Saket Choudhary saketkc

## README.md

      
              4 files
            
          
              8 forks
            
          
              3 comments
            
          
              35 stars
            
          
                fperez
                / README.md
            
            
              Last active
              July 1, 2021 04:43
            
              
                Polyglot Data Science with IPython
              
          
    Polyglot Data Science with IPython & friends

Author: Fernando Pérez.
A demonstration of how to use Python, Julia, Fortran and R cooperatively to analyze data, in the same process.
This is supported by the IPython kernel and a few extensions that take advantage of IPython's magic system to provide low-level integration between Python and other languages.
See the companion notebook for data preparation and setup.

  
## dask_sparse_corr.py
import dask
import dask.array as da
import dask.dataframe as dd
import sparse

@dask.delayed(pure=True)
def corr_on_chunked(chunk1, chunk2, corr_thresh=0.9):
    return sparse.COO.from_numpy((np.dot(chunk1, chunk2.T) > corr_thresh))

def chunked_corr_sparse_dask(data, chunksize=5000, corr_thresh=0.9):

## flow_cytometry.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              3 stars
            
          
                lmcinnes
                / flow_cytometry.ipynb
            
            
              Created
              September 8, 2018 22:19
            
              
                Flow Cytometry experiments with UMAP
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## R_EigenPCA_Plots.R
library(tidyverse)
library(MASS)
library(patchwork)
cbPalette <- c("#999999", "#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7")

# generate data with given cor matrix
a <- 0.9
s1 <- matrix(c(1,a,
               a,1), ncol = 2)
	import dask
	import dask.array as da
	import dask.dataframe as dd
	import sparse

	@dask.delayed(pure=True)
	def corr_on_chunked(chunk1, chunk2, corr_thresh=0.9):
	return sparse.COO.from_numpy((np.dot(chunk1, chunk2.T) > corr_thresh))

	def chunked_corr_sparse_dask(data, chunksize=5000, corr_thresh=0.9):
	library(tidyverse)
	library(MASS)
	library(patchwork)
	cbPalette <- c("#999999", "#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7")

	# generate data with given cor matrix
	a <- 0.9
	s1 <- matrix(c(1,a,
	a,1), ncol = 2)