Reading the data

[15]:

PATH_DIR = '/content/drive/MyDrive/01 - Iniciação Científica/02 - Datasets/exoplanets_confirmed/resampled_files/RESAMPLED_EN2_STAR_CHR_0101086161_20070516T060226_20071005T074409.csv'
# PATH_DIR = 'C:/Users/guisa/Google Drive/01 - Iniciação Científica/02 - Datasets/exoplanets_confirmed/resampled_files/RESAMPLED_EN2_STAR_CHR_0101086161_20070516T060226_20071005T074409.csv'
# PATH_DIR = 'C:/Users/guisa/Google Drive/01 - Iniciação Científica/02 - Datasets/exoplanets_confirmed/resampled_files/RESAMPLED_EN2_STAR_CHR_0102890318_20070206T133547_20070402T070302.csv'

[16]:

import pandas as pd

data = pd.read_csv(PATH_DIR)
data.head()

[16]:

	DATE	WHITEFLUX
0	2007-05-16 18:10:55.071642	112521.329834
1	2007-05-16 18:24:29.950108	112758.045853
2	2007-05-16 18:38:04.828574	112943.042225
3	2007-05-16 18:51:39.707040	112562.266242
4	2007-05-16 19:05:14.585506	112789.303079

[17]:

from datetime import datetime

time = data.DATE
flux = data.WHITEFLUX

try:
  time = [datetime.strptime(i, '%Y-%m-%d %H:%M:%S.%f') for i in time]
except:
  time = [datetime.strptime(i, '%Y-%m-%d %H:%M:%S') for i in time]

After, let’s import the tools package with the support algorithms

[ ]:

from tools import *

Plotting the chosen curve

[ ]:

viz.view_lightcurve(time, flux)

Feature: Periodograms

Spectrum generation

[ ]:

sample_time = pd.Series(time).diff().min()
sample_frequency = 1 / sample_time.seconds

print("The series have a time sample of {} minutes, so the sample frequency is {} Hz".format(sample_time, round(sample_frequency, 6)))

The series have a time sample of 0 days 00:13:34.878465 minutes, so the sample frequency is 0.001229 Hz

[ ]:

import scipy.signal as ssg

flux = ssg.detrend(flux, type='linear')

[ ]:

X, Y = ssg.periodogram(flux, fs=sample_frequency, scaling='density')

[ ]:

import numpy as np

viz.line_plot(np.log10(X), Y, title='Light Curve Frequency Spectrum', x_axis='Frequency [log10(Hz)]', y_axis='Magnitude')

/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:3: RuntimeWarning: divide by zero encountered in log10
  This is separate from the ipykernel package so we can avoid doing imports until

Generation algorithm

[ ]:

import numpy as np

s = X.shape
periodogram = np.zeros((s[0], 2))

[ ]:

eclipsing_binaries = False
exoplanets_confirmed = True

if eclipsing_binaries:
  DATA_DIR = '/content/drive/MyDrive/01 - Iniciação Científica/02 - Datasets/eclipsing_binaries'

elif exoplanets_confirmed:
  DATA_DIR = '/content/drive/MyDrive/01 - Iniciação Científica/02 - Datasets/exoplanets_confirmed/resampled_files'

[18]:

import os

DF = pd.DataFrame()

for root_dir_path, sub_dirs, files in os.walk(DATA_DIR):
    for j in range(0, len(files)):
        if files[j].endswith('.csv'):
            path = root_dir_path + "/" + files[j]
            data = pd.read_csv(path)
            time = data.DATE
            try:
              time = [datetime.strptime(i, '%Y-%m-%d %H:%M:%S.%f') for i in time]
            except:
              time = [datetime.strptime(i, '%Y-%m-%d %H:%M:%S') for i in time]

            flux = data.WHITEFLUX

            sample_time = pd.Series(time).diff().min()
            sample_frequency = 1 / sample_time.seconds

            # Detrend data
            detrend_flux = ssg.detrend(flux, type='linear')

            # Create the periodogram
            freq, spec = ssg.periodogram(detrend_flux, fs=sample_frequency)

            # Save the data on a pd.DataFrame
            DF = DF.append(pd.Series(spec), ignore_index=True)

[19]:

DF.head()

[19]:

	0	1	2	3	4	5	6	7	8	9	10	11	12	13	14	15	16	17	18	19	20	21	22	23	24	25	26	27	28	29	30	31	32	33	34	35	36	37	38	39	...	7486	7487	7488	7489	7490	7491	7492	7493	7494	7495	7496	7497	7498	7499	7500	7501	7502	7503	7504	7505	7506	7507	7508	7509	7510	7511	7512	7513	7514	7515	7516	7517	7518	7519	7520	7521	7522	7523	7524	7525
0	3.698734e-21	2.187372e+10	4.653541e+09	2.977435e+10	5.847694e+09	1.299638e+10	9.043435e+09	1.605398e+09	4.163878e+08	6.495074e+08	8.126626e+09	9.406637e+09	2.139047e+09	7.464040e+08	8.710111e+08	3.066070e+08	1.722429e+09	1.694147e+09	9.865663e+08	8.465616e+08	1.380645e+09	3.179946e+07	1.181358e+09	7.756270e+08	1.003634e+08	6.288176e+08	3.771828e+08	8.828726e+08	1.492417e+09	1.647794e+08	1.810905e+09	1.071801e+10	1.822772e+10	8.686493e+08	1.672761e+09	4.151073e+08	1.422037e+08	3.095936e+08	4.878045e+07	3.732714e+08	...	5.859518e+06	1.802153e+07	6.298346e+06	4.934046e+06	3.243160e+07	4.082484e+06	1.900234e+07	1.505044e+07	8.717856e+06	1.667094e+07	2.006054e+07	1.210509e+06	1.945082e+07	7.096113e+06	2.315154e+07	4.012920e+07	1.055361e+06	4.469378e+06	3.237999e+05	4.170387e+06	1.672472e+07	3.123520e+07	1.453152e+06	3.700304e+07	1.612176e+06	1.006348e+07	2.784085e+06	1.442023e+06	1.009989e+07	5.640032e+06	3.093162e+06	6.324198e+07	5.984340e+06	5.636384e+07	6.359579e+06	2.165289e+07	3.362567e+07	1.639384e+06	7.700957e+07	4.122675e+05
1	3.999557e-18	5.784624e+13	5.242573e+12	1.114427e+12	8.653755e+12	3.495333e+13	6.333985e+13	1.223317e+13	7.133227e+11	3.332728e+12	6.307572e+12	1.189972e+13	1.339273e+13	4.585274e+12	2.595879e+12	1.647835e+11	1.322158e+12	3.092180e+12	1.231179e+11	8.636186e+10	3.534272e+10	1.728992e+11	1.773730e+10	1.762227e+11	3.180256e+10	1.703417e+11	2.373593e+10	5.385853e+10	2.690612e+10	7.111801e+10	8.931761e+10	1.096729e+11	3.603436e+10	2.655039e+08	3.324433e+10	1.137900e+11	5.872237e+10	3.719629e+10	4.964274e+10	3.085536e+10	...	1.209086e+09	1.702009e+09	3.732716e+08	3.764944e+07	6.530433e+08	3.449799e+08	2.953255e+06	5.937585e+08	8.981582e+07	3.058008e+08	1.005418e+08	3.397017e+08	3.034542e+08	1.506536e+08	2.785713e+08	6.444151e+08	2.399501e+08	9.712044e+08	3.309554e+08	5.073232e+08	1.480754e+09	4.535894e+08	9.340738e+06	2.035568e+08	7.644298e+08	2.158474e+08	8.841379e+08	2.560128e+08	1.858450e+08	1.644058e+08	7.884955e+08	8.525404e+07	5.671301e+08	6.771197e+08	8.770928e+07	7.573039e+06	2.590354e+08	3.938666e+07	2.073784e+08	3.598600e+08
2	3.301438e-21	1.656106e+11	4.241954e+10	1.295592e+10	1.441850e+10	7.333357e+09	3.654204e+09	8.038780e+08	2.345564e+09	3.428295e+08	1.486851e+08	4.355384e+07	1.922543e+09	1.190937e+09	1.042278e+09	2.177381e+09	2.186346e+08	2.266618e+08	1.933830e+08	1.024137e+09	6.308557e+07	3.175023e+08	3.831862e+08	1.347591e+08	4.991692e+07	6.616579e+07	3.089654e+08	2.338376e+08	1.757878e+08	1.022475e+08	1.619658e+08	2.161862e+07	7.733964e+07	1.881846e+08	2.409856e+07	1.216204e+08	5.106637e+07	2.844362e+07	1.700110e+08	1.287244e+07	...	6.336029e+06	2.901623e+06	9.709432e+06	6.766949e+06	3.311118e+07	3.102628e+06	6.014224e+06	1.052508e+07	1.792224e+06	5.597886e+06	8.938615e+06	2.654949e+06	3.223749e+05	1.365606e+07	5.680955e+06	1.315171e+07	1.306965e+07	1.334836e+06	2.123376e+07	3.334838e+04	4.742393e+06	6.822047e+05	4.105110e+07	9.704217e+06	1.313942e+06	7.024191e+06	3.920979e+05	1.611153e+07	8.167207e+06	1.913767e+07	3.936906e+06	4.087972e+06	2.124753e+07	1.382830e+07	3.013891e+06	1.112224e+07	1.568576e+07	6.561321e+06	2.489063e+06	2.142671e+05
3	2.347411e-21	1.446522e+11	2.926439e+10	8.856258e+10	1.267793e+11	7.801648e+10	9.524482e+10	5.849805e+10	2.288253e+10	2.312979e+10	2.931245e+10	2.805120e+10	3.957929e+10	6.142179e+10	6.216595e+10	2.295419e+10	9.917353e+09	2.422448e+10	2.340713e+10	2.166599e+10	9.182803e+09	6.499000e+09	6.344703e+09	4.445389e+09	1.498852e+09	9.027348e+08	2.036861e+09	2.321052e+09	3.358732e+09	2.087908e+09	1.687891e+09	1.970376e+09	1.535445e+09	6.515868e+08	1.452884e+09	4.013471e+09	9.788411e+08	1.176883e+09	3.133791e+09	4.906828e+09	...	2.277813e+06	4.568980e+06	3.991391e+06	7.130943e+06	1.204470e+07	3.825498e+06	9.432747e+05	2.249743e+07	1.022491e+06	3.314838e+06	5.426386e+06	1.971414e+07	1.918997e+06	5.693808e+06	1.010783e+06	8.312123e+05	1.079153e+07	5.020188e+06	1.862797e+06	1.532614e+07	2.007534e+06	4.360234e+06	1.105087e+07	2.224375e+06	2.473986e+06	7.483401e+06	2.209326e+07	2.079834e+06	4.852925e+06	1.833137e+07	1.312425e+06	1.618716e+06	6.161822e+05	7.069934e+06	8.741769e+05	1.412689e+07	2.782050e+07	8.039433e+06	1.307975e+07	3.595673e+06
4	1.514690e-21	2.660556e+12	8.750812e+11	5.456667e+11	8.604106e+11	5.928171e+12	3.845155e+11	6.003512e+10	1.230223e+12	5.696613e+11	5.510373e+11	1.229502e+11	4.331146e+11	6.536904e+11	1.155310e+11	3.729638e+11	6.861902e+11	7.168059e+11	1.163156e+12	6.739932e+11	6.537787e+11	9.457468e+11	1.641149e+12	9.234042e+11	3.391170e+11	2.400593e+12	1.125012e+12	1.619200e+13	4.257016e+13	1.386066e+14	1.251609e+14	2.513605e+14	6.976831e+13	2.252078e+13	1.101076e+13	8.750051e+12	4.718911e+12	2.135353e+12	2.630677e+12	1.462807e+12	...	8.021413e+07	9.226670e+07	6.950245e+07	2.063020e+07	1.330526e+08	5.228473e+07	8.631832e+07	7.812558e+07	5.874413e+07	7.679085e+08	8.844318e+06	1.591009e+08	6.224376e+07	1.198233e+07	1.006110e+08	2.624271e+08	5.238574e+07	2.207024e+07	8.199011e+07	9.283523e+07	1.381196e+08	8.889676e+07	2.658051e+07	1.604157e+07	9.881702e+06	1.427925e+08	3.425586e+07	1.080499e+08	8.890381e+07	7.306812e+07	3.266698e+07	4.452323e+07	1.256674e+06	1.378539e+08	5.313656e+07	1.253566e+07	2.295495e+07	1.237998e+08	7.109648e+07	1.491803e+08

5 rows × 7526 columns

Saving feature

[ ]:

file_name = 'feature_periodograms.csv'

DF.to_csv(file_name, index=False)