File size: 14,377 Bytes
ed581c9
 
 
 
 
 
 
 
 
 
 
 
 
e863dee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ed581c9
 
 
 
 
e863dee
 
 
 
 
 
 
 
 
ed581c9
 
e863dee
ed581c9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7818025
 
 
 
 
 
 
 
 
 
 
 
 
 
e863dee
 
 
7818025
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e863dee
 
 
 
 
 
 
 
 
 
 
 
ed581c9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e863dee
ed581c9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
import numerapi
from numerapi import utils
from project_tools import project_config, project_utils
from typing import List, Dict
import pandas as pd
import numpy as np

napi = numerapi.NumerAPI()


# def get_round


# depreciated
# def get_model_history(model):
#     res = napi.daily_user_performances(model)
#     res = pd.DataFrame.from_dict(res)
#     res['payoutPending'] = res['payoutPending'].astype(np.float64)
#     res['payoutSettled'] = res['payoutSettled'].astype(np.float64)
#     res['stakeValue'] = res['stakeValue'].astype(np.float64)
#     res['deltaRatio'] = res['payoutPending'] / res['stakeValue']
#     res['realised_pl'] = project_utils.series_reverse_cumsum(res['payoutSettled'])
#     res['floating_pl'] = project_utils.series_reverse_cumsum(res['payoutPending']) - res['realised_pl']
#     res['current_stake'] = res['stakeValue'] - res['floating_pl']
#     rename_dict = {'stakeValue':'floating_stake'}
#     res = res.rename(columns=rename_dict)
#     # res['equity'] = res['stakeValue'] + res['floating_pl']
#     # cols = res.columns.tolist()
#     # res = res[['model'] + cols]
#
#     res['model'] = model
#     cols = ['model', 'date', 'current_stake', 'floating_stake', 'payoutPending', 'floating_pl', 'realised_pl']
#     res = res[cols]
#     return res


def get_portfolio_overview(models, onlylatest=True):
    res_df = []
    for m in models:
        # try:
        print(f'extracting information for model {m}')
        if onlylatest:
            mdf = get_model_history_v3(m).loc[0:0]
        else:
            mdf = get_model_history_v3(m)
        res_df.append(mdf)
        # except:
        #     print(f'no information for model {m} is available')
    if len(res_df)>0:
        res_df = pd.concat(res_df, axis=0)
        # res_df['date'] = res_df['date'].dt.date
        if onlylatest:
            return res_df.sort_values(by='floating_pl', ascending=False).reset_index(drop=True)
        else:
            return res_df.reset_index(drop=True)
    else:
        return None






def get_competitions(tournament=8):
    """Retrieves information about all competitions
    Args:
        tournament (int, optional): ID of the tournament, defaults to 8
            -- DEPRECATED there is only one tournament nowadays
    Returns:
        list of dicts: list of rounds
        Each round's dict contains the following items:
            * datasetId (`str`)
            * number (`int`)
            * openTime (`datetime`)
            * resolveTime (`datetime`)
            * participants (`int`): number of participants
            * prizePoolNmr (`decimal.Decimal`)
            * prizePoolUsd (`decimal.Decimal`)
            * resolvedGeneral (`bool`)
            * resolvedStaking (`bool`)
            * ruleset (`string`)
    Example:
        >>> NumerAPI().get_competitions()
        [
         {'datasetId': '59a70840ca11173c8b2906ac',
          'number': 71,
          'openTime': datetime.datetime(2017, 8, 31, 0, 0),
          'resolveTime': datetime.datetime(2017, 9, 27, 21, 0),
          'participants': 1287,
          'prizePoolNmr': Decimal('0.00'),
          'prizePoolUsd': Decimal('6000.00'),
          'resolvedGeneral': True,
          'resolvedStaking': True,
          'ruleset': 'p_auction'
         },
          ..
        ]
    """
    # self.logger.info("getting rounds...")

    query = '''
        query($tournament: Int!) {
          rounds(tournament: $tournament) {
            number
            resolveTime
            openTime
            resolvedGeneral
            resolvedStaking
          }
        }
    '''
    arguments = {'tournament': tournament}
    result = napi.raw_query(query, arguments)
    rounds = result['data']['rounds']
    # convert datetime strings to datetime.datetime objects
    for r in rounds:
        utils.replace(r, "openTime", utils.parse_datetime_string)
        utils.replace(r, "resolveTime", utils.parse_datetime_string)
        utils.replace(r, "prizePoolNmr", utils.parse_float_string)
        utils.replace(r, "prizePoolUsd", utils.parse_float_string)
    return rounds


def daily_submissions_performances(username: str) -> List[Dict]:
    """Fetch daily performance of a user's submissions.
    Args:
        username (str)
    Returns:
        list of dicts: list of daily submission performance entries
        For each entry in the list, there is a dict with the following
        content:
            * date (`datetime`)
            * correlation (`float`)
            * roundNumber (`int`)
            * mmc (`float`): metamodel contribution
            * fnc (`float`): feature neutral correlation
            * correlationWithMetamodel (`float`)
    Example:
        >>> api = NumerAPI()
        >>> api.daily_user_performances("uuazed")
        [{'roundNumber': 181,
          'correlation': -0.011765912,
          'date': datetime.datetime(2019, 10, 16, 0, 0),
          'mmc': 0.3,
          'fnc': 0.1,
          'correlationWithMetamodel': 0.87},
          ...
        ]
    """
    query = """
              query($username: String!) {
                v2UserProfile(username: $username) {
                  dailySubmissionPerformances {
                    date
                    correlation
                    corrPercentile
                    roundNumber
                    mmc
                    mmcPercentile
                    fnc
                    fncPercentile
                    correlationWithMetamodel
                  }
                }
              }
            """
    arguments = {'username': username}
    data = napi.raw_query(query, arguments)['data']['v2UserProfile']
    performances = data['dailySubmissionPerformances']
    # convert strings to python objects
    for perf in performances:
        utils.replace(perf, "date", utils.parse_datetime_string)
    # remove useless items
    performances = [p for p in performances
                    if any([p['correlation'], p['fnc'], p['mmc']])]
    return performances


def daily_submissions_performances_V3(modelname: str) -> List[Dict]:
    query = """
              query($modelName: String!) {
                v3UserProfile(modelName: $modelName) {
                    roundModelPerformances{
                        roundNumber
                        roundResolveTime
                        corr
                        corrPercentile
                        mmc
                        mmcMultiplier
                        mmcPercentile
                        tc
                        tcPercentile
                        tcMultiplier
                        fncV3
                        fncV3Percentile
                        corrWMetamodel
                        payout
                        roundResolved
                        roundResolveTime
                        corrMultiplier
                        mmcMultiplier
                        selectedStakeValue
                    }
                    stakeValue
                    nmrStaked
                }
              }
            """
    arguments = {'modelName': modelname}
    data = napi.raw_query(query, arguments)['data']['v3UserProfile']
    performances = data['roundModelPerformances']
    # convert strings to python objects
    for perf in performances:
        utils.replace(perf, "date", utils.parse_datetime_string)
    # remove useless items
    performances = [p for p in performances
                    if any([p['corr'], p['tc'], p['mmc']])]
    return performances


def get_lb_models(limit=20000, offset=0):
    query = """
           query($limit: Int, $offset: Int){
               v2Leaderboard(limit:$limit, offset:$offset){
                   username
               }           
           }
           """
    arguments = {'limit':limit, 'offset':offset}
    data = napi.raw_query(query, arguments)['data']['v2Leaderboard']
    model_list = [i['username'] for i in data]
    return model_list



def get_round_model_performance(roundNumber: int, model: str):
    query = """
              query($roundNumber: Int!, $username: String!) {
                  roundSubmissionPerformance(roundNumber: $roundNumber, username: $username) {
                      corrMultiplier
                      mmcMultiplier                      
                      roundDailyPerformances{
                          correlation
                          mmc
                          corrPercentile
                          mmcPercentile
                          payoutPending
                       }
                       selectedStakeValue
                   }
              }
            """
    arguments = {'roundNumber': roundNumber,'username': model}
    data = napi.raw_query(query, arguments)['data']['roundSubmissionPerformance']
    latest_performance = data['roundDailyPerformances'][-1] #[-1] ### issue with order
    res = {}
    res['model'] = model
    res['roundNumber'] = roundNumber
    res['corrMultiplier'] = data['corrMultiplier']
    res['mmcMultiplier'] = data['mmcMultiplier']
    res['selectedStakeValue'] = data['selectedStakeValue']
    for key in latest_performance.keys():
        res[key] = latest_performance[key]
    return res




def get_user_profile(username: str) -> List[Dict]:
    """Fetch daily performance of a user's submissions.
    Args:
        username (str)
    Returns:
        list of dicts: list of daily submission performance entries
        For each entry in the list, there is a dict with the following
        content:
            * date (`datetime`)
            * correlation (`float`)
            * roundNumber (`int`)
            * mmc (`float`): metamodel contribution
            * fnc (`float`): feature neutral correlation
            * correlationWithMetamodel (`float`)
    Example:
        >>> api = NumerAPI()
        >>> api.daily_user_performances("uuazed")
        [{'roundNumber': 181,
          'correlation': -0.011765912,
          'date': datetime.datetime(2019, 10, 16, 0, 0),
          'mmc': 0.3,
          'fnc': 0.1,
          'correlationWithMetamodel': 0.87},
          ...
        ]
    """
    query = """
              query($username: String!) {
                v2UserProfile(username: $username) {
                  dailySubmissionPerformances {
                    date
                    correlation
                    corrPercentile
                    roundNumber
                    mmc
                    mmcPercentile
                    fnc
                    fncPercentile
                    correlationWithMetamodel
                  }
                }
              }
            """
    arguments = {'username': username}
    data = napi.raw_query(query, arguments)['data']#['v2UserProfile']
    # performances = data['dailySubmissionPerformances']
    # # convert strings to python objects
    # for perf in performances:
    #     utils.replace(perf, "date", utils.parse_datetime_string)
    # # remove useless items
    # performances = [p for p in performances
    #                 if any([p['correlation'], p['fnc'], p['mmc']])]
    return data


def download_dataset(filename: str, dest_path: str = None,
                     round_num: int = None) -> None:
    """ Download specified file for the current active round.

    Args:
        filename (str): file to be downloaded
        dest_path (str, optional): complate path where the file should be
            stored, defaults to the same name as the source file
        round_num (int, optional): tournament round you are interested in.
            defaults to the current round
        tournament (int, optional): ID of the tournament, defaults to 8

    Example:
        >>> filenames = NumerAPI().list_datasets()
        >>> NumerAPI().download_dataset(filenames[0]}")
    """
    if dest_path is None:
        dest_path = filename

    query = """
    query ($filename: String!
           $round: Int) {
        dataset(filename: $filename
                round: $round)
    }
    """
    args = {'filename': filename, "round": round_num}

    dataset_url = napi.raw_query(query, args)['data']['dataset']
    utils.download_file(dataset_url, dest_path, show_progress_bars=True)
    
    
    
# function using V3UserProfile

def model_payout_history(model):
    napi = numerapi.NumerAPI()
    query = """
              query($model: String!) {
                  v3UserProfile(modelName: $model) {
                        roundModelPerformances{
                            payout
                            roundNumber
                            roundResolved
                            roundResolveTime
                            corrMultiplier
                            mmcMultiplier
                            selectedStakeValue
                        }
                        stakeValue
                        nmrStaked
                   }
              }
            """
    arguments = {'model': model}
    payout_info = napi.raw_query(query, arguments)['data']['v3UserProfile']['roundModelPerformances']
    payout_info = pd.DataFrame.from_dict(payout_info)
    payout_info = payout_info[~pd.isnull(payout_info['payout'])].reset_index(drop=True)
    return payout_info


def get_model_history_v3(model):
    res = model_payout_history(model)
    res = pd.DataFrame.from_dict(res)
    res['payout'] = res['payout'].astype(np.float64)
    res['current_stake'] = res['selectedStakeValue'].astype(np.float64)
    res['payout_cumsum'] = project_utils.series_reverse_cumsum(res['payout'])
    res['date'] = pd.to_datetime(res['roundResolveTime']).dt.date

    res['realised_pl'] = res['payout_cumsum']
    latest_realised_pl = res[res['roundResolved'] == True]['payout_cumsum'].values[0]
    res.loc[res['roundResolved'] == False, 'realised_pl'] = latest_realised_pl

    res['floating_pl'] = 0
    payoutPending_values = res[res['roundResolved'] == False]['payout'].values
    payoutPending_cumsum = payoutPending_values[::-1].cumsum()[::-1]
    res.loc[res['roundResolved'] == False, 'floating_pl'] = payoutPending_cumsum

    res['model'] = model
    #     res['floating_pl'] = res['current_stake'] + res['payoutPending']
    res['floating_stake'] = res['current_stake'] + res['floating_pl']
    cols = ['model', 'date', 'current_stake', 'floating_stake', 'payout', 'floating_pl', 'realised_pl', 'roundResolved',
            'roundNumber']
    res = res[cols]
    return res