] for r in rs] | |
| t0 = min(timestamps) | |
| timestamps = [t-t0 for t in timestamps] | |
| for name in names: | |
| series[name] = pd.DataFrame([r[name] for r in rs], index=timestamps) | |
| records[file_handle] = series | |
| ## graph the gravity data type for one record | |
| g = records[records.keys()[0]]['gravity'] | |
| plt.plot(g.index, g.x, 'r', g.index, g.y, 'g', g.index, g.z, 'b') | |
| plt.show() | |
| ## graph the gravity data type for a sequence of records | |
| for i,key in enumerate(records.keys()): | |
| g = records[key]['gravity'] | |
| plt.plot(g.index, g.x, 'r', g.index, g.y, 'g', g.index, g.z, 'b') | |
| plt.show() | |
| if i > 10: break | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment