import pytest
import pandas as pd
import numpy as np
from ml_investment.data import SF1Data
from ml_investment.features import calc_series_stats, QuarterlyFeatures, BaseCompanyFeatures,\
QuarterlyDiffFeatures, FeatureMerger, \
DailyAggQuarterFeatures
from ml_investment.utils import load_json, int_hash_of_str
from synthetic_data import GeneratedData
config = load_json('config.json')
loaders = [GeneratedData()]
if config['sf1_data_path'] is not None:
loaders.append(SF1Data(config['sf1_data_path']))
@pytest.mark.parametrize(
["series", "norm", "expected"],
[([10, 0, 1], False,
{'_mean': 3.6666666666666665,
'_median': 1.0,
'_max': 10.0,
'_min': 0.0,
'_std': 4.4969125210773475}),
([10, -30, 1, 4, 15.2], False,
{'_mean': 0.039999999999999855,
'_median': 4.0,
'_max': 15.2,
'_min': -30.0,
'_std': 15.798936673080249}),
([1], False,
"cashneq",
"rnd",
"sgna",
"ncfx",
"divyield",
"currentratio",
"netinccmn"
]
if __name__ == '__main__':
parser = argparse.ArgumentParser()
arg = parser.add_argument
arg('--config_path', type=str)
args = parser.parse_args()
config = load_json(args.config_path)
data_loader = SF1Data(config['sf1_data_path'])
tickers_df = data_loader.load_base_data(
currency=CURRENCY,
scalemarketcap=SCALE_MARKETCAP)
ticker_list = tickers_df['ticker'].unique().tolist()
fc1 = QuarterlyFeatures(
columns=QUARTER_COLUMNS,
quarter_counts=QUARTER_COUNTS,
max_back_quarter=MAX_BACK_QUARTER)
fc2 = BaseCompanyFeatures(cat_columns=CAT_COLUMNS)
fc3 = QuarterlyDiffFeatures(
'CHRIS/CME_CL1',
'ODA/POILBRE_USD',
'CHRIS/CME_NG1',
'ODA/PCOFFOTM_USD',
'ODA/PCOCO_USD',
'ODA/PORANG_USD',
'ODA/PBANSOP_USD',
'ODA/POLVOIL_USD',
'ODA/PLOGSK_USD',
'ODA/PCOTTIND_USD'
]
if __name__ == '__main__':
parser = argparse.ArgumentParser()
arg = parser.add_argument
arg('--config_path', type=str)
arg('--secrets_path', type=str)
args = parser.parse_args()
config = load_json(args.config_path)
secrets = load_json(args.secrets_path)
downloader = QuandlDownloader(config, secrets, sleep_time=0.8)
for code in tqdm(quandl_commodities_codes):
downloader.single_download('datasets/{}'.format(code),
'{}/{}.json'.format(config['commodities_data_path'],
code.replace('/', '_')))