Deepak Sadulla dsadulla

A Data Science geek. Recently curious about neural networks, CNNs, RNNs, LSTMs and GRUs on Keras and Tensorflow.

dsadulla / vif_fun.r

Created January 27, 2018 08:00 — forked from fawda123/vif_fun.r

	vif_func<-function(in_frame,thresh=10,trace=T,...){

	library(fmsb)

	if(any(!'data.frame' %in% class(in_frame))) in_frame<-data.frame(in_frame)

	#get initial vif value for all comparisons of variables
	vif_init<-NULL
	var_names <- names(in_frame)
	for(val in var_names){

dsadulla / LilLambda.ipynb

Created September 12, 2017 18:28 — forked from vakila/LilLambda.ipynb

Anjana Vakil, "Mary had a little lambda", EuroPython 2017: https://ep2017.europython.eu/conference/talks/mary-had-a-little-lambda

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

dsadulla / timeseries_cnn.py

Created August 21, 2017 03:38 — forked from jkleint/timeseries_cnn.py

Example of using Keras to implement a 1D convolutional neural network (CNN) for timeseries prediction.

	#!/usr/bin/env python
	"""
	Example of using Keras to implement a 1D convolutional neural network (CNN) for timeseries prediction.
	"""

	from __future__ import print_function, division

	import numpy as np
	from keras.layers import Convolution1D, Dense, MaxPooling1D, Flatten
	from keras.models import Sequential