import pandas as pd
import polars as pl
import scipy
from datetime import timedelta
from scipy.signal import savgol_filter
MAX_DELTA_FOR_INTERPOLATION = timedelta(minutes=3)

sensor_dataframe = pd.read_csv('proffast-2.2-outputs-20220604-ma.csv')
sampling_rate = "10 s"
print("After --------------------------------------")
df = sensor_dataframe.rename(columns={
    'UTC': 'utc',
    ' gndP': 'gnd_p',
    ' gndT': 'gnd_t',
    ' appSZA': 'app_sza',
    ' azimuth': 'azimuth',
    ' XH2O': 'xh2o',
    ' XAIR': 'xair',
    ' XCO2': 'xco2',
    ' XCH4': 'xch4',
    ' XCO': 'xco',
    ' XCH4_S5P': 'xch4_s5p'
}, errors="raise")
sensor_dataframe = df.filter(items=['utc', 'gnd_p', 'gnd_t', 'app_sza', 'azimuth', 'xh2o', 'xair', 'xco2', 'xch4', 'xco', 'xch4_s5p'])
"""
✗ sensor_dataframe is the output of get_sensor_dataframe (see above)
    Example:
                            me_gnd_p  me_gnd_t  me_app_sza  ...
    utc
    2021-10-20 07:00:23     950.91    289.05       78.45     ...
    2021-10-20 07:00:38     950.91    289.05       78.42     ...
    2021-10-20 07:01:24     950.91    289.05       78.31     ...
    ...                       ...       ...         ...
    [1204 rows x 8 columns]

✗ sampling_rate is (as of now) a custom type Rate:Literal[
    "10 min", "5 min", "2 min", "1 min", "30 sec", "15 sec", "10 sec", "5 sec", "2 sec", "1 sec"
    ]

✗ get_daily_dataframe (see below) will be called afterwards and joins the dataframes on "utc".
"""

output = sensor_dataframe.sort_values(by=['utc']) # sort according to time
output['utc'] = pd.to_datetime(output['utc'])
# Apply smoothing function for all data columns.
for column in output.columns[1::]:
    output[column] = scipy.signal.savgol_filter(pd.to_numeric(output[column]), 31, 3)
print("Original Dataset")
print(output)

output = output.set_index('utc')
output.index = pd.to_datetime(output.index)
output = output.resample(sampling_rate).mean()

sampling_delta = pd.to_timedelta(sampling_rate)
# The interpolating limit is dependant on the sampling rate.
interpolating_limit = int(MAX_DELTA_FOR_INTERPOLATION / sampling_delta)

if interpolating_limit != 0:
    output.interpolate(
        limit=interpolating_limit,
        inplace=True,
        limit_direction='both',
        limit_area='inside',
    )

print("After pandas interpolation")
print(output)

df = pl.from_pandas(sensor_dataframe)
q = df.lazy().with_column(pl.col('utc').str.strptime(pl.Datetime, fmt='%F %T').cast(pl.Datetime)).select([pl.col('utc'),
                pl.exclude('utc').map(lambda x: savgol_filter(x.to_numpy(), 31, 3)).explode()])
df = q.collect()
df = df.upsample(time_column="utc", every="10s")
print("After polars upscale")
print(df)