Skip to content

Instantly share code, notes, and snippets.

View reachsumit's full-sized avatar
😃

Sumit Kumar reachsumit

😃
109 followers · 5 following
View GitHub Profile
@reachsumit
reachsumit / field_aware_factorization_machine.ipynb
Created November 7, 2022 01:24
Field-Aware Factorization Machines
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@reachsumit
reachsumit / factorization_machine.ipynb
Created November 7, 2022 01:20
Factorization Machine
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@reachsumit
reachsumit / cf_implicit.py
Last active May 16, 2023 10:50
import numpy as np
import pandas as pd
from numpy import bincount, log, log1p
from scipy.sparse import coo_matrix, linalg
class ImplicitCF:
def __init__(self):
self.df = pd.read_csv("lastfm-dataset-360K/usersha1-artmbid-artname-plays.tsv", sep='\t', header=None, names=['user', 'artist', 'plays'], usecols=[0,2,3])
self.df['user'] = self.df['user'].astype("category")
@reachsumit
reachsumit / cf_explicit.py
Created September 26, 2022 04:23
import numpy as np
import pandas as pd
from numpy import bincount, log, log1p
from scipy.sparse import coo_matrix, linalg
class ExplicitCF:
def __init__(self):
self.df = pd.read_csv("ml-100k/u.data", sep='\t', header=None, names=['user', 'item', 'rating'], usecols=range(3))
self.df['user'] = self.df['user'].astype("category")
@reachsumit
reachsumit / fasttext_trained.py
Last active July 19, 2020 06:03
fasttext based spell-checker trained on Peter Norvig's "big.txt" training data
import io
import fasttext
def load_vectors(fname):
fin = io.open(fname, 'r', encoding='utf-8', newline='\n', errors='ignore')
n, d = map(int, fin.readline().split())
data = {}
for line in fin:
tokens = line.rstrip().split(' ')
data[tokens[0]] = map(float, tokens[1:])
@reachsumit
reachsumit / fasttext_pretrained.py
Created July 19, 2020 03:54
spell-check Norvig's test sets using pretrained FastText embeddings
import io
import fasttext
def load_vectors(fname):
fin = io.open(fname, 'r', encoding='utf-8', newline='\n', errors='ignore')
n, d = map(int, fin.readline().split())
data = {}
for line in fin:
tokens = line.rstrip().split(' ')
data[tokens[0]] = map(float, tokens[1:])
@reachsumit
reachsumit / Audio Steganography_ultrasound - receiver.ny
Created June 14, 2018 14:57
This code contains a demo for Audio Steganography. It is to be used by the receiver end, to extract the secret audio embedded within the public audio file.
;; replace the below frequency number with the original frequency used to embed the secret
(mult *track* (hzosc 17500.0))
@reachsumit
reachsumit / Audio Steganography_ultrasound - sender.ny
Last active March 25, 2024 16:06
This code was shared by Audacity user edgar-rft (https://forum.audacityteam.org/memberlist.php?mode=viewprofile&u=5642) to generate silent subliminals and is an implementation of Oliver M. Lowery's 1989 patent (https://patents.google.com/patent/US5159703A/en).
;nyquist plug-in
;version 1
;type process
;name "Subliminal..."
;action "Subliminal..."
;control carrier "Carrier" real "Hz" 17500 14000 20000
(setf carrier (max 14000 (min carrier 20000)))
;; We have two Nyquist frequencies, carrier/2 and *sound-srate*/2.
@reachsumit
reachsumit / Audio Steganography - receiver.py
Created June 14, 2018 14:43
This code contains a demo for Audio Steganography. It is to be used by the receiver end, to extract the secret text embedded in the audio file.
# Use wave package (native to Python) for reading the received audio file
import wave
song = wave.open("song_embedded.wav", mode='rb')
# Convert audio to byte array
frame_bytes = bytearray(list(song.readframes(song.getnframes())))
# Extract the LSB of each byte
extracted = [frame_bytes[i] & 1 for i in range(len(frame_bytes))]
# Convert byte array back to string
string = "".join(chr(int("".join(map(str,extracted[i:i+8])),2)) for i in range(0,len(extracted),8))
@reachsumit
reachsumit / Audio Steganography - sender.py
Last active June 14, 2023 06:33
This code contains a demo for Audio Steganography. It is to be used by sender end to embed text mentioned in string variable to the audio file.
# We will use wave package available in native Python installation to read and write .wav audio file
import wave
# read wave audio file
song = wave.open("song.wav", mode='rb')
# Read frames and convert to byte array
frame_bytes = bytearray(list(song.readframes(song.getnframes())))
# The "secret" text message
string='Peter Parker is the Spiderman!'
# Append dummy data to fill out rest of the bytes. Receiver shall detect and remove these characters.