def make_forecasts_for_Sander(): """2018 August: Hei igjen Ragnar. Har du statistikk på varsla faregrad over ein heil sesong for Noreg? Eit snitt. XX dagar med faregrad 1, XX dagar med faregrad 2, XX dagar med faregrad 3.... fordelt på XX varslingsdagar. :return: """ pickle_file_name = '{0}201808_avalanche_forecasts_sander.pickle'.format( env.local_storage) get_new = False all_dangers = [] if get_new: years = ['2012-13', '2013-14', '2014-15', '2015-16'] for y in years: from_date, to_date = gm.get_forecast_dates(y) region_ids = gm.get_forecast_regions(y, get_b_regions=True) all_dangers += gd.get_forecasted_dangers(region_ids, from_date, to_date) years = ['2016-17', '2017-18'] for y in years: from_date, to_date = gm.get_forecast_dates(y) region_ids = gm.get_forecast_regions(y, get_b_regions=True) all_dangers += gd.get_forecasted_dangers(region_ids, from_date, to_date) mp.pickle_anything(all_dangers, pickle_file_name) else: all_dangers = mp.unpickle_anything(pickle_file_name) output_forecast_problems = '{0}201808 Faregrader for Sander.txt'.format( env.output_folder) import pandas as pd all_dangers_dict = [] for a in all_dangers: all_dangers_dict.append(a.__dict__) col_names = list(all_dangers_dict[0].keys()) all_dangers_df = pd.DataFrame(all_dangers_dict, columns=col_names, index=range(0, len(all_dangers_dict), 1)) a = 1
def make_all_2015_16(): ## Get new or load from pickle. get_new = True ## Use already made data set. Remember to make get_new = False make_new_incident_list = True make_new_node_list = True ## Set dates from_date = dt.date(2015, 11, 30) to_date = dt.date(2016, 6, 1) # to_date = dt.date.today() ## Get regions # region_id = [112, 117, 116, 128] region_ids = gm.get_forecast_regions(year='2015-16') ## The output incident_ap_dl_json = '{0}incident_and_forecast.json'.format( env.output_folder) incident_ap_dl_csv = '{0}incident_and_forecast.csv'.format( env.output_folder) make_dataset(from_date_inn=from_date, to_date_inn=to_date, region_ids_inn=region_ids, incident_ap_dl_csv_inn=incident_ap_dl_csv, incident_ap_dl_json_inn=incident_ap_dl_json, get_new_inn=get_new, make_new_incident_list_inn=make_new_incident_list, make_new_node_list_inn=make_new_node_list)
def get_2016_17_warnings(how_to_get_data='Get new and dont pickle', pickle_file_name=None): ''' :param hot_to_get_data: 'Get new and dont pickle', 'Get new and save pickle' or 'Load pickle' :param file_name: Not needed if no pickles involved :return: ''' if 'Get new' in how_to_get_data: from_date = dt.date(2016, 11, 30) #to_date = dt.date.today() to_date = dt.date(2017, 5, 31) #region_ids = [3012, 3013] region_ids = gm.get_forecast_regions(year='2016-17') all_warnings = [] for region_id in region_ids: all_warnings += gd.get_forecasted_dangers(region_id, from_date, to_date, include_ikke_vurdert=False) # Sort by date all_warnings = sorted(all_warnings, key=lambda AvalancheDanger: AvalancheDanger.date) if 'and save pickle' in how_to_get_data: mp.pickle_anything(all_warnings, pickle_file_name) elif 'Load pickle' in how_to_get_data: all_warnings = mp.unpickle_anything(pickle_warnings_file_name) else: all_warnings = 'No valid data retrival method given in get_2015_16_warnings.' return all_warnings
def make_plots_for_regions(region_ids=None, year='2019-20', plot_folder=env.plot_folder + 'regionplots/'): """This method prepares data for plotting and calls on the plot methods. Pure administration. :param region_ids: [int] Forecast region ID as given in ForecastRegionKDV :param year: [string] :param plot_folder: [string] Folder for plot files :return: """ if not region_ids: region_ids = gm.get_forecast_regions(year) if not isinstance(region_ids, list): region_ids = [region_ids] for region_id in region_ids: problems, dangers, aval_indexes = _get_dl_prob_avindex(region_id, year=year) region_name = problems[0].region_name causes = [] # list of dates and causes for p in problems: causes.append(AvalancheCause(p.cause_tid, p.date, p.source)) danger_levels = [] for d in dangers: if d.nick != 'drift@svv' and d.danger_level > 0: # for these plots elrapp wil make noise. danger_levels.append( DangerLevel(d.danger_level, d.date, d.source, d)) # Only data with danger levels are plotted if len(danger_levels) is not 0: # Danger level histograms _plot_danger_levels(region_name, danger_levels, aval_indexes, year=year, plot_folder=plot_folder) # Cause horizontal line plots if int( year[0:4] ) > 2014: # modern avalanche problems was introduced winter of 2014-15 _plot_causes(region_name, causes, year=year, plot_folder=plot_folder)
def _get_raw_varsom(year, date, days, max_file_age=23): if date: season = gm.get_season_from_date(date) regions = gm.get_forecast_regions(year=season, get_b_regions=True) aw = [] from_date = date - dt.timedelta(days=days + 1) to_date = date single_warning = gf.get_avalanche_warnings(regions, from_date, to_date) for sw in single_warning: if sw.danger_level > 0: aw.append(sw) else: aw = gvp.get_all_forecasts(year=year, max_file_age=max_file_age) return aw
def make_2018_19_plots(plot_folder=env.plot_folder + 'regionplots/'): """Makes all plots for all regions and saves to web-app folder.""" from_date = dt.date(2018, 11, 15) to_date = dt.date.today() + dt.timedelta(days=2) if dt.date.today().year == 2018: to_date = dt.date(2019, 1, 1) region_ids = gm.get_forecast_regions('2018-19') for i in region_ids: problems, dangers, aval_indexes = get_data(i, from_date, to_date, get_new=True) make_plots_for_region(i, problems, dangers, aval_indexes, from_date, to_date, plot_folder=plot_folder)
def _get_all_snow(get_new=False): file_name = '{}observations and forecasts 2012-17.pickle'.format( env.local_storage) if get_new: all_observations = go.get_all_registrations('2012-12-01', '2017-07-01', geohazard_tids=10) years = ['2012-13', '2013-14', '2014-15', '2015-16', '2016-17'] all_forecasts = [] for y in years: from_date, to_date = gm.get_forecast_dates(y) region_ids = gm.get_forecast_regions(y) all_forecasts += gfa.get_avalanche_warnings( region_ids, from_date, to_date) mp.pickle_anything([all_observations, all_forecasts], file_name) else: [all_observations, all_forecasts] = mp.unpickle_anything(file_name) return all_observations, all_forecasts
def get_all_forecasts(year, lang_key=1, max_file_age=23): """Specialized method for getting all forecasts for one season. For the current season (at the time of writing, 2018-19), if a request has been made the last 23hrs, data is retrieved from a locally stored pickle, if not, new request is made to the regObs api. Previous seasons are not requested if a pickle is found in local storage. :param year: [string] Eg. season '2017-18' :param lang_key [int] 1 is norwegian, 2 is english :param max_file_age: [int] hrs how old the file is before new is retrieved :return valid_forecasts: [list of AvalancheWarning] """ from_date, to_date = gm.get_forecast_dates(year=year) file_name = '{0}all_forecasts_{1}_lk{2}.pickle'.format( env.local_storage, year, lang_key) file_date_limit = dt.datetime.now() - dt.timedelta(hours=max_file_age) # if we are well out of the current season (30 days) its little chance the data set has changed. current_season = gm.get_season_from_date(dt.date.today() - dt.timedelta(30)) # Get forecast regions used in the current year region_ids = gm.get_forecast_regions(year, get_b_regions=True) get_new = True if os.path.exists(file_name): # if file contains a season long gone, dont make new. if year == current_season: file_age = dt.datetime.fromtimestamp(os.path.getmtime(file_name)) # If file is newer than the given time limit, dont make new. if file_age > file_date_limit: # If file size larger than that of an nearly empty file, dont make new. if os.path.getsize(file_name) > 100: # 100 bytes limit get_new = False else: get_new = False if get_new: lg.info( "getvarsompickles.py -> get_all_forecasts: Get new {0} forecasts and pickle." .format(year)) all_forecasts = gfa.get_avalanche_warnings(region_ids, from_date, to_date, lang_key=lang_key) # Valid forecasts have a danger level. The other are empty. valid_forecasts = [] for f in all_forecasts: if f.danger_level > 0: valid_forecasts.append(f) mp.pickle_anything(valid_forecasts, file_name) else: valid_forecasts = mp.unpickle_anything(file_name) return valid_forecasts
def make_avalanche_problemes_for_techel(): """Gets forecastes and observed avalanche problems and dangers for Frank Techel. Takes 20-30 min to run a year. :return: """ pickle_file_name = '{0}runavalancheproblems_techel.pickle'.format( env.local_storage) years = ['2014-15', '2015-16', '2016-17', '2017-18'] get_new = False if get_new: forecast_problems = [] forecast_dangers = [] observed_dangers = [] observed_problems = [] for y in years: # Get forecast data. Different region ids from year to year. region_ids = gm.get_forecast_regions(year=y) from_date, to_date = gm.get_forecast_dates(y) forecast_problems += gp.get_forecasted_problems(region_ids, from_date, to_date, lang_key=2) forecast_dangers += gd.get_forecasted_dangers(region_ids, from_date, to_date, lang_key=2) # Get observed data. All older data in regObs have been mapped to new regions. region_ids = gm.get_forecast_regions(year='2016-17') from_date, to_date = gm.get_forecast_dates( y, padding=dt.timedelta(days=20)) this_years_observed_dangers = gd.get_observed_dangers(region_ids, from_date, to_date, lang_key=2) this_years_observed_problems = gp.get_observed_problems(region_ids, from_date, to_date, lang_key=2) # Update observations with forecast region ids and names used the respective years for od in this_years_observed_dangers: utm33x = od.metadata['Original data'].UTMEast utm33y = od.metadata['Original data'].UTMNorth region_id, region_name = gm.get_forecast_region_for_coordinate( utm33x, utm33y, y) od.region_regobs_id = region_id od.region_name = region_name for op in this_years_observed_problems: utm33x = op.metadata['Original data']['UtmEast'] utm33y = op.metadata['Original data']['UtmNorth'] region_id, region_name = gm.get_forecast_region_for_coordinate( utm33x, utm33y, y) op.region_regobs_id = region_id op.region_name = region_name observed_dangers += this_years_observed_dangers observed_problems += this_years_observed_problems mp.pickle_anything([ forecast_problems, forecast_dangers, observed_dangers, observed_problems ], pickle_file_name) else: [ forecast_problems, forecast_dangers, observed_dangers, observed_problems ] = mp.unpickle_anything(pickle_file_name) # Run EAWS mapping on all problems for p in forecast_problems: p.map_to_eaws_problems() for p in observed_problems: p.map_to_eaws_problems() output_forecast_problems = '{0}Techel forecast problems.csv'.format( env.output_folder) output_forecast_dangers = '{0}Techel forecast dangers.csv'.format( env.output_folder) output_observed_problems = '{0}Techel observed problems.csv'.format( env.output_folder) output_observed_dangers = '{0}Techel observed dangers.csv'.format( env.output_folder) import collections as coll # Write observed dangers to file with open(output_observed_dangers, 'w', encoding='utf-8') as f: make_header = True for d in observed_dangers: out_data = coll.OrderedDict([ ('Date', dt.date.strftime(d.date, '%Y-%m-%d')), ('Reg time', dt.datetime.strftime(d.registration_time, '%Y-%m-%d %H:%M')), ('Region id', d.region_regobs_id), ('Region', d.region_name), ('Municipal', d.municipal_name), ('Nick', d.nick), ('Competence', d.competence_level), ('DL', d.danger_level), ('Danger level', d.danger_level_name), ('Forecast correct', d.forecast_correct), # ('Table', d.data_table), # ('URL', d.url), ]) if make_header: f.write(' ;'.join([fe.make_str(d) for d in out_data.keys()]) + '\n') make_header = False f.write(' ;'.join([fe.make_str(d) for d in out_data.values()]) + '\n') # Write forecasted dangers to file with open(output_forecast_dangers, 'w', encoding='utf-8') as f: make_header = True for d in forecast_dangers: out_data = coll.OrderedDict([ ('Date', dt.date.strftime(d.date, '%Y-%m-%d')), ('Region id', d.region_regobs_id), ('Region', d.region_name), ('Nick', d.nick), ('DL', d.danger_level), ('Danger level', d.danger_level_name), # ('Table', d.data_table), # ('URL', d.url), ('Main message', ' '.join(d.main_message_en.split())) ]) if make_header: f.write(' ;'.join([fe.make_str(d) for d in out_data.keys()]) + '\n') make_header = False f.write(' ;'.join([fe.make_str(d) for d in out_data.values()]) + '\n') # Write forecasted problems to file with open(output_forecast_problems, 'w', encoding='utf-8') as f: make_header = True for p in forecast_problems: out_data = coll.OrderedDict([ ('Date', dt.date.strftime(p.date, '%Y-%m-%d')), ('Region id', p.region_regobs_id), ('Region', p.region_name), ('Nick', p.nick_name), ('Problem order', p.order), ('Problem', p.problem), ('EAWS problem', p.eaws_problem), ('Cause/ weaklayer', p.cause_name), # ('TypeTID', p.aval_type_tid), ('Type', p.aval_type), ('Size', p.aval_size), ('Trigger', p.aval_trigger), ('Probability', p.aval_probability), ('Distribution', p.aval_distribution), ('DL', p.danger_level), ('Danger level', p.danger_level_name), # ('Table', p.regobs_table), # ('URL', p.url) ]) if make_header: f.write(' ;'.join([fe.make_str(d) for d in out_data.keys()]) + '\n') make_header = False f.write(' ;'.join([fe.make_str(d) for d in out_data.values()]) + '\n') # Write observed problems to file with open(output_observed_problems, 'w', encoding='utf-8') as f: make_header = True for p in observed_problems: out_data = coll.OrderedDict([ ('Date', dt.date.strftime(p.date, '%Y-%m-%d')), ('Reg time', dt.datetime.strftime(p.registration_time, '%Y-%m-%d %H:%M')), ('Region id', p.region_regobs_id), ('Region', p.region_name), ('Municipal', p.municipal_name), ('Nick', p.nick_name), ('Competence', p.competence_level), # ('Problem order', p.order), ('EAWS problem', p.eaws_problem), ('Cause/ weaklayer', p.cause_name), # ('TypeTID', p.aval_type_tid), ('Type', p.aval_type), ('Catch 1', p.cause_attribute_crystal), ('Catch 2', p.cause_attribute_light), ('Catch 3', p.cause_attribute_soft), ('Catch 4', p.cause_attribute_thin), ('Size', p.aval_size), ('Trigger', p.aval_trigger), # ('Probability', p.aval_probability), # ('Distribution', p.aval_distribution), # ('RegID', p.regid), # ('Table', p.regobs_table), # ('URL', p.url) ]) if make_header: f.write(' ;'.join([fe.make_str(d) for d in out_data.keys()]) + '\n') make_header = False f.write(' ;'.join([fe.make_str(d) for d in out_data.values()]) + '\n')
for (key, val) in aval_types) aval_triggers = ', '.join("{!s} ({!r})".format(key, val) for (key, val) in aval_triggers) s = u'{0};{1};{2};{3};{4};{5};{6};{7}\n'.format( m.occurrences, danger_levels, problems, aval_triggers, cause_names, aval_types, m.main_message_no, m.main_message_en) l.write(s) l.close() if __name__ == "__main__": year = '2017-18' regions = gm.get_forecast_regions(year=year) date_from, date_to = gm.get_dates_from_season(year=year) # file names file_name_for_warnings_pickle = '{0}{1}'.format( env.local_storage, 'runmainmessage warnings.pickle') file_name_for_main_messages_pickle = '{0}{1}'.format( env.local_storage, 'runmainmessage main messages.pickle') file_name_for_main_messages_csv = '{0}{1}'.format( env.output_folder, 'Alle hovedbudskap {}.csv'.format(year)) ##### pickle the warnings and dataset with main messages # pickle_warnings(regions, date_from, date_to, file_name_for_warnings_pickle) main_messages = select_messages_with_more(file_name_for_warnings_pickle) mp.pickle_anything(main_messages, file_name_for_main_messages_pickle) main_messages = mp.unpickle_anything(file_name_for_main_messages_pickle)
def make_dl_incident_markus(): """ From the beginning of time: get all forecasts. and then get how many on dl 3. get all incidents, excpt elrapp, and all in back country all these, get all on days in regions of dl 3. get all with serious caracter on days and in regions on dl 3 :return: """ pickle_file_name = '{0}incident_on_dl3_for_markus.pickle'.format( env.local_storage) years = ['2012-13', '2013-14', '2014-15', '2015-16', '2016-17'] get_new = False all_dangers = [] all_incidents = [] if get_new: for y in years: # get forecast regions used this year from_date, to_date = gm.get_forecast_dates(y) # get incidents for this year and map to this years forecast regions this_year_incidents = go.get_incident(from_date, to_date, geohazard_tids=10) for i in this_year_incidents: utm33x = i.UTMEast utm33y = i.UTMNorth region_id, region_name = gm.get_forecast_region_for_coordinate( utm33x, utm33y, y) i.region_regobs_id = region_id i.region_name = region_name all_incidents += this_year_incidents # get regions and the forecasts used this year region_ids = gm.get_forecast_regions(y) all_dangers += gd.get_forecasted_dangers(region_ids, from_date, to_date) # in the end, pickle it all mp.pickle_anything([all_dangers, all_incidents], pickle_file_name) else: [all_dangers, all_incidents] = mp.unpickle_anything(pickle_file_name) all_dl3 = [] for d in all_dangers: if d.danger_level == 3: all_dl3.append(d) all_back_country_incidents = [] for i in all_incidents: if 'drift@svv' not in i.NickName: # if activity influenced is backcounty og scooter # should probably include 100 which is non specified incidents # giving this dataset the observations not specified if i.ActivityInfluencedTID in [ 100, 110, 111, 112, 113, 114, 115, 116, 117, 130 ]: all_back_country_incidents.append(i) all_back_country_incidents_with_consequence = [] for i in all_back_country_incidents: # If damageextent is nestenulykke, personer skadet eller personer omkommet if i.DamageExtentTID > 28: all_back_country_incidents_with_consequence.append(i) # find incidents in regions on days with danger level 3 # find incidetns in region on day with dl3 all_back_country_incidents_on_region_dl3 = [] all_back_country_incidents_with_consequence_on_region_dl3 = [] for d in all_dl3: danger_date = d.date danger_region_id = d.region_regobs_id for i in all_back_country_incidents: incident_date = i.DtObsTime.date() incident_region_id = i.ForecastRegionTID if incident_date == danger_date and incident_region_id == danger_region_id: all_back_country_incidents_on_region_dl3.append(i) for i in all_back_country_incidents_with_consequence: incident_date = i.DtObsTime.date() incident_region_id = i.ForecastRegionTID if incident_date == danger_date and incident_region_id == danger_region_id: all_back_country_incidents_with_consequence_on_region_dl3.append( i) print('Totalt varsler laget siden tidenes morgen: {}'.format( len(all_dangers))) print('Totalt varsler på fg 3: {}'.format(len(all_dl3))) print('Totalt antall hendelser i baklandet: {}'.format( len(all_back_country_incidents))) print('Totalt antall hendelser i baklandet med konsekvens: {}'.format( len(all_back_country_incidents_with_consequence))) print( 'Totalt antall hendelser i baklandet i regioner på dager med fg3: {}'. format(len(all_back_country_incidents_on_region_dl3))) print( 'Totalt antall hendelser i baklandet i regioner på dager med fg3 med konsekvens: {}' .format( len(all_back_country_incidents_with_consequence_on_region_dl3))) return
def __init__(self, regobs_types, seasons=('2017-18', '2018-19', '2019-20')): """ Object contains aggregated data used to generate labeled datasets. :param regobs_types: Tuple/list of string names for RegObs observation types to fetch. :param seasons: Tuple/list of string representations of avalanche seasons to fetch. """ self.regobs_types = regobs_types self.tree = {} aw = [] raw_regobs = {} for season in seasons: aw += gvp.get_all_forecasts(year=season) regions = gm.get_forecast_regions(year=season, get_b_regions=True) raw_regobs = { **raw_regobs, **_get_regobs_obs(regions, season, regobs_types) } for forecast in aw: row = { # Metadata 'region_id': forecast.region_id, 'region_name': forecast.region_name, 'region_type': forecast.region_type_name, 'date': forecast.date_valid, 'danger_level': forecast.danger_level, 'emergency_warning': float(forecast.emergency_warning == 'Ikke gitt') } label = OrderedDict({}) label[('CLASS', _NONE, 'danger_level')] = forecast.danger_level label[('CLASS', _NONE, 'emergency_warning')] = forecast.emergency_warning # Weather data weather = { 'precip_most_exposed': forecast.mountain_weather.precip_most_exposed, 'precip': forecast.mountain_weather.precip_region, 'wind_speed': WIND_SPEEDS.get(forecast.mountain_weather.wind_speed, 0), 'wind_change_speed': WIND_SPEEDS.get(forecast.mountain_weather.change_wind_speed, 0), 'temp_min': forecast.mountain_weather.temperature_min, 'temp_max': forecast.mountain_weather.temperature_max, 'temp_lev': forecast.mountain_weather.temperature_elevation, 'temp_freeze_lev': forecast.mountain_weather.freezing_level, } # We use multiple loops to get associated values near each other in e.g. .csv-files. for wind_dir in DIRECTIONS: weather[f"wind_dir_{wind_dir}"] = float( forecast.mountain_weather.wind_direction == wind_dir) for wind_dir in DIRECTIONS: weather[f"wind_chg_dir_{wind_dir}"] = float( forecast.mountain_weather.change_wind_direction == wind_dir) hours = [0, 6, 12, 18] for h in hours: weather[f"wind_chg_start_{h}"] = float( forecast.mountain_weather.change_hour_of_day_start == h) for h in hours: weather[f"temp_fl_start_{h}"] = float( forecast.mountain_weather.change_hour_of_day_start == h) row['weather'] = weather # Problem data prb = {} problem_types = [ PROBLEMS.get(p.avalanche_problem_type_id, _NONE) for p in forecast.avalanche_problems ] problems = {} prb['problem_amount'] = len(forecast.avalanche_problems) label[('CLASS', _NONE, 'problem_amount')] = prb['problem_amount'] for i in range(1, 4): label[('CLASS', _NONE, f"problem_{i}")] = _NONE for problem in PROBLEMS.values(): if problem in problem_types: index = problem_types.index(problem) problems[problem] = forecast.avalanche_problems[index] prb[f"problem_{problem}"] = -( problems[problem].avalanche_problem_id - 4) label[('CLASS', _NONE, f"problem_{index + 1}")] = problem else: problems[problem] = gf.AvalancheWarningProblem() prb[f"problem_{problem}"] = 0 for problem in PROBLEMS.values(): p_data = problems[problem] forecast_cause = CAUSES.get(p_data.aval_cause_id, _NONE) for cause in CAUSES.values(): prb[f"problem_{problem}_cause_{cause}"] = float( forecast_cause == cause) prb[f"problem_{problem}_dsize"] = p_data.destructive_size_ext_id prb[f"problem_{problem}_prob"] = p_data.aval_probability_id prb[f"problem_{problem}_trig"] = { 10: 0, 21: 1, 22: 2 }.get(p_data.aval_trigger_simple_id, 0) prb[f"problem_{problem}_dist"] = p_data.aval_distribution_id prb[f"problem_{problem}_lev_max"] = p_data.exposed_height_1 prb[f"problem_{problem}_lev_min"] = p_data.exposed_height_2 label[('CLASS', problem, "cause")] = forecast_cause label[('CLASS', problem, "dsize")] = p_data.destructive_size_ext_id label[('CLASS', problem, "prob")] = p_data.aval_probability_id label[('CLASS', problem, "trig")] = p_data.aval_trigger_simple_id label[('CLASS', problem, "dist")] = p_data.aval_distribution_id label[('CLASS', problem, "lev_fill")] = p_data.exposed_height_fill for n in range(1, 5): prb[f"problem_{problem}_lev_fill{n}"] = float( p_data.exposed_height_fill == n) for n in range(0, 8): aspect_attr_name = f"problem_{problem}_aspect_{DIRECTIONS[n]}" prb[aspect_attr_name] = float(p_data.valid_expositions[n]) label[('MULTI', problem, "aspect")] = p_data.valid_expositions.zfill(8) label[('REAL', problem, "lev_max")] = p_data.exposed_height_1 label[('REAL', problem, "lev_min")] = p_data.exposed_height_2 # Check for consistency if prb[f"problem_{problem}_lev_min"] > prb[ f"problem_{problem}_lev_max"]: continue row['problems'] = prb row['label'] = label # RegObs data row['regobs'] = {} current_regobs = raw_regobs.get( (forecast.region_id, forecast.date_valid), {}) # Use 5 most competent observations, and list both categories as well as scalars for obs_idx in range(0, 5): # One type of observation (test, danger signs etc.) at a time for regobs_type in self.regobs_types: obses = current_regobs[ regobs_type] if regobs_type in current_regobs else [] # Go through each requested class attribute from the specified observation type for attr, cat in REGOBS_CLASSES[regobs_type].items(): # We handle categories using 1-hot, so we step through each category for cat_name in cat.values(): attr_name = f"regobs_{REG_ENG[regobs_type]}_{_camel_to_snake(attr)}_{cat_name}_{obs_idx}" row['regobs'][attr_name] = obses[obs_idx][ cat_name] if len(obses) > obs_idx else 0 # Go through all requested scalars for attr, (regobs_attr, conv) in REGOBS_SCALARS[regobs_type].items(): attr_name = f"regobs_{REG_ENG[regobs_type]}_{_camel_to_snake(attr)}_{obs_idx}" try: row['regobs'][attr_name] = conv( obses[obs_idx] [regobs_attr]) if len(obses) > obs_idx else 0 except TypeError: row['regobs'][attr_name] = 0 # Check for consistency if weather['temp_min'] > weather['temp_max']: continue self.tree[(forecast.region_id, forecast.date_valid)] = row
def _get_regobs_obs(year, requested_types, date=None, days=None, max_file_age=23): regions = gm.get_forecast_regions(year=year, get_b_regions=True) observations = {} observations_neigh = {} varsomdata_obses = {} if len(requested_types) == 0: return observations file_name = f'{se.local_storage}regobs_v{CSV_VERSION}_{year}.pickle' file_date_limit = dt.datetime.now() - dt.timedelta(hours=max_file_age) current_season = gm.get_season_from_date(dt.date.today() - dt.timedelta(30)) number_of_records = 50 get_new = True try: # Don't fetch new data if old is cached. If older season file doesn't exists we get out via an exception. if dt.datetime.fromtimestamp(os.path.getmtime( file_name)) > file_date_limit or year != current_season: get_new = False if date: get_new = True except FileNotFoundError: pass if date: from_date = date - dt.timedelta(days=days) to_date = date else: from_date, to_date = gm.get_dates_from_season(year=year) if "AvalancheIndex" in requested_types: avalanche_index = True else: avalanche_index = False req_set = set(requested_types) & set(REG_ENG_V4.keys()) # Make sure all requested elements from RegObs actually have the information we need specified if not min( map(lambda x: set(list(x.keys())).issuperset(req_set), [REGOBS_CLASSES, REGOBS_SCALARS, REG_ENG])): raise RegObsRegTypeError() url = "https://api.regobs.no/v4/Search" query = { "LangKey": 1, "FromDate": from_date.isoformat(), "ToDate": to_date.isoformat(), "SelectedRegistrationTypes": None, "SelectedRegions": regions, "NumberOfRecords": number_of_records, "Offset": 0 } results = [] def send_req(queries): query = queries.pop() try: req = requests.post(url=url, json=query) return (req, query) except: return (None, query) if get_new: future_tuples = [] total_matches = requests.post(url=url + "/Count", json=query).json()["TotalMatches"] with futures.ThreadPoolExecutor(140) as executor: queries = [] while query["Offset"] < total_matches: queries.append(query.copy()) query["Offset"] += number_of_records for _ in range(0, len(queries)): future = executor.submit(send_req, queries) future_tuples.append((0, future)) while len(future_tuples): retries, future = future_tuples.pop() try: response, query = future.result() raw_obses = response.json() except: if retries < 5: future = executor.submit(send_req, [query]) future_tuples.insert(0, (retries + 1, future)) else: offset = json.loads(response.request.body)["Offset"] print( f"Failed to fetch regobs, offset {offset}, skipping", file=sys.stderr) continue results = results + raw_obses if not date: with open(file_name, 'wb') as handle: pickle.dump(results, handle, protocol=pickle.HIGHEST_PROTOCOL) else: try: with open(file_name, 'rb') as handle: results = pickle.load(handle) except: os.remove(file_name) return _get_regobs_obs(regions, year, requested_types, max_file_age) for raw_obs in results: date = dt.datetime.fromisoformat(raw_obs["DtObsTime"]).date() key = (date.isoformat(), raw_obs["ObsLocation"]["ForecastRegionTID"]) if key not in observations: observations[key] = {} observations_neigh[key] = {} varsomdata_obses[key] = [] for obs_type in req_set: if REG_ENG_V4[obs_type] not in raw_obs or not raw_obs[ REG_ENG_V4[obs_type]]: continue reg = raw_obs[REG_ENG_V4[obs_type]] # Ignore snow profiles of the old format if obs_type == "Snøprofil" and "StratProfile" not in reg: continue obs = {"competence": raw_obs["Observer"]["CompetenceLevelTID"]} try: for attr, categories in REGOBS_CLASSES[obs_type].items(): for cat_id, cat_name in categories.items(): if isinstance(reg, list): obs[cat_name] = 1 if cat_id in map( lambda x: x[attr], reg) else 0 else: obs[cat_name] = 1 if cat_id == reg[attr] else 0 except KeyError: pass try: for regobs_attr, conv in REGOBS_SCALARS[obs_type].values(): obs[regobs_attr] = 0 if isinstance(reg, list) and len(reg) > 0: obs[regobs_attr] = reg[0][regobs_attr] elif not isinstance(reg, list): obs[regobs_attr] = reg[regobs_attr] if obs[regobs_attr] is None: obs[regobs_attr] = 0 except KeyError: pass if obs_type not in observations[key]: observations[key][obs_type] = [] observations[key][obs_type].append(obs) varsomdata_obses[key] += go.Observation(raw_obs).Observations # We want the most competent observations first for key, date_region in observations.items(): for reg_key, reg_type in date_region.items(): reg_type.sort(key=lambda x: x['competence'], reverse=True) observations_neigh[key][reg_key] = reg_type.copy() rng = np.random.default_rng(1984) for (date, region), date_region in observations.items(): for reg_key in date_region.keys(): reg_neigh = [] for neighbour in rng.permutation(REGION_NEIGH[region]): try: reg_neigh += observations[(date, neighbour)][reg_key] except KeyError: pass reg_neigh.sort(key=lambda x: x['competence'], reverse=True) observations_neigh[(date, region)][reg_key] += reg_neigh df_dict = {} for key, observation in observations_neigh.items(): # Use 2 most competent observations, and list both categories as well as scalars for obs_idx in range(0, 2): # One type of observation (test, danger signs etc.) at a time for regobs_type in req_set: obses = observation[ regobs_type] if regobs_type in observation else [] # Go through each requested class attribute from the specified observation type for attr, cat in REGOBS_CLASSES[regobs_type].items(): # We handle categories using 1-hot, so we step through each category for cat_name in cat.values(): attr_name = f"regobs_{REG_ENG[regobs_type]}_{_camel_to_snake(attr)}_{cat_name}_{obs_idx}" if attr_name not in df_dict: df_dict[attr_name] = {} df_dict[attr_name][key] = obses[obs_idx][ cat_name] if len(obses) > obs_idx else 0 # Go through all requested scalars for attr, (regobs_attr, conv) in REGOBS_SCALARS[regobs_type].items(): attr_name = f"regobs_{REG_ENG[regobs_type]}_{_camel_to_snake(attr)}_{obs_idx}" if attr_name not in df_dict: df_dict[attr_name] = {} try: df_dict[attr_name][key] = conv( obses[obs_idx] [regobs_attr]) if len(obses) > obs_idx else 0 except TypeError: df_dict[attr_name][key] = 0 if "accuracy" not in df_dict: df_dict["accuracy"] = {} df_dict['accuracy'][key] = sum( map(lambda x: { 0: 0, 1: 1, 2: -1, 3: -1 }[x['ForecastCorrectTID']], observation['Skredfarevurdering']) ) if 'Skredfarevurdering' in observation else 0 if avalanche_index: if "regobs_avalancheidx" not in df_dict: df_dict["regobs_avalancheidx"] = {} avalanche_indices = list( map(lambda x: x.index, gm.get_avalanche_index(varsomdata_obses[key]))) if avalanche_indices: df_dict['regobs_avalancheidx'][key] = max(avalanche_indices) else: df_dict['regobs_avalancheidx'][key] = 0 return df_dict
def make_season_calender_plots(year='2019-20', plot_folder=env.plot_folder, html_folder=env.output_folder + 'views/', web_pickle_folder=env.output_folder + 'webpickles/'): """Makes observation calender plots for both observer and region for display on web page for the season 2018-19. Method includes a request for list of relevant observers.""" from_year = int(year[0:4]) to_year = int('20' + year[-2:]) from_day = dt.date(from_year, 11, 1) to_day = dt.date(to_year, 6, 30) # if the seasons expected end is after todays date, set it to today. if to_day > dt.date.today(): to_day = dt.date.today() # list of months to be plotted months = [] month = from_day while month < to_day: months.append(month) almost_next = month + dt.timedelta(days=35) month = dt.date(almost_next.year, almost_next.month, 1) # Get all regions region_ids = gm.get_forecast_regions(year) # get a list of relevant observers to plot and make pickle for adding to the web-folder all_observations_nest = gvp.get_all_observations(year, output='List', geohazard_tids=10) all_observations_list = gvp.get_all_observations(year, output='FlatList', geohazard_tids=10) observer_dict = {} for o in all_observations_nest: if o.ObserverID in observer_dict.keys(): observer_dict[o.ObserverID].add_one_observation_count() else: observer_dict[o.ObserverID] = ObserverData(o.ObserverID, o.NickName, observation_count_inn=1) observer_list = [] observer_list_web = [] ordered_observer_dict = col.OrderedDict( sorted(observer_dict.items(), key=lambda t: t[1].observation_count, reverse=True)) for k, v in ordered_observer_dict.items(): if v.observation_count > 4: observer_list.append( ObserverData(v.observer_id, v.observer_nick, observation_count_inn=v.observation_count)) observer_list_web.append( [v.observer_id, v.observer_nick, v.observation_count]) if not os.path.exists(web_pickle_folder): os.makedirs(web_pickle_folder) mp.pickle_anything(observer_list_web, '{0}observerlist.pickle'.format(web_pickle_folder)) # run the stuff make_observer_plots(all_observations_list, observer_list, months, plot_folder=plot_folder, html_folder=html_folder) make_region_plots(all_observations_list, region_ids, months, plot_folder=plot_folder, html_folder=html_folder) make_svv_plots(all_observations_list, observer_dict, region_ids, months, plot_folder=plot_folder, html_folder=html_folder)
plb.text( x + 20, -270, '*** {0} ganger er ett snoeskred med hoeysete index. \n' ' {1} som skredaktivitet og {2} med skjema for \n' ' enkeltskred.'.format(est_num_1, est_num_1_aval_act, est_num_1_aval)) return if __name__ == "__main__": season = '2017-18' ### Get all regions region_ids = gm.get_forecast_regions(season) from_date, to_date = gm.get_forecast_dates(season) # from_date, to_date = '2017-12-01', '2018-02-01' # region_ids = [3014, 3015] ### get and make the data set date_region, forecasted_dangers = step_1_make_data_set( region_ids, from_date, to_date) mp.pickle_anything([date_region, forecasted_dangers], '{0}runforavalancheactivity_step_1.pickle'.format( env.local_storage)) ### Find the observaton of highest value pr region pr date date_region, forecasted_dangers = mp.unpickle_anything( '{0}runforavalancheactivity_step_1.pickle'.format(env.local_storage)) date_region = step_2_find_most_valued(date_region)
from varsomdata import getmisc as gm from utilities import fencoding as fe import setenvironment as env __author__ = 'Ragnar Ekker' years = ['2014-15', '2015-16', '2016-17', '2017-18'] forecast_problems = [] forecast_dangers = [] observed_dangers = [] observed_problems = [] for y in years: # Get forecast data. Different region ids from year to year. region_ids = gm.get_forecast_regions(year=y) from_date, to_date = gm.get_forecast_dates(y) forecast_problems += gp.get_forecasted_problems(region_ids, from_date, to_date, lang_key=1) forecast_dangers += gd.get_forecasted_dangers(region_ids, from_date, to_date, lang_key=1) # Get observed data. All older data in regObs have been mapped to new regions. region_ids = gm.get_forecast_regions(year='2016-17') from_date, to_date = gm.get_forecast_dates(y, padding=dt.timedelta(days=20)) current_years_observed_dangers = gd.get_observed_dangers(region_ids,
plb.vlines(1200, 0, 650, lw=2, color='k') plb.vlines(1800, 0, 650, lw=2, color='k') plb.vlines(2400, 0, 650, lw=2, color='k') plb.xlim(-100, 2410) plb.ylim(-10, 700) plb.axis('off') plb.savefig(plot_file_name + file_ext) plb.close() return if __name__ == "__main__": regions = gm.get_forecast_regions(year='2016-17') date_from = "2016-12-01" date_to = "2017-06-01" pickle_warnings_file_name = '{0}{1}'.format( thisenv.local_storage, 'runForMatrix warnings.pickle') pickle_data_set_file_name = '{0}{1}'.format( thisenv.local_storage, 'runForMatrix data set.pickle') pickle_m3_file_name = '{0}{1}'.format(thisenv.local_storage, 'runForMatix m3.pickle') plot_m3_file_name = '{0}m3 {1}-{2}'.format(thisenv.plot_folder, date_from[0:4], date_to[2:4]) pickle_m3_v2_file_name = '{0}{1}'.format(thisenv.local_storage, 'runForMatix m3.v2.pickle') plot_m3_v2_file_name = '{0}m3 {1}-{2}.v2'.format(thisenv.plot_folder,