common.py

#! /usr/bin/env python
# -*- coding: utf-8 -*-

import io
import re

import numpy as np
import pandas as pd

from saqc.core.core import prepareMeta, readMeta
from saqc.flagger import SimpleFlagger, DmpFlagger
from saqc.core.config import Fields as F


TESTNODATA = (np.nan, -9999)


TESTFLAGGER = (SimpleFlagger(), DmpFlagger())


def initData(cols=2, start_date="2017-01-01", end_date="2017-12-31", freq="1h"):
    dates = pd.date_range(start=start_date, end=end_date, freq=freq)
    data = {}
    dummy = np.arange(len(dates))
    for col in range(1, cols+1):
        data[f"var{col}"] = dummy*(col)
    return pd.DataFrame(data, index=dates)


def initMetaString(metastring, data):
    cleaned = re.sub(r"\s*,\s*", r",",
                     re.sub(r"\|", r",",
                            re.sub(r"\n[ \t]+", r"\n",
                                   metastring)))
    fobj = io.StringIO(cleaned)
    meta = prepareMeta(readMeta(fobj), data)
    fobj.seek(0)
    return fobj, meta


def _getKeys(metadict):
    keys = list(metadict[0].keys())
    for row in metadict[1:]:
        for k in row.keys():
            if k not in keys:
                keys.append(k)
    return keys


def initMetaDict(metadict, data):
    df = pd.DataFrame(metadict)[_getKeys(metadict)]
    meta = prepareMeta(df, data)
    fobj = io.StringIO()
    meta.to_csv(fobj, index=False)
    fobj.seek(0)
    return fobj, meta