ampli/py/predict.py

from argparse import ArgumentParser, FileType
import numpy as np
import pandas as p
import statsmodels.formula.api as smf
import datetime as dt
import pickle
from pymodels import thirtyoffset, predweather, harmonic
from pprint import pprint
from util import datevalid
from signal import signal, SIGPIPE, SIG_DFL

def preddemand(model, weather, harmonics):
    harmstart = thirtyoffset(weather.index.min())
    utv = weather.index
    harmlen = len(utv)

    yharm = harmonic(harmlen, period=365.25 * 48, start=harmstart,
                     harmonics=harmonics[0], prefix="y")
    yharm.index = utv

    wharm = harmonic(harmlen, period=7 * 48, start=harmstart,
                     harmonics=harmonics[1], prefix="w")
    wharm.index = utv

    dharm = harmonic(harmlen, period=48, start=harmstart,
                     harmonics=harmonics[2], prefix="d")
    dharm.index = utv

    df = p.concat([yharm, wharm, dharm, weather], axis = 1)
    return model.predict(df)

def main():
    parser = ArgumentParser(description=
                            'Predict from harmonic model of cluster')
    parser.add_argument("-m", "--model-file", dest="model_file",
                        help="filename for models",
                        required = True,
                        type=FileType('rb'))
    parser.add_argument("-w", "--weather",  dest="weather_file",
                        help="input weather pickle path",
                        required=False,
                        type=FileType('rb'))
    parser.add_argument("-o", "--output", dest="output_file",
                        help="file to save result",
                        required=True, type=FileType('w'))
    parser.add_argument("-t", "--temperature", dest="temp",
                        help = "min and max temperature, if not using "
                        "weather dataset, e.g. 2.0 10.5", 
                        required=False,
                        type=float, nargs=2)
    parser.add_argument("-s", "--start-date", 
                        dest = "startdate", 
                        help = "start date for prediction; format: YYYY-MM-DD; default: 2018-01-01", 
                        metavar="START_DATE", 
                        required = True,
                        type = datevalid)
    parser.add_argument("-e", "--end-date", 
                        dest = "enddate", 
                        help = "end date for prediction; format: YYYY-MM-DD; default: 2018-02-01", 
                        metavar="END_DATE", 
                        required = True,
                        type = datevalid)
    parser.add_argument("-c", "--cluster",
                        dest = "cluster",
                        help = "cluster to predict for",
                        type = int,
                        required = True)
    parser.add_argument("--csv",
                        help="output as csv",
                        action="store_true")
    args = parser.parse_args()

    if args.temp is None and args.weather_file is None:
        parser.error("Either the temperature range or a weather "
                     "dataset must be specified")

    mods = pickle.load(args.model_file)

    if args.cluster not in mods["clusters"]:
        parser.error(f"cluster ('{args.cluster}') not in model")

    wdat = []
    
    if args.weather_file is not None:
        weather = p.read_pickle(args.weather_file)
        if (args.startdate < weather['temp_timestamp'].min() or 
            args.enddate > weather['temp_timestamp'].max()):
            parser.error("Start and or end date not in supplied weather dataset")

        wantedtimes = p.date_range(args.startdate,
                                   args.enddate, freq="30 min")
        wantedtimes = p.Series(wantedtimes.round(freq="30 min"))
        wanteddf = p.DataFrame(index=wantedtimes)
        weather = wanteddf.join(weather.set_index(['temp_timestamp']),
                                how='left').drop('temp_date', axis=1)
        weather.index.name = "read_time"
        weather = weather.fillna(method='ffill', axis=0)

        # Add rolling columns
        weather['min_rolling'] = weather['tmin_c'].rolling("1D").min()
        weather['max_rolling'] = weather['tmax_c'].rolling("1D").max()

        wharmstart = thirtyoffset(weather.index.min())
        wharm = harmonic(weather.shape[0], period=365.25 * 48, start=wharmstart,
                         harmonics=mods["weather_harmonics"])
        wharm.index = wantedtimes
        pred_max = weather['max_rolling'] - mods["max_temp"].predict(wharm)
        pred_min = weather['min_rolling'] - mods["min_temp"].predict(wharm)
        wdat = p.DataFrame({
            "max_resid": pred_max,
            "min_resid": pred_min
        })

    else:
        mint = min(args.temp)
        maxt = max(args.temp)
        pred_max = maxt - predweather(mods["max_temp"],
                               args.startdate,
                               args.enddate,
                               harmonics = mods["weather_harmonics"])
        pred_min = mint - predweather(mods["min_temp"],
                               args.startdate,
                               args.enddate,
                               harmonics = mods["weather_harmonics"])
        wdat = p.DataFrame({
            "max_resid": pred_max,
            "min_resid": pred_min
        })


    dpred = p.DataFrame(
        {
            "predicted": preddemand(mods["icp"][args.cluster], wdat, mods["icp_harmonics"])
        })

    if args.csv:
        signal(SIGPIPE, SIG_DFL) # Prevent broken pipe errors when piping to less or head
        dpred.to_csv(args.output_file)
    else:
        dpred.to_pickle(args.output_file)


    args.model_file.close()
    if args.weather_file is not None:
        args.weather_file.close()


if __name__ == "__main__":
    main()