statcompute

from xframes import XFrame, aggregate
 
df = XFrame.read_csv("Downloads/nycflights.csv", header = True, nrows = 11)
 
### SUBSETTING
sel_cols = ["origin", "dest", "distance", "dep_delay", "carrier"]
 
df2 = df[sel_cols]
# OR:
# df.sql("select " + ", ".join(sel_cols) + " from df")

statcompute

### GROWING LIST ###
base_lst1 <- function(df) {
  l <- list()
  for (i in seq(nrow(df))) l[[i]] <- as.list(df[i, ])
  return(l)
}
 
### PRE-ALLOCATING LIST ###
base_lst2 <- function(df) {
  l <- vector(mode = "list", length = nrow(df))

statcompute

### LIST() FUNCTION IN BASE PACKAGE ###
x1 <- as.list(iris[1, ])
names(x1)
# [1] "Sepal.Length" "Sepal.Width"  "Petal.Length" "Petal.Width"  "Species"
x1[["Sepal.Length"]]
# [1] 5.1
 
### ENVIRONMENT-BASED SOLUTION ###
envn_dict <- function(x) {
  e <- new.env(hash = TRUE)

statcompute

data one;
  array c{2} $ _temporary_ ("A", "B");
  do i = 1 to dim(c);
    x = c[i];
    do j = 1 to 2;
      y = round(rannor(1), 0.0001);
      output;
    end;
  end;
run;

statcompute

from astropy.io import ascii
 
from astropy.table import Table, join
 
from numpy import nanmean, nanmedian, array, sort
 
tbl1 = ascii.read("Downloads/nycflights.csv", format = "csv")
 
### SUBSETTING
sel_cols = ["origin", "dest", "distance", "dep_delay", "carrier"]

statcompute

from astropy.io.ascii import read
 
selected = ["origin", "dep_delay", "distance"]
 
csv = read("Downloads/nycflights.csv", format = 'csv', data_end = 11)[selected]
 
lst = map(lambda x: dict(zip(x.colnames, x)), csv)
 
from dataset import connect
 

statcompute

isoreg_bin <- function(data, y, x) {
  n1 <- 50
  n2 <- 10
  yname <- deparse(substitute(y))
  xname <- deparse(substitute(x))
  df1 <- data[, c(yname, xname)]
  df2 <- df1[!is.na(df1[, xname]), c(xname, yname)]
  cor <- cor(df2[, 2], df2[, 1], method = "spearman", use = "complete.obs")
  reg <- isoreg(df2[, 1], cor / abs(cor) * df2[, 2])
  cut <- knots(as.stepfun(reg))

statcompute

bump_bin <- function(data, y, x, n) {
  n1 <- 50
  n2 <- 10
  set.seed(2019)
  seeds <- c(0, round(runif(n) * as.numeric(paste('1e', ceiling(log10(n)) + 2, sep = '')), 0))
  yname <- deparse(substitute(y))
  xname <- deparse(substitute(x))
  df1 <- data[, c(yname, xname)]
  df2 <- df1[!is.na(df1[, xname]), c(xname, yname)]
  cor <- cor(df2[, 2], df2[, 1], method = "spearman", use = "complete.obs")

statcompute

from pandas import read_csv, DataFrame
from numpy.random import seed
from sklearn.preprocessing import scale
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score 
from keras.models import Sequential
from keras.constraints import maxnorm
from keras.optimizers import SGD
from keras.layers import Dense, Dropout
from multiprocessing import Pool, cpu_count

statcompute

from pandas import read_csv, DataFrame
from numpy.random import seed
from sklearn.preprocessing import minmax_scale
from sklearn.model_selection import train_test_split
from keras.layers import Input, Dense
from keras.models import Model
 
df = read_csv("credit_count.txt")
Y = df[df.CARDHLDR == 1].DEFAULTS
X = df[df.CARDHLDR == 1].ix[:, 2:12]