gdbassett

#' Flip the x and y axis
#'
#' This is accomplished by updating the x & y marks, updating the flipping the
#' scales, and updating the axis labels.
#'
#' WARNING: This currently works for rectangular layer figures.  It may not work with
#' multiple-layer figures, other marks, or signals.
#'
#' WARNING: No tests currently exist for this function
#'

gdbassett

import networkx as nx # NOTE: written against dev networkx 2.0
import logging
import inspect
import json

logger = logging.getLogger()
fileLogger = logging.FileHandler("~/Documents/Development/tmp/vega.log")
fileLogger.setLevel(logging.DEBUG)
logger.addHandler(fileLogger)

gdbassett

{
  "$schema": "https://vega.github.io/schema/vega-lite/v2.json",
  "vconcat": [
    {
      "data": {
        "values": [
          {
            "enum": "victim.industry2.52",
            "x": 471,
            "n": 1935,

gdbassett

# pick an enumeration
enum <- "action.*.variety"
# establish filter criteria (easier than a complex standard-eval  filter_ line)
df <- vcdb %>%
  dplyr::filter(plus.dbir_year == 2016, subset.2017dbir) %>%
  dplyr::filter(attribute.confidentiality.data_disclosure.Yes) %>%
  dplyr::filter(victim.industry2.92)

# establish priors from previous year
priors <- df %>%

gdbassett

speedrun <- XML::xmlParse("/livesplit.lss")
speedrun <- XML::xmlToList(speedrun)

chunk <- do.call(rbind, lapply(speedrun[['Segments']], function(segments) {
    
    segments.df <- do.call(rbind, lapply(segments[['SegmentHistory']], function(segment) {
        if ('RealTime' %in% names(segment))
        data.frame(`attemptID` = segment$.attrs['id'], RealTime = segment$RealTime)
    }))
    segments.df$name <- rep(segments$Name, nrow(segments.df))

gdbassett

---
title: "Test"
author: "Gabe"
date: "November 03, 2016"
output: html_document
params:
  df: data.frame()
  a: ""
  b: ""
  c: "FALSE"

gdbassett

#' @param df Dataframe with x and y columns.  (Hopefully in the future this can be x)
#' @param nlines The number of clusters.
#' @param ab a dataframe with a 'slopes' and 'intercepts' column and one row per initial line.  Dimensions must match nlines.
#' @param maxiter The maximum number of iterations to do
#' @export
#' @examples
linearKMeans <- function(df, ab=NULL, nlines=0, maxiter=1000) {
  # default number of lines
  nlines_default <- 5
  

gdbassett

> df <- df[!names(df) %in% c('root.victim.region',
+ 'root.victim.country',
+ 'root.summary',
+ 'root.summary=Source_Category',
+ 'root.victim.industry',
+ 'root.timeline.incident.year',
+ 'root.plus.dbir_year',
+ 'root.action.social.notes',
+ 'root.victim.secondary.notes',
+ 'root.action.hacking.notes',

gdbassett

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# based on http://scikit-learn.org/stable/auto_examples/document_clustering.html

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans, MiniBatchKMeans
from sklearn.metrics.pairwise import pairwise_distances
import numpy as np
from time import time
from collections import defaultdict

gdbassett

from sklearn.metrics.pairwise import pairwise_distances
import numpy as np

# X shoudl be a numpy matrix, very likely sparse matrix: http://docs.scipy.org/doc/scipy-0.14.0/reference/generated/scipy.sparse.csr_matrix.html#scipy.sparse.csr_matrix
# T1 > T2 for overlapping clusters
# T1 = Distance to centroid point to not include in other clusters
# T2 = Distance to centroid point to include in cluster
# T1 > T2 for overlapping clusters
# T1 < T2 will have points which reside in no clusters
# T1 == T2 will cause all points to reside in mutually exclusive clusters